{"meta":{"query_hash":"0e3a95b3d883","filters":{"topic":"Hydrological Forecasting Using AI"},"cohort_total":692,"direct_labels_cover":1,"predictions_cover":692,"exported":692,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/0e3a95b3d883","api":"https://metacan.xera.ac/api/v1/cohort?topic=Hydrological+Forecasting+Using+AI"},"results":[{"id":"W1003154759","doi":"10.11113/mjce.v25n2.305","title":"IMPROVEMENT OF STREAMFLOW SIMULATION FOR GAUGED SITE OF HYDROLOGICAL MODEL","year":2013,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Streamflow; Hydrometeorology; Hydrograph; Environmental science; Flood forecasting; Hydrological modelling; Hydrology (agriculture); Precipitation; Drainage basin; Meteorology; Climatology; Geology; Geography","score_opus":0.0234244262893942,"score_gpt":0.2513187940347455,"score_spread":0.2278943677453513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1003154759","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30719376,0.00007026177,0.6830989,0.00013383165,0.00005498807,0.00012927358,0.0004300504,0.002976714,0.0059122345],"genre_scores_gemma":[0.883064,0.00003823296,0.11505568,0.000020064903,0.000013206483,0.00010159641,0.0003374451,0.00010921409,0.0012607094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983,0.0000565142,0.000008916826,0.000034993587,0.000052273972,0.000017176408],"domain_scores_gemma":[0.99968743,0.00008791938,0.000025981015,0.000064443055,0.00011768044,0.00001665316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049860834,0.00025984383,0.0003152442,0.00024312435,0.00021317661,0.00023382773,0.0006379307,0.00030139578,0.0015849582],"category_scores_gemma":[0.001265167,0.00013658548,0.00033448133,0.0002403441,0.00011471329,0.0003380924,0.0002738146,0.00054889394,0.00026459357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004803325,0.0000711736,0.0034632937,0.000024559904,0.000023643592,0.00004429979,0.000041093168,0.9440237,0.007872285,0.0012731939,0.00059609953,0.042518634],"study_design_scores_gemma":[0.000004333065,0.000008808729,0.00042158365,9.419276e-7,0.0000018711434,0.000002670079,0.0000017170904,0.99815184,0.0010962704,0.000118022464,0.0001902572,0.0000016847608],"about_ca_topic_score_codex":0.009696,"about_ca_topic_score_gemma":0.007024526,"teacher_disagreement_score":0.009696,"about_ca_system_score_codex":0.00033868145,"about_ca_system_score_gemma":0.00056736113,"threshold_uncertainty_score":0.019279122},"labels":[],"label_agreement":null},{"id":"W137046381","doi":"10.1007/s10040-014-1204-3","title":"Short-term forecasting of groundwater levels under conditions of mine-tailings recharge using wavelet ensemble neural network models","year":2014,"lang":"en","type":"article","venue":"Hydrogeology Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Hydrogeology; Groundwater recharge; Wavelet; Wavelet transform; Robustness (evolution); Data mining; Computer science; Statistics; Artificial intelligence; Machine learning; Groundwater; Mathematics; Engineering; Geotechnical engineering; Aquifer","score_opus":0.0875086072542672,"score_gpt":0.2764750137947826,"score_spread":0.1889664065405154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W137046381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99161834,0.00006336123,0.007614088,0.00006163025,0.000020073028,0.0000031397344,0.00020176797,0.000046239416,0.00037144974],"genre_scores_gemma":[0.9990459,0.00002810233,0.0006509402,0.0000023967207,0.0000039868105,0.0000013447769,0.00015505488,0.0000016530632,0.000110617715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990845,0.0000150505,0.0000096975955,0.000023283364,0.000022441223,0.000021172325],"domain_scores_gemma":[0.9996686,0.00012804965,0.00005285273,0.00002915628,0.00009445382,0.000026817943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035170355,0.00031061287,0.0003472958,0.000380348,0.00015820721,0.00035594913,0.00033461145,0.00045046478,0.00030885058],"category_scores_gemma":[0.0011644828,0.0001262093,0.00031334927,0.0006077471,0.00016650521,0.0006564298,0.00024970822,0.0004226493,0.00005968621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038932895,0.00013891069,0.06764862,0.00003429573,0.00011821251,0.00018211259,0.00005403993,0.8930999,0.0056100436,0.00052369083,0.00069699064,0.031503823],"study_design_scores_gemma":[0.000002628067,0.000011650687,0.0072003137,9.108265e-7,0.0000066956613,0.000005129591,0.000010159856,0.9922845,0.00034281999,0.00010727462,0.000024898285,0.0000029483858],"about_ca_topic_score_codex":0.013023629,"about_ca_topic_score_gemma":0.012910151,"teacher_disagreement_score":0.013023629,"about_ca_system_score_codex":0.00033590943,"about_ca_system_score_gemma":0.00027427968,"threshold_uncertainty_score":0.025895596},"labels":[],"label_agreement":null},{"id":"W1433821","doi":"10.1007/978-3-540-79881-1_6","title":"Dynamic Neural Networks for Nonstationary Hydrological Time Series Modeling","year":2008,"lang":"en","type":"book-chapter","venue":"Water science and technology library","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Recurrent neural network; Multivariate adaptive regression splines; Time series; Computer science; Series (stratigraphy); Artificial neural network; Hydrological modelling; Multivariate statistics; Hydrology (agriculture); Meteorology; Regression analysis; Artificial intelligence; Machine learning; Climatology; Nonparametric regression; Geography; Geology","score_opus":0.009984418356038418,"score_gpt":0.18675999176768274,"score_spread":0.17677557341164432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1433821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025794476,0.022991927,0.9243267,0.0006496275,0.0009866311,0.000036061185,0.00036006272,0.0016294171,0.046440046],"genre_scores_gemma":[0.090673156,0.047803964,0.5794548,0.00052993477,0.001492996,0.00030782822,0.0020715517,0.00097118114,0.27669466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998971,0.000012846052,0.000008061402,0.000019660429,0.000056877892,0.0000053630038],"domain_scores_gemma":[0.9998448,0.000079064346,0.000008039614,0.000025088611,0.000039110364,0.000004008443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022680084,0.0008030468,0.00051282387,0.00046333065,0.00015418245,0.00070269656,0.0008572646,0.0007264855,0.009814412],"category_scores_gemma":[0.00063510775,0.00042881686,0.00032368663,0.0010989415,0.00028393508,0.0014358371,0.0004846594,0.001374722,0.0037046103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019455807,0.000047190202,0.00016296674,0.00040780733,0.000055358138,0.00006623354,0.0000497129,0.14908256,0.0032733823,0.059374705,0.04367807,0.74378246],"study_design_scores_gemma":[0.00000774233,0.000021198808,0.00037628066,0.00012288302,0.00003449373,0.00010473101,0.000017881583,0.75903124,0.0039809626,0.098982334,0.13729014,0.000030138115],"about_ca_topic_score_codex":0.002252038,"about_ca_topic_score_gemma":0.0035813164,"teacher_disagreement_score":0.009814412,"about_ca_system_score_codex":0.00039299147,"about_ca_system_score_gemma":0.00025635326,"threshold_uncertainty_score":0.032832503},"labels":[],"label_agreement":null},{"id":"W1490649547","doi":"10.3968/6573","title":"Economic Evaluation of Waterflood Using Regression and Classification Algorithms","year":2015,"lang":"en","type":"article","venue":"Advances in petroleum exploration and development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Artificial intelligence; Algorithm; Regression; Regression analysis; Artificial neural network; Dimension (graph theory); Machine learning; Integer (computer science); Statistical classification; Mathematics; Variable (mathematics); Computer science; Data mining; Pattern recognition (psychology); Statistics","score_opus":0.12982991852067582,"score_gpt":0.33682623543330437,"score_spread":0.20699631691262854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490649547","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53143376,0.0022767829,0.4434528,0.0010944055,0.00014824687,0.00047275165,0.0010569082,0.0006736533,0.019390699],"genre_scores_gemma":[0.9266763,0.00084678765,0.069936246,0.000052367734,0.000050505372,0.00014062879,0.00055621937,0.00005157365,0.0016894899],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963431,0.001339008,0.0002703314,0.0003781781,0.0014457231,0.00022363348],"domain_scores_gemma":[0.99141955,0.005006168,0.0011819792,0.000295146,0.0019778076,0.0001192484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056136847,0.0012258914,0.0012726518,0.0051861787,0.0003516653,0.0023630655,0.00095778104,0.0012456136,0.0015272581],"category_scores_gemma":[0.019878572,0.0003761284,0.0012594021,0.0057171886,0.00072376,0.0028243286,0.0007846529,0.0009339801,0.0003412532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020794285,0.0001564045,0.035303604,0.00016652617,0.00022229686,0.00011499443,0.00004199161,0.87365943,0.0007935236,0.0054318956,0.00083713187,0.08306428],"study_design_scores_gemma":[0.000008470646,0.00006150998,0.0057506077,0.00001798283,0.000017677577,0.000014934971,0.00004286789,0.99188775,0.0007277738,0.0010922002,0.0003602635,0.000017948252],"about_ca_topic_score_codex":0.016798992,"about_ca_topic_score_gemma":0.009476354,"teacher_disagreement_score":0.016798992,"about_ca_system_score_codex":0.0024047615,"about_ca_system_score_gemma":0.0012066994,"threshold_uncertainty_score":0.033402443},"labels":[],"label_agreement":null},{"id":"W1501803319","doi":"10.7202/705289ar","title":"Revue bibliographique des méthodes de prévision des débits","year":2005,"lang":"fr","type":"article","venue":"Revue des sciences de l eau","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Humanities; Philosophy; Mathematics","score_opus":0.18572909786063505,"score_gpt":0.3641992377861297,"score_spread":0.17847013992549468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501803319","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028058132,0.37933636,0.5621461,0.0033439593,0.0031149029,0.00017545273,0.003094281,0.0031809297,0.04280217],"genre_scores_gemma":[0.046506092,0.50314176,0.38233837,0.0024945997,0.005549521,0.000682775,0.007251192,0.0029480623,0.049087584],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99629265,0.0007936889,0.0004865141,0.0009829121,0.0012619883,0.00018221527],"domain_scores_gemma":[0.98959726,0.00622855,0.0004113522,0.001009881,0.0026085132,0.00014442932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037616056,0.0022048224,0.0024634465,0.0060894988,0.0008805832,0.0051055285,0.0033091246,0.0029311434,0.029323654],"category_scores_gemma":[0.018187419,0.001611843,0.0033157398,0.008215476,0.0013809943,0.0040646074,0.0016335533,0.0040283874,0.01619058],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019263034,0.000067332345,0.0014232151,0.008483062,0.00028896093,0.0001633788,0.00023606919,0.02082934,0.0018089681,0.06840123,0.049180817,0.848925],"study_design_scores_gemma":[0.00005597372,0.00013075674,0.0026872973,0.004923436,0.00031315893,0.00087135547,0.0001840673,0.054491077,0.004887484,0.05157306,0.8796495,0.00023278054],"about_ca_topic_score_codex":0.017700331,"about_ca_topic_score_gemma":0.0076078707,"teacher_disagreement_score":0.029323654,"about_ca_system_score_codex":0.0026538041,"about_ca_system_score_gemma":0.005221971,"threshold_uncertainty_score":0.09809744},"labels":[],"label_agreement":null},{"id":"W1507653781","doi":"10.1109/ijcnn.2005.1556346","title":"Wavelet networks: an alternative to classical neural networks","year":2006,"lang":"en","type":"article","venue":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Artificial neural network; Computer science; Series (stratigraphy); Robustness (evolution); Chaotic; Time series; Wavelet; Nonlinear system; Convergence (economics); Hénon map; Artificial intelligence; Algorithm; Machine learning; Geology","score_opus":0.04432940016179775,"score_gpt":0.2732083081549565,"score_spread":0.22887890799315874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1507653781","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036625448,0.0037775938,0.9851099,0.0008588167,0.00033989738,0.000039644212,0.00015374881,0.0002690174,0.0057888203],"genre_scores_gemma":[0.20045473,0.013533341,0.77407706,0.00048084618,0.0013590805,0.0002759622,0.0005065038,0.00022051693,0.009091922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919957,0.0002927035,0.000057828227,0.00010738938,0.00030525008,0.00003726983],"domain_scores_gemma":[0.9991086,0.00048150457,0.000096064265,0.00011196336,0.00016970302,0.000032046853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015146444,0.00077343575,0.00081687816,0.0010398141,0.00023973096,0.0014410766,0.0012542598,0.0009989586,0.0023421717],"category_scores_gemma":[0.004466022,0.00032598266,0.0006472462,0.0022234332,0.000536054,0.0021309948,0.0010997007,0.0016472082,0.0009358244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018809245,0.00007615598,0.001638606,0.0006085484,0.00028733403,0.00024490364,0.00010980274,0.2274065,0.0038966506,0.28964382,0.0055288533,0.4703707],"study_design_scores_gemma":[0.00003518221,0.00006293495,0.00049196306,0.00007770332,0.000038349674,0.00011466132,0.00003471656,0.79715824,0.0012963677,0.17715837,0.02350435,0.000027121314],"about_ca_topic_score_codex":0.0015714264,"about_ca_topic_score_gemma":0.0013826862,"teacher_disagreement_score":0.0023421717,"about_ca_system_score_codex":0.00040424732,"about_ca_system_score_gemma":0.00044632005,"threshold_uncertainty_score":0.008010268},"labels":[],"label_agreement":null},{"id":"W1520564701","doi":"","title":"하천 수리특성을 고려한 확률론적 유속공식에 의한 하천유량 산정","year":2009,"lang":"ko","type":"article","venue":"대한토목학회논문집 B","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rating curve; Stage (stratigraphy); Entropy (arrow of time); Principle of maximum entropy; Mathematics; Probabilistic logic; Geology; Statistics; Thermodynamics; Physics; Geomorphology","score_opus":0.017767026067509815,"score_gpt":0.24208860799742746,"score_spread":0.22432158192991764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1520564701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017708894,0.00006903045,0.9799294,0.000068615045,0.000041876312,0.000023449924,0.00006911174,0.00047519736,0.0016143926],"genre_scores_gemma":[0.5352674,0.00032911013,0.45603034,0.00006715363,0.00006426467,0.00009343707,0.00032527075,0.00012539492,0.0076975906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998179,0.000023165669,0.000017873781,0.00003965018,0.000087875356,0.000013586728],"domain_scores_gemma":[0.99959975,0.00012810263,0.000028919447,0.000025717418,0.00020274628,0.000014750985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037925708,0.0003280284,0.00030374996,0.00070818944,0.0002628393,0.00058239547,0.000653709,0.0003427506,0.0018337483],"category_scores_gemma":[0.001512378,0.00014608166,0.00042825416,0.0007836557,0.00018359996,0.0012125336,0.00026966343,0.0006102092,0.00073054514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005617921,0.00006185397,0.011519204,0.00019071579,0.000041301155,0.00011650209,0.00018977291,0.42811602,0.028358921,0.027357476,0.0022451475,0.50174695],"study_design_scores_gemma":[0.0000028302647,0.000016749033,0.001057438,0.000003707325,0.000005527988,0.000026748397,0.0000079697065,0.99145705,0.0035031564,0.0015302487,0.0023770924,0.000011588912],"about_ca_topic_score_codex":0.011791453,"about_ca_topic_score_gemma":0.0098884655,"teacher_disagreement_score":0.011791453,"about_ca_system_score_codex":0.00044401348,"about_ca_system_score_gemma":0.0008582977,"threshold_uncertainty_score":0.023445666},"labels":[],"label_agreement":null},{"id":"W1546550509","doi":"","title":"Predicting Dissolved Oxygen Concentration in Urban Watersheds: A Comparison of Fuzzy Number Based and Bayesian Data-Driven Approaches","year":2014,"lang":"en","type":"article","venue":"The Journal of Macrodynamic Analysis (Memorial University of Newfoundland)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; University of Victoria","keywords":"Linear regression; Bayesian probability; Environmental science; Fuzzy logic; Hydrology (agriculture); Linear model; Statistics; Computer science; Mathematics; Artificial intelligence; Geology","score_opus":0.025749672600655225,"score_gpt":0.23534396868028062,"score_spread":0.2095942960796254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546550509","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.736299,0.0006316686,0.2571419,0.00063719985,0.000044398297,0.0001294776,0.00040299052,0.00029552678,0.004417822],"genre_scores_gemma":[0.9532766,0.00025235917,0.045612413,0.000046021356,0.000011090945,0.000049918803,0.00024404548,0.000011943822,0.00049561064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996749,0.000108013424,0.000030749936,0.000052148513,0.000111023124,0.000023093098],"domain_scores_gemma":[0.99788254,0.0015038489,0.00012829044,0.000045759072,0.0003770148,0.000062628314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020202661,0.00044463333,0.0004321894,0.0012383637,0.0002833561,0.0008387611,0.00086809596,0.00063463335,0.00045667577],"category_scores_gemma":[0.0044260137,0.00027136618,0.00045260784,0.0006105868,0.0002059373,0.0008691612,0.00042274618,0.0004677503,0.00008799955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025486713,0.0002068527,0.019171432,0.00008147869,0.00009971788,0.000036858444,0.000081992526,0.89759165,0.0012756648,0.0015598307,0.00024196912,0.0793977],"study_design_scores_gemma":[0.000008769978,0.0000260835,0.0016712076,0.0000064245614,0.000009443548,0.00000370349,0.000021107297,0.99736017,0.00032548502,0.00047903124,0.000081105674,0.000007316153],"about_ca_topic_score_codex":0.03848626,"about_ca_topic_score_gemma":0.033661403,"teacher_disagreement_score":0.03848626,"about_ca_system_score_codex":0.001372306,"about_ca_system_score_gemma":0.0010952506,"threshold_uncertainty_score":0.076524496},"labels":[],"label_agreement":null},{"id":"W1547948191","doi":"10.1109/ijcnn.2005.1556324","title":"A comparative study of artificial neural network techniques for river stage forecasting","year":2006,"lang":"en","type":"article","venue":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Artificial neural network; Stage (stratigraphy); Drainage basin; Computer science; Set (abstract data type); Artificial intelligence; Hydrology (agriculture); Operations research; Geography; Engineering; Geology; Cartography","score_opus":0.1021571644482742,"score_gpt":0.3062610319167942,"score_spread":0.20410386746852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1547948191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47822937,0.030884808,0.43861195,0.0032873265,0.0006109857,0.0002504851,0.00039651687,0.0008576682,0.046870887],"genre_scores_gemma":[0.86953884,0.00870754,0.11767927,0.00016114919,0.00018719787,0.00009286864,0.00029782,0.000085288455,0.0032500126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966498,0.0018428693,0.00021276847,0.00019140042,0.0010024153,0.00010070322],"domain_scores_gemma":[0.9861399,0.010989282,0.00030863794,0.00032980661,0.0021191265,0.00011337221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077179354,0.0006917478,0.0006207272,0.0030906335,0.000334248,0.0012126843,0.0009080198,0.0010185369,0.001084374],"category_scores_gemma":[0.019567074,0.00024896913,0.0006238584,0.0031534997,0.00038016838,0.00238646,0.0005947001,0.0008222857,0.0002065593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001277708,0.00031088493,0.016363895,0.0009315979,0.00050366146,0.00017645516,0.00056170754,0.3775731,0.002441116,0.012890254,0.0021090528,0.58486056],"study_design_scores_gemma":[0.000039819926,0.0004778612,0.008800894,0.00017073264,0.0000949771,0.00008741835,0.00033839417,0.97855395,0.0019769517,0.0046735127,0.004731431,0.000054049015],"about_ca_topic_score_codex":0.0069480618,"about_ca_topic_score_gemma":0.009294514,"teacher_disagreement_score":0.0077179354,"about_ca_system_score_codex":0.0010531915,"about_ca_system_score_gemma":0.0005725736,"threshold_uncertainty_score":0.040816844},"labels":[],"label_agreement":null},{"id":"W154867600","doi":"","title":"Downscaling Climate Variables to River Basin Scale in India for IPCC SRES Scenarios Using Support Vector Machine","year":2008,"lang":"en","type":"article","venue":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Downscaling; Climatology; Environmental science; Climate change; Scale (ratio); Drainage basin; Climate model; Water cycle; Water resources; Environmental resource management; Precipitation; Meteorology; Geography; Geology; Cartography","score_opus":0.02184007349841403,"score_gpt":0.25062327180661337,"score_spread":0.22878319830819935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W154867600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98163235,0.000104109844,0.012201113,0.00022932087,0.00006033143,0.00004372811,0.0018713815,0.00072166073,0.003136049],"genre_scores_gemma":[0.9908817,0.000054628494,0.0074793557,0.000018610583,0.0000051530114,0.000024317911,0.0012365183,0.000030019566,0.00026964894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99989104,0.000027189843,0.0000096843405,0.000025908335,0.000024215664,0.000021976692],"domain_scores_gemma":[0.99969935,0.00011143317,0.000033764296,0.000035632962,0.00010169878,0.000018270506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035861557,0.0003301697,0.00023417377,0.0004886569,0.00028690905,0.00044699063,0.00042623084,0.0002523936,0.00085052353],"category_scores_gemma":[0.0011149909,0.00017831194,0.00045694422,0.0009538701,0.00021742705,0.00037751626,0.0002341327,0.0006022095,0.00015013458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021412662,0.000085507854,0.025857493,0.000056956007,0.000053915708,0.00014855573,0.00010978296,0.9364418,0.0028919848,0.00075635465,0.002381483,0.03100209],"study_design_scores_gemma":[0.00002705021,0.00005211405,0.03285701,0.0000072104285,0.000028960176,0.000014270482,0.00013696692,0.96185195,0.0035194922,0.0005518119,0.00093345344,0.000019711077],"about_ca_topic_score_codex":0.060822155,"about_ca_topic_score_gemma":0.052105226,"teacher_disagreement_score":0.060822155,"about_ca_system_score_codex":0.00074983074,"about_ca_system_score_gemma":0.0006531311,"threshold_uncertainty_score":0.120936275},"labels":[],"label_agreement":null},{"id":"W1556672459","doi":"10.1109/ijcnn.2005.1556347","title":"Streamflow forecasting with uncertainty estimate using Bayesian learning for ANN","year":2006,"lang":"en","type":"article","venue":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Artificial neural network; Streamflow; Bayesian probability; Machine learning; Artificial intelligence; Multilayer perceptron; Bayesian network; Perceptron; Hydrograph; Reliability (semiconductor); Data mining; Surface runoff","score_opus":0.054180399978147,"score_gpt":0.2747479837418177,"score_spread":0.2205675837636707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556672459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042692102,0.0005547423,0.9544106,0.00030681843,0.000031957192,0.000034729983,0.00007578285,0.0003634002,0.0015298086],"genre_scores_gemma":[0.8502659,0.00067128934,0.14719267,0.00007811582,0.000081136175,0.00016484514,0.00021443793,0.000051722236,0.0012798209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992436,0.00040843984,0.000038129296,0.00006418663,0.00021291875,0.000032854776],"domain_scores_gemma":[0.99761415,0.0018363922,0.00015423434,0.00008555468,0.0002793345,0.000030290563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026330447,0.00046990992,0.0006303804,0.000617248,0.00029979664,0.0007585533,0.0006183473,0.00067251176,0.00084689615],"category_scores_gemma":[0.010136353,0.0005274782,0.00042995543,0.0005839337,0.00040413727,0.0018085212,0.00057187054,0.0009254629,0.0002322132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005671111,0.00002890802,0.0010434893,0.00003526152,0.0000395496,0.000020967127,0.000029054007,0.9522865,0.0008442234,0.0059797843,0.0004313868,0.03920414],"study_design_scores_gemma":[0.0000021165504,0.000003641841,0.00013867328,0.0000029328392,0.0000022136016,0.000002108906,0.0000010572679,0.99757355,0.0001241924,0.0020752596,0.00007119049,0.0000031068907],"about_ca_topic_score_codex":0.006544626,"about_ca_topic_score_gemma":0.00638856,"teacher_disagreement_score":0.006544626,"about_ca_system_score_codex":0.00081149815,"about_ca_system_score_gemma":0.0006433596,"threshold_uncertainty_score":0.0139250755},"labels":[],"label_agreement":null},{"id":"W1588334962","doi":"","title":"A comparison of different decision algorithms used in volumetric storm cells classification","year":2002,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Support vector machine; Computer science; Radar; Algorithm; Rough set; Data set; Statistical classification; Storm; Decision table; Data mining; Decision support system; Artificial intelligence; Machine learning; Decision rule; Set (abstract data type); Training set; Database; Meteorology; Geography","score_opus":0.08031928922161695,"score_gpt":0.30135891453936053,"score_spread":0.22103962531774357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588334962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44492808,0.0059315497,0.5343486,0.0005759192,0.00039585598,0.0008879171,0.0008497301,0.001833185,0.010249135],"genre_scores_gemma":[0.66006917,0.0017366536,0.33519986,0.00012840734,0.00007401466,0.00031530685,0.0009742502,0.00009131505,0.0014109829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936187,0.0027217218,0.00085488346,0.0005427234,0.0019159504,0.00034605913],"domain_scores_gemma":[0.9830341,0.012530282,0.00052245293,0.000786249,0.0029553634,0.00017163505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008314752,0.0009502414,0.0012893204,0.0036775582,0.00064102496,0.0018095545,0.0010953961,0.0010509208,0.0009944404],"category_scores_gemma":[0.02139894,0.00026709877,0.00093383284,0.0030884468,0.00033212453,0.0015625145,0.00052614295,0.0007466243,0.00050178467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018420764,0.000492457,0.011720798,0.0006379982,0.0004162765,0.000102872385,0.00030911583,0.0857806,0.004830444,0.0032679015,0.0018501397,0.8887493],"study_design_scores_gemma":[0.0002836322,0.0024528478,0.014030279,0.00023044032,0.000553238,0.00037424066,0.0009362951,0.9396498,0.028792396,0.004877789,0.007710316,0.000108726344],"about_ca_topic_score_codex":0.0036640132,"about_ca_topic_score_gemma":0.0021898951,"teacher_disagreement_score":0.008314752,"about_ca_system_score_codex":0.0009845551,"about_ca_system_score_gemma":0.0008055473,"threshold_uncertainty_score":0.043973148},"labels":[],"label_agreement":null},{"id":"W1627096583","doi":"10.1029/2005wr003971","title":"Bayesian neural network for rainfall‐runoff modeling","year":2006,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":154,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Posterior probability; Artificial neural network; Bayesian probability; Gaussian; Bayesian linear regression; Conjugate prior; Prior probability; Computer science; Bayes' theorem; Bayesian hierarchical modeling; Bayesian network; Bayesian experimental design; Statistics; Mathematics; Bayesian inference; Artificial intelligence","score_opus":0.059830166891381,"score_gpt":0.30927526635414915,"score_spread":0.24944509946276816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1627096583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040743705,0.0009791956,0.99197054,0.00017449148,0.00005039926,0.000030581406,0.00012047154,0.00034542492,0.0022544758],"genre_scores_gemma":[0.61232513,0.0039474624,0.3683436,0.00027781536,0.00028819128,0.00069301826,0.001024111,0.00019025715,0.012910475],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993932,0.00023949398,0.0000359812,0.00009652256,0.0001875117,0.000047188674],"domain_scores_gemma":[0.99918956,0.00054970826,0.000069567715,0.000024464107,0.00014733878,0.000019321682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014440852,0.00083978515,0.0009866984,0.00082016725,0.00038724643,0.00092876883,0.0013949669,0.0012934813,0.0026838507],"category_scores_gemma":[0.003706749,0.0006626374,0.00065303745,0.0010804726,0.00043517505,0.0012684356,0.00074402435,0.0015853635,0.0006904924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024536623,0.000016273989,0.00031446197,0.000041824387,0.000032032232,0.00002003213,0.000015808213,0.96382296,0.00029107646,0.008242885,0.0005072355,0.026670843],"study_design_scores_gemma":[0.0000016692934,0.0000027765907,0.000046299116,0.0000045975294,0.0000030967074,0.000002330119,0.0000010761356,0.9967951,0.00005451307,0.0027667698,0.00031903948,0.0000027584902],"about_ca_topic_score_codex":0.01755172,"about_ca_topic_score_gemma":0.014119321,"teacher_disagreement_score":0.01755172,"about_ca_system_score_codex":0.0012151396,"about_ca_system_score_gemma":0.0011221942,"threshold_uncertainty_score":0.034899116},"labels":[],"label_agreement":null},{"id":"W1641747283","doi":"10.1029/2005wr004317","title":"Spiking modular neural networks: A neural network modeling approach for hydrological processes","year":2006,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Computer science; Modular design; Evapotranspiration; Layer (electronics); Discretization; Artificial intelligence; Mathematics","score_opus":0.07393577446529037,"score_gpt":0.29549013376074523,"score_spread":0.22155435929545486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1641747283","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012361726,0.00041544225,0.9848845,0.00018665683,0.000051953437,0.000026323924,0.00011278624,0.00022757366,0.001733018],"genre_scores_gemma":[0.74097717,0.0019093526,0.2513482,0.00018955702,0.00016839062,0.00023214403,0.00034233293,0.0000914919,0.0047413893],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998293,0.000055369568,0.000009865192,0.000037948143,0.0000517264,0.000015748634],"domain_scores_gemma":[0.9997367,0.00012088959,0.000041125826,0.000021647724,0.00006553919,0.0000140268285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051302137,0.0006793995,0.00043720624,0.0004447404,0.00026069896,0.0005502032,0.0010517606,0.00078385655,0.0009679547],"category_scores_gemma":[0.0011528076,0.0002999619,0.000788255,0.00071934785,0.00039798536,0.00096813176,0.000636103,0.0009234506,0.0001536324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015171741,0.000014045075,0.0004843597,0.000038189726,0.000042851876,0.000034110843,0.000019521389,0.96856713,0.0018247983,0.011121103,0.00035873873,0.017480023],"study_design_scores_gemma":[9.666613e-7,0.0000046821674,0.000058036447,0.0000018371529,0.0000028203885,0.000004113813,0.0000012707977,0.9967752,0.0001521062,0.0027256915,0.00027115367,0.0000020406924],"about_ca_topic_score_codex":0.004636174,"about_ca_topic_score_gemma":0.0045255716,"teacher_disagreement_score":0.004636174,"about_ca_system_score_codex":0.00068416586,"about_ca_system_score_gemma":0.0006585612,"threshold_uncertainty_score":0.009218395},"labels":[],"label_agreement":null},{"id":"W1645841444","doi":"","title":"Fractal analysis and graph theory applied to the spatial and temporal variability of soil water content","year":2010,"lang":"en","type":"article","venue":"EGUGA","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fractal dimension; Fractal; Water content; Spatial variability; Fractal analysis; Spatial analysis; Soil science; Mathematics; Environmental science; Remote sensing; Statistics; Geography; Geology","score_opus":0.010937819208632479,"score_gpt":0.20489882193202144,"score_spread":0.19396100272338895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1645841444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15595047,0.0023336937,0.83627206,0.00041866186,0.00009761161,0.00007660563,0.0005618586,0.00034590124,0.0039431774],"genre_scores_gemma":[0.8394293,0.002029702,0.15645024,0.00007126691,0.00015663469,0.00014113972,0.0005558284,0.000066957815,0.0010988445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939454,0.0002722214,0.00003994789,0.00011990696,0.00012736415,0.000046061334],"domain_scores_gemma":[0.995031,0.0036774788,0.0005613125,0.00023913455,0.00040276005,0.000088372515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011556603,0.0003839347,0.0005615357,0.0044940175,0.0003444983,0.0010058216,0.00035415127,0.00041438566,0.00058813853],"category_scores_gemma":[0.005778994,0.0002133954,0.0011060755,0.0029057455,0.0011327757,0.0008901801,0.0004097512,0.000615843,0.000084514264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014822386,0.00006303558,0.025719209,0.00046781698,0.00037001143,0.00054180453,0.0008076422,0.5069527,0.0120791085,0.20741712,0.0023526794,0.24308063],"study_design_scores_gemma":[0.000009710992,0.000062460786,0.022826979,0.000037067723,0.000043065298,0.00024553048,0.00014646677,0.85060173,0.0011024616,0.12109695,0.0037710355,0.00005649296],"about_ca_topic_score_codex":0.0058895554,"about_ca_topic_score_gemma":0.002661358,"teacher_disagreement_score":0.0058895554,"about_ca_system_score_codex":0.0010865222,"about_ca_system_score_gemma":0.0006415748,"threshold_uncertainty_score":0.011710584},"labels":[],"label_agreement":null},{"id":"W1701542504","doi":"10.22059/jdesert.2008.36302","title":"Monthly runoff forecasting by means of artificial neural networks (ANNs)","year":2008,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Self-organizing map; Artificial neural network; Computer science; Process (computing); Multilayer perceptron; Artificial intelligence; Nonlinear system; Cluster (spacecraft); Perceptron; Machine learning; Data mining","score_opus":0.25778487131520333,"score_gpt":0.4645149259986607,"score_spread":0.20673005468345734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1701542504","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19753295,0.00224552,0.7870762,0.0008317513,0.0002611861,0.00007450885,0.0008418628,0.0027825928,0.008353473],"genre_scores_gemma":[0.807165,0.0018919157,0.18731457,0.000099392004,0.00015487644,0.00008470026,0.0007192295,0.00007099244,0.002499269],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997671,0.00007092249,0.00002168334,0.00004235743,0.000082946135,0.000014949731],"domain_scores_gemma":[0.9995863,0.00023205504,0.00005687198,0.000027150623,0.000086408436,0.000011326076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062276865,0.00039164937,0.00041838232,0.0007734019,0.00018138748,0.0006007199,0.00042377182,0.00050591567,0.0010793549],"category_scores_gemma":[0.0020795362,0.0002168765,0.00030441643,0.0010497731,0.00014539322,0.0011150812,0.0002802882,0.0005532947,0.0003374461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011568939,0.00008487676,0.0093623595,0.00016810311,0.00013543892,0.000070939575,0.000067705674,0.7396634,0.0055303364,0.0039879857,0.0030027,0.23781046],"study_design_scores_gemma":[0.000004759469,0.000011025331,0.0013592457,0.0000090257545,0.00000881247,0.00000780289,0.0000070300825,0.9956252,0.00055955135,0.0016355756,0.0007658266,0.000006222514],"about_ca_topic_score_codex":0.00644977,"about_ca_topic_score_gemma":0.010855215,"teacher_disagreement_score":0.00644977,"about_ca_system_score_codex":0.00040578996,"about_ca_system_score_gemma":0.00031213873,"threshold_uncertainty_score":0.012824416},"labels":[],"label_agreement":null},{"id":"W17054965","doi":"10.1016/j.jbiomech.2006.09.002","title":"3-Dimensional Density Dependent Model of Seawater Intrusion for the Pine Rivers Shire, North Brisbane, Queensland","year":2006,"lang":"en","type":"article","venue":"Journal of Biomechanics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Groundwater recharge; Aquifer; Shire; Hydrology (agriculture); Saltwater intrusion; Seawater; Geology; Groundwater; Oceanography; Geography; Geotechnical engineering; Archaeology","score_opus":0.015933114483491835,"score_gpt":0.21156669523360042,"score_spread":0.1956335807501086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W17054965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6456798,0.0018403482,0.2112536,0.003712849,0.00035485346,0.00031414046,0.0067390534,0.0014682545,0.12863725],"genre_scores_gemma":[0.94530123,0.00045406073,0.009969431,0.00014187198,0.000023681527,0.00017615838,0.0013718739,0.00018168785,0.042380005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986243,0.000028381239,0.000005798904,0.00003834657,0.00003547753,0.000029496541],"domain_scores_gemma":[0.9998367,0.00004434188,0.00002392145,0.000011857797,0.00005895239,0.000024128089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020135884,0.00042459712,0.0004083085,0.0003667014,0.00060953264,0.0010155903,0.0014998442,0.0015824031,0.010805475],"category_scores_gemma":[0.0008161103,0.00053044636,0.00057755783,0.00033797216,0.0006676389,0.0004598794,0.00079519476,0.0006706975,0.001038775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041648454,0.000024975361,0.0029434005,0.000039096158,0.0000115038665,0.00020957533,0.00007770722,0.98800874,0.001841414,0.0029553478,0.0016531448,0.0021933666],"study_design_scores_gemma":[0.000013169225,0.000014596646,0.0022537936,0.000006867228,0.0000048838724,0.00003494471,0.00004218595,0.9949262,0.00011252602,0.0005531865,0.0020249789,0.000012561358],"about_ca_topic_score_codex":0.18937063,"about_ca_topic_score_gemma":0.09504822,"teacher_disagreement_score":0.18937063,"about_ca_system_score_codex":0.0021146284,"about_ca_system_score_gemma":0.0016019882,"threshold_uncertainty_score":0.37653673},"labels":[],"label_agreement":null},{"id":"W1714964298","doi":"10.7202/705565ar","title":"Estimation de la température de l'eau de rivière en utilisant les réseaux de neurones et la régression linéaire multiple","year":2005,"lang":"fr","type":"article","venue":"Revue des sciences de l eau","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Institut National de la Recherche Scientifique","funders":"","keywords":"Humanities; Physics; Art","score_opus":0.049192025233671756,"score_gpt":0.3409508910492579,"score_spread":0.29175886581558613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1714964298","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5983049,0.0017770273,0.39067963,0.00023615305,0.00013188999,0.00017094403,0.0010826753,0.0018635308,0.0057531744],"genre_scores_gemma":[0.89307684,0.0011349736,0.0942944,0.000043879085,0.000015317635,0.00016570126,0.00090348633,0.00016783719,0.010197608],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996039,0.000048062197,0.00002287124,0.00015422012,0.00012552028,0.00004541221],"domain_scores_gemma":[0.9993917,0.00019257897,0.00007318582,0.000057084053,0.00026643628,0.000019063027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008461814,0.001106673,0.0010170988,0.0007543392,0.00038666802,0.0012407185,0.0009049166,0.00086559623,0.0017344359],"category_scores_gemma":[0.0024489684,0.00044506244,0.001686383,0.0009796568,0.00031893895,0.00097300136,0.00045213182,0.0008546371,0.0009844693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031505668,0.000108258544,0.063081235,0.00066940696,0.00051417,0.00030741707,0.0005663173,0.5659011,0.11434007,0.0013937043,0.001086404,0.2517169],"study_design_scores_gemma":[0.000022605856,0.0002673614,0.08566438,0.00010999908,0.00025326546,0.00019152135,0.00040620755,0.8578708,0.047752533,0.0012155214,0.0061209993,0.0001247773],"about_ca_topic_score_codex":0.09784383,"about_ca_topic_score_gemma":0.1268728,"teacher_disagreement_score":0.09784383,"about_ca_system_score_codex":0.0015912122,"about_ca_system_score_gemma":0.0020282653,"threshold_uncertainty_score":0.1945486},"labels":[],"label_agreement":null},{"id":"W1768166163","doi":"10.14796/jwmm.r215-20","title":"Comparison of Neural Networks to Ormsbee's Method for Rain Generation - applied to Toronto, Ontario","year":2003,"lang":"en","type":"article","venue":"Journal of Water Management Modeling","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Artificial neural network; Key (lock); Rain rate; Function (biology); Meteorology; Environmental science; Hydrology (agriculture); Computer science; Geography; Engineering; Artificial intelligence; Geotechnical engineering; Precipitation","score_opus":0.06070284139289353,"score_gpt":0.31115279864869416,"score_spread":0.25044995725580066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1768166163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5295039,0.0070782225,0.38435644,0.0018219277,0.0007838297,0.00051173306,0.002994831,0.0039253207,0.0690238],"genre_scores_gemma":[0.8914662,0.0017696808,0.078216195,0.00012560276,0.000075741635,0.00012360691,0.0016396163,0.00036601973,0.026217299],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996623,0.00009315094,0.000020951536,0.0000536457,0.00011053765,0.00005937381],"domain_scores_gemma":[0.9988116,0.00047054962,0.000032388394,0.000058270874,0.00059005036,0.000037064805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010863142,0.00053513644,0.0004175018,0.0007906216,0.00067418086,0.0008858265,0.00083166215,0.00047241832,0.005903044],"category_scores_gemma":[0.0042036506,0.00018767928,0.0002939835,0.0013728498,0.00027633805,0.00064723444,0.00044979196,0.00032390552,0.0006137672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006240818,0.00008936929,0.00880203,0.00022038362,0.00014374469,0.000084850544,0.00016921991,0.5200303,0.0012491316,0.0063103647,0.010833855,0.45144263],"study_design_scores_gemma":[0.000032864355,0.000022740256,0.0034535914,0.000015519432,0.000022617754,0.0000094081115,0.00007011871,0.9926762,0.00065999466,0.0008549188,0.002174017,0.000008023698],"about_ca_topic_score_codex":0.77080685,"about_ca_topic_score_gemma":0.80550784,"teacher_disagreement_score":0.22919315,"about_ca_system_score_codex":0.0058983336,"about_ca_system_score_gemma":0.004585148,"threshold_uncertainty_score":0.4610858},"labels":[],"label_agreement":null},{"id":"W1821939522","doi":"10.1029/2008wr007196","title":"Regional low‐flow frequency analysis using single and ensemble artificial neural networks","year":2009,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale pour la Gestion des Déchets Radioactifs","keywords":"Artificial neural network; Generalization; Jackknife resampling; Computer science; Ensemble learning; Quantile; Ensemble forecasting; Artificial intelligence; Perceptron; Multilayer perceptron; Parametric statistics; Nonparametric statistics; Regression; Machine learning; Mathematics; Statistics; Estimator","score_opus":0.09425411509377377,"score_gpt":0.31540218962023336,"score_spread":0.2211480745264596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1821939522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5542983,0.00047226413,0.4396309,0.00013666126,0.000057066216,0.00003566076,0.0005849407,0.0010481275,0.003736109],"genre_scores_gemma":[0.94991356,0.00013901081,0.048888985,0.00001110442,0.000033093933,0.000016260652,0.00044916905,0.000033840308,0.0005149626],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997904,0.00004906928,0.000011473669,0.00005464742,0.000069550755,0.000024886602],"domain_scores_gemma":[0.9994727,0.00020161844,0.00007875593,0.00006919949,0.00015446922,0.000023358893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007233963,0.0003307923,0.0004648465,0.0015174745,0.00024387191,0.00059834134,0.00039367768,0.00025201752,0.00060599425],"category_scores_gemma":[0.0019206683,0.00013760594,0.00043742178,0.00096327154,0.000106080835,0.0008455153,0.00030509752,0.00031112204,0.00014021728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008096451,0.00005144165,0.03299958,0.00004915919,0.00021633839,0.000109332796,0.000081904596,0.76422316,0.0043912306,0.0014000932,0.00084569474,0.19555111],"study_design_scores_gemma":[0.000002814111,0.000008816202,0.0086856615,0.00000339626,0.000018452567,0.000011291139,0.00001644605,0.98971796,0.0006265821,0.00061590294,0.00028463165,0.000008048101],"about_ca_topic_score_codex":0.02087036,"about_ca_topic_score_gemma":0.022912562,"teacher_disagreement_score":0.02087036,"about_ca_system_score_codex":0.00052422046,"about_ca_system_score_gemma":0.00036756293,"threshold_uncertainty_score":0.041497767},"labels":[],"label_agreement":null},{"id":"W1827830884","doi":"10.17485/ijst/2015/v8i14/54370","title":"Rainfall Runoff Analysis using Artificial Neural Network","year":2015,"lang":"en","type":"article","venue":"Indian Journal of Science and Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Indian Institute of Technology Roorkee","keywords":"Hydrograph; Surface runoff; Runoff model; Artificial neural network; Computer science; Runoff curve number; Environmental science; Hydrology (agriculture); Vflo; Process (computing); Machine learning; Watershed; Geology; Geotechnical engineering; Ecology","score_opus":0.03305647505014399,"score_gpt":0.26483991569750365,"score_spread":0.23178344064735967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1827830884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30768833,0.000743421,0.6782913,0.0003347919,0.000085253014,0.00026207967,0.0008772309,0.002397914,0.009319694],"genre_scores_gemma":[0.9392886,0.00040757467,0.057076078,0.000035549514,0.00002706482,0.0001523065,0.00060759,0.00004231299,0.0023627991],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997938,0.000049198683,0.000020238485,0.00004101869,0.00007965662,0.000016107591],"domain_scores_gemma":[0.99968576,0.00014576709,0.000044630404,0.00001535435,0.00010113306,0.0000072276916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003635206,0.00043763447,0.00034763766,0.00089698425,0.00014970744,0.00048262838,0.00038589875,0.00036510293,0.0018966284],"category_scores_gemma":[0.00097311346,0.00013261914,0.0004196621,0.0009501274,0.000115358285,0.0005538888,0.00019724105,0.00035541644,0.00029844063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013285359,0.00014656158,0.0068528582,0.00016348316,0.00008209998,0.000106695086,0.000029305942,0.87834835,0.008514842,0.00089904136,0.00083600305,0.10388787],"study_design_scores_gemma":[0.0000029271912,0.000021309246,0.0013875255,0.0000048085767,0.0000053013277,0.000009986053,0.0000060567318,0.9967488,0.0012367027,0.0003500412,0.00022203519,0.0000045679735],"about_ca_topic_score_codex":0.0036084051,"about_ca_topic_score_gemma":0.0024808778,"teacher_disagreement_score":0.0036084051,"about_ca_system_score_codex":0.00046530532,"about_ca_system_score_gemma":0.0003233064,"threshold_uncertainty_score":0.00717479},"labels":[],"label_agreement":null},{"id":"W1854912902","doi":"10.1002/wrcr.20517","title":"Urban water demand forecasting and uncertainty assessment using ensemble wavelet-bootstrap-neural network models","year":2013,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":205,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Ste. Anne's Hospital","funders":"","keywords":"Autoregressive integrated moving average; Autoregressive model; Wavelet; Statistics; Bootstrap aggregating; Econometrics; Artificial neural network; Computer science; Bootstrap model; Ensemble forecasting; Bootstrapping (finance); Moving average; Time series; Mathematics; Artificial intelligence","score_opus":0.13176638131771926,"score_gpt":0.3268046037635469,"score_spread":0.19503822244582766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1854912902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43545622,0.00057375117,0.55942464,0.0002152003,0.000054986187,0.00004024775,0.00046776075,0.00037976162,0.0033874814],"genre_scores_gemma":[0.9774969,0.00018638343,0.021438247,0.000015179804,0.000018222994,0.000025192523,0.0002559236,0.000012053259,0.0005519406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978095,0.00006849155,0.0000117736745,0.000039746235,0.000077039505,0.000022069684],"domain_scores_gemma":[0.99960774,0.00019321578,0.000050164486,0.000025094601,0.000113698625,0.000010121224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071520894,0.00050241477,0.00045001326,0.000589149,0.00019563739,0.0004940164,0.0006474519,0.00041569327,0.00046573643],"category_scores_gemma":[0.0019859918,0.00019933608,0.00043038864,0.0006599636,0.00014960399,0.0008083851,0.00038107496,0.00042415923,0.00008426938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032353648,0.000024424611,0.0028985976,0.000017551012,0.000031603064,0.00003539044,0.0000142881545,0.969537,0.0004482821,0.00076384447,0.00022796082,0.025968716],"study_design_scores_gemma":[5.373183e-7,0.0000028946245,0.00029113464,6.600989e-7,0.0000019010785,0.0000017941364,0.0000017067148,0.9994479,0.00006709648,0.00015949743,0.000023745395,0.0000010903938],"about_ca_topic_score_codex":0.019894479,"about_ca_topic_score_gemma":0.018298488,"teacher_disagreement_score":0.019894479,"about_ca_system_score_codex":0.0006274413,"about_ca_system_score_gemma":0.00044661755,"threshold_uncertainty_score":0.039557338},"labels":[],"label_agreement":null},{"id":"W1874570887","doi":"10.1002/hyp.9495","title":"Multifractal behaviour of long‐term karstic discharge fluctuations","year":2012,"lang":"en","type":"article","venue":"Hydrological Processes","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Multifractal system; Karst; Hydrology (agriculture); Aquifer; Geology; Hydrogeology; Series (stratigraphy); Sampling (signal processing); Time series; Environmental science; Groundwater; Statistics; Fractal; Mathematics; Geotechnical engineering; Physics","score_opus":0.031226980537431472,"score_gpt":0.27567264642424627,"score_spread":0.2444456658868148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1874570887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891762,0.000045643756,0.010139702,0.00006227017,0.0000038353196,0.0000057798106,0.00012503557,0.00006452702,0.00037704076],"genre_scores_gemma":[0.99946576,0.000009428893,0.00041230317,0.0000016958875,0.0000017970385,0.0000011642211,0.000051023904,0.000002488774,0.000054314405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99986327,0.000029875928,0.000007852128,0.00003536642,0.00003630268,0.000027209166],"domain_scores_gemma":[0.9992893,0.00026142938,0.00019331105,0.00007390534,0.00010845774,0.00007364642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049126835,0.00017077097,0.00013576394,0.0008463883,0.00018667591,0.00034690517,0.0002038594,0.00022110881,0.0006442346],"category_scores_gemma":[0.0025834634,0.00011096753,0.00019913053,0.0005651499,0.00032846775,0.00038605533,0.00026611457,0.00026420763,0.00008428441],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029376548,0.00019162346,0.35012415,0.00010068859,0.00017791009,0.00090775255,0.0012769733,0.4830558,0.07985766,0.010989789,0.0016354122,0.071388505],"study_design_scores_gemma":[0.0000053622066,0.00002820834,0.23831476,0.0000052791643,0.000010456265,0.000086535445,0.000054099895,0.7579315,0.0016036443,0.0016045751,0.00033743243,0.000018176233],"about_ca_topic_score_codex":0.0064621456,"about_ca_topic_score_gemma":0.003989403,"teacher_disagreement_score":0.0064621456,"about_ca_system_score_codex":0.00048811623,"about_ca_system_score_gemma":0.00017492472,"threshold_uncertainty_score":0.0128490925},"labels":[],"label_agreement":null},{"id":"W188910934","doi":"","title":"Application of Bayesian Inference Techniques for Calibrating Eutrophication Models","year":2008,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Bayesian inference; Calibration; Bayesian probability; Inference; Computer science; Frequentist inference; Data mining; Water quality; Machine learning; Quality (philosophy); Artificial intelligence; Statistics; Mathematics; Ecology","score_opus":0.01881704567188581,"score_gpt":0.25621952168803286,"score_spread":0.23740247601614706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W188910934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037700278,0.0001090213,0.9946015,0.00012667586,0.000009758397,0.000015341488,0.0000334903,0.00010080273,0.0012335802],"genre_scores_gemma":[0.28467274,0.0008104168,0.71241444,0.00012174189,0.00007167362,0.00020902949,0.00027319256,0.00015912805,0.0012676097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974632,0.0014367872,0.00015974445,0.00027150186,0.0005992363,0.00006954574],"domain_scores_gemma":[0.9914568,0.006299714,0.00084757124,0.00051648024,0.00081692974,0.00006249831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007514737,0.0007203031,0.0007191398,0.0022626477,0.00054108095,0.0012525844,0.0016138271,0.00081886706,0.0015829102],"category_scores_gemma":[0.030391406,0.00088345446,0.0008128084,0.0017296218,0.001147484,0.0019740588,0.0015128814,0.0018126174,0.0003157706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010655897,0.000021463906,0.0010595043,0.00006701266,0.00006112044,0.000035029992,0.00011119755,0.87606287,0.00066638534,0.07264705,0.00038832249,0.048869394],"study_design_scores_gemma":[0.0000061931287,0.0000057879834,0.00029713116,0.000022336413,0.000009860275,0.0000140287575,0.000014416383,0.9442068,0.0005135832,0.05400483,0.0008916065,0.000013355527],"about_ca_topic_score_codex":0.010006619,"about_ca_topic_score_gemma":0.008549458,"teacher_disagreement_score":0.010006619,"about_ca_system_score_codex":0.0015824378,"about_ca_system_score_gemma":0.0014433655,"threshold_uncertainty_score":0.03974217},"labels":[],"label_agreement":null},{"id":"W1920848989","doi":"10.1109/ijcnn.1999.830759","title":"Real-time short-term natural water inflows forecasting using recurrent neural networks","year":2003,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Recurrent neural network; Computer science; Autoregressive model; Inflow; Artificial neural network; Hydropower; Backpropagation; Term (time); Scheduling (production processes); Moving average; Artificial intelligence; Econometrics; Meteorology; Engineering; Mathematical optimization; Mathematics; Geography","score_opus":0.03410762630490464,"score_gpt":0.2514515452857924,"score_spread":0.21734391898088776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1920848989","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6296518,0.00062356924,0.36562476,0.00032118452,0.00007578299,0.000025230793,0.00017087426,0.0012797983,0.0022270589],"genre_scores_gemma":[0.9726972,0.00018990002,0.02642609,0.000017960014,0.000014676428,0.000015242859,0.00017845393,0.000014779269,0.0004456257],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977976,0.00008000983,0.000019442405,0.000035230405,0.00006405794,0.000021591479],"domain_scores_gemma":[0.9991875,0.0004948457,0.00009346407,0.000055372882,0.00014979708,0.000018888319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00108377,0.00035842025,0.00031206734,0.00025063058,0.000119437995,0.00038815785,0.00038613574,0.00036432428,0.0002922659],"category_scores_gemma":[0.0027814712,0.00015782073,0.0002083498,0.00023911281,0.00019587556,0.00080747664,0.00015823224,0.0003547215,0.00014552152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019721649,0.00009641676,0.004508473,0.000068092726,0.00007206071,0.00010079252,0.00005389954,0.8591539,0.013427134,0.001396432,0.0006623756,0.12026319],"study_design_scores_gemma":[0.000003588148,0.000030144363,0.0005064462,0.0000019080371,0.000006946731,0.000007636765,0.0000031731197,0.99684453,0.002210277,0.00029418073,0.00008798076,0.0000031797902],"about_ca_topic_score_codex":0.0045186705,"about_ca_topic_score_gemma":0.0050845146,"teacher_disagreement_score":0.0045186705,"about_ca_system_score_codex":0.00031619234,"about_ca_system_score_gemma":0.00021312496,"threshold_uncertainty_score":0.008984685},"labels":[],"label_agreement":null},{"id":"W194799047","doi":"","title":"Fuzzy Neural Networks for water level and discharge forecasting","year":2010,"lang":"en","type":"article","venue":"Institutional Research Information System University of Ferrara (University of Ferrara)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Fuzzy logic; Fuzzy number; Neuro-fuzzy; Fuzzy set; Extension (predicate logic); Set (abstract data type); Mathematics; Adaptive neuro fuzzy inference system; Artificial intelligence; Fuzzy set operations; Variable (mathematics); Computer science; Data mining; Fuzzy control system","score_opus":0.11175630366288936,"score_gpt":0.2622277553820683,"score_spread":0.15047145171917892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W194799047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01309162,0.0027180421,0.9773393,0.00043499185,0.00014122516,0.000047638972,0.00012734439,0.00035176578,0.0057480265],"genre_scores_gemma":[0.66704875,0.003707627,0.31366438,0.00020138553,0.00026469104,0.0002723676,0.00042676434,0.000063140375,0.014350836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994615,0.0001931936,0.000035137495,0.00009155169,0.0001821414,0.000036432622],"domain_scores_gemma":[0.9994567,0.00031603518,0.000048113725,0.000028594412,0.00014031856,0.000010199336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011183865,0.000561955,0.0006443322,0.00079763576,0.00035882316,0.0010865466,0.0008263982,0.0011141314,0.0014990197],"category_scores_gemma":[0.002967275,0.0003148447,0.0005355546,0.0010862119,0.00047585656,0.0010583013,0.0005089573,0.0012957879,0.00034376374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042162614,0.00001981672,0.00037165164,0.00006393013,0.00003668766,0.00004294158,0.00003542814,0.9076363,0.0011491253,0.020033984,0.000726416,0.06984163],"study_design_scores_gemma":[0.0000022788015,0.0000036994031,0.00008882795,0.000007489324,0.000002882016,0.0000033642934,0.000003109499,0.9941526,0.00023913498,0.004983267,0.00050855573,0.000004830659],"about_ca_topic_score_codex":0.014155228,"about_ca_topic_score_gemma":0.008604367,"teacher_disagreement_score":0.014155228,"about_ca_system_score_codex":0.001320235,"about_ca_system_score_gemma":0.0008869751,"threshold_uncertainty_score":0.02814567},"labels":[],"label_agreement":null},{"id":"W1949379220","doi":"10.1109/nafips.2005.1548642","title":"Hydrologic model Calibration using Fuzzy TSK surrogate model","year":2005,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Surrogate model; Robustness (evolution); Mathematical optimization; Curse of dimensionality; Computer science; Calibration; Fuzzy logic; Minification; Function (biology); Algorithm; Mathematics; Artificial intelligence; Statistics","score_opus":0.05084249324267324,"score_gpt":0.26240280372994634,"score_spread":0.2115603104872731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1949379220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1327735,0.00010425956,0.8597894,0.00023253393,0.00004059428,0.000076017146,0.00034751333,0.00074756186,0.005888604],"genre_scores_gemma":[0.87929535,0.00013727606,0.1183664,0.00003184198,0.00000780794,0.00013096938,0.00048309288,0.000076056895,0.0014712671],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995415,0.00016391874,0.00003830543,0.00006699937,0.0001543148,0.000035071942],"domain_scores_gemma":[0.9990368,0.00037622324,0.00009040895,0.00013815463,0.0003315545,0.000026874912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010641742,0.00043635935,0.00071957824,0.00045565132,0.00045499136,0.0010275132,0.0006608753,0.0009892513,0.0015102437],"category_scores_gemma":[0.0035812315,0.00028957415,0.0006182283,0.0009119053,0.00047358766,0.0010177173,0.0005322151,0.0010014304,0.00038804443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021884758,0.000009713646,0.000328055,0.000015045421,0.000006444314,0.00001379211,0.000013701272,0.99152184,0.0012229573,0.001450896,0.00012760004,0.0052681123],"study_design_scores_gemma":[0.0000022627958,0.0000061918386,0.0000946497,0.0000019708639,0.0000011386683,0.0000039577385,0.000004707902,0.99823123,0.0008365039,0.0006457969,0.00016851166,0.0000031133777],"about_ca_topic_score_codex":0.00475093,"about_ca_topic_score_gemma":0.0026244123,"teacher_disagreement_score":0.00475093,"about_ca_system_score_codex":0.00078748807,"about_ca_system_score_gemma":0.001206908,"threshold_uncertainty_score":0.009446561},"labels":[],"label_agreement":null},{"id":"W1960909337","doi":"10.1139/s08-041","title":"Modelling nitrogen composition in streams on the Boreal Plain using genetic adaptive general regression neural networks","year":2008,"lang":"en","type":"article","venue":"Journal of Environmental Engineering and Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Lakehead University; Alberta Health Services; Canadian Natural Resources; University of Alberta","funders":"","keywords":"Watershed; STREAMS; Environmental science; Artificial neural network; Hydrology (agriculture); Regression; Water quality; Mean squared error; Computer science; Ecology; Machine learning; Statistics; Mathematics; Engineering; Biology","score_opus":0.02063669630692865,"score_gpt":0.19962060308664886,"score_spread":0.1789839067797202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960909337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866927,0.000051731513,0.012509958,0.000037367925,0.0000048246097,0.000013799433,0.00006421859,0.00007523912,0.00055026467],"genre_scores_gemma":[0.9946755,0.00004000039,0.0049302634,0.000004431071,0.0000024305891,0.000008241033,0.000074566546,0.000002905793,0.00026174408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992967,0.000018609755,0.000004997154,0.000019533682,0.000015453534,0.000011652732],"domain_scores_gemma":[0.99982965,0.00008003496,0.000033326007,0.0000062582017,0.00004144737,0.000009224851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032104086,0.0003234337,0.00018451431,0.00031236527,0.00024914247,0.0003736054,0.00029967006,0.00027936246,0.00016385093],"category_scores_gemma":[0.00067306316,0.00013000838,0.00023307696,0.0003501429,0.00022002427,0.00029034045,0.0001233954,0.00016511833,0.000026776484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004541892,0.000036269947,0.023230257,0.000010598105,0.00002042548,0.00004164402,0.00002761244,0.96532446,0.0018892644,0.00016133042,0.00005773644,0.00915493],"study_design_scores_gemma":[0.0000042969627,0.00001466935,0.006080822,0.0000010985217,0.0000053758718,0.0000043178716,0.000014258961,0.99325657,0.00044027236,0.00013350476,0.00004159982,0.0000031655907],"about_ca_topic_score_codex":0.16935976,"about_ca_topic_score_gemma":0.17842399,"teacher_disagreement_score":0.16935976,"about_ca_system_score_codex":0.000931423,"about_ca_system_score_gemma":0.0008633145,"threshold_uncertainty_score":0.33674794},"labels":[],"label_agreement":null},{"id":"W1964195888","doi":"10.1139/s03-006","title":"Acid deposition in the eastern United States and neural network predictions for the future","year":2003,"lang":"en","type":"article","venue":"Journal of Environmental Engineering and Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Acid rain; Acid deposition; Environmental science; Sulfur dioxide; Precipitation; Pollution; Nitrate; Sulfur; Ammonium; Air pollution; Deposition (geology); Environmental protection; Environmental chemistry; Environmental engineering; Atmospheric sciences; Meteorology; Chemistry; Ecology; Geography; Soil science; Biology; Inorganic chemistry; Geology","score_opus":0.006693755125859917,"score_gpt":0.1874018242185571,"score_spread":0.18070806909269718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964195888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928599,0.0003053601,0.002254432,0.0005958601,0.000036370173,0.0000061911032,0.0013591882,0.00006607604,0.0025167055],"genre_scores_gemma":[0.99776745,0.00018433346,0.0006055757,0.000021233765,0.000008436161,0.0000048523634,0.00071753305,0.000004273942,0.0006863282],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99994814,0.000015528944,0.000005595284,0.0000146774455,0.000008921299,0.0000071163504],"domain_scores_gemma":[0.9997004,0.000111351816,0.00006195534,0.000011490265,0.00009205921,0.00002282577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035384705,0.0002674754,0.00012284327,0.0004448205,0.0002169851,0.0005478953,0.00020952219,0.00043323546,0.0012276915],"category_scores_gemma":[0.0013836332,0.00017874005,0.00023439893,0.00060635793,0.00016234166,0.0005186074,0.00020679027,0.00034225674,0.00018072024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013013477,0.000042094376,0.17249934,0.000038955524,0.000096194686,0.00025718223,0.000081923106,0.812236,0.0005160018,0.0016069278,0.0020510722,0.010444132],"study_design_scores_gemma":[0.000015280986,0.000015873005,0.04971961,0.000017064185,0.000017899085,0.000027449252,0.00007448158,0.94738287,0.0002721813,0.0015486969,0.00089952914,0.000009064587],"about_ca_topic_score_codex":0.152165,"about_ca_topic_score_gemma":0.14802402,"teacher_disagreement_score":0.152165,"about_ca_system_score_codex":0.0013401512,"about_ca_system_score_gemma":0.00047329903,"threshold_uncertainty_score":0.3025586},"labels":[],"label_agreement":null},{"id":"W1964298122","doi":"10.1007/s00521-004-0413-4","title":"An ensemble of neural networks for weather forecasting","year":2004,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":318,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Artificial neural network; Computer science; Perceptron; Ensemble forecasting; Multilayer perceptron; Ensemble learning; Weather forecasting; Artificial intelligence; Wind speed; Machine learning; Meteorology","score_opus":0.029770359021225573,"score_gpt":0.2707457742965049,"score_spread":0.24097541527527935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964298122","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09142225,0.0042245807,0.89431924,0.00056144386,0.0010906805,0.00007033294,0.0005215311,0.0015011108,0.006288859],"genre_scores_gemma":[0.739322,0.0018209461,0.24855968,0.00027390063,0.0005097435,0.00013070188,0.0010066454,0.00014064144,0.008235573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999495,0.00013007071,0.00003990728,0.00010849,0.00015661641,0.000069947746],"domain_scores_gemma":[0.99894565,0.0003318102,0.000053120624,0.00015306116,0.0004676124,0.00004871276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015949354,0.0006251361,0.001242438,0.0008577184,0.0005358102,0.0007900903,0.0010725351,0.00084195327,0.0018545152],"category_scores_gemma":[0.0032374556,0.0004596905,0.0008148918,0.0014078002,0.00020833174,0.0017406895,0.00084061973,0.0015199851,0.00055375445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024288164,0.00015680869,0.0028669331,0.000078047415,0.00045545955,0.00006760441,0.000054515607,0.5648243,0.0032102675,0.0036353967,0.0060131676,0.4183946],"study_design_scores_gemma":[0.0000050072445,0.000023767883,0.00033617072,0.0000047340145,0.00003983462,0.000007666263,0.000004114387,0.9970703,0.00048587038,0.0014175846,0.00059977133,0.000005073463],"about_ca_topic_score_codex":0.009114851,"about_ca_topic_score_gemma":0.013874273,"teacher_disagreement_score":0.009114851,"about_ca_system_score_codex":0.00044975744,"about_ca_system_score_gemma":0.0006247033,"threshold_uncertainty_score":0.018123627},"labels":[],"label_agreement":null},{"id":"W1967936067","doi":"10.1139/l09-074","title":"Reference evapotranspiration forecasting using different artificial neural networks algorithms","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Backpropagation; Evapotranspiration; Algorithm; Mean squared error; Artificial intelligence; Computer science; Machine learning; Statistics; Mathematics","score_opus":0.04540665865782659,"score_gpt":0.2191634154699389,"score_spread":0.1737567568121123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967936067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65316224,0.0026842556,0.33495322,0.00043609738,0.00018891385,0.000083952335,0.00025890997,0.00081556593,0.007416838],"genre_scores_gemma":[0.91906863,0.00068694184,0.0783269,0.000037586244,0.000021271457,0.000053722404,0.00022473106,0.000022435961,0.0015577059],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997008,0.000069012734,0.00003537376,0.000071676186,0.00009640652,0.00002675839],"domain_scores_gemma":[0.99959797,0.00015368199,0.00006049041,0.000024529812,0.00014992106,0.000013341564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007451281,0.0005654101,0.00047318832,0.00066004536,0.00022924056,0.000592867,0.00074200175,0.0005680513,0.0004021161],"category_scores_gemma":[0.001589651,0.00022989107,0.00054541306,0.00088826654,0.00018605059,0.0005756176,0.0003173015,0.00040408454,0.000109973524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001303195,0.000099100245,0.004472963,0.0000952916,0.000080746926,0.000073871975,0.00004695481,0.9146643,0.0034795757,0.00074092427,0.0004442831,0.07567158],"study_design_scores_gemma":[0.0000037887623,0.000018011524,0.00091548875,0.000005178224,0.000008253137,0.000007508657,0.000005126405,0.99812764,0.00064273906,0.00014774667,0.000113959286,0.0000046274627],"about_ca_topic_score_codex":0.010952359,"about_ca_topic_score_gemma":0.0088884225,"teacher_disagreement_score":0.010952359,"about_ca_system_score_codex":0.0005946811,"about_ca_system_score_gemma":0.000493681,"threshold_uncertainty_score":0.021777213},"labels":[],"label_agreement":null},{"id":"W1969367207","doi":"10.1139/l00-016","title":"Real-time daily flow forecasting using black-box models, diffusion processes, and neural networks","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Context (archaeology); Black box; Computer science; Outlier; Surface runoff; Field (mathematics); Term (time); Autoregressive model; Streamflow; Environmental science; Meteorology; Econometrics; Machine learning; Artificial intelligence; Geography; Mathematics; Ecology; Cartography","score_opus":0.014075502087621943,"score_gpt":0.17916090237237225,"score_spread":0.1650854002847503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969367207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.698587,0.0016123648,0.29329336,0.0006083698,0.000082571925,0.00008421858,0.00040121193,0.00062495185,0.0047059264],"genre_scores_gemma":[0.97934765,0.00046011122,0.019048758,0.000025860616,0.000017749484,0.00003517372,0.00016140242,0.00001663931,0.00088668714],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995776,0.0001965112,0.000020921072,0.00007041704,0.00009658291,0.000037852795],"domain_scores_gemma":[0.99854726,0.0010511122,0.00016981435,0.000041176005,0.00015852292,0.000032005457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017620601,0.0009049653,0.0005616136,0.0008128119,0.00024527055,0.00097217376,0.0005810678,0.0008041246,0.00065913174],"category_scores_gemma":[0.0033631714,0.0002704472,0.0003791118,0.0008807909,0.00042513822,0.0016771836,0.00037118015,0.0005927001,0.00012317134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007573363,0.000026620954,0.0016458858,0.000033578628,0.00002608575,0.000021080408,0.000031626612,0.98542804,0.0005083175,0.00086249347,0.00011037163,0.011230144],"study_design_scores_gemma":[0.000003896008,0.000013340222,0.00047538633,0.0000038718654,0.0000035819423,0.0000022094785,0.0000057660372,0.99884367,0.00021442796,0.00036520814,0.00006443258,0.000004071841],"about_ca_topic_score_codex":0.055516265,"about_ca_topic_score_gemma":0.03301431,"teacher_disagreement_score":0.055516265,"about_ca_system_score_codex":0.0014986714,"about_ca_system_score_gemma":0.00091442064,"threshold_uncertainty_score":0.11038625},"labels":[],"label_agreement":null},{"id":"W1969391747","doi":"10.2166/hydro.2008.006","title":"Improving groundwater level forecasting with a feedforward neural network and linearly regressed projected precipitation","year":2008,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Groundwater; Groundwater recharge; Aquifer; Precipitation; Feedforward neural network; Surface runoff; Artificial neural network; Environmental science; Feed forward; Hydrology (agriculture); Component (thermodynamics); Meteorology; Geology; Computer science; Engineering; Geography; Machine learning; Geotechnical engineering; Ecology","score_opus":0.04257155452134622,"score_gpt":0.21790547285475584,"score_spread":0.1753339183334096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969391747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2649359,0.00038535683,0.7285579,0.00019864553,0.0001571648,0.000090420064,0.00023665748,0.002521964,0.0029160532],"genre_scores_gemma":[0.85619944,0.00011648707,0.1404069,0.000074756834,0.000053016305,0.000108062515,0.0002914882,0.000043583408,0.002706339],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998154,0.00004099736,0.00001692458,0.000055552653,0.00004443267,0.000026684032],"domain_scores_gemma":[0.9994867,0.00023935427,0.00004008607,0.000037572434,0.00017634137,0.000019949734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000778119,0.000641883,0.0005282487,0.00043174613,0.00022113115,0.00037863373,0.0006645087,0.0007189367,0.0009946912],"category_scores_gemma":[0.0019094142,0.00028563145,0.00048278808,0.0005057395,0.00019083844,0.0006024928,0.000424722,0.0006436537,0.00029258456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018685049,0.00015818432,0.003044923,0.00005828529,0.00010352485,0.000082815146,0.000040605726,0.7469136,0.009762254,0.0005231713,0.0008704815,0.23825534],"study_design_scores_gemma":[0.0000048358424,0.000023073244,0.0004416311,0.0000017930762,0.0000064747765,0.0000040654054,0.0000011639786,0.9982231,0.001125924,0.00008954765,0.00007522302,0.0000030302215],"about_ca_topic_score_codex":0.012265964,"about_ca_topic_score_gemma":0.010665645,"teacher_disagreement_score":0.012265964,"about_ca_system_score_codex":0.0004819179,"about_ca_system_score_gemma":0.0006056675,"threshold_uncertainty_score":0.024389088},"labels":[],"label_agreement":null},{"id":"W1971665758","doi":"10.1061/(asce)1084-0699(2001)6:5(367)","title":"Multivariate Reservoir Inflow Forecasting Using Temporal Neural Networks","year":2001,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Hydro-Québec; Centre de Géomatique du Québec; Institut National de la Recherche Scientifique","funders":"","keywords":"Inflow; Multivariate statistics; Recurrent neural network; Computer science; Artificial neural network; Multilayer perceptron; Reservoir computing; Time series; Hydropower; Multivariate analysis; Artificial intelligence; Hydrology (agriculture); Machine learning; Geology; Engineering","score_opus":0.04033891197865237,"score_gpt":0.2443177684813604,"score_spread":0.20397885650270803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971665758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.843396,0.00017333272,0.15113431,0.00032036172,0.00006637147,0.000032158077,0.0003015162,0.0007835824,0.003792387],"genre_scores_gemma":[0.98309916,0.00006971681,0.01621661,0.000011343378,0.000007978201,0.000012547859,0.00011572894,0.000009560047,0.00045742837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997378,0.00010595931,0.000017608221,0.00003670338,0.0000740205,0.000027827818],"domain_scores_gemma":[0.9988444,0.0007562475,0.000078204306,0.000103029925,0.00018536617,0.000032725347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010964993,0.00030406954,0.00028708883,0.00026611227,0.0001334578,0.00031133596,0.00026662197,0.00027481338,0.000896953],"category_scores_gemma":[0.0039108354,0.00010321269,0.0002293363,0.00049397827,0.00013571761,0.00091625395,0.00021435854,0.00036790207,0.00012127873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006935396,0.00018222224,0.010199881,0.000079840116,0.000059331633,0.00013667706,0.000059424947,0.7982224,0.015131607,0.0029761894,0.0009784908,0.17128041],"study_design_scores_gemma":[0.000006964154,0.000060221668,0.0010563736,0.0000015739655,0.0000067515953,0.0000094445495,0.0000052620558,0.99495786,0.003309603,0.0004052449,0.00017657614,0.000004175945],"about_ca_topic_score_codex":0.006447278,"about_ca_topic_score_gemma":0.004855039,"teacher_disagreement_score":0.006447278,"about_ca_system_score_codex":0.0003561331,"about_ca_system_score_gemma":0.00027220833,"threshold_uncertainty_score":0.012819529},"labels":[],"label_agreement":null},{"id":"W1972858106","doi":"10.1016/j.aqpro.2015.02.070","title":"Forecasting of Time Series Significant Wave Height Using Wavelet Decomposed Neural Network","year":2015,"lang":"en","type":"article","venue":"Aquatic Procedia","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Oceanic and Atmospheric Administration","keywords":"Wavelet; Series (stratigraphy); Significant wave height; Artificial neural network; Mathematics; Data set; Wave height; Meteorology; Transformation (genetics); Wavelet transform; Geodesy; Statistics; Algorithm; Geography; Geology; Wind wave; Computer science; Artificial intelligence","score_opus":0.0702267558650177,"score_gpt":0.24021605441751478,"score_spread":0.1699892985524971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972858106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4761612,0.0007070146,0.5188818,0.00016581996,0.00010881585,0.00003426522,0.00025869755,0.0004875786,0.0031948432],"genre_scores_gemma":[0.9693954,0.00029192044,0.028382167,0.000019860454,0.000014326439,0.000024097728,0.00021781688,0.000013146754,0.0016412785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990475,0.000017214426,0.000006481207,0.000023346625,0.00003245995,0.000015821965],"domain_scores_gemma":[0.99988496,0.000049445465,0.000015725751,0.000008144677,0.00003582431,0.000005803555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029630068,0.000338143,0.00029646797,0.00030205568,0.00012178796,0.00038889216,0.00035705641,0.0003152932,0.000425303],"category_scores_gemma":[0.0006045319,0.0001439463,0.00029015585,0.0004628168,0.000089351466,0.00050423335,0.00019930546,0.00035916452,0.00013255315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082598235,0.0000679075,0.006119406,0.00004464871,0.00005542792,0.00007516976,0.00002958251,0.92002493,0.00583416,0.0006896061,0.0004217074,0.06655477],"study_design_scores_gemma":[0.000001125635,0.000008054219,0.00050265645,0.0000010250607,0.000002635436,0.0000028079096,0.0000022530041,0.999071,0.0002691283,0.000084179876,0.000053747794,0.0000014119219],"about_ca_topic_score_codex":0.0065294276,"about_ca_topic_score_gemma":0.0059284074,"teacher_disagreement_score":0.0065294276,"about_ca_system_score_codex":0.00020839511,"about_ca_system_score_gemma":0.00028572028,"threshold_uncertainty_score":0.012982845},"labels":[],"label_agreement":null},{"id":"W1973140804","doi":"10.1061/(asce)1084-0699(2007)12:1(52)","title":"Cluster-Based Hydrologic Prediction Using Genetic Algorithm-Trained Neural Networks","year":2006,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"University of Saskatchewan","keywords":"Artificial neural network; Computer science; Cluster analysis; Data mining; Artificial intelligence; Nonlinear system; Algorithm; Genetic algorithm; Backpropagation; Cluster (spacecraft); Machine learning; Pattern recognition (psychology)","score_opus":0.008433622081119077,"score_gpt":0.19312047917664182,"score_spread":0.18468685709552274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973140804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2860686,0.00019947087,0.70955664,0.00023588855,0.000042115473,0.00011792633,0.00012612737,0.00096227153,0.0026909534],"genre_scores_gemma":[0.8704216,0.000103538936,0.12804529,0.00003376746,0.000013660018,0.0001019237,0.00015382419,0.000043047006,0.001083427],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996339,0.00014155723,0.00001530195,0.00009032023,0.000084679865,0.000034228833],"domain_scores_gemma":[0.99873513,0.00072378694,0.00012919538,0.000074952106,0.00030647972,0.000030446508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011733174,0.0006352657,0.0006882698,0.0010122788,0.00045893085,0.0006610038,0.0008532623,0.0007174285,0.00059639924],"category_scores_gemma":[0.003738019,0.00037724408,0.000564321,0.001063526,0.00045401874,0.00085135794,0.0004278908,0.00059269584,0.000126305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028322973,0.000016710936,0.00072909467,0.000007185365,0.00002651679,0.000011432335,0.000019310077,0.985962,0.00025913116,0.00067220017,0.00012658745,0.01214139],"study_design_scores_gemma":[0.0000020981727,0.000003883375,0.0000761599,6.2159006e-7,0.0000019103113,0.0000010638722,0.0000013881809,0.9994948,0.000100210294,0.0002979563,0.000018517889,0.0000013587021],"about_ca_topic_score_codex":0.032594517,"about_ca_topic_score_gemma":0.019338012,"teacher_disagreement_score":0.032594517,"about_ca_system_score_codex":0.0016896946,"about_ca_system_score_gemma":0.0012082567,"threshold_uncertainty_score":0.06480956},"labels":[],"label_agreement":null},{"id":"W1977675654","doi":"10.1139/s02-018","title":"Modelling approach for high flow rate in wastewater treatment operation","year":2002,"lang":"en","type":"article","venue":"Journal of Environmental Engineering and Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Inflow; Wastewater; Sewage treatment; Black box; Sanitary sewer; Artificial neural network; Environmental science; Effluent; Computer science; Transfer function; Engineering; Environmental engineering; Artificial intelligence; Meteorology","score_opus":0.01982968040800462,"score_gpt":0.18372258385374823,"score_spread":0.16389290344574362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977675654","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04413242,0.0005316864,0.94200474,0.00036181428,0.00007518255,0.00008569642,0.00025654174,0.00078598404,0.011765825],"genre_scores_gemma":[0.9193384,0.0008750483,0.06170015,0.00008542337,0.000043024454,0.00027176482,0.0003403685,0.00007693117,0.01726874],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979156,0.000050162515,0.00001167074,0.000047555553,0.00007830295,0.000020745585],"domain_scores_gemma":[0.999833,0.000067852045,0.000029892493,0.000012462007,0.00004992401,0.0000068561344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000340813,0.0006195821,0.0004595034,0.00043999054,0.0003347691,0.0007932664,0.001088191,0.00092072546,0.002597521],"category_scores_gemma":[0.00072778267,0.00027835535,0.0005675891,0.0004609432,0.0003110894,0.0008080516,0.00039164658,0.0007881111,0.0006345729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000175169,0.000021875923,0.0004448973,0.000036981568,0.000016141543,0.00005111727,0.000042211926,0.98291343,0.0020952274,0.004179385,0.000290238,0.009890949],"study_design_scores_gemma":[0.0000027487147,0.000014514252,0.00019192636,0.000003652446,0.0000049981422,0.000014065588,0.0000070773253,0.99624914,0.00056466326,0.0017674384,0.001175029,0.0000047934914],"about_ca_topic_score_codex":0.015976496,"about_ca_topic_score_gemma":0.009502695,"teacher_disagreement_score":0.015976496,"about_ca_system_score_codex":0.00094274484,"about_ca_system_score_gemma":0.0010223273,"threshold_uncertainty_score":0.03176701},"labels":[],"label_agreement":null},{"id":"W1979534414","doi":"10.1007/s00477-015-1048-y","title":"A stepwise-cluster forecasting approach for monthly streamflows based on climate teleconnections","year":2015,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Xiamen University of Technology","keywords":"Streamflow; Teleconnection; Stepwise regression; Percentile; Linear regression; Environmental science; Climatology; Meteorology; Statistics; Mathematics; Geography; Precipitation; Drainage basin","score_opus":0.07859099363446719,"score_gpt":0.33185403636735533,"score_spread":0.25326304273288813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979534414","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10174228,0.00016608738,0.89424413,0.0001755615,0.00008839934,0.0001409564,0.00063582795,0.0010533298,0.0017535542],"genre_scores_gemma":[0.6647247,0.00016745745,0.33026692,0.000048579026,0.00007031968,0.00023121406,0.001538969,0.00014152216,0.0028102947],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997081,0.00007703441,0.000025008409,0.00008958487,0.00006730521,0.000032928816],"domain_scores_gemma":[0.99876803,0.0005427429,0.00007022118,0.00011354224,0.00043150823,0.00007392021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000953972,0.0005933973,0.0007156882,0.0010927218,0.00078862766,0.00067752314,0.0018437866,0.0004910401,0.002154521],"category_scores_gemma":[0.00310147,0.0004280099,0.0010086063,0.0018740793,0.00022473713,0.00083993044,0.0005779686,0.0008131883,0.00042992324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013905384,0.00007463857,0.0034198388,0.00003693757,0.00013950613,0.00006401795,0.00008399046,0.91010785,0.0017026165,0.0035457173,0.0014997693,0.079186045],"study_design_scores_gemma":[0.0000024248118,0.0000045240918,0.00019283639,6.2773273e-7,0.0000070357096,0.0000020822922,0.000003786587,0.99910164,0.00012293154,0.0004781391,0.00008106649,0.000002993472],"about_ca_topic_score_codex":0.05455622,"about_ca_topic_score_gemma":0.064248644,"teacher_disagreement_score":0.05455622,"about_ca_system_score_codex":0.0006651252,"about_ca_system_score_gemma":0.0017831221,"threshold_uncertainty_score":0.108477354},"labels":[],"label_agreement":null},{"id":"W1980806603","doi":"10.1016/j.jhydrol.2006.01.016","title":"Improvement of rainfall-runoff forecasts through mean areal rainfall optimization","year":2006,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Streamflow; Environmental science; Surface runoff; Rain gauge; Meteorology; Watershed; Sampling (signal processing); Hydrology (agriculture); Computer science; Filter (signal processing); Precipitation; Drainage basin; Geology; Geography; Machine learning","score_opus":0.01000500431389701,"score_gpt":0.22335218786402514,"score_spread":0.21334718355012813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980806603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24190235,0.00027181514,0.75260186,0.00032467762,0.00007848286,0.000046013778,0.00020196599,0.0013955496,0.003177315],"genre_scores_gemma":[0.91049826,0.00006324182,0.088401556,0.000048066988,0.000044943292,0.000043171694,0.00013685306,0.00006301473,0.00070080464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997508,0.000099046556,0.000015340023,0.00005528223,0.00005461395,0.000024862085],"domain_scores_gemma":[0.9990969,0.0005577485,0.000081748985,0.00004997344,0.0001886613,0.000025027084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092622417,0.0003722535,0.00069830625,0.0003688123,0.00024197824,0.0005286502,0.0003962551,0.0003901729,0.0009041602],"category_scores_gemma":[0.003004463,0.0003852647,0.00027156237,0.0004621181,0.00021576378,0.0006464682,0.00035638286,0.00060246204,0.00017849923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012299066,0.00003553601,0.0012417833,0.000017557108,0.000034961726,0.000011463788,0.000021101849,0.94027954,0.0032883747,0.0007463572,0.00056123675,0.053639103],"study_design_scores_gemma":[0.0000053746344,0.0000061861842,0.00011038762,3.393134e-7,0.0000023342175,0.0000012993697,9.807691e-7,0.99933237,0.00034808592,0.00014725362,0.00004440231,9.788216e-7],"about_ca_topic_score_codex":0.0054380423,"about_ca_topic_score_gemma":0.0063087153,"teacher_disagreement_score":0.0054380423,"about_ca_system_score_codex":0.00043653388,"about_ca_system_score_gemma":0.00076770526,"threshold_uncertainty_score":0.010812759},"labels":[],"label_agreement":null},{"id":"W1981491171","doi":"10.1061/(asce)1084-0699(2007)12:3(273)","title":"Artificial Neural Networks Approximation of Density Dependent Saltwater Intrusion Process in Coastal Aquifers","year":2007,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Aquifer; Saltwater intrusion; Artificial neural network; Flow (mathematics); Multilayer perceptron; Process (computing); Perceptron; Geology; Computer simulation; Computer science; Groundwater; Geotechnical engineering; Simulation; Machine learning; Mechanics","score_opus":0.010531606961727204,"score_gpt":0.22251455880523346,"score_spread":0.21198295184350627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981491171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64381033,0.00030896347,0.3512658,0.00019605362,0.000040280007,0.00002779844,0.00007778879,0.0004022774,0.003870714],"genre_scores_gemma":[0.98446554,0.00011215607,0.014350187,0.000013133554,0.0000072893317,0.000019253925,0.000046074085,0.000006068103,0.0009803608],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999274,0.000026565265,0.0000061978185,0.0000121315115,0.000017347535,0.000010346315],"domain_scores_gemma":[0.9996636,0.00020678,0.000036478377,0.000013621474,0.00006924037,0.000010358056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034867623,0.00034052558,0.0003008899,0.00024198976,0.00017160525,0.00026940388,0.00035965364,0.00041494952,0.0004145595],"category_scores_gemma":[0.001203454,0.00015946745,0.0001902527,0.00028409646,0.00022021863,0.00036160747,0.00017283735,0.00034149634,0.0000658529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019336954,0.000011219337,0.00094412116,0.0000071236063,0.0000062064323,0.000018178556,0.000008847388,0.9923516,0.0008559525,0.00032351524,0.000050894803,0.0054030656],"study_design_scores_gemma":[4.5891505e-7,0.0000024069107,0.00009954779,5.0622003e-7,5.40732e-7,8.3011815e-7,8.6834746e-7,0.9997023,0.00011068574,0.000071184186,0.000010191069,5.147856e-7],"about_ca_topic_score_codex":0.013105449,"about_ca_topic_score_gemma":0.008311371,"teacher_disagreement_score":0.013105449,"about_ca_system_score_codex":0.00042583895,"about_ca_system_score_gemma":0.00032242635,"threshold_uncertainty_score":0.026058316},"labels":[],"label_agreement":null},{"id":"W1982717852","doi":"10.5194/hess-8-940-2004","title":"Generalisation for neural networks through data sampling and training procedures, with applications to streamflow predictions","year":2004,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Golder Associates (Canada); Université Laval","funders":"","keywords":"Boosting (machine learning); Artificial neural network; Computer science; Machine learning; Artificial intelligence; Streamflow; Training (meteorology); Bayesian probability; Perceptron; Stacking; Data mining; Geography","score_opus":0.10006071760503267,"score_gpt":0.2941618640285655,"score_spread":0.19410114642353282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982717852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0809893,0.0010656817,0.91340613,0.00036925357,0.00006987761,0.0002509062,0.00017126492,0.0023058096,0.0013717308],"genre_scores_gemma":[0.499499,0.000582688,0.49701786,0.00015109777,0.00006152332,0.00046351147,0.0006345809,0.0002553492,0.001334416],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998722,0.00074130774,0.00008267007,0.00017824306,0.00021185791,0.00006399798],"domain_scores_gemma":[0.99121886,0.006447723,0.00042465478,0.00058687985,0.0012343206,0.00008756305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007563513,0.0011491287,0.00082651706,0.0011091073,0.0005471746,0.0007573734,0.0011424832,0.0012463968,0.0014882024],"category_scores_gemma":[0.019859094,0.0005860944,0.0010908793,0.0010598258,0.00068431546,0.0014225121,0.0012964068,0.0021751835,0.0004776605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001372143,0.00010243772,0.002716706,0.00013374155,0.000104578234,0.000067054076,0.00013684225,0.82637143,0.0020099264,0.0028217565,0.0008242709,0.164574],"study_design_scores_gemma":[0.000008153845,0.00003508629,0.000554287,0.000015328227,0.000009441545,0.00000945848,0.000012430353,0.99618787,0.0010064406,0.0017904626,0.00036479277,0.0000063006646],"about_ca_topic_score_codex":0.009756588,"about_ca_topic_score_gemma":0.009915466,"teacher_disagreement_score":0.009756588,"about_ca_system_score_codex":0.0009911271,"about_ca_system_score_gemma":0.00079968077,"threshold_uncertainty_score":0.0400002},"labels":[],"label_agreement":null},{"id":"W1983323276","doi":"10.1061/(asce)1084-0699(2009)14:2(172)","title":"Comparative Study of ANNs versus Parametric Methods in Rainfall Frequency Analysis","year":2009,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Quantile; Parametric statistics; Artificial neural network; Monte Carlo method; Computer science; Nonparametric statistics; Parametric model; Statistics; A priori and a posteriori; Sample size determination; Mathematics; Machine learning","score_opus":0.04749253731008371,"score_gpt":0.3527484706663596,"score_spread":0.3052559333562759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983323276","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54694676,0.006623975,0.4274665,0.0011127554,0.00022759657,0.00011999497,0.00026830973,0.0012626974,0.015971385],"genre_scores_gemma":[0.9470669,0.0013143548,0.04989102,0.00010163857,0.00007833643,0.00006088119,0.00014092223,0.000041844145,0.0013040854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814725,0.0012036881,0.00009609381,0.00012321757,0.0003477441,0.00008189918],"domain_scores_gemma":[0.9812398,0.01692284,0.00039525368,0.00039304272,0.0009600009,0.00008906741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049668527,0.0005558218,0.0006009678,0.0011086753,0.000210004,0.0007094172,0.0004867226,0.00073519687,0.0010556484],"category_scores_gemma":[0.016206687,0.00019915026,0.00033076454,0.0010035215,0.00027358445,0.0011685019,0.00049614377,0.00046222605,0.00017840274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087284675,0.00019556658,0.008253046,0.00025068366,0.00022914125,0.00010948112,0.0000885885,0.69510525,0.0012846539,0.004384149,0.0007319469,0.28849465],"study_design_scores_gemma":[0.00001547119,0.00012111146,0.0019391505,0.000020091864,0.000024250607,0.000027076683,0.000027001466,0.99587303,0.0006141038,0.0010284999,0.00030066044,0.000009473074],"about_ca_topic_score_codex":0.0026693437,"about_ca_topic_score_gemma":0.0025307743,"teacher_disagreement_score":0.0049668527,"about_ca_system_score_codex":0.00039509014,"about_ca_system_score_gemma":0.00032447948,"threshold_uncertainty_score":0.026267529},"labels":[],"label_agreement":null},{"id":"W1987988006","doi":"10.1016/j.ecoleng.2011.06.022","title":"Abiotic influences on dissolved oxygen in a riverine environment","year":2011,"lang":"en","type":"article","venue":"Ecological Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Periphyton; Macrophyte; Abiotic component; Environmental science; Biomass (ecology); Nutrient; Hydrology (agriculture); Linear regression; Ecology; Multilayer perceptron; Effluent; Environmental engineering; Artificial neural network; Computer science; Mathematics; Statistics; Biology; Machine learning; Engineering","score_opus":0.0200143099645987,"score_gpt":0.18692492190377938,"score_spread":0.16691061193918066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987988006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99768436,0.000054115935,0.0013456943,0.00007051523,0.000008998015,0.0000031528343,0.00014314435,0.000010039466,0.000679899],"genre_scores_gemma":[0.999521,0.000029905688,0.00021278216,0.000005428118,0.0000047357216,0.0000016488949,0.0000655108,0.0000023601226,0.00015661976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99991703,0.000028115513,0.000007690599,0.000021934442,0.00001602854,0.000009209131],"domain_scores_gemma":[0.9996007,0.00019191313,0.00006534835,0.000021882173,0.00006326656,0.00005695889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002539568,0.00017879833,0.00015391158,0.00030115966,0.00027216368,0.00063479604,0.00020514219,0.00025669395,0.0003925036],"category_scores_gemma":[0.00091839564,0.0001536431,0.00016247174,0.00040358407,0.00034901642,0.00048197008,0.00028439972,0.00024971634,0.000049287188],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004154436,0.0001517591,0.87402713,0.000101068385,0.00027240106,0.00031108063,0.0003392419,0.05235611,0.05242147,0.0016180429,0.00036830173,0.017617922],"study_design_scores_gemma":[0.000017793278,0.00013474224,0.8823384,0.0000041356902,0.00006569374,0.000050612012,0.00033094487,0.11109524,0.004262308,0.0009288374,0.0007516089,0.000019652696],"about_ca_topic_score_codex":0.014512326,"about_ca_topic_score_gemma":0.020236077,"teacher_disagreement_score":0.014512326,"about_ca_system_score_codex":0.00060643826,"about_ca_system_score_gemma":0.00024952166,"threshold_uncertainty_score":0.028855741},"labels":[],"label_agreement":null},{"id":"W1989273813","doi":"10.2166/nh.2006.008","title":"Absolute and relative measures for evaluating the forecasting performance of time series models for daily streamflows","year":2006,"lang":"en","type":"article","venue":"Hydrology research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nova Scotia Department of Agriculture","funders":"Mendez National Institute of Transplantation Foundation","keywords":"Outlier; Mean squared error; Streamflow; Autoregressive model; Statistics; Econometrics; Series (stratigraphy); Term (time); Mathematics; Goodness of fit; Time series; Index (typography); Computer science; Geography","score_opus":0.15966278412176965,"score_gpt":0.3546036679979047,"score_spread":0.19494088387613506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989273813","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16319129,0.0045843804,0.81877476,0.00036968838,0.000554013,0.00033784684,0.0032027136,0.002457819,0.006527471],"genre_scores_gemma":[0.71466535,0.0012246751,0.2757249,0.00020018083,0.0002486347,0.0007293197,0.004733606,0.0005691994,0.0019042324],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9837794,0.006464657,0.00251033,0.0016478682,0.005268478,0.00032935903],"domain_scores_gemma":[0.9579325,0.026660249,0.0050817505,0.0050341943,0.0049802726,0.00031111419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025492769,0.002141439,0.0015680955,0.007486485,0.0005626823,0.002043777,0.0017032615,0.0021057113,0.0014732989],"category_scores_gemma":[0.07714616,0.0005124569,0.0022211338,0.006635007,0.0012297017,0.00358116,0.0016006571,0.0019354074,0.00073061127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007364617,0.00049935485,0.083717816,0.0017265662,0.00297757,0.0004043112,0.0009487642,0.5762081,0.01834619,0.02223531,0.0069511775,0.2852483],"study_design_scores_gemma":[0.00006667383,0.0010459558,0.06372277,0.00041230308,0.0004640589,0.0004968911,0.0009672269,0.88498986,0.018271105,0.017879426,0.011226307,0.00045743285],"about_ca_topic_score_codex":0.0029241296,"about_ca_topic_score_gemma":0.0027314397,"teacher_disagreement_score":0.025492769,"about_ca_system_score_codex":0.00068313937,"about_ca_system_score_gemma":0.0008386372,"threshold_uncertainty_score":0.13482028},"labels":[],"label_agreement":null},{"id":"W1989687941","doi":"10.1139/l09-027","title":"Characterization of 1-h rainfall temporal patterns using a Kohonen neural network: a Québec City case study","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Storm; Range (aeronautics); Self-organizing map; Rain gauge; Environmental science; Meteorology; Cluster analysis; Intensity (physics); Artificial neural network; Geography; Computer science; Artificial intelligence; Engineering; Precipitation","score_opus":0.021147549837206476,"score_gpt":0.2123159043904544,"score_spread":0.1911683545532479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989687941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928201,0.000092478884,0.0030213443,0.00016915,0.000004281697,0.000065983346,0.0016682482,0.000074076226,0.0020843023],"genre_scores_gemma":[0.99509096,0.00006989736,0.002574057,0.000015067486,0.0000021734843,0.000020989455,0.0009478959,0.0000076171746,0.0012714692],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983966,0.000024989742,0.000008096085,0.00003661845,0.000042381434,0.00004811403],"domain_scores_gemma":[0.99941576,0.00022490496,0.000049860315,0.000038950267,0.00021920115,0.0000512637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032779705,0.00042662676,0.00023071606,0.00096054183,0.0006828721,0.00065199455,0.000906178,0.0006302717,0.0015644915],"category_scores_gemma":[0.001244054,0.00018863191,0.00028160634,0.0018209118,0.0003851178,0.00032043847,0.00024202855,0.00031370914,0.000117145435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051179563,0.00049376633,0.27907854,0.0002095543,0.0002109356,0.0046124496,0.0009671746,0.63610935,0.006418728,0.0023652872,0.0063139745,0.06270849],"study_design_scores_gemma":[0.000045815486,0.0000703655,0.13260962,0.000017044766,0.000042459367,0.00016395458,0.0009325476,0.86315155,0.0011233957,0.00029946436,0.0015057784,0.000037997226],"about_ca_topic_score_codex":0.9372248,"about_ca_topic_score_gemma":0.9519539,"teacher_disagreement_score":0.062775195,"about_ca_system_score_codex":0.0079386365,"about_ca_system_score_gemma":0.0024077136,"threshold_uncertainty_score":0.12628973},"labels":[],"label_agreement":null},{"id":"W1992169881","doi":"10.3923/jas.2008.4487.4499","title":"Neural Network Model for Nile River Inflow Forecasting Based on Correlation Analysis of Historical Inflow Data","year":2008,"lang":"en","type":"article","venue":"Journal of Applied Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Inflow; Artificial neural network; Environmental science; Hydrology (agriculture); Meteorology; Computer science; Geology; Geography; Artificial intelligence; Geotechnical engineering","score_opus":0.1250414215299447,"score_gpt":0.2720821697235326,"score_spread":0.1470407481935879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992169881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30002114,0.0012371356,0.6893329,0.00071167486,0.00032259317,0.00008174015,0.00060062436,0.0011305724,0.006561643],"genre_scores_gemma":[0.9741158,0.00032412788,0.021355404,0.00005998262,0.0000730539,0.00010892258,0.00031697264,0.000024861427,0.0036209028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997812,0.000061481805,0.000019589448,0.000060996077,0.000042002146,0.00003479355],"domain_scores_gemma":[0.99924326,0.00044432894,0.00005705348,0.000021134727,0.00021145908,0.000022852852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081189955,0.00047752602,0.0007754564,0.0006085366,0.00039710762,0.00065030344,0.00088889006,0.0008140788,0.0018489716],"category_scores_gemma":[0.0019134715,0.0003222518,0.00043031768,0.0008426937,0.00024660217,0.0007883204,0.00036992328,0.00097557256,0.0003152899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090171794,0.00003826137,0.0010027902,0.000018662613,0.000042221014,0.000022379167,0.000011226541,0.97774315,0.0003612838,0.0005682388,0.00042688384,0.019674614],"study_design_scores_gemma":[0.0000020687457,0.0000037136917,0.00008431882,6.4030974e-7,0.0000028316342,9.859627e-7,6.026075e-7,0.9997452,0.000041835054,0.00009946552,0.000017374983,0.0000010161832],"about_ca_topic_score_codex":0.023805616,"about_ca_topic_score_gemma":0.014413977,"teacher_disagreement_score":0.023805616,"about_ca_system_score_codex":0.0007340774,"about_ca_system_score_gemma":0.0008589019,"threshold_uncertainty_score":0.047334135},"labels":[],"label_agreement":null},{"id":"W1994234742","doi":"10.1016/j.jhydrol.2007.10.050","title":"Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system","year":2007,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":215,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Natural Sciences and Engineering Research Council; Institut National de la Recherche Scientifique; Hydro-Québec","funders":"","keywords":"Adaptive neuro fuzzy inference system; Jackknife resampling; Interpretability; Computer science; Artificial neural network; Neuro-fuzzy; Cluster analysis; Artificial intelligence; Data mining; Flood myth; Machine learning; Fuzzy logic; Fuzzy control system; Statistics; Mathematics; Geography","score_opus":0.04319348890226257,"score_gpt":0.27467806065592254,"score_spread":0.23148457175365997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994234742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9178803,0.000091318965,0.0804384,0.00009092062,0.0000261763,0.000026669426,0.00019088786,0.00019697996,0.0010583956],"genre_scores_gemma":[0.98761857,0.00002109751,0.012091273,0.0000050208378,0.0000046377445,0.000008110283,0.0000686936,0.000003980793,0.00017854574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986744,0.000035690995,0.0000142087765,0.00003210534,0.00003358619,0.000016899781],"domain_scores_gemma":[0.99947065,0.00029829374,0.0000433426,0.000025817151,0.0001379135,0.00002391397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059071125,0.00027345534,0.0003978033,0.0007759361,0.00029148092,0.00040081466,0.00044074573,0.00043451283,0.0005876077],"category_scores_gemma":[0.0018205937,0.0001967585,0.00035264884,0.0004851625,0.00014032616,0.00037751824,0.00021453683,0.0002831792,0.00009600038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005016184,0.00014030818,0.03781463,0.000060887,0.00015772476,0.00015335131,0.00014527446,0.8362844,0.007823148,0.00059010636,0.0005012206,0.11582735],"study_design_scores_gemma":[0.000009169311,0.000018033494,0.006570658,0.0000019908282,0.000018271927,0.000008810928,0.000015632502,0.9924972,0.00065307855,0.00016336502,0.000037415615,0.000006403152],"about_ca_topic_score_codex":0.024937661,"about_ca_topic_score_gemma":0.027901925,"teacher_disagreement_score":0.024937661,"about_ca_system_score_codex":0.0005576023,"about_ca_system_score_gemma":0.0004297999,"threshold_uncertainty_score":0.049584985},"labels":[],"label_agreement":null},{"id":"W1997834047","doi":"10.1109/joe.2013.2241934","title":"A Proposed ANN and FLSM Hybrid Model for Tidal Current Magnitude and Direction Forecasting","year":2013,"lang":"en","type":"article","venue":"IEEE Journal of Oceanic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Magnitude (astronomy); Artificial neural network; Current (fluid); Computer science; Tidal current; Least-squares function approximation; Fourier series; Geology; Mathematics; Artificial intelligence; Statistics; Oceanography; Physics","score_opus":0.022845074034356108,"score_gpt":0.2209421017696725,"score_spread":0.1980970277353164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997834047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073755376,0.00046619528,0.9160093,0.00040411882,0.0001647947,0.000049534265,0.00029703358,0.0011182138,0.0077355085],"genre_scores_gemma":[0.8731371,0.00025891198,0.11656454,0.00013083409,0.00008305732,0.00013035485,0.00042528368,0.000046696892,0.009223273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984956,0.000032735545,0.0000112910375,0.000041158994,0.00004801339,0.000017132605],"domain_scores_gemma":[0.9998485,0.00004871561,0.000015097668,0.000010311222,0.00006897705,0.000008304862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000310482,0.000405085,0.00037879802,0.00032869735,0.00021393548,0.00048682702,0.00083863805,0.0006658832,0.0014663412],"category_scores_gemma":[0.00063202303,0.00021775838,0.0004594881,0.0003599692,0.00013794095,0.0006992099,0.0003613783,0.00046825552,0.00035781818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007365879,0.000061780396,0.0015676845,0.000060089664,0.00006755419,0.00007555543,0.000027716833,0.90509826,0.0047864825,0.0018806304,0.00113831,0.085162364],"study_design_scores_gemma":[0.0000032405544,0.000014808526,0.00022279206,0.0000024544972,0.0000044554013,0.000010744138,0.000001998421,0.9988778,0.00031736604,0.00026721586,0.00027311352,0.0000039337606],"about_ca_topic_score_codex":0.009132323,"about_ca_topic_score_gemma":0.010543378,"teacher_disagreement_score":0.009132323,"about_ca_system_score_codex":0.0003236953,"about_ca_system_score_gemma":0.00052320934,"threshold_uncertainty_score":0.018158317},"labels":[],"label_agreement":null},{"id":"W1998765045","doi":"10.1017/s0373463303002285","title":"A New Approach to Sequential Tidal Prediction","year":2003,"lang":"en","type":"article","venue":"Journal of Navigation","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Tide gauge; Artificial neural network; Tidal Model; Feedforward neural network; Tidal power; Least-squares function approximation; Computer science; Algorithm; Geology; Engineering; Artificial intelligence; Marine engineering; Statistics; Mathematics; Oceanography; Sea level","score_opus":0.027798272877620538,"score_gpt":0.2566319178573187,"score_spread":0.22883364497969816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998765045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002205715,0.00009338577,0.99565494,0.00009735462,0.00008575594,0.000024940246,0.000050037983,0.00025412158,0.0015336575],"genre_scores_gemma":[0.27667555,0.0007063819,0.7083283,0.00025888844,0.00040084159,0.00031055638,0.0004986552,0.00021547308,0.012605423],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990214,0.00013857144,0.00006875431,0.0002996722,0.00040890317,0.000062751176],"domain_scores_gemma":[0.99888045,0.0003763165,0.00011832123,0.00020314734,0.0003714385,0.00005027492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009871,0.00091330137,0.00095536455,0.0007590229,0.00048374277,0.000978482,0.0018584701,0.0007304526,0.003502302],"category_scores_gemma":[0.00297253,0.0005077934,0.00078422454,0.0011816296,0.0006338547,0.0019836437,0.0012943317,0.0016400621,0.00089976616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010327937,0.00013697126,0.0021885722,0.00016463047,0.00013596744,0.00020079856,0.00019652417,0.5740136,0.0061762664,0.07233041,0.0047937115,0.33955932],"study_design_scores_gemma":[0.000005535807,0.000028122506,0.00013154764,0.000006610661,0.000012272322,0.000032708223,0.000006029848,0.98398083,0.0006606039,0.012067992,0.0030584158,0.00000933305],"about_ca_topic_score_codex":0.0074288263,"about_ca_topic_score_gemma":0.0075619775,"teacher_disagreement_score":0.0074288263,"about_ca_system_score_codex":0.00061836705,"about_ca_system_score_gemma":0.00143233,"threshold_uncertainty_score":0.014771163},"labels":[],"label_agreement":null},{"id":"W1999378232","doi":"10.1061/(asce)1084-0699(2000)5:4(424)","title":"Performance Evaluation of Artificial Neural Networks for Runoff Prediction","year":2000,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Mean squared error; Statistic; Computer science; Surface runoff; Regression; Linear regression; Nonlinear system; Statistics; Machine learning; Mathematics","score_opus":0.02266431642366356,"score_gpt":0.23186249774098958,"score_spread":0.209198181317326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999378232","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93720156,0.002348387,0.053686783,0.00048224613,0.0001670495,0.000062935665,0.000254638,0.0004555079,0.0053408835],"genre_scores_gemma":[0.99113363,0.00039336592,0.0073429127,0.000026894935,0.000031203817,0.00002586271,0.00023160454,0.0000119950655,0.0008026313],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883205,0.000523687,0.00012542587,0.00011497361,0.00033815837,0.00006575196],"domain_scores_gemma":[0.9949345,0.0033059716,0.00024092996,0.00017385205,0.0012571585,0.00008764502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041666063,0.0006629947,0.00040621863,0.00074341946,0.00021550574,0.0005460797,0.00042012343,0.0006402517,0.00046794856],"category_scores_gemma":[0.010098578,0.00013064704,0.00023603789,0.0007188168,0.00020626195,0.0007074714,0.00035617093,0.00037748818,0.00014630875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007835743,0.00022083207,0.021712516,0.00016429606,0.00021534572,0.00010631592,0.00006317985,0.8499656,0.0030941614,0.00066065334,0.0007668614,0.122246735],"study_design_scores_gemma":[0.000012008164,0.00018761479,0.004051013,0.000010791873,0.000024819048,0.00001068716,0.000019642677,0.9932754,0.0020484505,0.00015843939,0.0001937589,0.000007303226],"about_ca_topic_score_codex":0.0134830205,"about_ca_topic_score_gemma":0.008968757,"teacher_disagreement_score":0.0134830205,"about_ca_system_score_codex":0.00084957265,"about_ca_system_score_gemma":0.00047082212,"threshold_uncertainty_score":0.026809096},"labels":[],"label_agreement":null},{"id":"W2000836571","doi":"10.6000/1929-6029.2015.04.01.10","title":"Inferential Procedures for Comparing the Accuracy and Intrinsic Measures of Multivariate Receiver Operating Characteristic (MROC) Curve","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University Grants Commission; Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Receiver operating characteristic; Multivariate statistics; Sensitivity (control systems); Multivariate analysis; Measure (data warehouse); Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics; Computer science; Data mining","score_opus":0.19233957179186317,"score_gpt":0.44406478633007207,"score_spread":0.2517252145382089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000836571","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011367035,0.0015758584,0.9834208,0.0003176774,0.00010544527,0.000500779,0.0010150757,0.0006957231,0.0010015987],"genre_scores_gemma":[0.23424599,0.0014740006,0.7571922,0.00036046302,0.00039777491,0.003650172,0.0020320453,0.00020061228,0.0004468848],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93075,0.048633337,0.0053169006,0.0053248825,0.009392744,0.00058208214],"domain_scores_gemma":[0.67105794,0.29434636,0.014840046,0.012105345,0.007007035,0.00064328045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053681664,0.0024307822,0.0033074913,0.011577254,0.0010013182,0.0029852039,0.0026283944,0.0024077937,0.0028840576],"category_scores_gemma":[0.2266727,0.0005553532,0.0028602702,0.0070040645,0.0028698388,0.003221665,0.0024986335,0.004168516,0.000718462],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010476481,0.000685429,0.062885016,0.003699007,0.003799423,0.000747175,0.0014022967,0.13933223,0.0051936363,0.12776306,0.00852606,0.64491904],"study_design_scores_gemma":[0.00016017194,0.001947687,0.028735315,0.00093194674,0.0010407405,0.0012059321,0.0009750785,0.7072138,0.009536589,0.23425849,0.013587399,0.00040683328],"about_ca_topic_score_codex":0.0012750026,"about_ca_topic_score_gemma":0.00089085894,"teacher_disagreement_score":0.053681664,"about_ca_system_score_codex":0.001505595,"about_ca_system_score_gemma":0.0024112174,"threshold_uncertainty_score":0.28389913},"labels":[],"label_agreement":null},{"id":"W2001676017","doi":"10.1029/2000wr900368","title":"Artificial neural network modeling of water table depth fluctuations","year":2001,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":443,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Waterloo; Hydro-Québec; Institut National de la Recherche Scientifique","funders":"Northwestern University; Rockefeller Foundation","keywords":"Recurrent neural network; Artificial neural network; Water table; Computer science; Aquifer; Hydrometeorology; Groundwater; Water level; Table (database); Calibration; Probabilistic neural network; Probabilistic logic; Artificial intelligence; Hydrology (agriculture); Data mining; Machine learning; Time delay neural network; Statistics; Geology; Geotechnical engineering; Mathematics; Meteorology; Geography","score_opus":0.10980942485369294,"score_gpt":0.3242874505308015,"score_spread":0.21447802567710855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001676017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6975293,0.00036409352,0.29741406,0.00022506686,0.000046713427,0.000034113007,0.00023742014,0.00032755904,0.0038217017],"genre_scores_gemma":[0.9897419,0.000087160006,0.009269918,0.000008107452,0.000005706014,0.000021504473,0.00007410731,0.0000052165346,0.00078641187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998845,0.000039778304,0.000008114017,0.000028126533,0.000022346378,0.000017233984],"domain_scores_gemma":[0.99971265,0.00015495297,0.000043751737,0.00001457719,0.00006415781,0.000009955105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003918305,0.00035427453,0.00026569146,0.00025677547,0.0001843186,0.00036243524,0.00051530177,0.00051139924,0.00043413482],"category_scores_gemma":[0.0016390068,0.00015241666,0.00022170685,0.0004358476,0.00023437793,0.00056312815,0.00017575211,0.00032127538,0.000068630674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001215374,0.0000075036924,0.00095383247,0.000004900805,0.000007734675,0.000014188239,0.000007162771,0.9941268,0.00044451485,0.0006186699,0.00003909269,0.0037634985],"study_design_scores_gemma":[7.196805e-7,0.0000029448452,0.0001593985,3.9266885e-7,9.95485e-7,0.0000014180387,0.0000010080902,0.99959034,0.00008371481,0.0001353315,0.000023088325,6.856945e-7],"about_ca_topic_score_codex":0.01691148,"about_ca_topic_score_gemma":0.010690555,"teacher_disagreement_score":0.01691148,"about_ca_system_score_codex":0.0006983462,"about_ca_system_score_gemma":0.00040280822,"threshold_uncertainty_score":0.03362608},"labels":[],"label_agreement":null},{"id":"W2003002624","doi":"10.1029/01eo00031","title":"Global water data: A newly endangered species","year":2001,"lang":"en","type":"article","venue":"Eos","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":233,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Exploit; Endangered species; The Internet; Data science; Water sector; Computer science; Environmental resource management; Environmental science; Business; Water supply; World Wide Web; Ecology; Computer security; Environmental engineering","score_opus":0.05367552657852936,"score_gpt":0.26242631712015074,"score_spread":0.20875079054162138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003002624","genre_codex":"dataset","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031491432,0.026000032,0.068416275,0.2106657,0.011450145,0.00022769041,0.47660336,0.0133600235,0.16178529],"genre_scores_gemma":[0.18780656,0.03255202,0.121991605,0.028565915,0.003097415,0.00036788837,0.55037206,0.0036167444,0.071629815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991757,0.00015694193,0.00007447624,0.00012295016,0.000428676,0.000041254963],"domain_scores_gemma":[0.99666023,0.0009599587,0.00034111593,0.0008738748,0.0007094927,0.00045534156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017713053,0.00042795527,0.0002966543,0.0020246683,0.0007363608,0.0021437644,0.0010298,0.0012703388,0.0120350495],"category_scores_gemma":[0.007579648,0.0001934067,0.00020958453,0.0056197005,0.0007607982,0.0046680397,0.0029375553,0.0015946673,0.0058734766],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010988844,0.00002742729,0.0062377094,0.00039481535,0.00003192874,0.00021762705,0.00026286283,0.0010813903,0.0026022128,0.038052097,0.7250235,0.2259586],"study_design_scores_gemma":[0.000006535015,0.000011042988,0.0030732523,0.00010904507,0.000009000312,0.00015095854,0.00015772608,0.00086886634,0.00070216873,0.016597113,0.97829926,0.000015070846],"about_ca_topic_score_codex":0.005385709,"about_ca_topic_score_gemma":0.00731578,"teacher_disagreement_score":0.0120350495,"about_ca_system_score_codex":0.0005659614,"about_ca_system_score_gemma":0.0012170445,"threshold_uncertainty_score":0.04026121},"labels":[],"label_agreement":null},{"id":"W2004803051","doi":"10.1016/j.cageo.2010.07.005","title":"Quantile regression neural networks: Implementation in R and application to precipitation downscaling","year":2010,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":402,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Division of Ocean Sciences","keywords":"Quantile regression; Quantile; Overfitting; Cumulative distribution function; Artificial neural network; Downscaling; Statistics; Computer science; Mathematics; Probability density function; Precipitation; Artificial intelligence","score_opus":0.010829301110639159,"score_gpt":0.28582308075231444,"score_spread":0.27499377964167526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004803051","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03446011,0.00020800742,0.9305331,0.00040642574,0.00013191956,0.000091083064,0.001544699,0.029704189,0.0029204062],"genre_scores_gemma":[0.27005717,0.00017913395,0.71728015,0.0002113953,0.000056847464,0.0002614295,0.002050583,0.003259383,0.006643826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969506,0.000100590914,0.000027571192,0.00006669929,0.00007693363,0.000033145054],"domain_scores_gemma":[0.9984515,0.00085236283,0.000096557866,0.00020176196,0.00035976275,0.000038020087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014768492,0.00045572862,0.0003566079,0.00042717697,0.00033599464,0.0005742006,0.0011411362,0.0005456866,0.013544835],"category_scores_gemma":[0.009002642,0.000423603,0.00036620675,0.0007946883,0.00024274563,0.00061337656,0.0006633726,0.0010509203,0.0029797193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045459412,0.00018153158,0.006482706,0.00024202837,0.00020166146,0.00021309934,0.00025363677,0.357973,0.0058063986,0.01260416,0.04055548,0.5750318],"study_design_scores_gemma":[0.00005163206,0.000018501663,0.0009634138,0.000008521156,0.0000170444,0.00003124141,0.000012947839,0.9872643,0.0037521024,0.004137149,0.0037317579,0.0000114104205],"about_ca_topic_score_codex":0.011881549,"about_ca_topic_score_gemma":0.014914482,"teacher_disagreement_score":0.013544835,"about_ca_system_score_codex":0.00039364502,"about_ca_system_score_gemma":0.00076822995,"threshold_uncertainty_score":0.045311987},"labels":[],"label_agreement":null},{"id":"W2005742470","doi":"10.1016/j.jhydrol.2006.10.031","title":"Reservoir storage loss due to grounded ice during winter operation","year":2006,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hydro-Québec; Institut National de la Recherche Scientifique","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Hydroelectricity; Hydrology (agriculture); Water resources; Water level; Environmental science; Surface water; Geology; Water storage; Oceanography; Geotechnical engineering; Geography; Environmental engineering; Engineering","score_opus":0.010897924091452137,"score_gpt":0.23553930889336275,"score_spread":0.22464138480191062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005742470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99825615,0.0000566092,0.000642485,0.00003133274,0.000017727734,0.0000032117787,0.00046568143,0.000037839978,0.0004890228],"genre_scores_gemma":[0.9996439,0.000015934951,0.000045005207,0.000004024021,0.0000039408496,9.2847324e-7,0.00018681824,0.0000033869924,0.00009605094],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99988925,0.000011613166,0.000011516749,0.000017322902,0.000030901796,0.000039413037],"domain_scores_gemma":[0.99886084,0.0006325622,0.00019314286,0.000058514324,0.00016298016,0.0000919362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003296228,0.00022148037,0.0003510761,0.0003786251,0.0003002666,0.00048229197,0.00024439424,0.00030516007,0.0011285567],"category_scores_gemma":[0.0016484217,0.00013438195,0.0002639621,0.00046006002,0.00023056564,0.00044028737,0.00023515128,0.00034885044,0.00012913585],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012657036,0.0003719634,0.6603593,0.00016589067,0.00041574144,0.0038325896,0.00036460866,0.22771311,0.04567194,0.00066646805,0.00254044,0.04524084],"study_design_scores_gemma":[0.00007123551,0.0006747437,0.674173,0.000022903498,0.00025274168,0.00097318523,0.00041129245,0.3015017,0.02068095,0.00066608406,0.0005346101,0.000037611077],"about_ca_topic_score_codex":0.008162547,"about_ca_topic_score_gemma":0.008026154,"teacher_disagreement_score":0.008162547,"about_ca_system_score_codex":0.0005584379,"about_ca_system_score_gemma":0.00029632304,"threshold_uncertainty_score":0.016230106},"labels":[],"label_agreement":null},{"id":"W2006299203","doi":"10.1002/hyp.1359","title":"Application of fuzzy logic to forecast seasonal runoff","year":2003,"lang":"en","type":"article","venue":"Hydrological Processes","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Surface runoff; Snowpack; Fuzzy logic; Snowmelt; Environmental science; Heuristic; Structural basin; Hydrology (agriculture); Meteorology; Variable (mathematics); Climatology; Snow; Computer science; Mathematics; Geography; Geology; Artificial intelligence","score_opus":0.02182742165712414,"score_gpt":0.2512049093186492,"score_spread":0.22937748766152505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006299203","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4274301,0.00030392478,0.5616728,0.00037043786,0.00007185671,0.00013906944,0.00027988237,0.0005905698,0.009141369],"genre_scores_gemma":[0.97183603,0.00007415616,0.027212678,0.000018641284,0.0000077440245,0.000019913685,0.00007040295,0.0000057416155,0.00075462466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971515,0.0000878355,0.000022896527,0.000037343652,0.00010546665,0.000031321164],"domain_scores_gemma":[0.9991424,0.0005024058,0.000082895174,0.000018059003,0.00022935879,0.000024855228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094361964,0.00029582114,0.00024921802,0.00094005046,0.00039212834,0.0009028457,0.00038453523,0.0003942547,0.0010169065],"category_scores_gemma":[0.0022784024,0.00017712169,0.0003417403,0.00056872226,0.00027175221,0.000383277,0.0001760186,0.0003394223,0.00011971016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008544454,0.000030388823,0.0029703942,0.000027854909,0.00002075237,0.000073724914,0.000073227464,0.9655626,0.0021170436,0.0016839458,0.00024214352,0.027112575],"study_design_scores_gemma":[0.0000035162655,0.0000131061415,0.00032944264,0.0000037492184,0.0000036001663,0.0000030702715,0.000013186882,0.99850404,0.00037020826,0.0006311991,0.00012149745,0.0000034223763],"about_ca_topic_score_codex":0.07548645,"about_ca_topic_score_gemma":0.044717286,"teacher_disagreement_score":0.07548645,"about_ca_system_score_codex":0.0020359338,"about_ca_system_score_gemma":0.001243152,"threshold_uncertainty_score":0.15009415},"labels":[],"label_agreement":null},{"id":"W2007974164","doi":"10.1111/0885-9507.00199","title":"Neural Network‐Based Long‐Term Hydropower Forecasting System","year":2000,"lang":"en","type":"article","venue":"Computer-Aided Civil and Infrastructure Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hydro-Québec; Institut National de la Recherche Scientifique; Natural Sciences and Engineering Research Council of Canada; Université Laval","funders":"","keywords":"Overfitting; Computer science; Recurrent neural network; Artificial neural network; Feedforward neural network; Feed forward; Term (time); Artificial intelligence; Hydropower; Machine learning; Engineering; Control engineering","score_opus":0.006439691324542921,"score_gpt":0.17451779488633531,"score_spread":0.1680781035617924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007974164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.277765,0.00155591,0.6880066,0.0011125171,0.00094483636,0.00019516404,0.0018278597,0.0055948454,0.022997333],"genre_scores_gemma":[0.9424104,0.00028707355,0.045797188,0.00016991151,0.00013478808,0.00015301845,0.00083867274,0.000032336364,0.010176561],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998293,0.000021266325,0.000016519827,0.00006758785,0.00004462136,0.000020722086],"domain_scores_gemma":[0.9995665,0.00010801829,0.000040502073,0.000029822346,0.00022983305,0.000025335228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053998124,0.0005094718,0.0006439421,0.0007662771,0.0006031423,0.00075149356,0.0009193106,0.00080617046,0.003247022],"category_scores_gemma":[0.0010266291,0.00031781135,0.00030523658,0.0008350508,0.00021588498,0.00088399,0.00041895141,0.0006846566,0.00096988364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042299036,0.00037364225,0.0053109042,0.000102358994,0.00019183272,0.00012185678,0.000048009202,0.6376792,0.008870788,0.0012114538,0.0057076206,0.33995926],"study_design_scores_gemma":[0.000008197435,0.000018796623,0.00058014237,0.000002663849,0.0000149461375,0.000006121745,0.0000025415618,0.99817896,0.0007156599,0.00022144064,0.00024509607,0.0000055327723],"about_ca_topic_score_codex":0.016147744,"about_ca_topic_score_gemma":0.016266005,"teacher_disagreement_score":0.016147744,"about_ca_system_score_codex":0.00085710647,"about_ca_system_score_gemma":0.0008016038,"threshold_uncertainty_score":0.032107472},"labels":[],"label_agreement":null},{"id":"W2010355833","doi":"10.1139/cjce-2012-0373","title":"Stochastic approach to determination of suspended sediment concentration in tidal rivers by artificial neural network and genetic algorithm","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fluvial; Sediment; Silt; Tidal Model; Artificial neural network; Hydrology (agriculture); Environmental science; Sediment transport; Tidal river; Geology; Estuary; Geotechnical engineering; Geomorphology; Oceanography; Computer science; Machine learning","score_opus":0.008189551207841478,"score_gpt":0.17702230654169981,"score_spread":0.16883275533385833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010355833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021602934,0.0005667174,0.9744746,0.00021391394,0.000045074605,0.000048368227,0.000044450928,0.00022315772,0.0027807357],"genre_scores_gemma":[0.77268213,0.00091695227,0.22087258,0.000127972,0.000095274365,0.00033606598,0.0002281132,0.00005629616,0.0046847123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961394,0.00011258666,0.000027569979,0.0000912688,0.00011316645,0.000041445383],"domain_scores_gemma":[0.99944633,0.0003006417,0.00007716995,0.000012808608,0.00014533952,0.000017666815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007973052,0.0006217732,0.0007406648,0.0008910151,0.00046226263,0.0007829275,0.0011775139,0.0010794232,0.0007259387],"category_scores_gemma":[0.0015971609,0.00049382995,0.00078631047,0.0010041901,0.00048554974,0.0005966432,0.0005260086,0.00086240895,0.00012193182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008693431,0.000010113508,0.00051921443,0.000027291813,0.000017507267,0.00003072082,0.000015278909,0.989602,0.0003955822,0.0018957631,0.00011991804,0.007357843],"study_design_scores_gemma":[0.0000013411343,0.0000034258367,0.00006977156,0.000002194031,0.000001747165,0.0000036495778,0.0000018821188,0.99929726,0.00007314591,0.00047101488,0.00007248268,0.0000020398297],"about_ca_topic_score_codex":0.02017104,"about_ca_topic_score_gemma":0.011205888,"teacher_disagreement_score":0.02017104,"about_ca_system_score_codex":0.0011099909,"about_ca_system_score_gemma":0.0013743928,"threshold_uncertainty_score":0.04010725},"labels":[],"label_agreement":null},{"id":"W2010957016","doi":"10.2166/wqrjc.2014.007","title":"Modeling of hourly river water temperatures using artificial neural networks","year":2014,"lang":"en","type":"article","venue":"Water Quality Research Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Fisheries and Oceans Canada; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Environmental science; Water quality; Mean squared error; Artificial neural network; Hydrology (agriculture); Water level; Water resources; Current (fluid); Meteorology; Statistics; Ecology; Mathematics; Computer science; Geology; Machine learning; Geography","score_opus":0.19580458567585982,"score_gpt":0.3894510997049801,"score_spread":0.19364651402912028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010957016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6514014,0.00034061106,0.34136117,0.00018951952,0.00007249041,0.00005439169,0.0005068908,0.00079518737,0.0052782455],"genre_scores_gemma":[0.98454547,0.000109491455,0.014007056,0.000010795716,0.000009582278,0.00005080257,0.0001882477,0.000015873835,0.0010626479],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998425,0.000050835803,0.000014250177,0.000040998122,0.000034268578,0.000016961118],"domain_scores_gemma":[0.999713,0.00016950376,0.000039729588,0.000016381893,0.000052501004,0.000008848467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032301247,0.00036506812,0.00030417248,0.0003143825,0.00023085314,0.000482141,0.00046818235,0.00053573586,0.00069234375],"category_scores_gemma":[0.000985435,0.00024010612,0.00039448327,0.00051308714,0.00015171457,0.00048027525,0.00018964833,0.00043691104,0.00014885665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001274655,0.000015804839,0.0016631186,0.00000894181,0.000013777038,0.000011899438,0.000010862195,0.9921153,0.00048819976,0.00014544549,0.00005830931,0.005455632],"study_design_scores_gemma":[6.5858313e-7,0.000003118491,0.0003598406,6.8661126e-7,0.0000013129668,0.0000014548986,0.0000017562385,0.99942446,0.0001036763,0.000069354835,0.000032185457,0.0000014451371],"about_ca_topic_score_codex":0.016843112,"about_ca_topic_score_gemma":0.014682068,"teacher_disagreement_score":0.016843112,"about_ca_system_score_codex":0.000533571,"about_ca_system_score_gemma":0.0004352232,"threshold_uncertainty_score":0.03349012},"labels":[],"label_agreement":null},{"id":"W2012384995","doi":"10.1139/s03-066","title":"Implementing artificial neural network models for real-time water colour forecasting in a water treatment plant","year":2004,"lang":"en","type":"article","venue":"Journal of Environmental Engineering and Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Upgrade; Artificial neural network; Key (lock); Computer science; Process (computing); Artificial intelligence; Operations research; Engineering","score_opus":0.02182283879960046,"score_gpt":0.2087449496552841,"score_spread":0.18692211085568364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012384995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46092486,0.00025175032,0.5254888,0.0007176886,0.00012775631,0.00012956734,0.00016695076,0.0032658642,0.0089268265],"genre_scores_gemma":[0.93489593,0.00014976267,0.06100328,0.00005068375,0.000014396554,0.00007230028,0.00011363642,0.000029607783,0.0036703828],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998029,0.000077232755,0.0000132755,0.00002894958,0.000054067303,0.000023579561],"domain_scores_gemma":[0.9992556,0.00046102918,0.000048836693,0.00004073938,0.00016814558,0.000025525385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006980072,0.0005254759,0.0003118014,0.00031033493,0.0003970929,0.00066335994,0.0006767033,0.0010845538,0.0014776271],"category_scores_gemma":[0.001922868,0.00035764324,0.0002751836,0.00044720547,0.00029303544,0.00095471536,0.00030040462,0.0008907274,0.00028723557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012498391,0.00008562513,0.0017371662,0.000028305674,0.00001582927,0.000044037213,0.000046611323,0.9560888,0.0029334116,0.0004495835,0.00043678243,0.03800887],"study_design_scores_gemma":[0.0000046427035,0.00002301067,0.00018442127,0.0000020108878,0.0000036413726,0.0000024148978,0.0000065193663,0.99827695,0.0011909606,0.00017316267,0.00012844705,0.0000038741805],"about_ca_topic_score_codex":0.029292068,"about_ca_topic_score_gemma":0.031113349,"teacher_disagreement_score":0.029292068,"about_ca_system_score_codex":0.0012092417,"about_ca_system_score_gemma":0.0008748473,"threshold_uncertainty_score":0.058243155},"labels":[],"label_agreement":null},{"id":"W2012683105","doi":"10.2495/sdp-v10-n1-66-75","title":"Using artificial intelligence to forecast monthly rainfall under present and future climates for the bowen basin, Queensland, Australia","year":2015,"lang":"en","type":"article","venue":"International Journal of Sustainable Development and Planning","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"B. Macfie Family Foundation","keywords":"Climatology; GCM transcription factors; Environmental science; Structural basin; Climate change; Meteorology; Precipitation; General Circulation Model; Geography; Geology; Oceanography","score_opus":0.11196978578938609,"score_gpt":0.3346249767381964,"score_spread":0.2226551909488103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012683105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9843879,0.0004866002,0.009372687,0.00080375763,0.00004349081,0.00004878038,0.000852853,0.00030765534,0.003696326],"genre_scores_gemma":[0.99164504,0.00022705644,0.0062681716,0.000033863023,0.00001469198,0.00001957639,0.0006348521,0.000010703167,0.001146033],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998386,0.000041933912,0.000019359844,0.000040521907,0.000040892453,0.000018717396],"domain_scores_gemma":[0.99961084,0.00015674069,0.00006139019,0.000018585131,0.00010861169,0.000043943226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060080056,0.00032222876,0.00021977833,0.00074634864,0.00039809485,0.00073306134,0.00035881306,0.00031671973,0.000738023],"category_scores_gemma":[0.0024429057,0.00023532848,0.0002518818,0.0007727292,0.00024266119,0.00057687203,0.00039186858,0.00038611825,0.00011843644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015373886,0.00013903262,0.08894962,0.00010856566,0.00015999476,0.00024393309,0.00039204568,0.83373904,0.003076558,0.00072157977,0.002564148,0.069751784],"study_design_scores_gemma":[0.000020825826,0.0000361886,0.041551292,0.000013487351,0.000020745681,0.00001184047,0.00014157646,0.9563497,0.0003233609,0.0005897388,0.0009270265,0.000014224073],"about_ca_topic_score_codex":0.3377717,"about_ca_topic_score_gemma":0.29143485,"teacher_disagreement_score":0.3377717,"about_ca_system_score_codex":0.0016737147,"about_ca_system_score_gemma":0.0014522902,"threshold_uncertainty_score":0.6716113},"labels":[],"label_agreement":null},{"id":"W2016479499","doi":"10.1016/j.jhydrol.2009.02.042","title":"Diagnostic study and modeling of the annual positive water temperature onset","year":2009,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Hydro-Québec; Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mean squared error; Environmental science; Hydrology (agriculture); STREAMS; Annual cycle; Drainage; Water cycle; Drainage basin; Vegetation (pathology); Parametric statistics; Water level; Climatology; Physical geography; Statistics; Geology; Mathematics; Geography; Cartography; Ecology","score_opus":0.008483256124487885,"score_gpt":0.23331695971358388,"score_spread":0.224833703589096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016479499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9276655,0.00024219761,0.06664318,0.00047448894,0.00007521452,0.00007339808,0.00045623395,0.00037366946,0.003996246],"genre_scores_gemma":[0.9966763,0.000020644433,0.002922449,0.000007641907,0.000010323598,0.000006830299,0.00007798189,0.0000069873017,0.000270882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992466,0.00002635406,0.0000052335213,0.00001502013,0.000013944815,0.000014823099],"domain_scores_gemma":[0.99841475,0.0012020889,0.000133522,0.000039376802,0.00013746621,0.00007273498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005216562,0.00045172512,0.0002663572,0.0005693126,0.00027344885,0.0005004844,0.00077868125,0.0007815739,0.0012702843],"category_scores_gemma":[0.0031614704,0.00025630096,0.00031086677,0.00032618878,0.00030277617,0.0004578173,0.00029917475,0.0005527639,0.0000681469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035091172,0.0001829061,0.016133336,0.000057427693,0.000024344143,0.00041958436,0.000060696057,0.95862883,0.008671501,0.004596023,0.0007176809,0.010156829],"study_design_scores_gemma":[0.000006745598,0.000010730551,0.00052834884,7.400854e-7,0.0000020201776,0.000012177167,0.000003296823,0.9988398,0.00043209252,0.00013009596,0.000032008607,0.0000020278928],"about_ca_topic_score_codex":0.008328741,"about_ca_topic_score_gemma":0.0032509472,"teacher_disagreement_score":0.008328741,"about_ca_system_score_codex":0.0006090448,"about_ca_system_score_gemma":0.00056816335,"threshold_uncertainty_score":0.016560495},"labels":[],"label_agreement":null},{"id":"W2017587036","doi":"10.1016/s0022-1694(00)00214-6","title":"Daily reservoir inflow forecasting using artificial neural networks with stopped training approach","year":2000,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":617,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Hydro-Québec; Natural Sciences and Engineering Research Council; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overfitting; Inflow; Backpropagation; Artificial neural network; Computer science; Generalization; Training (meteorology); Artificial intelligence; Multivariate statistics; Early stopping; Machine learning; Time series; Meteorology; Mathematics","score_opus":0.07284336732487058,"score_gpt":0.25312158007906665,"score_spread":0.1802782127541961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017587036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40384874,0.0006317453,0.5906144,0.00027145413,0.00019505434,0.000059433438,0.00022333127,0.0009455768,0.0032102873],"genre_scores_gemma":[0.9521647,0.00010478026,0.04557264,0.000036428086,0.000041833533,0.000056042856,0.00025823465,0.00004095224,0.0017242344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996655,0.00012063223,0.00003338568,0.000071395254,0.00007511742,0.000034082226],"domain_scores_gemma":[0.99765944,0.0014376374,0.00014061361,0.00014941345,0.00054970256,0.00006318664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015444998,0.0005563799,0.00086554006,0.0006406121,0.00045151135,0.00067084807,0.00094070536,0.0010787505,0.0009789487],"category_scores_gemma":[0.004051185,0.00060648395,0.00052764005,0.00064992486,0.00038914935,0.00091115705,0.00036277022,0.0010967547,0.00019189804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020644469,0.000072666895,0.0033228633,0.000029544108,0.00007550781,0.000060938808,0.000029968405,0.9441269,0.0012093335,0.0008495314,0.00047334883,0.04954303],"study_design_scores_gemma":[0.0000035813623,0.000006684373,0.00018162534,9.3624493e-7,0.0000035683797,0.000001633834,7.7536714e-7,0.99947757,0.00018927951,0.00010646943,0.000026263388,0.0000016333058],"about_ca_topic_score_codex":0.009959797,"about_ca_topic_score_gemma":0.009809168,"teacher_disagreement_score":0.009959797,"about_ca_system_score_codex":0.0006049524,"about_ca_system_score_gemma":0.000620333,"threshold_uncertainty_score":0.019803643},"labels":[],"label_agreement":null},{"id":"W2020315078","doi":"10.2495/sdp-v10-n1-29-41","title":"Using lagged and forecast climate indices with artificial intelligence to predict monthly rainfall in the brisbane catchment, Queensland, Australia","year":2015,"lang":"en","type":"article","venue":"International Journal of Sustainable Development and Planning","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"B. Macfie Family Foundation","keywords":"Climatology; Environmental science; El Niño Southern Oscillation; Streamflow; Meteorology; Drainage basin; Index (typography); Forecast skill; Geography; Geology; Computer science","score_opus":0.08057802488843593,"score_gpt":0.313067027670807,"score_spread":0.23248900278237108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020315078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99512106,0.000099213496,0.0026675705,0.00016224981,0.000012780596,0.000018792405,0.00025308563,0.00008182417,0.0015834093],"genre_scores_gemma":[0.9962913,0.00006329394,0.0028526746,0.000012418515,0.000004386177,0.00001136134,0.00026637426,0.0000049912082,0.0004932657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983346,0.000055552435,0.000014959437,0.00003791546,0.000038072714,0.000019964918],"domain_scores_gemma":[0.9996284,0.00013678474,0.00006395936,0.00002480661,0.00011413282,0.0000317861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005812875,0.00032584436,0.00025858538,0.0004800128,0.0002622363,0.0006867664,0.0004307365,0.00031786226,0.00062080706],"category_scores_gemma":[0.0020952048,0.00024540364,0.0002468313,0.0007522423,0.00022334352,0.00055408076,0.0003629835,0.00044980957,0.0001169635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019115295,0.00030007208,0.18677577,0.000102015154,0.00018099467,0.00027886627,0.00045780907,0.76897365,0.0046604364,0.0007540614,0.001191528,0.036133762],"study_design_scores_gemma":[0.000019609613,0.00005891354,0.07101098,0.000012045204,0.000023985933,0.0000113223205,0.00011525991,0.9275078,0.00054893584,0.0002902075,0.00038477796,0.000016197562],"about_ca_topic_score_codex":0.23227927,"about_ca_topic_score_gemma":0.24928136,"teacher_disagreement_score":0.23227927,"about_ca_system_score_codex":0.0016407869,"about_ca_system_score_gemma":0.0011405374,"threshold_uncertainty_score":0.46185452},"labels":[],"label_agreement":null},{"id":"W2023347862","doi":"10.1007/s11269-008-9382-1","title":"Enhancing Inflow Forecasting Model at Aswan High Dam Utilizing Radial Basis Neural Network and Upstream Monitoring Stations Measurements","year":2008,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ottawa Mental Health Centre; Royal Military College of Canada","funders":"","keywords":"Inflow; Upstream (networking); Artificial neural network; Hydrogeology; Hydrology (agriculture); Water level; Environmental science; Computer science; Meteorology; Engineering; Machine learning; Cartography; Geotechnical engineering; Geography","score_opus":0.061487234655311154,"score_gpt":0.22976944227456722,"score_spread":0.16828220761925605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023347862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8375277,0.000083507424,0.1542816,0.00036923363,0.00013566646,0.00004871702,0.00049960834,0.0012047114,0.0058492157],"genre_scores_gemma":[0.98797345,0.00003661869,0.010488855,0.000012446175,0.000011502139,0.00001898829,0.00017165985,0.000013823934,0.0012726974],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998777,0.000026402078,0.0000073412752,0.000032685242,0.000036588808,0.00001917878],"domain_scores_gemma":[0.9996861,0.00007566549,0.00003303223,0.000023323408,0.0001581592,0.000023792405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004080163,0.00051054906,0.000418864,0.00033853183,0.0004732783,0.00045563895,0.00060890696,0.0005280667,0.00067966146],"category_scores_gemma":[0.00080495834,0.00032995892,0.00030500093,0.00048680615,0.00015023613,0.0008352367,0.00027830413,0.0006635338,0.00020953438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007356399,0.00010025428,0.009782703,0.000016141812,0.000020282565,0.000060304003,0.000028288185,0.9611021,0.003064684,0.0004975071,0.000909773,0.024344292],"study_design_scores_gemma":[0.0000017808447,0.000005130577,0.00051430985,3.472858e-7,0.0000028088666,0.0000012965575,0.000002209803,0.9990294,0.00036341173,0.000050030623,0.000027364811,0.0000018873671],"about_ca_topic_score_codex":0.035440654,"about_ca_topic_score_gemma":0.044009905,"teacher_disagreement_score":0.035440654,"about_ca_system_score_codex":0.0007191899,"about_ca_system_score_gemma":0.00094912713,"threshold_uncertainty_score":0.070468724},"labels":[],"label_agreement":null},{"id":"W2025651937","doi":"10.1061/(asce)1084-0699(2006)11:3(199)","title":"Application of Support Vector Machine in Lake Water Level Prediction","year":2006,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":268,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Support vector machine; Structural risk minimization; Artificial neural network; Computer science; Autoregressive model; Multilayer perceptron; Mean squared error; Quadratic programming; Correlation coefficient; Machine learning; Minification; Perceptron; Artificial intelligence; Least squares support vector machine; Data mining; Mathematical optimization; Mathematics; Statistics","score_opus":0.008079776733601744,"score_gpt":0.18831738023550781,"score_spread":0.18023760350190607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025651937","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5275397,0.005704743,0.45767874,0.0011961915,0.00021948485,0.00003057652,0.00019161252,0.00088382524,0.006555151],"genre_scores_gemma":[0.9802767,0.000458333,0.01865146,0.000023294444,0.000033381788,0.000006473571,0.000047729416,0.000007417273,0.00049529667],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956304,0.00020874362,0.000022394954,0.00004701551,0.00012761605,0.00003112661],"domain_scores_gemma":[0.99899,0.0007676988,0.000056974488,0.00003427798,0.0001317093,0.00001943042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007827761,0.00029236625,0.00033886344,0.00053150405,0.00013970373,0.0004397601,0.0002553928,0.00048475942,0.0007377163],"category_scores_gemma":[0.0025908437,0.00010773823,0.00021135066,0.0007471791,0.00021419919,0.00049634505,0.0002724615,0.00038727708,0.00016088386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019964714,0.000091915965,0.017394397,0.00012432176,0.00011652358,0.0002271116,0.00006169875,0.61862916,0.005712801,0.0034328385,0.0012717714,0.35273772],"study_design_scores_gemma":[0.0000051359684,0.00007425926,0.0017448349,0.00000841168,0.00001198262,0.000036163266,0.000018437813,0.9938724,0.0016377965,0.0018030191,0.000780526,0.0000069746184],"about_ca_topic_score_codex":0.0022648845,"about_ca_topic_score_gemma":0.0016401963,"teacher_disagreement_score":0.0022648845,"about_ca_system_score_codex":0.00019718314,"about_ca_system_score_gemma":0.00020656642,"threshold_uncertainty_score":0.0045033693},"labels":[],"label_agreement":null},{"id":"W2027996677","doi":"10.1007/s11269-012-0143-9","title":"Comparison of Record-Extension Techniques for Water Quality Variables","year":2012,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"National Water Center, United Arab Emirates University; Helwan University; National Research Centre","keywords":"Monte Carlo method; Ordinary least squares; Statistics; Robustness (evolution); Econometrics; Standard error; Population; Population variance; Variance (accounting); Regression; Percentile; Mathematics","score_opus":0.05722857590310414,"score_gpt":0.3196002365147445,"score_spread":0.26237166061164036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027996677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3015366,0.0012102782,0.68719435,0.00021651063,0.0001642176,0.00017963882,0.00087996176,0.0021679173,0.006450509],"genre_scores_gemma":[0.5652895,0.0012102649,0.42643425,0.000080998136,0.00010569227,0.00017993819,0.0018315394,0.00032677542,0.004541043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951506,0.00018572377,0.000046209316,0.00008326963,0.00012589993,0.00004379544],"domain_scores_gemma":[0.9907987,0.006649455,0.00022312811,0.00068337657,0.0015462025,0.000099142235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034868773,0.0005062951,0.00045651343,0.0012386333,0.0003368812,0.00083645654,0.0007854039,0.0005535302,0.002181265],"category_scores_gemma":[0.010458012,0.00024735948,0.00053779926,0.0015674566,0.00016092867,0.0017480438,0.000690153,0.00082123955,0.0006350511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021647357,0.0003092797,0.017726295,0.00025587328,0.00025088765,0.000047652422,0.00029228002,0.056155298,0.0099681225,0.0027813949,0.0012284116,0.90881974],"study_design_scores_gemma":[0.00019423173,0.00046202,0.033459328,0.000059868362,0.00032507582,0.0001370117,0.0002466206,0.9385746,0.019054977,0.0030477955,0.0043648514,0.00007361266],"about_ca_topic_score_codex":0.005442702,"about_ca_topic_score_gemma":0.005184688,"teacher_disagreement_score":0.005442702,"about_ca_system_score_codex":0.00024546354,"about_ca_system_score_gemma":0.0005737033,"threshold_uncertainty_score":0.018440545},"labels":[],"label_agreement":null},{"id":"W2029490203","doi":"10.1061/(asce)he.1943-5584.0000273","title":"Modeling the Time Variation of Reservoir Trap Efficiency","year":2010,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"AGE-WELL","keywords":"Inflow; Empirical modelling; Soft computing; Trap (plumbing); Genetic programming; Reservoir modeling; Computer science; Sedimentation; Reservoir computing; Artificial neural network; Deposition (geology); Genetic algorithm; Hydrology (agriculture); Soil science; Sediment; Geology; Environmental science; Petroleum engineering; Machine learning; Geotechnical engineering; Geomorphology; Simulation; Environmental engineering","score_opus":0.009851759152751029,"score_gpt":0.2052195120320972,"score_spread":0.19536775287934618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029490203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7510555,0.0001863932,0.24454127,0.00022366479,0.000021122232,0.00003505011,0.00039657007,0.00022618368,0.0033141451],"genre_scores_gemma":[0.9933622,0.00006361731,0.005290393,0.000007380177,0.000004877097,0.000020723619,0.000079522106,0.000016561085,0.0011548487],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998084,0.000047696514,0.000014203819,0.00006247523,0.000029881183,0.000037419653],"domain_scores_gemma":[0.9988041,0.00069732004,0.00027420273,0.00006193847,0.00012983658,0.000032667776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000743548,0.00037330168,0.00033301802,0.00052584865,0.0001785549,0.0006623426,0.0007301672,0.0009047109,0.00068273186],"category_scores_gemma":[0.003498189,0.00035484307,0.00036494544,0.0006056917,0.00042597065,0.00089869683,0.0003396411,0.0005779995,0.00012369038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017103943,0.000013257778,0.004714223,0.000015169995,0.000013713474,0.0000818953,0.0000305197,0.98915917,0.0011139166,0.0015278119,0.00006905021,0.0032440715],"study_design_scores_gemma":[6.7661273e-7,0.0000031683437,0.0008436517,0.0000010663816,0.0000024699173,0.000008840677,0.0000029559344,0.99869674,0.00017258793,0.00022234376,0.000042865788,0.0000026988987],"about_ca_topic_score_codex":0.010145542,"about_ca_topic_score_gemma":0.005642267,"teacher_disagreement_score":0.010145542,"about_ca_system_score_codex":0.00067783246,"about_ca_system_score_gemma":0.00047265366,"threshold_uncertainty_score":0.020172954},"labels":[],"label_agreement":null},{"id":"W2031954295","doi":"10.3166/isi.16.3.113-139","title":"Variable optimization for flood prediction","year":2011,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy","score_opus":0.026789432314880426,"score_gpt":0.21084521030372178,"score_spread":0.18405577798884135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031954295","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013126547,0.009437198,0.95305026,0.0026439112,0.0015283712,0.000039830556,0.0003271653,0.0005769845,0.01926971],"genre_scores_gemma":[0.5856802,0.012781808,0.30296415,0.00101447,0.00343063,0.00048376474,0.0012443232,0.0008186635,0.09158207],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997353,0.000108343076,0.000012277189,0.00007249468,0.00005167529,0.000019871992],"domain_scores_gemma":[0.9991534,0.0005875492,0.000045543806,0.000045742032,0.0001417335,0.000026038382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081962475,0.0009197083,0.0011734562,0.000508668,0.00037417942,0.0011282144,0.0006952623,0.0010265596,0.00902422],"category_scores_gemma":[0.002938212,0.0003666219,0.0005998888,0.0011484874,0.00065601885,0.00079827645,0.00069453876,0.0020404642,0.0012264122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052312327,0.00004737591,0.0002965454,0.00017482368,0.000081405924,0.000025805582,0.0000287617,0.82783526,0.0009319049,0.031990886,0.016304413,0.12223051],"study_design_scores_gemma":[0.000005477179,0.000012728739,0.000111965324,0.000014028867,0.000006153086,0.0000031119932,0.0000036266454,0.9792707,0.00018740045,0.017414086,0.0029658496,0.000004839673],"about_ca_topic_score_codex":0.0058287205,"about_ca_topic_score_gemma":0.0033389789,"teacher_disagreement_score":0.00902422,"about_ca_system_score_codex":0.0005964749,"about_ca_system_score_gemma":0.0005039436,"threshold_uncertainty_score":0.030189037},"labels":[],"label_agreement":null},{"id":"W2031991569","doi":"10.1145/2484838.2484840","title":"Learning uncertainty models from weather forecast performance databases using quantile regression","year":2013,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Quantile regression; Quantile; Numerical weather prediction; Computer science; Prediction interval; Forecast skill; Data mining; Forecast verification; Cluster analysis; Weather forecasting; Machine learning; Artificial intelligence; Statistics; Mathematics; Meteorology","score_opus":0.06420358001373258,"score_gpt":0.26472833231493026,"score_spread":0.20052475230119768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031991569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39101985,0.00052451895,0.60493636,0.00037407433,0.0000319607,0.0001119588,0.0008706178,0.0011342231,0.0009963968],"genre_scores_gemma":[0.9480173,0.00020891562,0.049800877,0.0000336203,0.000030087303,0.00009238916,0.0014985583,0.000028933464,0.00028928678],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869317,0.000604122,0.000116811156,0.00024104484,0.00025350673,0.00009143185],"domain_scores_gemma":[0.9900832,0.007694478,0.00075566425,0.00070692046,0.00067586405,0.00008392058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005096251,0.00079783465,0.0008296264,0.0014918923,0.00024102956,0.0011837475,0.0011319428,0.00065459334,0.00063238875],"category_scores_gemma":[0.0170067,0.0003269846,0.00069367816,0.0014419992,0.00032428125,0.0014551835,0.00081425026,0.0013026282,0.00024777398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014392611,0.0001088963,0.0069103413,0.00003996676,0.000079498255,0.000037758484,0.00007957016,0.92427224,0.000782805,0.0015963884,0.00041374992,0.06553487],"study_design_scores_gemma":[0.0000025993293,0.000012190279,0.0008283901,0.0000022699794,0.000004002598,0.0000034189313,0.000007926868,0.99792045,0.000300866,0.0008703202,0.000043990956,0.0000035186504],"about_ca_topic_score_codex":0.006892053,"about_ca_topic_score_gemma":0.003645192,"teacher_disagreement_score":0.006892053,"about_ca_system_score_codex":0.00085424015,"about_ca_system_score_gemma":0.00043038497,"threshold_uncertainty_score":0.026951909},"labels":[],"label_agreement":null},{"id":"W2038098184","doi":"10.1002/hyp.6928","title":"Stream temperature modelling using artificial neural networks: application on Catamaran Brook, New Brunswick, Canada","year":2008,"lang":"en","type":"article","venue":"Hydrological Processes","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Fisheries and Oceans Canada; Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tributary; Mean squared error; Environmental science; Air temperature; Hydrology (agriculture); Drainage basin; Mean radiant temperature; Coefficient of determination; Ecology; Meteorology; Statistics; Mathematics; Climate change; Geology; Geography","score_opus":0.040361647246029836,"score_gpt":0.22863492192608934,"score_spread":0.1882732746800595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038098184","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903206,0.00023620058,0.0034322292,0.00014920175,0.000024176214,0.00009704483,0.0013080148,0.00017648042,0.0042558415],"genre_scores_gemma":[0.9906595,0.0002158821,0.0043251864,0.00002064275,0.000003978575,0.00004509075,0.0012439061,0.000019452955,0.0034665018],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982977,0.000023164308,0.000011521073,0.000042933785,0.000056996938,0.00003554146],"domain_scores_gemma":[0.99903995,0.00019984349,0.000042527918,0.000029463088,0.00062961585,0.00005850166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047192702,0.00061030197,0.00033979173,0.00049781625,0.0009263769,0.0008575574,0.0008983052,0.0004320901,0.0014729819],"category_scores_gemma":[0.0011227834,0.0002859053,0.00044829832,0.0011867168,0.00026098944,0.00026417561,0.0003068337,0.00043625766,0.00017828202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027869837,0.0002506493,0.18531348,0.00017705468,0.00017019194,0.00053759053,0.00032352537,0.76123273,0.0032147996,0.0006790391,0.003629418,0.044192873],"study_design_scores_gemma":[0.000043552245,0.000045442874,0.0595083,0.000025165105,0.00003350664,0.000018549605,0.00030286453,0.93668586,0.0013507898,0.00012883311,0.0018207564,0.00003640033],"about_ca_topic_score_codex":0.97841954,"about_ca_topic_score_gemma":0.983691,"teacher_disagreement_score":0.021580458,"about_ca_system_score_codex":0.012833363,"about_ca_system_score_gemma":0.009528361,"threshold_uncertainty_score":0.093113005},"labels":[],"label_agreement":null},{"id":"W2041021326","doi":"10.1111/j.1752-1688.2003.tb03708.x","title":"ANN OUTPUT UPDATING OF LUMPED CONCEPTUAL RAINFALL/RUNOFF FORECASTING MODELS<sup>1</sup>","year":2003,"lang":"en","type":"article","venue":"JAWRA Journal of the American Water Resources Association","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Streamflow; Artificial neural network; Conceptual model; Statement (logic); Computer science; Scheme (mathematics); Surface runoff; Simple (philosophy); Problem statement; Mathematics; Artificial intelligence; Engineering; Management science","score_opus":0.022266029018699108,"score_gpt":0.21667647041311353,"score_spread":0.1944104413944144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041021326","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8214434,0.00026392032,0.16818959,0.0002519388,0.00015426507,0.000097565724,0.0004113221,0.0016937098,0.0074942484],"genre_scores_gemma":[0.9859256,0.000039358205,0.01323431,0.000017396345,0.0000070903607,0.000021560409,0.00016987696,0.00001951653,0.0005652886],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965537,0.0001251791,0.000041306703,0.00006618126,0.000081625585,0.000030344609],"domain_scores_gemma":[0.99832314,0.0008793218,0.00017762372,0.00014590014,0.00044260893,0.00003134408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014733811,0.00070299266,0.00030554054,0.0002752841,0.0001519978,0.0005205654,0.00073169294,0.00042281128,0.0012292126],"category_scores_gemma":[0.0047972496,0.00018655491,0.0002554315,0.0003903574,0.00022801307,0.0006545497,0.00036443892,0.00052832195,0.00020261183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039033833,0.000106648375,0.0057071694,0.00013297754,0.00007544802,0.00007174386,0.000050805025,0.90176415,0.0046889563,0.00066292676,0.00062804227,0.08572081],"study_design_scores_gemma":[0.000010828054,0.000053960215,0.0010266348,0.000005630811,0.000014511843,0.000008496929,0.000005147479,0.9950991,0.0034124176,0.00020491685,0.00015317339,0.000005170608],"about_ca_topic_score_codex":0.005384627,"about_ca_topic_score_gemma":0.005692232,"teacher_disagreement_score":0.005384627,"about_ca_system_score_codex":0.0006133833,"about_ca_system_score_gemma":0.000287441,"threshold_uncertainty_score":0.010706544},"labels":[],"label_agreement":null},{"id":"W2041534329","doi":"10.1016/j.jhydrol.2004.12.001","title":"Groundwater level forecasting using artificial neural networks","year":2005,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":665,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Artificial neural network; Groundwater; Computer science; Feedforward neural network; Feed forward; Groundwater resources; Water resources; Machine learning; Environmental science; Artificial intelligence; Aquifer; Engineering; Ecology; Control engineering","score_opus":0.09678811329542164,"score_gpt":0.274602285667172,"score_spread":0.17781417237175035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041534329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2767419,0.001698948,0.7086672,0.0010019025,0.00062075123,0.000053906428,0.0005362419,0.0014009795,0.009278171],"genre_scores_gemma":[0.9564079,0.00043642518,0.040544916,0.00007473215,0.000113103764,0.00003109022,0.00021772274,0.000022388427,0.0021517728],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998622,0.000034349156,0.000016991098,0.000031914595,0.000037620044,0.000016858614],"domain_scores_gemma":[0.99892765,0.00067406485,0.00009018595,0.00004842028,0.00023421475,0.00002552431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052942144,0.0003599759,0.00043538687,0.0007193646,0.00018498483,0.00061029097,0.0004560128,0.00062180037,0.0010009515],"category_scores_gemma":[0.002867693,0.0002624004,0.00029294772,0.00094414176,0.00021942721,0.0008491615,0.00023870872,0.00073758216,0.00023010837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014870588,0.00006521147,0.0038690385,0.00004661529,0.00007057815,0.000048103087,0.00001769354,0.8954777,0.0017712382,0.00162416,0.0013779678,0.095483],"study_design_scores_gemma":[0.000002915876,0.0000034272462,0.00022706029,0.0000017798521,0.000004153681,0.0000016025018,0.0000011922566,0.99880874,0.00021804939,0.0006646723,0.00006456473,0.0000017942787],"about_ca_topic_score_codex":0.009617483,"about_ca_topic_score_gemma":0.00860422,"teacher_disagreement_score":0.009617483,"about_ca_system_score_codex":0.0005099803,"about_ca_system_score_gemma":0.00029357654,"threshold_uncertainty_score":0.019123018},"labels":[],"label_agreement":null},{"id":"W2043507675","doi":"10.3741/jkwra.2013.46.8.857","title":"Inflow Estimation into Chungju Reservoir Using RADAR Forecasted Precipitation Data and ANFIS","year":2013,"lang":"en","type":"article","venue":"Journal of Korea Water Resources Association","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nowcasting; Precipitation; Environmental science; Adaptive neuro fuzzy inference system; Meteorology; Flash flood; Radar; Extrapolation; Flood myth; Inflow; Remote sensing; Computer science; Fuzzy logic; Geography; Mathematics; Fuzzy control system; Statistics; Artificial intelligence","score_opus":0.02454166672403434,"score_gpt":0.2546429227964877,"score_spread":0.23010125607245335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043507675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726174,0.0001257765,0.024554377,0.000105931504,0.00002970425,0.00004019909,0.00038273045,0.00039102236,0.0017528327],"genre_scores_gemma":[0.9948409,0.000066457,0.004315543,0.0000070547158,0.0000039900374,0.000017951324,0.00020466762,0.000007634596,0.0005357106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992895,0.000009615162,0.000009846483,0.000018718,0.000016310161,0.000016517692],"domain_scores_gemma":[0.999838,0.00004627943,0.000025916474,0.000007855226,0.00006607976,0.000015901895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020894126,0.00049245195,0.0003334844,0.0006667074,0.00036588567,0.00046725944,0.00033019585,0.0003158197,0.00067594147],"category_scores_gemma":[0.0004961064,0.00032777424,0.00043483335,0.00054909464,0.00012250894,0.0005782788,0.0003336081,0.00036185436,0.00008118682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003824064,0.00024607504,0.08130016,0.00028232302,0.00011930659,0.0011129823,0.00035031128,0.7909788,0.025362382,0.0011976013,0.0014542644,0.09721334],"study_design_scores_gemma":[0.0000071527274,0.00003114856,0.007922314,0.000008736925,0.00002094499,0.000016010115,0.000050561855,0.98950213,0.0021720103,0.00013064803,0.00012881166,0.000009587587],"about_ca_topic_score_codex":0.039798368,"about_ca_topic_score_gemma":0.039504044,"teacher_disagreement_score":0.039798368,"about_ca_system_score_codex":0.00048395214,"about_ca_system_score_gemma":0.00097480376,"threshold_uncertainty_score":0.07913345},"labels":[],"label_agreement":null},{"id":"W2044112403","doi":"10.1504/ijw.2015.068959","title":"Evaluation of soft computing algorithms for estimation of spatial transmissivity","year":2015,"lang":"en","type":"article","venue":"International Journal of Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Soft computing; Adaptive neuro fuzzy inference system; Computer science; Algorithm; Mean squared error; Piecewise linear function; Tree (set theory); Data mining; Artificial intelligence; Machine learning; Artificial neural network; Fuzzy logic; Mathematics; Statistics; Fuzzy control system","score_opus":0.08369166880760748,"score_gpt":0.34463410327175525,"score_spread":0.2609424344641478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044112403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104569994,0.00085682113,0.889803,0.00020999707,0.000058061698,0.000082675135,0.00005574704,0.00030432604,0.0040593427],"genre_scores_gemma":[0.75144863,0.00057568727,0.24652353,0.000056765166,0.00003395297,0.00012585401,0.00010801238,0.000047852147,0.001079807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912554,0.0003476727,0.00006466014,0.000111989604,0.00030503716,0.000045137385],"domain_scores_gemma":[0.9960167,0.002959357,0.00018868149,0.00014903292,0.0006261847,0.000060038357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023184658,0.00073870906,0.0006293344,0.0014277154,0.0003101072,0.0010528554,0.00057251356,0.0008848209,0.000942273],"category_scores_gemma":[0.008279914,0.00019796607,0.0005132703,0.00089179655,0.0003725807,0.0011388639,0.0007420548,0.00059955096,0.00016375426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019183494,0.000085186,0.0027733275,0.00016289702,0.000086028296,0.000050586303,0.000064879,0.78562033,0.0030398131,0.006033773,0.00032645886,0.20156495],"study_design_scores_gemma":[0.0000029764626,0.000033236953,0.00027221994,0.000006993544,0.000005314869,0.000009520103,0.000011869583,0.99786454,0.000859608,0.0008319836,0.00009924538,0.0000024538413],"about_ca_topic_score_codex":0.002227847,"about_ca_topic_score_gemma":0.0015356196,"teacher_disagreement_score":0.0023184658,"about_ca_system_score_codex":0.00051703636,"about_ca_system_score_gemma":0.0006447945,"threshold_uncertainty_score":0.012261391},"labels":[],"label_agreement":null},{"id":"W2045859675","doi":"10.1109/ifsa-nafips.2013.6608480","title":"Non-parametric interval forecast models from fuzzy clustering of Numerical Weather Predictions","year":2013,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Numerical weather prediction; Cluster analysis; Probabilistic forecasting; Computer science; Probabilistic logic; Weather forecasting; Data mining; Forecast skill; Parametric statistics; Interval (graph theory); Fuzzy logic; Weather prediction; Global Forecast System; Set (abstract data type); Fuzzy clustering; Machine learning; Artificial intelligence; Statistics; Meteorology; Mathematics","score_opus":0.025175641848688382,"score_gpt":0.2273286863428888,"score_spread":0.2021530444942004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045859675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07838374,0.00016964697,0.9192532,0.00009782495,0.000041803578,0.0000827003,0.0002207071,0.0003260543,0.0014243652],"genre_scores_gemma":[0.8641372,0.00019107685,0.13279709,0.000022906634,0.000044344473,0.00019313682,0.00048570338,0.00004775496,0.0020808866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955636,0.00015698599,0.000029331542,0.00009957428,0.00011710975,0.000040591993],"domain_scores_gemma":[0.997216,0.0018482613,0.00032058507,0.0001535313,0.00041111052,0.000050492403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022850165,0.0005407742,0.00061811844,0.0007783211,0.00029034322,0.00078537734,0.0013782117,0.0006203061,0.0013776139],"category_scores_gemma":[0.00607392,0.00028940936,0.0006313551,0.00080541294,0.00039540234,0.00094881834,0.00043938617,0.0009317638,0.00024199321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003728714,0.000017990362,0.0005286298,0.000022529512,0.000019207762,0.000010458995,0.00004019067,0.97845,0.0003913351,0.0037778872,0.00016315965,0.016541343],"study_design_scores_gemma":[8.1040963e-7,0.000004042453,0.00013070254,0.0000010290354,0.0000012894728,0.000001529912,0.0000020438674,0.9991844,0.000084066836,0.0005580671,0.000029595012,0.0000023841717],"about_ca_topic_score_codex":0.011417069,"about_ca_topic_score_gemma":0.008197623,"teacher_disagreement_score":0.011417069,"about_ca_system_score_codex":0.0007434503,"about_ca_system_score_gemma":0.0006862594,"threshold_uncertainty_score":0.022701204},"labels":[],"label_agreement":null},{"id":"W2046156160","doi":"10.1002/2013wr014650","title":"Wavelet‐based multiscale performance analysis: An approach to assess and improve hydrological models","year":2014,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Wavelet; Computer science; Wavelet transform; Scale (ratio); Measure (data warehouse); Series (stratigraphy); Mean squared error; Data mining; Statistics; Mathematics; Artificial intelligence; Geology","score_opus":0.1154676127361794,"score_gpt":0.3194811420773527,"score_spread":0.20401352934117328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046156160","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03165533,0.00021320427,0.96671563,0.00016185283,0.000026050722,0.00003130123,0.000051728068,0.00022453348,0.0009203278],"genre_scores_gemma":[0.7337167,0.00034349322,0.26491544,0.00006365145,0.0000868303,0.00013418523,0.00014287417,0.00012692076,0.00046998475],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867815,0.00066697714,0.00008589444,0.00014729692,0.00034555394,0.000076100645],"domain_scores_gemma":[0.99638736,0.0019986087,0.0005104897,0.0004011513,0.00062109495,0.00008129692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059968242,0.001110001,0.0009849882,0.0027102756,0.00031484623,0.0011297852,0.0008039242,0.0011250076,0.0009683509],"category_scores_gemma":[0.013821936,0.00038896335,0.0010315562,0.0015346323,0.000679849,0.0015445447,0.0014098744,0.0010232097,0.00014393464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060120256,0.00009006703,0.002697086,0.00007809391,0.00015297878,0.000051632927,0.000061489125,0.8970145,0.003618888,0.025009466,0.000698832,0.0704668],"study_design_scores_gemma":[0.0000015022051,0.0000149238895,0.00020440436,0.0000033728327,0.000005738585,0.0000024460287,0.00000405713,0.9971456,0.00020669767,0.0023056075,0.00010274833,0.0000029313403],"about_ca_topic_score_codex":0.002056654,"about_ca_topic_score_gemma":0.0009661714,"teacher_disagreement_score":0.0059968242,"about_ca_system_score_codex":0.00078196754,"about_ca_system_score_gemma":0.00074077526,"threshold_uncertainty_score":0.03171462},"labels":[],"label_agreement":null},{"id":"W2046498361","doi":"10.4296/cwrj3203179","title":"A Review of Statistical Water Temperature Models","year":2007,"lang":"en","type":"review","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":299,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistical model; Parametric statistics; Parametric model; Computer science; Econometrics; Environmental science; Statistics; Mathematics; Machine learning","score_opus":0.0448873083798638,"score_gpt":0.2703972339283417,"score_spread":0.2255099255484779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046498361","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001987148,0.86058474,0.11868005,0.002295595,0.0018341697,0.000070510076,0.00094965677,0.0007639201,0.012834277],"genre_scores_gemma":[0.019499306,0.93106985,0.038238857,0.0005451243,0.0016807592,0.000120924036,0.0013927134,0.000103011276,0.0073495028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994898,0.00010679716,0.00006461811,0.00010048724,0.00021300209,0.000025297482],"domain_scores_gemma":[0.9984861,0.0009040691,0.00011143388,0.00009060124,0.00037256718,0.000035316156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012747117,0.0014926547,0.0017780352,0.0021939322,0.0003573939,0.0014222934,0.0021134717,0.0010858425,0.0045893607],"category_scores_gemma":[0.0028923466,0.0005508035,0.0010930856,0.0057155867,0.00053977384,0.002243109,0.0005980335,0.0011281541,0.003558126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046518824,0.000076998884,0.0011068427,0.005598133,0.00021062001,0.0001539375,0.000064711814,0.03165145,0.0008760732,0.027383616,0.040195238,0.89263576],"study_design_scores_gemma":[0.000022108477,0.00013839401,0.0018036732,0.002003422,0.00022073221,0.000569847,0.00009582013,0.053520847,0.0014475931,0.045429196,0.89464754,0.000100862824],"about_ca_topic_score_codex":0.0043428317,"about_ca_topic_score_gemma":0.0033092175,"teacher_disagreement_score":0.0045893607,"about_ca_system_score_codex":0.00083111867,"about_ca_system_score_gemma":0.0022756672,"threshold_uncertainty_score":0.015352905},"labels":[],"label_agreement":null},{"id":"W2046785557","doi":"10.1016/j.jhydrol.2011.06.013","title":"A wavelet neural network conjunction model for groundwater level forecasting","year":2011,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":636,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoregressive integrated moving average; Groundwater; Artificial neural network; Environmental science; Aquifer; Watershed; Moving average; Autoregressive model; Wavelet; Hydrology (agriculture); Computer science; Meteorology; Statistics; Time series; Machine learning; Artificial intelligence; Engineering; Mathematics; Geography","score_opus":0.15731392097699998,"score_gpt":0.2549453713901056,"score_spread":0.09763145041310561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046785557","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060978685,0.00045812194,0.9346201,0.00028925948,0.00017550649,0.000023636796,0.00016710699,0.0003536444,0.002933976],"genre_scores_gemma":[0.87443143,0.00048329867,0.117262065,0.0000996881,0.00011981045,0.000089598776,0.00027882546,0.000061565945,0.0071737524],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986553,0.000036999427,0.000009787235,0.00003402143,0.00003537139,0.000018304852],"domain_scores_gemma":[0.9996371,0.00018158228,0.00002380086,0.00002707588,0.00011008556,0.000020259411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000676154,0.00032515114,0.00062586006,0.0002927891,0.00027462744,0.00050260685,0.0010740628,0.0007918363,0.0021901878],"category_scores_gemma":[0.0014866536,0.00032496027,0.00042012404,0.0008017825,0.00022515921,0.0009691202,0.00067564804,0.0012679555,0.00046183955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013764716,0.00007014304,0.00062351034,0.000032182346,0.000053964977,0.000048841248,0.000019019555,0.9087164,0.002752961,0.0041066394,0.0010122468,0.08242648],"study_design_scores_gemma":[0.0000012346427,0.0000040237883,0.00002354333,4.0550242e-7,0.0000020993668,0.0000013815585,3.749394e-7,0.99965656,0.00008455356,0.00018459355,0.000040489536,7.456446e-7],"about_ca_topic_score_codex":0.0062943147,"about_ca_topic_score_gemma":0.0050655757,"teacher_disagreement_score":0.0062943147,"about_ca_system_score_codex":0.00036318478,"about_ca_system_score_gemma":0.00052204815,"threshold_uncertainty_score":0.012515366},"labels":[],"label_agreement":null},{"id":"W2048036286","doi":"10.2478/sggw-2013-0007","title":"Using support vector regression to predict direct runoff, base flow and total flow in a mountainous watershed with limited data in Uttaranchal, India","year":2013,"lang":"en","type":"article","venue":"Annals of Warsaw University of Life Sciences – SGGW Land Reclamation","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Surface runoff; Base flow; Watershed; Support vector machine; Environmental science; Hydrology (agriculture); Water resources; Flow (mathematics); Geography; Mathematics; Computer science; Drainage basin; Engineering; Ecology; Machine learning; Cartography; Geotechnical engineering","score_opus":0.06623861588025744,"score_gpt":0.26249616741307863,"score_spread":0.1962575515328212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048036286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99898714,0.0000078835965,0.0007142053,0.00002487377,0.0000014226157,0.0000046239406,0.00007203858,0.00003174179,0.0001561748],"genre_scores_gemma":[0.99898225,0.000011131061,0.0007014283,0.0000025644545,0.0000011575626,0.0000059104555,0.0001743795,0.0000016301705,0.000119606746],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998615,0.000039607687,0.000014023535,0.000025486019,0.00003212077,0.000027296132],"domain_scores_gemma":[0.9994504,0.00032587955,0.000059320028,0.00003306938,0.00009379721,0.000037597987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002745384,0.00025595128,0.00025990058,0.0006158046,0.0002829862,0.0005178588,0.00045300473,0.0002576006,0.00033632474],"category_scores_gemma":[0.00088176026,0.00014657238,0.00035953778,0.00078611006,0.00020717233,0.0002747128,0.00023554894,0.00031883133,0.00008867724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043320778,0.00066108356,0.42361313,0.0001290953,0.000207379,0.0012884986,0.0007418238,0.49853197,0.012500991,0.00054030784,0.0010452722,0.060307294],"study_design_scores_gemma":[0.00002098905,0.00015971427,0.1895983,0.000006884142,0.000036825266,0.00006172644,0.0005901578,0.8061949,0.0028543638,0.0001929992,0.00026243084,0.000020686832],"about_ca_topic_score_codex":0.054143503,"about_ca_topic_score_gemma":0.058131054,"teacher_disagreement_score":0.054143503,"about_ca_system_score_codex":0.00067528273,"about_ca_system_score_gemma":0.00060513284,"threshold_uncertainty_score":0.10765666},"labels":[],"label_agreement":null},{"id":"W2048774798","doi":"10.1016/j.ecolmodel.2011.11.023","title":"Simulations of runoff and evapotranspiration in Chinese fir plantation ecosystems using artificial neural networks","year":2011,"lang":"en","type":"article","venue":"Ecological Modelling","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Evapotranspiration; Surface runoff; Environmental science; Hydrology (agriculture); Ecosystem; Forest ecology; Ecology; Geology; Biology","score_opus":0.09067187323571424,"score_gpt":0.2599964636773821,"score_spread":0.16932459044166787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048774798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936985,0.00007430301,0.004039771,0.00014585162,0.000028061284,0.000009982056,0.00013805782,0.00006485992,0.00180072],"genre_scores_gemma":[0.9988154,0.000031193635,0.0005697722,0.000010818915,0.0000042012243,0.0000101739615,0.000058670183,0.000005044456,0.00049466966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998869,0.000027047126,0.0000084225685,0.00002895182,0.000013935048,0.000034714096],"domain_scores_gemma":[0.99930835,0.0004074493,0.000071386414,0.00002637323,0.000106245716,0.00008025945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042831787,0.00056449603,0.00057737174,0.0005837462,0.0006274927,0.0006475695,0.00080807705,0.0010617165,0.0010997693],"category_scores_gemma":[0.0011959927,0.00045191872,0.000682272,0.00071156427,0.0006965386,0.0008576052,0.0003573716,0.00062367145,0.00007234093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021422658,0.000022819071,0.0019845476,0.000006972079,0.000012466433,0.00002090552,0.000011123812,0.99684465,0.00016063411,0.0001715969,0.000058370715,0.0006845549],"study_design_scores_gemma":[0.0000036406725,0.0000048701927,0.0004885845,5.053824e-7,0.0000031996333,0.0000010752739,0.0000065939967,0.99935466,0.000060261398,0.00006269554,0.000012064791,0.0000019047701],"about_ca_topic_score_codex":0.12289263,"about_ca_topic_score_gemma":0.0689605,"teacher_disagreement_score":0.12289263,"about_ca_system_score_codex":0.002569037,"about_ca_system_score_gemma":0.0013856435,"threshold_uncertainty_score":0.2443546},"labels":[],"label_agreement":null},{"id":"W2050292603","doi":"10.1007/s11269-006-0326-4","title":"An Intelligent Decision Support System for Management of Floods","year":2006,"lang":"en","type":"article","venue":"Digital Scholarship - UNLV (University of Nevada Reno)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":141,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Decision support system; Flood myth; Flood forecasting; Flood control; Flooding (psychology); Computer science; Intelligent decision support system; Operations research; Engineering; Artificial intelligence; Geography","score_opus":0.01942775047152231,"score_gpt":0.22559761671662515,"score_spread":0.20616986624510283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050292603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027589038,0.00070758874,0.9234549,0.0009795027,0.00031703233,0.00054569915,0.0014481952,0.030986525,0.013971523],"genre_scores_gemma":[0.42980415,0.00075350737,0.55476844,0.00060257077,0.00019417731,0.0008861183,0.00207369,0.00021346664,0.010703893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963737,0.00009871867,0.000051196406,0.00006874463,0.000115478106,0.000028480665],"domain_scores_gemma":[0.9993734,0.00031406945,0.000048328508,0.000051401737,0.00016120553,0.000051665847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009986655,0.00055330206,0.00062929565,0.00086850225,0.0005912407,0.0014911359,0.001066825,0.00079325575,0.0070544],"category_scores_gemma":[0.0021363625,0.00021509662,0.00032096528,0.0006894315,0.00028061628,0.0011205769,0.0006327755,0.00064964895,0.0017308219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000866093,0.00043462843,0.003960939,0.000749733,0.00019993469,0.0008901686,0.0006489252,0.14748254,0.034705475,0.022870945,0.044958763,0.7422319],"study_design_scores_gemma":[0.00024005608,0.00025471087,0.0014845023,0.00009361144,0.00013065919,0.0002196212,0.00012427178,0.9169401,0.0123653915,0.014711734,0.053372666,0.000062656894],"about_ca_topic_score_codex":0.0036744599,"about_ca_topic_score_gemma":0.0034146511,"teacher_disagreement_score":0.0070544,"about_ca_system_score_codex":0.0006320592,"about_ca_system_score_gemma":0.0009436817,"threshold_uncertainty_score":0.023599267},"labels":[],"label_agreement":null},{"id":"W2051789594","doi":"10.1061/(asce)ee.1943-7870.0000439","title":"Application of Artificial Neural Networks for Filtration Optimization","year":2011,"lang":"en","type":"article","venue":"Journal of Environmental Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Natural Sciences and Engineering Research Council of Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Filtration (mathematics); Turbidity; Artificial neural network; Particle (ecology); Water treatment; Particle swarm optimization; Environmental science; SCADA; Biological system; Sensitivity (control systems); Process engineering; Environmental engineering; Computer science; Statistics; Engineering; Mathematics; Artificial intelligence; Machine learning; Ecology; Biology","score_opus":0.01393237031424915,"score_gpt":0.18922130690041122,"score_spread":0.17528893658616207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051789594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09655153,0.001973707,0.8888576,0.00065836706,0.0001661154,0.0001722423,0.00019585481,0.0009628657,0.010461691],"genre_scores_gemma":[0.86050993,0.00086611457,0.13350117,0.00013135029,0.00006925919,0.00035531778,0.00025091472,0.00006168641,0.00425423],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959844,0.00016072353,0.00003707473,0.00006203025,0.000104132865,0.000037557],"domain_scores_gemma":[0.99898845,0.0006829411,0.00007115629,0.00003150905,0.00020832341,0.000017540842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012566976,0.0010631031,0.0008449423,0.0008177068,0.0003407599,0.00097439607,0.0006628332,0.001150832,0.0013640033],"category_scores_gemma":[0.0028661937,0.0005089743,0.00054101646,0.00093576516,0.00034352593,0.00056615024,0.00057544286,0.0009096659,0.00020287897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013920328,0.000015245639,0.00025207864,0.000020832595,0.000019949974,0.00001422403,0.0000064163614,0.9862585,0.0002635531,0.00044392736,0.00010571062,0.012585778],"study_design_scores_gemma":[0.0000012974741,0.0000046941973,0.000041143398,0.000001807663,0.0000017410539,0.0000010532568,0.0000011141459,0.99955267,0.00010088976,0.00022101765,0.000071247494,0.0000012506434],"about_ca_topic_score_codex":0.0136184655,"about_ca_topic_score_gemma":0.008432695,"teacher_disagreement_score":0.0136184655,"about_ca_system_score_codex":0.00089958444,"about_ca_system_score_gemma":0.00085717026,"threshold_uncertainty_score":0.02707839},"labels":[],"label_agreement":null},{"id":"W2052914342","doi":"10.1177/0309133312444943","title":"Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting","year":2012,"lang":"en","type":"article","venue":"Progress in Physical Geography Earth and Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":310,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Université Laval","funders":"","keywords":"Benchmarking; Computer science; Benchmark (surveying); Artificial neural network; Streamflow; Transparency (behavior); Field (mathematics); Set (abstract data type); Flood forecasting; Modular design; Operations research; Data science; Management science; Flood myth; Artificial intelligence","score_opus":0.034318546842484574,"score_gpt":0.26192204143543596,"score_spread":0.22760349459295137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052914342","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017373918,0.23841737,0.047639932,0.67229205,0.005054517,0.000027983473,0.00036788336,0.00024179612,0.018584576],"genre_scores_gemma":[0.5786125,0.26859477,0.06169571,0.047153644,0.02369146,0.00028160066,0.00046052167,0.0004134161,0.019096388],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964551,0.0018137734,0.00019473316,0.00052505854,0.00074618246,0.0002652458],"domain_scores_gemma":[0.984536,0.011363566,0.00043695033,0.0012210554,0.001697951,0.00074445264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01571707,0.00053550815,0.001124442,0.0015171365,0.0016061325,0.0057194633,0.001990476,0.005014196,0.0047936174],"category_scores_gemma":[0.023466444,0.00043771084,0.0005106778,0.0017788276,0.007350261,0.01823576,0.0034499196,0.0071591777,0.0011825598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025080272,0.00020410858,0.003019566,0.0010190428,0.00010785477,0.00013554026,0.0019992536,0.01305032,0.0005299829,0.5500799,0.07466489,0.35493878],"study_design_scores_gemma":[0.000025492453,0.000059612317,0.0014250784,0.00088641833,0.000015332736,0.00010268796,0.0025032035,0.018446468,0.00022985827,0.83124536,0.14498201,0.000078505145],"about_ca_topic_score_codex":0.0040983544,"about_ca_topic_score_gemma":0.004329863,"teacher_disagreement_score":0.01571707,"about_ca_system_score_codex":0.0024581768,"about_ca_system_score_gemma":0.0025152662,"threshold_uncertainty_score":0.08312082},"labels":[],"label_agreement":null},{"id":"W2053915393","doi":"10.1007/s11270-005-9068-8","title":"Application of Bayesian Regularized BP Neural Network Model for Trend Analysis, Acidity and Chemical Composition of Precipitation in North Carolina","year":2006,"lang":"en","type":"article","venue":"Water Air & Soil Pollution","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Precipitation; Compositional data; Linear regression; Mathematics; Nonlinear system; Artificial neural network; Chemistry; Ion; Acid rain; Correlation coefficient; Biological system; Statistics; Computer science; Meteorology; Artificial intelligence; Physics","score_opus":0.007905262899472248,"score_gpt":0.21180166028015157,"score_spread":0.20389639738067933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053915393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96195143,0.00010910954,0.032908868,0.00043341902,0.000036911828,0.000034193185,0.00046090464,0.0002539458,0.0038111315],"genre_scores_gemma":[0.99362624,0.00004768925,0.005260733,0.000014893414,0.000007083434,0.00001342424,0.00022721432,0.000009204866,0.00079349923],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997874,0.00006162566,0.000013929463,0.000049158083,0.00005704841,0.000030866137],"domain_scores_gemma":[0.9990742,0.00033091742,0.000065878325,0.000035666522,0.00045928312,0.000034058758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006427336,0.00024383911,0.00032811845,0.00058267504,0.00050609536,0.0005133961,0.00097375567,0.0004561639,0.0006545681],"category_scores_gemma":[0.0024546117,0.00022347536,0.0002549493,0.0008253759,0.00015563826,0.00038210774,0.00034894425,0.00036124088,0.00007957066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011092896,0.000091774964,0.02631343,0.00002944869,0.00005495195,0.00012987673,0.00008689393,0.9453034,0.0014522903,0.00097259955,0.0008638299,0.024590606],"study_design_scores_gemma":[0.000004401111,0.0000046803266,0.0041826284,0.0000013180887,0.000005542786,0.0000026236232,0.00001797914,0.99537957,0.0001346304,0.00015308468,0.000109591085,0.000003887524],"about_ca_topic_score_codex":0.5319858,"about_ca_topic_score_gemma":0.51162744,"teacher_disagreement_score":0.5319858,"about_ca_system_score_codex":0.0019541765,"about_ca_system_score_gemma":0.0027045542,"threshold_uncertainty_score":0.94154084},"labels":[],"label_agreement":null},{"id":"W2053934894","doi":"10.2166/hydro.2012.130","title":"Improving reliability of river flow forecasting using neural networks, wavelets and self-organising maps","year":2012,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Reliability (semiconductor); Artificial neural network; Computer science; Wavelet; Cluster (spacecraft); Artificial intelligence; Data mining; Machine learning; Pattern recognition (psychology)","score_opus":0.01698085648674403,"score_gpt":0.21523494156368034,"score_spread":0.19825408507693631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053934894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3095836,0.0008920395,0.68670243,0.00030500416,0.000113835194,0.000036261423,0.00012673922,0.00065011356,0.0015899768],"genre_scores_gemma":[0.9553305,0.0003461647,0.043797955,0.000020050531,0.000059071222,0.000021673593,0.00011876562,0.000020312085,0.00028545412],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931526,0.00022779721,0.00006701417,0.00009802249,0.0002456235,0.00004624266],"domain_scores_gemma":[0.99689,0.0019140649,0.00030341622,0.00025230707,0.0006046785,0.000035601617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023128309,0.0004973884,0.00063431705,0.001290981,0.00020796656,0.0006945692,0.00049562973,0.0005423354,0.00027588868],"category_scores_gemma":[0.009304732,0.0002245482,0.00050497235,0.0011674816,0.00032935987,0.0015231849,0.00055296015,0.0004987688,0.00011775896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022746033,0.00006809742,0.013232996,0.0001316044,0.00016406807,0.00012790861,0.00013918115,0.743958,0.006541609,0.0019979586,0.00063707406,0.232774],"study_design_scores_gemma":[0.0000037007264,0.000026498557,0.0020335612,0.000006095813,0.000012119643,0.00001230456,0.000015924985,0.9952957,0.0014033661,0.0010474182,0.00013599847,0.000007340833],"about_ca_topic_score_codex":0.002818978,"about_ca_topic_score_gemma":0.0019209352,"teacher_disagreement_score":0.002818978,"about_ca_system_score_codex":0.000305307,"about_ca_system_score_gemma":0.00032650176,"threshold_uncertainty_score":0.012231529},"labels":[],"label_agreement":null},{"id":"W2055002961","doi":"10.1175/jamc-d-11-0143.1","title":"Wet-Bulb Temperature from Relative Humidity and Air Temperature","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Meteorology and Climatology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":724,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Relative humidity; Wet-bulb temperature; Air temperature; Dry-bulb temperature; Environmental science; Humidity; Approximation error; Density of air; Apparent temperature; Atmospheric temperature range; Atmospheric sciences; Range (aeronautics); Meteorology; Thermodynamics; Materials science; Mathematics; Physics; Statistics; Composite material","score_opus":0.014677868133215196,"score_gpt":0.2153732959083431,"score_spread":0.2006954277751279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055002961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28300142,0.0052844184,0.6129411,0.00048924034,0.0017867786,0.00045005864,0.022584679,0.010907053,0.0625553],"genre_scores_gemma":[0.80421025,0.003770488,0.13514486,0.00028674898,0.00021202384,0.0006248336,0.012145978,0.0021225002,0.04148217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989981,0.00009650446,0.00005584696,0.00019672759,0.0006003192,0.00005243475],"domain_scores_gemma":[0.9995732,0.0001454051,0.00007262213,0.000050917584,0.00013899259,0.000018963505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004884481,0.00067703164,0.0006260408,0.00079068344,0.00016448727,0.0007492262,0.0007801489,0.0003031115,0.008880135],"category_scores_gemma":[0.0018408368,0.0003618183,0.00065884594,0.0011144648,0.0002223665,0.00060645735,0.00043616391,0.0011165417,0.007037336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080078613,0.00024604617,0.052133333,0.0025992426,0.0005309529,0.0004671434,0.0009244595,0.054550193,0.41036934,0.013429965,0.04770048,0.4162481],"study_design_scores_gemma":[0.000056997626,0.00043852956,0.17447409,0.00019974008,0.00024199962,0.000979923,0.00020948617,0.2452812,0.41193593,0.006418823,0.15948774,0.00027553775],"about_ca_topic_score_codex":0.0029594107,"about_ca_topic_score_gemma":0.0037242784,"teacher_disagreement_score":0.008880135,"about_ca_system_score_codex":0.00047019697,"about_ca_system_score_gemma":0.00038956376,"threshold_uncertainty_score":0.029707015},"labels":[],"label_agreement":null},{"id":"W2056678350","doi":"10.1139/p07-037","title":"Artificial neural network forecasting of nonlinear Markov processes","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Physics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of British Columbia","keywords":"Robustness (evolution); Artificial neural network; Markov chain; Nonlinear system; Computer science; Markov process; Noise (video); Series (stratigraphy); Time series; Algorithm; Representation (politics); Machine learning; Artificial intelligence; Mathematics; Statistics; Physics","score_opus":0.03518432295705386,"score_gpt":0.2343695193693554,"score_spread":0.19918519641230154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056678350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74775225,0.0004568888,0.24442394,0.00051417865,0.00014557838,0.000070643124,0.00025762094,0.00025486798,0.0061239256],"genre_scores_gemma":[0.9780226,0.00015178302,0.020133324,0.000021383321,0.000017074615,0.000030682586,0.00013532629,0.000013864839,0.0014741455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996619,0.0001332372,0.000026202877,0.000057492416,0.00007636887,0.000044804056],"domain_scores_gemma":[0.99728835,0.0021114887,0.00017749784,0.000067495144,0.00031730978,0.00003787799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016324283,0.0004801336,0.000483383,0.00051935733,0.0002550592,0.0005785986,0.00045022438,0.0005375053,0.00090558245],"category_scores_gemma":[0.0075217853,0.0002321096,0.00045198118,0.00061837444,0.00031800772,0.00069063297,0.0004488349,0.00090516184,0.000108868466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050422448,0.000019056519,0.0015385635,0.000027261744,0.000019326457,0.000028457374,0.000019139352,0.98447096,0.0006028872,0.0033472804,0.00016139215,0.009715247],"study_design_scores_gemma":[6.757731e-7,0.0000032378077,0.00014560204,0.0000011865991,7.2755523e-7,9.12905e-7,9.39433e-7,0.99931884,0.00013548558,0.00036525505,0.000025934976,0.0000011643408],"about_ca_topic_score_codex":0.014417074,"about_ca_topic_score_gemma":0.013063142,"teacher_disagreement_score":0.014417074,"about_ca_system_score_codex":0.0010726225,"about_ca_system_score_gemma":0.0006485469,"threshold_uncertainty_score":0.028666317},"labels":[],"label_agreement":null},{"id":"W2061342019","doi":"10.1016/s0022-1694(01)00534-0","title":"Noise reduction in chaotic hydrologic time series: facts and doubts","year":2002,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":95,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Noise reduction; Noise (video); Computer science; Chaotic; Reduction (mathematics); Raw data; Series (stratigraphy); Time series; Reliability (semiconductor); Algorithm; Environmental science; Statistics; Mathematics; Artificial intelligence; Machine learning; Geology","score_opus":0.016304554143942974,"score_gpt":0.21161308617157595,"score_spread":0.195308532027633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061342019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3719727,0.104015045,0.24526443,0.23613212,0.0032151341,0.000058772814,0.0008097119,0.000584712,0.037947383],"genre_scores_gemma":[0.95375615,0.017492166,0.01536499,0.0040495736,0.0055750855,0.000028348266,0.00013720273,0.00006346577,0.0035329603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990133,0.00015525255,0.00009615004,0.00019081461,0.00044933625,0.0000951935],"domain_scores_gemma":[0.9829912,0.012428323,0.0009474158,0.0018057519,0.001555248,0.00027204433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043416545,0.0003362095,0.0007430133,0.0008988048,0.00051710237,0.0017026771,0.0012066282,0.0020941074,0.0016087022],"category_scores_gemma":[0.023294713,0.00027877575,0.000514351,0.00064113375,0.0042044194,0.0045539797,0.0009378287,0.0026473047,0.0003630766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011242768,0.00021872175,0.02982056,0.0008897698,0.00034048382,0.0011159341,0.0011742571,0.07240502,0.010276915,0.24929519,0.021368114,0.6119707],"study_design_scores_gemma":[0.00010784019,0.00028655265,0.02138476,0.00035766006,0.00011186464,0.00095374644,0.001034194,0.14084458,0.008767622,0.7877886,0.03820783,0.00015469168],"about_ca_topic_score_codex":0.0016994624,"about_ca_topic_score_gemma":0.00095246534,"teacher_disagreement_score":0.0043416545,"about_ca_system_score_codex":0.0008206501,"about_ca_system_score_gemma":0.00037304024,"threshold_uncertainty_score":0.02296108},"labels":[],"label_agreement":null},{"id":"W2061559695","doi":"10.1016/j.watres.2014.01.008","title":"Settling velocities of multifractal flocs formed in chemical coagulation process","year":2014,"lang":"en","type":"article","venue":"Water Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Red River College","funders":"National Research Council Canada; National Science Council","keywords":"Settling; Flocculation; Fractal dimension; Multifractal system; Fractal; Coagulation; Sedimentation; Mass distribution; Chemistry; Mineralogy; Materials science; Physics; Thermodynamics; Mathematics; Geology; Mathematical analysis","score_opus":0.06451070819741589,"score_gpt":0.3493409058472965,"score_spread":0.2848301976498806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061559695","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978873,0.00007081264,0.0016544486,0.000013882839,0.000007778593,0.0000027838087,0.00004266423,0.00002013304,0.0003001112],"genre_scores_gemma":[0.99898916,0.00002588489,0.0005404072,0.0000021632102,0.0000019634701,0.000001568755,0.000050784616,0.0000031771485,0.0003850601],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999325,0.000005256602,0.000004783845,0.000017572092,0.000017865212,0.00002200086],"domain_scores_gemma":[0.9996369,0.0001144143,0.00006518993,0.000019768857,0.000110258254,0.000053549727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018178206,0.0001576347,0.00014640058,0.0007277417,0.00032325185,0.00035203464,0.00020637564,0.00037361463,0.00075697433],"category_scores_gemma":[0.00073451095,0.000102143895,0.00019730144,0.00029629958,0.00018998515,0.00031671548,0.00015662547,0.00023727486,0.000108832544],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012336517,0.0003385345,0.09578738,0.00016516201,0.000104644205,0.0007186623,0.0007680685,0.14627737,0.6823664,0.004595304,0.0013764835,0.06626845],"study_design_scores_gemma":[0.000024156108,0.00031978657,0.1102532,0.000011573913,0.000029820052,0.00012388402,0.00025848017,0.75931215,0.12828182,0.00073579117,0.00061043457,0.000038975555],"about_ca_topic_score_codex":0.0054037524,"about_ca_topic_score_gemma":0.0037402376,"teacher_disagreement_score":0.0054037524,"about_ca_system_score_codex":0.00043867488,"about_ca_system_score_gemma":0.00022920186,"threshold_uncertainty_score":0.010744631},"labels":[],"label_agreement":null},{"id":"W2062087947","doi":"10.1016/j.jhydrol.2014.03.057","title":"Applications of hybrid wavelet–Artificial Intelligence models in hydrology: A review","year":2014,"lang":"en","type":"review","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":724,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Wavelet; Hydrological modelling; Robustness (evolution); Artificial intelligence; Geology","score_opus":0.066665002833659,"score_gpt":0.33916376913884233,"score_spread":0.2724987663051833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062087947","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047138162,0.9949232,0.0029103293,0.00038183894,0.00019811405,0.00000933106,0.000032222208,0.000016392081,0.0010571621],"genre_scores_gemma":[0.0027462477,0.9946162,0.0019438679,0.000121426936,0.0002118883,0.000009310858,0.000043650958,0.0000034370598,0.00030396698],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997899,0.000036057085,0.00003606111,0.000044490684,0.00007988606,0.0000136035005],"domain_scores_gemma":[0.9989561,0.00069065345,0.000091272865,0.00003157776,0.00019920812,0.000031250434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010772722,0.00092067756,0.001312737,0.0020494373,0.00018765673,0.0011189774,0.0013240132,0.0011333784,0.002566641],"category_scores_gemma":[0.002205113,0.00032695872,0.0007074768,0.0036339315,0.00042268191,0.0016056066,0.0007088451,0.0010442745,0.00097313995],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004484135,0.00009289952,0.00035611689,0.013926581,0.00016876581,0.00010442723,0.000040854182,0.0031251153,0.0012151126,0.0063581066,0.008516855,0.9660503],"study_design_scores_gemma":[0.00006365142,0.00033735984,0.0027666818,0.010426015,0.0008835209,0.0014529629,0.0001814179,0.009272488,0.0030830998,0.02321557,0.9481876,0.00012960655],"about_ca_topic_score_codex":0.0012829865,"about_ca_topic_score_gemma":0.00140789,"teacher_disagreement_score":0.002566641,"about_ca_system_score_codex":0.00039725722,"about_ca_system_score_gemma":0.0010343589,"threshold_uncertainty_score":0.008586228},"labels":[],"label_agreement":null},{"id":"W2062362242","doi":"10.1061/(asce)1084-0699(2009)14:1(91)","title":"Comparative Studies in Problems of Missing Extreme Daily Streamflow Records","year":2008,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Imputation (statistics); Streamflow; Artificial neural network; Computer science; Regression; Data mining; Mean squared error; Genetic algorithm; Statistics; Artificial intelligence; Mathematics; Machine learning; Cartography; Geography","score_opus":0.13184363194116414,"score_gpt":0.28560308859078903,"score_spread":0.1537594566496249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062362242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55755496,0.005470707,0.43256447,0.0006703192,0.00013242867,0.00010239992,0.0002858557,0.00059678586,0.0026220568],"genre_scores_gemma":[0.85020554,0.0011517126,0.14709446,0.000055893273,0.000104021026,0.000059280468,0.0005496827,0.00007069588,0.0007087697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917088,0.0053142207,0.0005858063,0.00072037056,0.0014592453,0.00021166298],"domain_scores_gemma":[0.9033899,0.086553305,0.0028198264,0.0027175427,0.004150339,0.00036908826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020669866,0.000584189,0.0013347097,0.0020316627,0.00057982636,0.00097149285,0.0017418558,0.0015901953,0.0009595055],"category_scores_gemma":[0.08252392,0.0003439657,0.0010021854,0.0025197782,0.0007357506,0.002463445,0.0009102065,0.00081111933,0.00013918596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011026565,0.00028354314,0.018155862,0.0011608682,0.0007444423,0.00051107706,0.0006385616,0.74728584,0.0016156025,0.004978713,0.0010798905,0.22244291],"study_design_scores_gemma":[0.000057527184,0.00065796863,0.010929524,0.00013656172,0.00014887402,0.00061802974,0.00038998594,0.97562224,0.0051585874,0.004538947,0.0016813815,0.000060367944],"about_ca_topic_score_codex":0.0025928777,"about_ca_topic_score_gemma":0.0027655158,"teacher_disagreement_score":0.020669866,"about_ca_system_score_codex":0.0005776415,"about_ca_system_score_gemma":0.0005689776,"threshold_uncertainty_score":0.109313965},"labels":[],"label_agreement":null},{"id":"W2064759236","doi":"10.2166/hydro.2010.029","title":"Comparison of three data-driven techniques in modelling the evapotranspiration process","year":2010,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; University of Saskatchewan","funders":"","keywords":"Evapotranspiration; Environmental science; Precipitation; Process (computing); Genetic programming; Meteorology; Computer science; Machine learning; Geography; Ecology","score_opus":0.0796410368638506,"score_gpt":0.335718559851994,"score_spread":0.2560775229881434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064759236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55715305,0.0010005324,0.43387148,0.0005143712,0.00007273133,0.00016685197,0.00037717356,0.00058753375,0.0062563433],"genre_scores_gemma":[0.9097066,0.0004997353,0.088728115,0.0000427831,0.000013762912,0.000109009336,0.00026215927,0.000027411414,0.00061043847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955076,0.00017461622,0.000048614515,0.00006407252,0.00013042579,0.000031434083],"domain_scores_gemma":[0.9981957,0.0012096333,0.00012752925,0.00009066719,0.00033804346,0.000038360522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015336828,0.0008213448,0.00048115486,0.0008292422,0.00024588656,0.00089755614,0.0008747844,0.00094006746,0.00044387337],"category_scores_gemma":[0.004537062,0.0003288591,0.0008877817,0.0008124537,0.00021977541,0.0010357162,0.000547341,0.00087873254,0.00010891405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002541816,0.00017144435,0.0047695045,0.00012577802,0.00013166775,0.000054886867,0.00009322015,0.9274204,0.0026875285,0.002245797,0.000106308566,0.06193938],"study_design_scores_gemma":[0.000013032804,0.000054645865,0.00078394107,0.0000066101225,0.000020257998,0.000009968098,0.000012822995,0.9969037,0.0015406109,0.00042864963,0.00021638743,0.000009347156],"about_ca_topic_score_codex":0.013051029,"about_ca_topic_score_gemma":0.007821345,"teacher_disagreement_score":0.013051029,"about_ca_system_score_codex":0.0008434095,"about_ca_system_score_gemma":0.0006797791,"threshold_uncertainty_score":0.025950134},"labels":[],"label_agreement":null},{"id":"W2065572909","doi":"10.1016/s0043-1354(01)00287-1","title":"A neural network model to predict the wastewater inflow incorporating rainfall events","year":2002,"lang":"en","type":"article","venue":"Water Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":138,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Inflow; Artificial neural network; Sewage treatment; Wastewater; Process (computing); Environmental science; Engineering; Computer science; Environmental engineering; Artificial intelligence; Meteorology","score_opus":0.11522032968527601,"score_gpt":0.3114035109861496,"score_spread":0.1961831813008736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065572909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4876603,0.0009609223,0.4945709,0.0011716951,0.00074431923,0.00008012815,0.00095917354,0.0012368428,0.012615703],"genre_scores_gemma":[0.9746616,0.00022849075,0.019016217,0.0000754246,0.00007511615,0.00005419089,0.0002734783,0.00002020652,0.0055953446],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999225,0.000009390852,0.0000062309587,0.00002961221,0.000017775761,0.000014478227],"domain_scores_gemma":[0.9997297,0.0001249594,0.000028633443,0.000010209607,0.000089552974,0.000016984113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033150197,0.00042492125,0.00043493617,0.00037881985,0.00030551403,0.0005136076,0.0007812165,0.00090146053,0.0014205904],"category_scores_gemma":[0.0009374276,0.0003148111,0.0003074894,0.0006606407,0.00029057387,0.00077655487,0.00027032266,0.000780211,0.00023558958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005462142,0.000058262875,0.0010084694,0.000019264062,0.000022301483,0.000025834128,0.000009393095,0.98061347,0.00081117614,0.0007527222,0.00052360556,0.016100802],"study_design_scores_gemma":[0.0000021888548,0.0000038476974,0.00007862875,4.9693637e-7,0.000002068569,9.537708e-7,5.328706e-7,0.99963784,0.000098465505,0.00014341273,0.00003041219,0.0000011013656],"about_ca_topic_score_codex":0.027052794,"about_ca_topic_score_gemma":0.021326862,"teacher_disagreement_score":0.027052794,"about_ca_system_score_codex":0.0008229802,"about_ca_system_score_gemma":0.0007261131,"threshold_uncertainty_score":0.05379063},"labels":[],"label_agreement":null},{"id":"W2066563436","doi":"10.1007/s11707-013-0354-2","title":"Combining BPANN and wavelet analysis to simulate hydro-climatic processes—a case study of the Kaidu River, North-west China","year":2013,"lang":"en","type":"article","venue":"Frontiers of Earth Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Precipitation; Surface runoff; Environmental science; Wavelet; Scale (ratio); Linear regression; Climatology; Hydrology (agriculture); Meteorology; Statistics; Geography; Mathematics; Geology; Cartography; Computer science","score_opus":0.010133239902622597,"score_gpt":0.22060238467967255,"score_spread":0.21046914477704995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066563436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98488706,0.00006723278,0.013002932,0.00012664749,0.000035927107,0.000024138038,0.0001298591,0.0001535473,0.0015726738],"genre_scores_gemma":[0.9964097,0.00003904039,0.003039792,0.000010155266,0.0000042515317,0.000011995387,0.00007932055,0.000007848572,0.00039790448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981934,0.000053765336,0.000016622827,0.00003667397,0.000032791293,0.000040878294],"domain_scores_gemma":[0.99944717,0.00026632912,0.000032590386,0.00004217493,0.0001744375,0.00003723451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093286746,0.00070353015,0.00057603663,0.00065807847,0.00052923424,0.00076669233,0.0007900824,0.0010247461,0.0005915513],"category_scores_gemma":[0.0014214856,0.00038506894,0.00060982286,0.00081992225,0.0003761895,0.0007628771,0.00041881704,0.0005732474,0.00010161287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000703004,0.000096454016,0.008774047,0.000023599277,0.00004462888,0.00016092381,0.00004160786,0.97862214,0.0010697802,0.00031825685,0.00017038082,0.010607955],"study_design_scores_gemma":[0.0000044921603,0.00001322275,0.0012496575,9.953503e-7,0.000008128148,0.000003825179,0.000018079045,0.9983804,0.00019350488,0.000085784355,0.00003876532,0.000003124969],"about_ca_topic_score_codex":0.08694667,"about_ca_topic_score_gemma":0.058857366,"teacher_disagreement_score":0.08694667,"about_ca_system_score_codex":0.0010307844,"about_ca_system_score_gemma":0.0011704102,"threshold_uncertainty_score":0.17288119},"labels":[],"label_agreement":null},{"id":"W2066589941","doi":"10.1061/(asce)he.1943-5584.0000195","title":"Closure to “Comparative Study of ANNs versus Parametric Methods in Rainfall Frequency Analysis” by Jianxun He and Caterina Valeo","year":2010,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Closure (psychology); Parametric statistics; Hydrology (agriculture); Geology; Mathematics; Statistics; Geotechnical engineering","score_opus":0.02538193401437074,"score_gpt":0.3285253469418705,"score_spread":0.3031434129274998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066589941","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13328946,0.05060236,0.60018563,0.061626915,0.07421739,0.0004772151,0.0019035677,0.0019555876,0.07574181],"genre_scores_gemma":[0.75486356,0.018466558,0.09983432,0.010321347,0.022606364,0.00043387053,0.0020484522,0.0013423986,0.090083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973404,0.0012903194,0.00017422925,0.0004508328,0.0006349512,0.000109306915],"domain_scores_gemma":[0.9856732,0.009922326,0.00042692362,0.0008486363,0.0029479272,0.00018113125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004818301,0.00063749705,0.0008891108,0.0010144226,0.0006337246,0.0020103077,0.0014059164,0.0013785274,0.011644649],"category_scores_gemma":[0.031842668,0.00023762125,0.0011558727,0.0012795018,0.00087193627,0.0020448694,0.0011781815,0.0012016578,0.0016424819],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015696293,0.0003392209,0.00811242,0.0013806253,0.00073623867,0.0008103597,0.0007354937,0.099251546,0.008455029,0.08255061,0.20995577,0.5861031],"study_design_scores_gemma":[0.00018130682,0.00088108645,0.020851234,0.001150229,0.0005318511,0.0009971771,0.00097430614,0.5844416,0.023588892,0.094642445,0.27151984,0.0002400432],"about_ca_topic_score_codex":0.0048643625,"about_ca_topic_score_gemma":0.0034985477,"teacher_disagreement_score":0.011644649,"about_ca_system_score_codex":0.0007535514,"about_ca_system_score_gemma":0.0008094716,"threshold_uncertainty_score":0.03895527},"labels":[],"label_agreement":null},{"id":"W2069309835","doi":"10.4296/cwrj2604537","title":"Noise Reduction Approach in Chaotic Hydrologic Time Series Revisited","year":2001,"lang":"en","type":"article","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Uniwersytet Medyczny w Lodzi","keywords":"Noise reduction; Noise (video); Chaotic; Series (stratigraphy); Reduction (mathematics); Time series; Computer science; Algorithm; Nonlinear system; Mathematics; Artificial intelligence; Machine learning; Geology; Physics","score_opus":0.013842569550651275,"score_gpt":0.18799902292700335,"score_spread":0.17415645337635208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069309835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030998185,0.0007476975,0.96389616,0.00052435487,0.00006806087,0.000023263368,0.000022454711,0.00012992366,0.0035899407],"genre_scores_gemma":[0.7432761,0.0020177464,0.24785994,0.00023658323,0.00036016922,0.000092487186,0.00010257257,0.00009364168,0.005960768],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948657,0.00019532896,0.000032031592,0.00007342783,0.00018014242,0.000032451946],"domain_scores_gemma":[0.9984478,0.0011324206,0.00010138981,0.00009816004,0.00019625072,0.000023886763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012691589,0.00043044015,0.0005091718,0.000996753,0.00030907505,0.00073990884,0.00049839594,0.0005026001,0.0006907073],"category_scores_gemma":[0.004944972,0.00017145558,0.0005094422,0.0007640648,0.0012864071,0.00087408745,0.00064152584,0.0007794946,0.00017181417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017609252,0.00006298449,0.0029326957,0.0003209014,0.00009379973,0.00042606812,0.00071515766,0.48760968,0.016440773,0.263067,0.0013568248,0.22679809],"study_design_scores_gemma":[0.000008042944,0.000049938466,0.0008237205,0.000019165958,0.000015634045,0.00008856496,0.00006646127,0.93106616,0.0033754471,0.061618358,0.002849949,0.000018592644],"about_ca_topic_score_codex":0.0020027908,"about_ca_topic_score_gemma":0.0011622244,"teacher_disagreement_score":0.0020027908,"about_ca_system_score_codex":0.00044296507,"about_ca_system_score_gemma":0.00043212448,"threshold_uncertainty_score":0.0067120194},"labels":[],"label_agreement":null},{"id":"W2070424919","doi":"10.1016/j.cageo.2012.06.023","title":"Nonlinear regression in environmental sciences by support vector machines combined with evolutionary strategy","year":2012,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Support vector machine; Random forest; Artificial neural network; Benchmark (surveying); Computer science; Regression; Artificial intelligence; Machine learning; Feature selection; Decision tree; Evolutionary algorithm; Linear regression; Tree (set theory); Data mining; Statistics; Mathematics","score_opus":0.015561807506458167,"score_gpt":0.23893716408002522,"score_spread":0.22337535657356705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070424919","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03484109,0.001036983,0.9614845,0.00036753734,0.0001207578,0.000027002743,0.000015783278,0.00016116058,0.0019451248],"genre_scores_gemma":[0.64378166,0.0009416173,0.3493761,0.00015409384,0.000265998,0.00015363221,0.00005937986,0.000067122644,0.0052002883],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969375,0.00016512335,0.000020822223,0.00003620201,0.00006664999,0.000017534856],"domain_scores_gemma":[0.9984658,0.0011992528,0.000069436355,0.00006178406,0.00016887402,0.000034898014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012029146,0.00048619727,0.00078547205,0.000532846,0.00028974176,0.00055826653,0.0006727589,0.00093237037,0.0010082427],"category_scores_gemma":[0.003662318,0.0003491444,0.0005380392,0.0007041345,0.00049183064,0.0009891518,0.0006530116,0.0010469392,0.00025128428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053175976,0.00006878445,0.00088232465,0.000080317994,0.0001077824,0.000049409246,0.000037028974,0.86245435,0.001929209,0.014064329,0.0006593236,0.119614],"study_design_scores_gemma":[0.0000032534435,0.000007708222,0.000041081497,0.0000019032809,0.0000036664,0.000002653606,0.0000010880464,0.9974408,0.00016843702,0.0022365488,0.00009119711,0.0000016881845],"about_ca_topic_score_codex":0.0027426472,"about_ca_topic_score_gemma":0.0022729381,"teacher_disagreement_score":0.0027426472,"about_ca_system_score_codex":0.0003448989,"about_ca_system_score_gemma":0.0004842581,"threshold_uncertainty_score":0.0063616633},"labels":[],"label_agreement":null},{"id":"W2070479370","doi":"10.1002/hyp.445","title":"Improving extreme hydrologic events forecasting using a new criterion for artificial neural network selection","year":2001,"lang":"en","type":"article","venue":"Hydrological Processes","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Hydro-Québec; Institut National de la Recherche Scientifique; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Mean squared error; Artificial neural network; Computer science; Selection (genetic algorithm); Statistics; Artificial intelligence; Mathematics","score_opus":0.1327814914663188,"score_gpt":0.28389542855572525,"score_spread":0.15111393708940646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070479370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12914436,0.00025781812,0.86727023,0.00035614424,0.00005916502,0.00010513722,0.00006427731,0.00042063073,0.0023222524],"genre_scores_gemma":[0.8208618,0.00013515688,0.17716052,0.00012559081,0.00011722628,0.0001794675,0.00021966202,0.000062777945,0.0011377092],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981591,0.0008797526,0.00015597008,0.00013452387,0.00060223445,0.00006835449],"domain_scores_gemma":[0.9929571,0.0033961975,0.00043075148,0.00022485129,0.0028146335,0.00017642956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004766596,0.00064867735,0.0010242806,0.0016991987,0.00029356868,0.0009856387,0.00091309816,0.0009768445,0.0008932082],"category_scores_gemma":[0.013723352,0.00024099232,0.0003101421,0.00097374734,0.00065593474,0.0012526757,0.00088079344,0.0006550018,0.00023547705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004157319,0.00031326327,0.008913068,0.00017628883,0.00013066223,0.00017616464,0.00007671602,0.74398863,0.010864984,0.007101206,0.0023022457,0.225541],"study_design_scores_gemma":[0.000014116736,0.00003405842,0.00043087357,0.0000034036486,0.000005139851,0.000008707858,0.0000033007452,0.9979826,0.0009343745,0.00048389632,0.00009563743,0.0000038051173],"about_ca_topic_score_codex":0.002043068,"about_ca_topic_score_gemma":0.0024733972,"teacher_disagreement_score":0.004766596,"about_ca_system_score_codex":0.00074118905,"about_ca_system_score_gemma":0.0010398217,"threshold_uncertainty_score":0.025208473},"labels":[],"label_agreement":null},{"id":"W2070724539","doi":"10.1175/mwr-d-13-00085.1","title":"Wavelet Analysis of Seasonal Rainfall Variability of the Upper Blue Nile Basin, Its Teleconnection to Global Sea Surface Temperature, and Its Forecasting by an Artificial Neural Network","year":2013,"lang":"en","type":"article","venue":"Monthly Weather Review","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Teleconnection; Climatology; Environmental science; Sea surface temperature; Principal component analysis; Structural basin; Meteorology; Geology; Geography; Mathematics; Statistics","score_opus":0.019710805631615206,"score_gpt":0.24197369535626903,"score_spread":0.22226288972465383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070724539","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.989431,0.000054444936,0.009937416,0.00003769083,0.000008282048,0.0000050063813,0.00005968076,0.00003344631,0.0004330097],"genre_scores_gemma":[0.9986941,0.000026413714,0.001131026,0.0000020076457,0.0000022217635,0.000002407533,0.000037557213,0.0000017272727,0.00010249702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99994874,0.00001433707,0.000003437302,0.000011875311,0.000011971121,0.000009689703],"domain_scores_gemma":[0.9998653,0.00007411753,0.000020061234,0.0000071262057,0.000026144377,0.000007372722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024353823,0.00020983447,0.00012256105,0.00034176648,0.00009702367,0.0003097104,0.0001371306,0.00014760577,0.00029818097],"category_scores_gemma":[0.00073517935,0.00008319966,0.0001653058,0.00037716678,0.0001033554,0.00016789333,0.00013600015,0.0002027763,0.00003719912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021167622,0.00010108754,0.08345315,0.000041224288,0.00011733094,0.00034467792,0.00008480419,0.8242568,0.014486877,0.0006684809,0.00042998992,0.07580399],"study_design_scores_gemma":[0.000002140506,0.000008837696,0.016182294,0.0000013365162,0.0000050991057,0.0000069147072,0.000012955029,0.9831284,0.00052950456,0.00007373009,0.000046705867,0.0000020324317],"about_ca_topic_score_codex":0.0071799234,"about_ca_topic_score_gemma":0.0040189587,"teacher_disagreement_score":0.0071799234,"about_ca_system_score_codex":0.0002115067,"about_ca_system_score_gemma":0.0001703293,"threshold_uncertainty_score":0.014276266},"labels":[],"label_agreement":null},{"id":"W2072106824","doi":"10.1061/(asce)he.1943-5584.0000245","title":"Comparison of Multivariate Regression and Artificial Neural Networks for Peak Urban Water-Demand Forecasting: Evaluation of Different ANN Learning Algorithms","year":2010,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":257,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Artificial neural network; Water resources; Multilayer perceptron; Multivariate statistics; Bayesian multivariate linear regression; Water supply; Linear regression; Backpropagation; Computer science; Conjugate gradient method; Levenberg–Marquardt algorithm; Regression; Regression analysis; Multivariate adaptive regression splines; Perceptron; Machine learning; Environmental science; Statistics; Algorithm; Mathematics; Environmental engineering","score_opus":0.05244877557447699,"score_gpt":0.30187594575346016,"score_spread":0.24942717017898317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072106824","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59884304,0.0054661995,0.3831454,0.0011735508,0.00038237395,0.00026463886,0.0006056544,0.0017178586,0.00840126],"genre_scores_gemma":[0.9174804,0.0016549093,0.07829803,0.00010582402,0.00008999045,0.00017258426,0.00044511852,0.000087784094,0.0016653308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800986,0.0011819236,0.00016378718,0.00023564577,0.00030741448,0.000101342244],"domain_scores_gemma":[0.99068844,0.0073732226,0.0004376444,0.00021231834,0.0011836339,0.000104760344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00618406,0.0017553922,0.0012452471,0.0017892699,0.00032384563,0.00091357506,0.0010888148,0.00088948774,0.0009116226],"category_scores_gemma":[0.011827423,0.00040915867,0.0008800409,0.0015146652,0.0002525821,0.0014149493,0.00064481783,0.00096491113,0.00021449287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005094057,0.00017806672,0.005736537,0.00015224521,0.00022654464,0.00003610286,0.00003331917,0.9091577,0.0004642422,0.0007957066,0.00041642986,0.08229381],"study_design_scores_gemma":[0.000010426142,0.000056388082,0.00089994026,0.000010411833,0.0000200621,0.00000455832,0.000010533689,0.998502,0.00026184224,0.00014342573,0.00007473891,0.0000056336453],"about_ca_topic_score_codex":0.018318955,"about_ca_topic_score_gemma":0.011390325,"teacher_disagreement_score":0.018318955,"about_ca_system_score_codex":0.0012319796,"about_ca_system_score_gemma":0.0008699122,"threshold_uncertainty_score":0.036424637},"labels":[],"label_agreement":null},{"id":"W2074502742","doi":"10.1007/s11270-014-1966-1","title":"Comparison of OLS, ANN, KTRL, KTRL2, RLOC, and MOVE as Record-Extension Techniques for Water Quality Variables","year":2014,"lang":"en","type":"article","venue":"Water Air & Soil Pollution","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ste. Anne's Hospital","funders":"National Water Center, United Arab Emirates University; Natural Sciences and Engineering Research Council of Canada; National Research Centre","keywords":"Outlier; Artificial neural network; Statistics; Missing data; Heteroscedasticity; Variance (accounting); Ordinary least squares; Computer science; Data mining; Mathematics; Econometrics; Artificial intelligence; Accounting","score_opus":0.02863041547380158,"score_gpt":0.3010997865267117,"score_spread":0.27246937105291014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074502742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81680876,0.002177446,0.1673976,0.0005421562,0.00021789291,0.000088529814,0.0020146437,0.0032090785,0.0075438344],"genre_scores_gemma":[0.9338517,0.0006184033,0.05826315,0.000098831544,0.00006530778,0.000055003267,0.0021881084,0.00022930292,0.00463007],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992459,0.00037650263,0.00006185116,0.00013862862,0.00011592824,0.00006130653],"domain_scores_gemma":[0.9952884,0.003413039,0.0002209858,0.0003375778,0.00066233217,0.000077658144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028134715,0.0007970307,0.00061348267,0.0009958057,0.00028476788,0.0009383605,0.0006942929,0.0005433596,0.0015002777],"category_scores_gemma":[0.006361473,0.0001733222,0.00060991937,0.0009806845,0.00015382649,0.0011980903,0.00046469583,0.0007389868,0.0005170085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019676425,0.00046109172,0.062042944,0.0005269223,0.0011424157,0.000081095735,0.0003006697,0.2529092,0.0071083317,0.002615226,0.0046481956,0.6661962],"study_design_scores_gemma":[0.000062793595,0.00031128616,0.03827691,0.00004530775,0.0003319406,0.000042544834,0.00020804786,0.9534406,0.0044621318,0.0005656406,0.0022045379,0.0000482339],"about_ca_topic_score_codex":0.015880445,"about_ca_topic_score_gemma":0.020184979,"teacher_disagreement_score":0.015880445,"about_ca_system_score_codex":0.00036889705,"about_ca_system_score_gemma":0.00074626046,"threshold_uncertainty_score":0.031575978},"labels":[],"label_agreement":null},{"id":"W2076132658","doi":"10.5194/piahs-366-177-2015","title":"Estimation of discharge in rivers by different artificial neural network algorithms: case of the Algerian Coastal basin","year":2015,"lang":"en","type":"article","venue":"Proceedings of the International Association of Hydrological Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Artificial neural network; Structural basin; Estimation; Algorithm; Computer science; Geology; Artificial intelligence; Engineering; Geomorphology","score_opus":0.02248008192885278,"score_gpt":0.2504046577407681,"score_spread":0.2279245758119153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076132658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9837474,0.00035081222,0.013265412,0.00038533963,0.000018232391,0.000020502415,0.00025087013,0.00013168072,0.0018297984],"genre_scores_gemma":[0.99491054,0.00015400672,0.00392032,0.000013196639,0.0000069419607,0.0000122048605,0.00014258665,0.000009587327,0.0008305398],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998265,0.000086969616,0.000015966463,0.000023479835,0.00002228677,0.000024820092],"domain_scores_gemma":[0.99905926,0.0006601337,0.000045471385,0.000047307112,0.00015838367,0.000029413908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008748644,0.00037139375,0.00037436478,0.00056496385,0.0004141392,0.00054064195,0.0005698362,0.00076810044,0.0012274203],"category_scores_gemma":[0.0022390469,0.00018389396,0.00046361142,0.0007719785,0.0003402024,0.000440955,0.00038320883,0.00034118915,0.00009877318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029455536,0.00010055076,0.021214642,0.00008564891,0.00006298957,0.0004361996,0.000081678685,0.94893914,0.0011694918,0.0006438769,0.00054974033,0.026421417],"study_design_scores_gemma":[0.000019600813,0.000039727758,0.016323213,0.000012461886,0.00002565019,0.00002696513,0.000079652425,0.9818782,0.00099646,0.00036405167,0.00022175931,0.0000122784095],"about_ca_topic_score_codex":0.09943447,"about_ca_topic_score_gemma":0.05837207,"teacher_disagreement_score":0.09943447,"about_ca_system_score_codex":0.0008728419,"about_ca_system_score_gemma":0.00057301694,"threshold_uncertainty_score":0.19771141},"labels":[],"label_agreement":null},{"id":"W2076438059","doi":"10.1061/41143(394)47","title":"Applications of Artificial Neural Networks in Urban Water System","year":2010,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Combined sewer; Environmental science; Stormwater; Surface runoff; Hydrology (agriculture); Snowmelt; Hydraulics; Artificial neural network; Water quality; Urban runoff; Retention basin; Environmental engineering; Computer science; Engineering; Geotechnical engineering; Machine learning","score_opus":0.009880289216616187,"score_gpt":0.21273358496338876,"score_spread":0.20285329574677258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076438059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0883565,0.043173376,0.8198195,0.0033947483,0.00057987636,0.00013239525,0.00030671025,0.00067741744,0.04355957],"genre_scores_gemma":[0.8499225,0.034849674,0.10584219,0.0004899709,0.00063583464,0.00013301964,0.0002511169,0.000056337496,0.007819364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996044,0.00017131092,0.00003903643,0.000050717317,0.00011081886,0.000023737924],"domain_scores_gemma":[0.99921584,0.0005286428,0.000045332104,0.000028123493,0.00016936891,0.0000125536835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009840773,0.00060114596,0.0004716734,0.00069485296,0.0002275685,0.000743732,0.0004215082,0.00077713566,0.0012046886],"category_scores_gemma":[0.0022829052,0.00023408269,0.00030523425,0.0017160198,0.00035264698,0.00063759886,0.00049743464,0.00051961455,0.00022773194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004549924,0.000041623756,0.0027632029,0.00025448253,0.00008027054,0.00012736456,0.00006131211,0.7994831,0.00092338945,0.00987702,0.0013057719,0.18503688],"study_design_scores_gemma":[0.000007663702,0.00003654087,0.0010340641,0.000080493366,0.000024181427,0.00003730862,0.000045469907,0.977028,0.0010490069,0.014918811,0.005721062,0.000017303786],"about_ca_topic_score_codex":0.0054492205,"about_ca_topic_score_gemma":0.0050007515,"teacher_disagreement_score":0.0054492205,"about_ca_system_score_codex":0.0005503417,"about_ca_system_score_gemma":0.0003146749,"threshold_uncertainty_score":0.010835052},"labels":[],"label_agreement":null},{"id":"W2076934757","doi":"10.1007/s12303-011-0032-x","title":"Assessment of groundwater corrosivity in Hamedan Province, Iran using an adaptive neuro-fuzzy inference system (ANFIS)","year":2011,"lang":"en","type":"article","venue":"Geosciences Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Adaptive neuro fuzzy inference system; Inference system; Fuzzy inference system; Groundwater; Inference; Neuro-fuzzy; Environmental science; Fuzzy logic; Geology; Computer science; Artificial intelligence; Geotechnical engineering; Fuzzy control system","score_opus":0.09468993889470788,"score_gpt":0.2925731237364684,"score_spread":0.19788318484176048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076934757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99819905,0.00005212886,0.001149839,0.000025503261,0.0000043802866,0.000016354667,0.00014038624,0.00001959618,0.000392644],"genre_scores_gemma":[0.9991161,0.000043071137,0.00065131875,0.0000025390716,0.0000017985647,0.0000059133786,0.000076273405,6.0366466e-7,0.00010232531],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996631,0.00006044049,0.00003676257,0.00004815281,0.00014934318,0.000042232023],"domain_scores_gemma":[0.99959487,0.00007947226,0.00007835799,0.000014241811,0.000206273,0.00002679107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052374846,0.00047913875,0.00046985128,0.0014609173,0.00047351478,0.00046265428,0.000627237,0.0005300829,0.00021591771],"category_scores_gemma":[0.0007861306,0.00025405295,0.00047120918,0.0013700495,0.00030617914,0.0004087242,0.0003319577,0.00020369171,0.000058655718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041657846,0.00032790692,0.88113725,0.00020039588,0.00029724455,0.0011593949,0.00080948573,0.063019074,0.014362468,0.00035786896,0.0006487256,0.037263688],"study_design_scores_gemma":[0.000054402648,0.00062125485,0.7399058,0.000041724652,0.0002819565,0.0004143789,0.0035741883,0.24504139,0.008699702,0.0006304099,0.00066525815,0.00006961649],"about_ca_topic_score_codex":0.0731908,"about_ca_topic_score_gemma":0.09442218,"teacher_disagreement_score":0.0731908,"about_ca_system_score_codex":0.0009937013,"about_ca_system_score_gemma":0.00080844597,"threshold_uncertainty_score":0.14552957},"labels":[],"label_agreement":null},{"id":"W2077482464","doi":"10.1016/j.jhydrol.2006.02.018","title":"Reply to the comments of Dr. Ashu Jain on “Integration of artificial neural networks with conceptual models in rainfall–runoff modeling” by Jieyun Chen and Barry J. Adams","year":2006,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Chen; Surface runoff; Artificial neural network; Hydrology (agriculture); Environmental science; Meteorology; Computer science; Geology; Artificial intelligence; Geography; Geotechnical engineering; Ecology; Biology","score_opus":0.022079192580406116,"score_gpt":0.23548236541814935,"score_spread":0.21340317283774324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077482464","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018497303,0.0023697729,0.00019573601,0.9562147,0.040370874,0.000009372167,0.00011432292,0.000031746236,0.0005084121],"genre_scores_gemma":[0.0022934324,0.0020705578,0.000308022,0.9584204,0.03362502,0.000029025883,0.00006401575,0.000035843375,0.0031535886],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741286,0.00062520773,0.0005204046,0.0003585245,0.0008566776,0.00022626751],"domain_scores_gemma":[0.9832481,0.008721739,0.0010883193,0.00030683234,0.00555113,0.0010837994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004191192,0.0009983368,0.0013070337,0.00079463614,0.0025821861,0.0027572094,0.0028188976,0.022774152,0.006662418],"category_scores_gemma":[0.038136587,0.00074888783,0.0012968305,0.0011639517,0.0019901972,0.003722759,0.0016939702,0.030898534,0.0071637784],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003162958,0.000007223988,0.00014463086,0.00007026383,0.000012596829,0.00014614243,0.00008512307,0.000048752645,0.00008777217,0.0005822627,0.9958972,0.0028864418],"study_design_scores_gemma":[0.00005123529,0.00003735564,0.0017942442,0.00035292775,0.0000390775,0.0008155658,0.00062926585,0.0004257982,0.0005722273,0.0031952292,0.99200386,0.0000830854],"about_ca_topic_score_codex":0.008478695,"about_ca_topic_score_gemma":0.010318754,"teacher_disagreement_score":0.022774152,"about_ca_system_score_codex":0.0023006091,"about_ca_system_score_gemma":0.0030520076,"threshold_uncertainty_score":0.022288024},"labels":[],"label_agreement":null},{"id":"W2078471177","doi":"10.1109/oceans.2007.4449252","title":"Application of decision tree techniques for the Prediction of Significant Wave Height","year":2007,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fetch; Significant wave height; Wind speed; Wave height; Bin; Decision tree; Wind wave; Wind wave model; Data set; Wave model; Set (abstract data type); Meteorology; Computer science; Data mining; Geology; Artificial intelligence; Algorithm; Geography","score_opus":0.023794644838713696,"score_gpt":0.254041257107664,"score_spread":0.23024661226895032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078471177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08778875,0.0009878931,0.9076582,0.00028113014,0.00008813395,0.00013935572,0.00037404778,0.0010905258,0.0015919203],"genre_scores_gemma":[0.73977464,0.00065994513,0.25735414,0.00008375399,0.000063097534,0.00018313155,0.0007174542,0.00005149468,0.0011123471],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988481,0.00055393047,0.00011590375,0.00011964088,0.00027783852,0.000084732405],"domain_scores_gemma":[0.9930912,0.0056779226,0.00029668302,0.00014790791,0.0006801354,0.0001061811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003169647,0.0009753499,0.0011006026,0.0022587788,0.00045687953,0.0007849281,0.00075173244,0.0007090968,0.0013139629],"category_scores_gemma":[0.008215996,0.00032685586,0.00087626267,0.0019281061,0.00024078724,0.0010030336,0.00043902005,0.0010122393,0.00043574913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027421248,0.00015123982,0.0057947435,0.00013664381,0.00016297854,0.0001225365,0.00014755836,0.6556981,0.0019518995,0.0024904322,0.0012635409,0.33180603],"study_design_scores_gemma":[0.000009680896,0.000043884716,0.0005171271,0.000010276368,0.000012357601,0.000014024808,0.000015681953,0.99685293,0.0005370836,0.0017306102,0.0002499688,0.00000635177],"about_ca_topic_score_codex":0.008461406,"about_ca_topic_score_gemma":0.0052039516,"teacher_disagreement_score":0.008461406,"about_ca_system_score_codex":0.0005351117,"about_ca_system_score_gemma":0.00084060733,"threshold_uncertainty_score":0.016824305},"labels":[],"label_agreement":null},{"id":"W2080445761","doi":"10.1016/j.jhydrol.2011.01.024","title":"Prediction of event-based stormwater runoff quantity and quality by ANNs developed using PMI-based input selection","year":2011,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Surface runoff; Stormwater; Environmental science; Computer science; Water quality; Artificial neural network; Hydrology (agriculture); Machine learning; Engineering","score_opus":0.10113159568163871,"score_gpt":0.2864622869758555,"score_spread":0.1853306912942168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080445761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9193114,0.00010562998,0.07711294,0.00011082286,0.00008153863,0.000048323123,0.0004738305,0.0008546569,0.0019008059],"genre_scores_gemma":[0.99195427,0.0000320553,0.0073888246,0.000012021873,0.000012562857,0.000024608657,0.0002412386,0.000010489245,0.00032390826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998636,0.000034175115,0.000015624913,0.000038727027,0.000027647806,0.000020244377],"domain_scores_gemma":[0.999186,0.00042160813,0.00008912115,0.000052165025,0.0002123948,0.00003874066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089371385,0.00057504425,0.0005146921,0.0005457904,0.00023697979,0.00042567516,0.00044073482,0.00049842324,0.0005871813],"category_scores_gemma":[0.0018637149,0.0004104819,0.00042472972,0.00050969404,0.00021331405,0.0005682625,0.00023430264,0.0005566626,0.00014493935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015354632,0.00011874864,0.019005403,0.000025630476,0.00007758179,0.000047631027,0.000017936078,0.9579097,0.0019663286,0.0001826816,0.00035705496,0.020137709],"study_design_scores_gemma":[0.0000049375053,0.000008536755,0.0023305502,8.2218804e-7,0.000004812409,0.0000026651499,0.0000013184441,0.9972045,0.00037210173,0.000051695806,0.000016335303,0.0000016907699],"about_ca_topic_score_codex":0.008420638,"about_ca_topic_score_gemma":0.00856303,"teacher_disagreement_score":0.008420638,"about_ca_system_score_codex":0.00066264946,"about_ca_system_score_gemma":0.00039670453,"threshold_uncertainty_score":0.016743243},"labels":[],"label_agreement":null},{"id":"W2081670007","doi":"10.1029/2010wr009945","title":"Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada","year":2011,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":490,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Autoregressive integrated moving average; Artificial neural network; Mean squared error; Wavelet; Autoregressive model; Linear regression; Statistics; Econometrics; Demand forecasting; Moving average; Computer science; Environmental science; Meteorology; Mathematics; Time series; Artificial intelligence; Geography; Operations research","score_opus":0.12572098077634136,"score_gpt":0.3559706911852541,"score_spread":0.23024971040891273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081670007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6309145,0.0019625656,0.35444698,0.00076211203,0.00015037935,0.0001972829,0.00073477894,0.0010090665,0.0098223025],"genre_scores_gemma":[0.9114737,0.0007052644,0.08263524,0.000058199996,0.000026663261,0.0000814046,0.000513418,0.000072162235,0.0044339583],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933463,0.00025641653,0.0000336404,0.00008280271,0.00024209959,0.000050485058],"domain_scores_gemma":[0.9987062,0.0005716692,0.0001120693,0.000048856833,0.00051138253,0.000049861137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017806183,0.0006715114,0.00038405438,0.0009771475,0.00036163625,0.0007628971,0.0008570718,0.00029879363,0.0009872322],"category_scores_gemma":[0.005562632,0.00022141088,0.0003744478,0.0012432324,0.00020333215,0.0006898179,0.00044066887,0.00046186792,0.00014644861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000387101,0.00017802477,0.027450416,0.00015659936,0.0003036421,0.00010936778,0.00011805125,0.67017335,0.0036731465,0.0028984773,0.0017994556,0.2927524],"study_design_scores_gemma":[0.000011297875,0.00001959153,0.0043263733,0.000004443996,0.000017892233,0.000004559207,0.00001780362,0.994576,0.00060520653,0.0001503328,0.00025737862,0.000009109969],"about_ca_topic_score_codex":0.5787212,"about_ca_topic_score_gemma":0.5861595,"teacher_disagreement_score":0.42127877,"about_ca_system_score_codex":0.0026161901,"about_ca_system_score_gemma":0.0033633949,"threshold_uncertainty_score":0.8475195},"labels":[],"label_agreement":null},{"id":"W2082214945","doi":"10.1016/j.jhydrol.2010.06.032","title":"Comparison of parametric and non-parametric estimations of the annual date of positive water temperature onset","year":2010,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hydro-Québec; Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Longitude; Mean squared error; Latitude; Environmental science; Regression analysis; Regression; Land cover; Elevation (ballistics); Statistics; Precipitation; Parametric statistics; Generalized additive model; Climatology; Hydrology (agriculture); Mathematics; Meteorology; Geography; Land use; Geology","score_opus":0.009398493332852477,"score_gpt":0.27570368326029393,"score_spread":0.26630518992744145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082214945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82904196,0.00049115706,0.16674936,0.00012114399,0.00006613865,0.000051220555,0.0005231546,0.0006282785,0.0023275847],"genre_scores_gemma":[0.9874049,0.00007840269,0.011575902,0.000013311073,0.00001745619,0.000024389592,0.0005292538,0.0000670124,0.0002892856],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963291,0.0024360933,0.00027165443,0.00041681353,0.0003197692,0.00022663575],"domain_scores_gemma":[0.7675162,0.21716602,0.004246937,0.0061648977,0.0043706605,0.00053534977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013923627,0.00075604115,0.0005676478,0.0012618882,0.000238851,0.0014742386,0.0012561632,0.0009244697,0.0015989131],"category_scores_gemma":[0.087490834,0.0003402384,0.000778192,0.00089838443,0.00052736956,0.002128438,0.0009942951,0.0008713523,0.00035206016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010570876,0.0006221265,0.14687285,0.00080651895,0.0013038372,0.00031825912,0.0017815768,0.46756735,0.0119582815,0.0046295766,0.0014894997,0.3520793],"study_design_scores_gemma":[0.0001353667,0.0008289393,0.09391136,0.00007397887,0.00032227946,0.00030620955,0.0006274213,0.89340466,0.00662272,0.0029528034,0.000663128,0.00015102874],"about_ca_topic_score_codex":0.0022212258,"about_ca_topic_score_gemma":0.0019486832,"teacher_disagreement_score":0.013923627,"about_ca_system_score_codex":0.00027960865,"about_ca_system_score_gemma":0.00058572664,"threshold_uncertainty_score":0.073636055},"labels":[],"label_agreement":null},{"id":"W2084659163","doi":"10.1080/09593332308618384","title":"Modeling a Full-Scale Primary Sedimentation Tank Using Artificial Neural Networks","year":2002,"lang":"en","type":"article","venue":"Environmental Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sedimentation; Artificial neural network; Suspended solids; Engineering; Empirical modelling; Full scale; Process engineering; Environmental science; Computer science; Environmental engineering; Simulation; Artificial intelligence; Wastewater","score_opus":0.0228107048172805,"score_gpt":0.2134185712555414,"score_spread":0.1906078664382609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084659163","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22588445,0.00048375412,0.7615717,0.00032886403,0.00007726886,0.0001238469,0.00045690808,0.0012248444,0.009848352],"genre_scores_gemma":[0.9475582,0.00045823643,0.043905325,0.000040554023,0.000019857349,0.00018106628,0.00024208512,0.000035540408,0.0075591346],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998977,0.000017293516,0.0000074661343,0.000034108063,0.00002669924,0.000016662558],"domain_scores_gemma":[0.99985075,0.00007135218,0.000025314825,0.000009606499,0.000033720717,0.000009303288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024745573,0.0005563887,0.0004293486,0.00030150128,0.00034371178,0.000628109,0.0007379604,0.001052166,0.0015765138],"category_scores_gemma":[0.00041700836,0.0003213388,0.0005508809,0.00038486565,0.0003738008,0.0007103125,0.00040042534,0.00054358854,0.00025396043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009162117,0.000009252223,0.00026552367,0.0000140903685,0.0000058604564,0.000019089992,0.0000068097265,0.9952602,0.0013968042,0.00025533943,0.0000486462,0.002709225],"study_design_scores_gemma":[0.0000010500337,0.0000059616527,0.00009149669,0.0000011946468,0.0000016343092,0.0000022979245,0.0000016234943,0.9994099,0.00022157274,0.00018058148,0.00008078491,0.0000019209804],"about_ca_topic_score_codex":0.015931536,"about_ca_topic_score_gemma":0.012678814,"teacher_disagreement_score":0.015931536,"about_ca_system_score_codex":0.00069108926,"about_ca_system_score_gemma":0.0009096517,"threshold_uncertainty_score":0.031677604},"labels":[],"label_agreement":null},{"id":"W2084678032","doi":"10.1016/j.jhydrol.2010.05.040","title":"Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques","year":2010,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":357,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial neural network; Principal component analysis; Data pre-processing; Preprocessor; Computer science; Singular spectrum analysis; Time series; Context (archaeology); Series (stratigraphy); Data mining; Benchmark (surveying); Mode (computer interface); Pattern recognition (psychology); Artificial intelligence; Machine learning; Singular value decomposition","score_opus":0.029892463798092735,"score_gpt":0.25064333460213034,"score_spread":0.2207508708040376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084678032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30154902,0.0002111868,0.6949593,0.00012375195,0.00012028195,0.000045613928,0.00014986587,0.00170725,0.0011338083],"genre_scores_gemma":[0.9056361,0.00011129414,0.09317886,0.000023418146,0.00005124539,0.0000577875,0.0002118081,0.00005101548,0.0006784688],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99989986,0.000022541113,0.000009303727,0.000030050676,0.000024930781,0.000013325754],"domain_scores_gemma":[0.9994721,0.00027951758,0.00006616585,0.000040834915,0.00012378738,0.000017697976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043082068,0.00067729136,0.00044458802,0.0003672829,0.00019993338,0.0003581347,0.0005227253,0.00033463602,0.0007837833],"category_scores_gemma":[0.0018673083,0.00029386804,0.0004475078,0.00062495377,0.00016042018,0.0005776591,0.00038317597,0.0005430016,0.000175823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018573791,0.000121023215,0.0023610776,0.000059548387,0.00009638291,0.000066817585,0.000030547824,0.85218644,0.013923678,0.00086589856,0.00056559476,0.12953722],"study_design_scores_gemma":[0.0000032069713,0.000010161882,0.00036298914,7.458078e-7,0.000005634737,0.0000021534777,7.94243e-7,0.99824035,0.0011525748,0.00018415475,0.000035629753,0.0000015832946],"about_ca_topic_score_codex":0.004615332,"about_ca_topic_score_gemma":0.004621163,"teacher_disagreement_score":0.004615332,"about_ca_system_score_codex":0.00028902607,"about_ca_system_score_gemma":0.00037712956,"threshold_uncertainty_score":0.0091769695},"labels":[],"label_agreement":null},{"id":"W2086262337","doi":"10.4296/cwrj2503279","title":"Backcasting to Test the Use of Neural Networks for Predicting Runoff in Canadian Rivers","year":2000,"lang":"en","type":"article","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Fisheries and Oceans Canada","keywords":"Surface runoff; Snow; Artificial neural network; Structural basin; Environmental science; Data set; Test data; Meteorology; Hydrology (agriculture); Statistics; Computer science; Geography; Mathematics; Engineering; Machine learning; Geology; Ecology","score_opus":0.028354728913685803,"score_gpt":0.2047391459613226,"score_spread":0.1763844170476368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086262337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97042745,0.0005214556,0.020130293,0.0005611977,0.0002827423,0.00023615602,0.0028879622,0.00081575563,0.0041369633],"genre_scores_gemma":[0.9824041,0.0002517872,0.013910025,0.00008419895,0.00003122012,0.000106484666,0.0018980845,0.000051017018,0.0012630917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926466,0.00016364033,0.0000674795,0.00014612077,0.00025343563,0.00010471493],"domain_scores_gemma":[0.99589765,0.0019788786,0.00021680885,0.00037384656,0.0013568633,0.00017597397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003156742,0.0010960972,0.00044360964,0.0005344766,0.0009675278,0.00075668836,0.001228329,0.0009862046,0.0012138381],"category_scores_gemma":[0.011049325,0.0003860034,0.0007731819,0.00075207104,0.00073852,0.0012852945,0.00081898255,0.001993274,0.00027203554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021264649,0.0011318763,0.019019045,0.00015601126,0.00028747725,0.000062413696,0.00018439066,0.8787687,0.006241766,0.0017650218,0.0043649604,0.08589196],"study_design_scores_gemma":[0.00049457507,0.00067780825,0.015589722,0.000021815607,0.00010508877,0.00000771996,0.000081510305,0.97087675,0.009990234,0.0009983603,0.0011118948,0.000044669156],"about_ca_topic_score_codex":0.77763855,"about_ca_topic_score_gemma":0.55923146,"teacher_disagreement_score":0.22236145,"about_ca_system_score_codex":0.0039626765,"about_ca_system_score_gemma":0.0057206047,"threshold_uncertainty_score":0.44734192},"labels":[],"label_agreement":null},{"id":"W2087937041","doi":"10.1061/(asce)he.1943-5584.0000542","title":"Discussion of “Comparison of Multivariate Regression and Artificial Neural Networks for Peak Urban Water-Demand Forecasting: Evaluation of Different ANN Learning Algorithms” by Jan Adamowski and Christina Karapataki","year":2012,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial neural network; Multivariate statistics; Computer science; Artificial intelligence; Machine learning; Regression; Algorithm; Econometrics; Statistics; Mathematics","score_opus":0.04163679777494468,"score_gpt":0.2839894611181368,"score_spread":0.2423526633431921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087937041","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044906825,0.03127315,0.2748966,0.5486899,0.050622236,0.00042225723,0.0016390791,0.00077320973,0.046776798],"genre_scores_gemma":[0.5401043,0.021918535,0.17823955,0.14976403,0.0437973,0.00080205215,0.0011838498,0.000651652,0.06353867],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966348,0.0017195087,0.0002526262,0.000308151,0.0009722546,0.000112790665],"domain_scores_gemma":[0.98450005,0.011117468,0.00029926794,0.0003193237,0.0036588917,0.000105029394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0095950095,0.0006347474,0.0006985615,0.00078839133,0.0009290754,0.002833183,0.0019843641,0.0029859503,0.0057956898],"category_scores_gemma":[0.04072449,0.000264801,0.0014604179,0.001397448,0.00090342615,0.0025966836,0.00084374024,0.002854576,0.0011715122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015927892,0.00042254568,0.0072526215,0.0018142936,0.0014205563,0.0007970165,0.0006430079,0.14789398,0.006951932,0.20258069,0.34728295,0.2813476],"study_design_scores_gemma":[0.00038172465,0.00091625226,0.015415564,0.0015966744,0.0008184806,0.00054698176,0.0013625508,0.36296186,0.018614326,0.22160625,0.3753956,0.00038370065],"about_ca_topic_score_codex":0.0067721466,"about_ca_topic_score_gemma":0.007349593,"teacher_disagreement_score":0.0095950095,"about_ca_system_score_codex":0.0011424473,"about_ca_system_score_gemma":0.0010087889,"threshold_uncertainty_score":0.050743878},"labels":[],"label_agreement":null},{"id":"W2088059832","doi":"10.1089/ees.2006.0069","title":"Modeling the Disinfection of Waterborne Bacteria Using Neural Networks","year":2007,"lang":"en","type":"article","venue":"Environmental Engineering Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Simulated annealing; Artificial neural network; Backpropagation; Computer science; Biological system; Artificial intelligence; Machine learning; Biology","score_opus":0.009841366285232148,"score_gpt":0.20058203139842887,"score_spread":0.1907406651131967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088059832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2877129,0.0005399115,0.7046249,0.0003160542,0.00004710782,0.00009355473,0.00026578922,0.0005013076,0.005898505],"genre_scores_gemma":[0.9536808,0.00049623946,0.0428225,0.000036061978,0.000022086479,0.00014827319,0.00016339772,0.00002346873,0.0026072178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998318,0.000047393023,0.000011603422,0.000040145715,0.000045165758,0.000023900036],"domain_scores_gemma":[0.99951446,0.0003156766,0.000069391055,0.000016187452,0.00007464942,0.0000095678915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044988975,0.00063986005,0.00044288693,0.0005188096,0.00024277087,0.00057833723,0.00063654874,0.0007950478,0.0008198735],"category_scores_gemma":[0.001352559,0.00031928456,0.00048359178,0.00061901007,0.00036299316,0.0010813288,0.00025479912,0.0005038329,0.000111724556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000784523,0.00000770792,0.0003028881,0.00001105083,0.000006119009,0.000007627964,0.000008477177,0.9961945,0.00062772626,0.0005194758,0.000026458343,0.0022802309],"study_design_scores_gemma":[8.746723e-7,0.000003908933,0.000080310005,8.120035e-7,0.000001469527,0.0000014025079,0.0000013145146,0.99920183,0.00026621524,0.00039633815,0.00004421187,0.0000013126505],"about_ca_topic_score_codex":0.014998641,"about_ca_topic_score_gemma":0.011270988,"teacher_disagreement_score":0.014998641,"about_ca_system_score_codex":0.0009537943,"about_ca_system_score_gemma":0.00066470006,"threshold_uncertainty_score":0.029822707},"labels":[],"label_agreement":null},{"id":"W2089043653","doi":"10.1007/s00477-012-0626-5","title":"Non-linear fuzzy-set based uncertainty propagation for improved DO prediction using multiple-linear regression","year":2012,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Victoria","funders":"","keywords":"Linear regression; Mathematics; Proper linear model; Probabilistic logic; Fuzzy logic; Linear model; Variance (accounting); Fuzzy set; Generalized linear model; Statistics; Econometrics; Computer science; Bayesian multivariate linear regression; Artificial intelligence","score_opus":0.0592420782868421,"score_gpt":0.3642333117326244,"score_spread":0.30499123344578233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089043653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020248404,0.00016393303,0.9786426,0.00006093009,0.00003553919,0.000013259915,0.000025511159,0.00022510909,0.000584665],"genre_scores_gemma":[0.8223161,0.00020679843,0.17576325,0.00004780137,0.00004287667,0.000068295114,0.00008583986,0.000041292365,0.0014277416],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962294,0.000098506025,0.0000323995,0.00008287748,0.00013485638,0.000028334583],"domain_scores_gemma":[0.99892277,0.0006931233,0.0000814383,0.00005236314,0.0002291667,0.00002110314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010643131,0.00068387535,0.0008500678,0.0005963666,0.00041414335,0.00085649703,0.0010673185,0.00075632613,0.00093953736],"category_scores_gemma":[0.0031780107,0.00042602504,0.0007626121,0.0006405639,0.00031349776,0.0013218637,0.0005764208,0.0011137882,0.00017244951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009867003,0.000051346826,0.00038752428,0.000046804016,0.000056149926,0.000042103227,0.000039293922,0.9187497,0.003782835,0.0021919452,0.00030207634,0.074251555],"study_design_scores_gemma":[9.2507787e-7,0.0000034417228,0.000036434358,0.0000010650689,0.000002800717,0.0000018065293,7.4435815e-7,0.99943274,0.0003232885,0.00017252381,0.000022464115,0.0000018240802],"about_ca_topic_score_codex":0.008430741,"about_ca_topic_score_gemma":0.0072551803,"teacher_disagreement_score":0.008430741,"about_ca_system_score_codex":0.00063142995,"about_ca_system_score_gemma":0.0005882767,"threshold_uncertainty_score":0.01676333},"labels":[],"label_agreement":null},{"id":"W2090018636","doi":"10.1139/l06-111","title":"Suspended sediment prediction using two different feed-forward back-propagation algorithms","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sediment; Multilinear map; Artificial neural network; Algorithm; Streamflow; Backpropagation; Upstream (networking); Environmental science; Gradient descent; Hydrology (agriculture); Drainage basin; Computer science; Geology; Geotechnical engineering; Artificial intelligence; Mathematics; Geomorphology; Geography; Telecommunications","score_opus":0.01504355846084663,"score_gpt":0.21292299939409898,"score_spread":0.19787944093325235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090018636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12843403,0.0005205784,0.866322,0.00033140142,0.00019465975,0.0001016539,0.0001641546,0.0012443273,0.0026871678],"genre_scores_gemma":[0.65927094,0.00038688877,0.33470982,0.00011132609,0.00006642287,0.00019662979,0.00034829622,0.000067460445,0.004842158],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995316,0.00011536101,0.000046427238,0.000085259955,0.00016004685,0.00006133154],"domain_scores_gemma":[0.9986551,0.0006501046,0.00010629591,0.00006254544,0.00048363302,0.000042344946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014272131,0.0012085456,0.00075325696,0.0010062808,0.00040699364,0.001124111,0.0011564867,0.0015529771,0.001096107],"category_scores_gemma":[0.004143929,0.0005543238,0.0007748119,0.0009731102,0.00039464651,0.0013996636,0.00077240093,0.001154743,0.00034564576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043057642,0.00022721397,0.0035085508,0.00013866772,0.00015820982,0.00008671721,0.00007849085,0.71248436,0.005010699,0.001443022,0.0007162435,0.27571714],"study_design_scores_gemma":[0.000010882294,0.000031449345,0.0002699039,0.000004279688,0.000010588651,0.0000048231254,0.0000038797166,0.99797064,0.0014059854,0.00019130913,0.00009004414,0.000006214171],"about_ca_topic_score_codex":0.01045736,"about_ca_topic_score_gemma":0.00948906,"teacher_disagreement_score":0.01045736,"about_ca_system_score_codex":0.0007666825,"about_ca_system_score_gemma":0.0007927737,"threshold_uncertainty_score":0.02079302},"labels":[],"label_agreement":null},{"id":"W2091310371","doi":"10.2478/v10098-011-0002-z","title":"Periodic structures of Great Lakes levels using wavelet analysis","year":2011,"lang":"en","type":"article","venue":"Journal of Hydrology and Hydromechanics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Continuous wavelet transform; Wavelet; Environmental science; Scale (ratio); Wavelet transform; Period (music); Hydrology (agriculture); Physical geography; Geology; Climatology; Geography; Discrete wavelet transform; Cartography","score_opus":0.048682942827151326,"score_gpt":0.24984139856970936,"score_spread":0.20115845574255803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091310371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8364302,0.0003648707,0.15705419,0.00012691088,0.00002102154,0.000038515485,0.00039577964,0.00015524804,0.005413279],"genre_scores_gemma":[0.9667117,0.00020899039,0.031853374,0.000008287736,0.000016212476,0.000024178114,0.00037160754,0.000022983757,0.0007826227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999162,0.000017784872,0.000006844514,0.000017296541,0.000026649921,0.000015279744],"domain_scores_gemma":[0.9998109,0.00006961761,0.000046726796,0.00001873504,0.000042957337,0.000011138126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023389596,0.00015185554,0.00011792381,0.0011646688,0.00016205816,0.00056211994,0.00011182442,0.00012076024,0.0009200927],"category_scores_gemma":[0.0009730579,0.000121994366,0.00023257882,0.0012896236,0.00020736798,0.0003616949,0.00027535995,0.0001883562,0.00013539576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044531663,0.00006756068,0.12992643,0.00029748073,0.0002522847,0.0011262466,0.0020640807,0.114077814,0.13113429,0.034764737,0.0040853075,0.58175844],"study_design_scores_gemma":[0.000027304066,0.00008867321,0.41362917,0.000043735752,0.00008094325,0.00031691292,0.00056585943,0.5545072,0.007917725,0.017727163,0.005035621,0.000059708524],"about_ca_topic_score_codex":0.0026305916,"about_ca_topic_score_gemma":0.0023285476,"teacher_disagreement_score":0.0026305916,"about_ca_system_score_codex":0.00017030853,"about_ca_system_score_gemma":0.00018942116,"threshold_uncertainty_score":0.005230546},"labels":[],"label_agreement":null},{"id":"W2091983911","doi":"10.1139/l05-122","title":"Artificial-intelligence-based detection tests for the identification of shifts and trends in Canadian hydrometric data","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Natural Resources Canada","keywords":"Artificial neural network; Identification (biology); Artificial intelligence; Complement (music); Computer science; Test data; Data mining; Statistics; Mathematics","score_opus":0.03574657892267715,"score_gpt":0.238269208376874,"score_spread":0.20252262945419683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091983911","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8459262,0.0005169551,0.14263202,0.00037302548,0.00018412537,0.0005963523,0.0013059601,0.0008745371,0.007590654],"genre_scores_gemma":[0.8991145,0.00009882734,0.098658755,0.000051056402,0.00003038207,0.00036543614,0.00095988426,0.000035166904,0.00068596203],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.987608,0.004429287,0.0016363858,0.0009209139,0.004943408,0.000462024],"domain_scores_gemma":[0.8917089,0.08269822,0.00697542,0.0022013634,0.015243661,0.0011724952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013613323,0.00076024956,0.0005385628,0.005921768,0.0008649308,0.0013236369,0.0013294327,0.0009183349,0.0015926583],"category_scores_gemma":[0.09171172,0.0002357626,0.00071649964,0.0040740534,0.0010847972,0.001972732,0.0012587989,0.0010406472,0.00032278008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002687455,0.0009418545,0.57126236,0.0007306789,0.0007441635,0.00046741508,0.0013450242,0.037545003,0.013636936,0.0089126015,0.0047188774,0.3570076],"study_design_scores_gemma":[0.00036669892,0.0018748475,0.40052757,0.00015448962,0.00026150641,0.00071239885,0.001597448,0.5555462,0.026028186,0.0072482694,0.005398778,0.00028359628],"about_ca_topic_score_codex":0.017153235,"about_ca_topic_score_gemma":0.022430014,"teacher_disagreement_score":0.98284674,"about_ca_system_score_codex":0.0020275773,"about_ca_system_score_gemma":0.0024422144,"threshold_uncertainty_score":0.07199502},"labels":[],"label_agreement":null},{"id":"W2095484178","doi":"10.1061/(asce)0733-9496(2003)129:2(146)","title":"Seasonal Prediction with Error Estimation of Columbia River Streamflow in British Columbia","year":2003,"lang":"en","type":"article","venue":"Journal of Water Resources Planning and Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BC Hydro (Canada); Dow Chemical (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Streamflow; Pacific decadal oscillation; Climatology; Environmental science; Precipitation; Teleconnection; Jackknife resampling; Linear regression; Water year; Sea surface temperature; Regression; Meteorology; Mathematics; Statistics; Geography; Drainage basin; Estimator; Geology","score_opus":0.009075874074992376,"score_gpt":0.19954103157848388,"score_spread":0.1904651575034915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095484178","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99154353,0.0001067019,0.0056885513,0.00014790814,0.000013523308,0.000016539,0.0008203568,0.0001896248,0.0014734013],"genre_scores_gemma":[0.9950264,0.000040610466,0.0028219013,0.000010492921,0.000002662432,0.000011031276,0.0008675976,0.0000149137895,0.001204397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996711,0.000068130685,0.000022760845,0.000085994674,0.000098087046,0.00005391843],"domain_scores_gemma":[0.9981488,0.00055758975,0.00014037691,0.00012183451,0.0009476092,0.000083711435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088482175,0.00031393414,0.00027539226,0.0006654613,0.00043687754,0.0006703885,0.0005366832,0.00029767398,0.0011062947],"category_scores_gemma":[0.005838956,0.00019843777,0.00016010218,0.001040834,0.0002554096,0.0003164378,0.00039025582,0.0005744469,0.00023364766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030812342,0.00010318647,0.29421756,0.00005621923,0.00013249379,0.00014487845,0.0002731533,0.5549511,0.0023488558,0.0007511129,0.003522528,0.14319082],"study_design_scores_gemma":[0.000016338094,0.000014931962,0.11707084,0.000011664044,0.000013183407,0.000013018239,0.00009929388,0.88063365,0.001096047,0.00019762978,0.0008156748,0.000017687928],"about_ca_topic_score_codex":0.8760306,"about_ca_topic_score_gemma":0.89567125,"teacher_disagreement_score":0.123969376,"about_ca_system_score_codex":0.0041935095,"about_ca_system_score_gemma":0.0043087285,"threshold_uncertainty_score":0.24939889},"labels":[],"label_agreement":null},{"id":"W2096243037","doi":"10.1897/08-569.1","title":"A cautionary note on implications of the well-mixed compartment assumption as applied to mass balance models of chemical fate in flowing systems","year":2009,"lang":"en","type":"article","venue":"Environmental Toxicology and Chemistry","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Compartment (ship); Balance (ability); Biochemical engineering; Environmental science; Chemistry; Environmental chemistry; Biology; Geology; Neuroscience; Engineering; Oceanography","score_opus":0.011092244783356398,"score_gpt":0.22423614160647812,"score_spread":0.2131438968231217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096243037","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030766629,0.01942541,0.27085143,0.59403807,0.06000728,0.0003662747,0.0018448748,0.0025658892,0.020134116],"genre_scores_gemma":[0.4031132,0.016183073,0.2422887,0.25585973,0.0335722,0.0010146371,0.00049251434,0.0017476311,0.04572828],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9815092,0.010591097,0.0024729895,0.001522513,0.0034538675,0.00045021993],"domain_scores_gemma":[0.92637753,0.054245308,0.0028230036,0.0058575463,0.009849986,0.0008467189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027558666,0.0014192692,0.0028546955,0.0012801376,0.0043813963,0.0050060526,0.012172692,0.0065435446,0.0034810961],"category_scores_gemma":[0.11885065,0.00082520134,0.0028015024,0.0020991727,0.007972404,0.006035576,0.0042753536,0.02096947,0.0025660757],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008880946,0.00022547808,0.013208704,0.0025134583,0.0008005496,0.0069446745,0.006932528,0.056785364,0.008757831,0.33001935,0.4694541,0.10346984],"study_design_scores_gemma":[0.00026587033,0.00038717157,0.006415779,0.0017853631,0.00035080127,0.0027520913,0.0038354963,0.1288489,0.011213758,0.55892277,0.2845899,0.0006321183],"about_ca_topic_score_codex":0.035227653,"about_ca_topic_score_gemma":0.0392737,"teacher_disagreement_score":0.035227653,"about_ca_system_score_codex":0.0024900106,"about_ca_system_score_gemma":0.0035324353,"threshold_uncertainty_score":0.14574593},"labels":[],"label_agreement":null},{"id":"W2097453622","doi":"10.2166/hydro.2011.044","title":"Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data","year":2011,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Multivariate adaptive regression splines; Surface runoff; Watershed; Artificial neural network; Multivariate statistics; Mars Exploration Program; Environmental science; Hydrology (agriculture); Regression analysis; Bayesian multivariate linear regression; Computer science; Machine learning; Engineering","score_opus":0.13052155274347838,"score_gpt":0.2971876465423763,"score_spread":0.1666660937988979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097453622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8610559,0.0006440592,0.1358414,0.00023066417,0.000058497117,0.00005960037,0.00007804255,0.00026411097,0.0017677795],"genre_scores_gemma":[0.9757268,0.00026228925,0.023449877,0.000021173591,0.000014060455,0.000029366556,0.00007527703,0.00001373726,0.00040736079],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999476,0.0002925757,0.000041845775,0.00005245153,0.00009846872,0.000038775383],"domain_scores_gemma":[0.9982009,0.0012275865,0.00011871031,0.000070418224,0.00032756408,0.000054674565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021666412,0.00046463695,0.0005146641,0.000815434,0.00019843511,0.00062189496,0.00062275556,0.00043461644,0.00043223205],"category_scores_gemma":[0.004962872,0.00024762072,0.0006100958,0.00069644436,0.0001892208,0.0008441303,0.0005324335,0.00058176275,0.00009166814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041553238,0.00014615104,0.007936793,0.000051812247,0.00014211287,0.000041397176,0.00005380838,0.92880845,0.0011386918,0.0007431093,0.0001696585,0.06035246],"study_design_scores_gemma":[0.000004928403,0.00003721841,0.0006432185,0.0000021608766,0.000008631201,0.0000023634966,0.0000071038685,0.9989913,0.00015797165,0.00011612905,0.000026343954,0.0000025645973],"about_ca_topic_score_codex":0.013645548,"about_ca_topic_score_gemma":0.009873407,"teacher_disagreement_score":0.013645548,"about_ca_system_score_codex":0.00055532245,"about_ca_system_score_gemma":0.0006282667,"threshold_uncertainty_score":0.027132273},"labels":[],"label_agreement":null},{"id":"W2102017823","doi":"10.1061/(asce)he.1943-5584.0000188","title":"Comparing Sigmoid Transfer Functions for Neural Network Multistep Ahead Streamflow Forecasting","year":2010,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Environment and Climate Change Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sigmoid function; Artificial neural network; Perceptron; Computer science; Nonlinear system; Transfer function; Multilayer perceptron; Artificial intelligence; Streamflow; Algorithm; Mathematical optimization; Machine learning; Mathematics","score_opus":0.027808445636118017,"score_gpt":0.21777748401035799,"score_spread":0.18996903837423998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102017823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75292325,0.0029834285,0.23480438,0.0005994277,0.00020324001,0.00023932091,0.00027650062,0.00068795873,0.007282477],"genre_scores_gemma":[0.97183007,0.0006250611,0.026303882,0.00004581288,0.000009736717,0.00007626641,0.00013059117,0.00003165413,0.0009469995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994905,0.00024517905,0.000054430915,0.000051375315,0.00010589714,0.000052556843],"domain_scores_gemma":[0.997038,0.0019647044,0.00009437965,0.00015098344,0.00068306143,0.00006892777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004885394,0.00074912835,0.0004996665,0.0011131502,0.0003012892,0.0009859124,0.00058592233,0.00088417024,0.0009619824],"category_scores_gemma":[0.011016963,0.00022248275,0.0005487033,0.00093029795,0.00037187876,0.0014822016,0.0006183588,0.000803025,0.00025924473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015431807,0.00015777141,0.0072805383,0.00038999153,0.00016445294,0.00009671765,0.00018874664,0.84133214,0.004882038,0.0034038268,0.0006732553,0.13988732],"study_design_scores_gemma":[0.000023351353,0.0002520035,0.0028828145,0.000038500828,0.000034399272,0.000015227624,0.000085492306,0.9894723,0.005100884,0.0015730652,0.00050005974,0.00002173016],"about_ca_topic_score_codex":0.0079217255,"about_ca_topic_score_gemma":0.00446179,"teacher_disagreement_score":0.0079217255,"about_ca_system_score_codex":0.0010705604,"about_ca_system_score_gemma":0.0007599309,"threshold_uncertainty_score":0.025836706},"labels":[],"label_agreement":null},{"id":"W2106008453","doi":"10.1109/igarss.1989.576326","title":"A Modified Probabilistic Relaxation Approach To Land-cover Classification","year":2005,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Probabilistic logic; Cover (algebra); Land cover; Relaxation (psychology); Computer science; Environmental science; Artificial intelligence; Land use; Engineering; Civil engineering; Psychology","score_opus":0.046267089871714816,"score_gpt":0.24703781081402287,"score_spread":0.20077072094230805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106008453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006659574,0.00018268394,0.9913902,0.0002554787,0.00004573641,0.0000353939,0.00010779473,0.00015220208,0.001170861],"genre_scores_gemma":[0.2866702,0.00035990143,0.7055887,0.0003580432,0.00042563028,0.00036936646,0.00083098264,0.00019922141,0.0051979776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999193,0.00035184802,0.000054273594,0.00016126731,0.00017008193,0.00006946321],"domain_scores_gemma":[0.9970401,0.0020523523,0.00016639271,0.00023715415,0.0004137241,0.00009027732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026016221,0.0005835835,0.001615669,0.0009035664,0.0005700869,0.0012448154,0.0034701778,0.0013318781,0.0043009073],"category_scores_gemma":[0.006916007,0.0009939673,0.0011491971,0.0018720671,0.000885948,0.002311358,0.0013446708,0.0021714205,0.0005723002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008506285,0.00005373285,0.00028154431,0.000063153806,0.00006520701,0.000034219098,0.000047762645,0.9106109,0.0007206991,0.01814546,0.0017928741,0.06809942],"study_design_scores_gemma":[0.0000054890397,0.0000047443964,0.000026961141,0.0000017469226,0.000003476063,0.0000029396097,0.0000018454261,0.9946419,0.00005875212,0.0050723385,0.00017754654,0.0000022854308],"about_ca_topic_score_codex":0.0118998075,"about_ca_topic_score_gemma":0.00889215,"teacher_disagreement_score":0.0118998075,"about_ca_system_score_codex":0.0009401826,"about_ca_system_score_gemma":0.0012617265,"threshold_uncertainty_score":0.023661077},"labels":[],"label_agreement":null},{"id":"W2111960238","doi":"10.5194/hess-10-485-2006","title":"Clustering of heterogeneous precipitation fields for the assessment and possible improvement of lumped neural network models for streamflow forecasts","year":2006,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Coquitlam College; Université Laval; Golder Associates (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Precipitation; Cluster analysis; Orography; Artificial neural network; Streamflow; Environmental science; Surface runoff; Self-organizing map; Watershed; Computer science; Rain gauge; Perceptron; Multilayer perceptron; Meteorology; Machine learning; Geography; Drainage basin","score_opus":0.0255196953726457,"score_gpt":0.2580244808052393,"score_spread":0.23250478543259362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111960238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20517448,0.00021802583,0.79222685,0.00013148056,0.00004807371,0.00008908739,0.00018935386,0.00074292865,0.0011797104],"genre_scores_gemma":[0.9259347,0.000063318235,0.07299624,0.000025090145,0.000013426586,0.000063136984,0.0001650444,0.000025045847,0.00071391684],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996132,0.00016254469,0.000030419502,0.00008707512,0.00008258885,0.00002418646],"domain_scores_gemma":[0.99906594,0.0004736982,0.00011646003,0.00013412829,0.00017105739,0.00003876809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015110557,0.00047415704,0.0005652692,0.00076519384,0.00025314963,0.0006720223,0.0006364693,0.0004394157,0.0008969688],"category_scores_gemma":[0.0039964365,0.00027864822,0.00039504023,0.00067229936,0.00026054267,0.0013081335,0.00059803145,0.00047196102,0.00014337698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054177628,0.000026862286,0.00095645944,0.00002092388,0.000043698376,0.00001210949,0.000022257727,0.9718552,0.001097333,0.0010476862,0.0001320279,0.0247312],"study_design_scores_gemma":[0.0000017951577,0.000006087733,0.00022238556,0.0000013720651,0.0000025719278,0.0000012955277,0.0000027172719,0.9990293,0.0002365447,0.00045129165,0.00004269041,0.0000021175074],"about_ca_topic_score_codex":0.0068460824,"about_ca_topic_score_gemma":0.008012748,"teacher_disagreement_score":0.0068460824,"about_ca_system_score_codex":0.0009240725,"about_ca_system_score_gemma":0.00044832373,"threshold_uncertainty_score":0.013612449},"labels":[],"label_agreement":null},{"id":"W2114210944","doi":"10.1007/978-94-015-9341-0_13","title":"Streamflow Data Infilling Techniques Based on Concepts of Groups and Neural Networks","year":2000,"lang":"en","type":"book-chapter","venue":"Water science and technology library","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Streamflow; Evapotranspiration; Missing data; Surface runoff; Series (stratigraphy); Hydrology (agriculture); Environmental science; Computer science; Geography; Geology; Cartography; Machine learning; Drainage basin; Ecology","score_opus":0.01566357357379906,"score_gpt":0.21682626730319762,"score_spread":0.20116269372939857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114210944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038537565,0.00023828694,0.9941136,0.000044794273,0.00006658643,0.000017189348,0.00003043451,0.00040709192,0.0012282443],"genre_scores_gemma":[0.085929185,0.00053061685,0.9069652,0.000055325567,0.00014594705,0.00010043151,0.00021977993,0.00023936215,0.005814219],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967957,0.00007994888,0.000025334133,0.000067591325,0.0001237766,0.000023652121],"domain_scores_gemma":[0.9990434,0.000517301,0.00006180065,0.00015226705,0.00019278764,0.000032337204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080640515,0.00064939825,0.00080554996,0.0011389051,0.00030940495,0.0006786521,0.0010761833,0.0004683752,0.003405717],"category_scores_gemma":[0.0031909917,0.00039157917,0.00069734297,0.0012523839,0.0005949416,0.00206225,0.0010534363,0.0013821496,0.0008893458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014456939,0.00007876858,0.0010428849,0.00017853436,0.00009112618,0.000112028014,0.00022493607,0.15019742,0.008909173,0.06836896,0.005671822,0.7649797],"study_design_scores_gemma":[0.00001302236,0.00005445828,0.00046815406,0.000026678008,0.000036870355,0.00007423969,0.000029558263,0.9355968,0.00878589,0.043742433,0.011154321,0.000017533062],"about_ca_topic_score_codex":0.0014208285,"about_ca_topic_score_gemma":0.002918478,"teacher_disagreement_score":0.003405717,"about_ca_system_score_codex":0.00025998757,"about_ca_system_score_gemma":0.00029384842,"threshold_uncertainty_score":0.011393249},"labels":[],"label_agreement":null},{"id":"W2114419783","doi":"10.1139/l07-142","title":"Initial assessment of bridge backwater using an artificial neural network approach","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Bridge (graph theory); Flood myth; Engineering; Field (mathematics); Linear regression; Computer science; Hydrology (agriculture); Civil engineering; Geotechnical engineering; Machine learning; Mathematics; Geography","score_opus":0.06001608395685955,"score_gpt":0.24962156291427273,"score_spread":0.1896054789574132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114419783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80098814,0.0004857151,0.19113211,0.00022702331,0.00004165684,0.00014796645,0.00026009695,0.000439315,0.006278001],"genre_scores_gemma":[0.96741,0.00017388683,0.030707892,0.000026914928,0.000006386616,0.000061215025,0.00014431805,0.000007708976,0.0014616245],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996464,0.000114487324,0.000034812954,0.00006498447,0.000109249675,0.000030076802],"domain_scores_gemma":[0.9994349,0.00022081715,0.000052206542,0.000033850556,0.00023951332,0.000018794732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010228559,0.0006167884,0.0004390263,0.00086867687,0.00020344424,0.00060899346,0.00043268778,0.0007597603,0.0008842676],"category_scores_gemma":[0.0028035974,0.00023193088,0.0002491408,0.0004991985,0.00017861756,0.001072874,0.0004123999,0.00041528294,0.00015322745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000343999,0.00022800501,0.02205117,0.00017474683,0.00007123105,0.00027019889,0.00017141417,0.7693663,0.035843804,0.0012503532,0.0005720992,0.16965663],"study_design_scores_gemma":[0.0000055241167,0.000105913954,0.0051790653,0.0000149819625,0.000010814376,0.000016071599,0.00004338955,0.9882357,0.005782709,0.0003418462,0.00025131486,0.000012701719],"about_ca_topic_score_codex":0.004759539,"about_ca_topic_score_gemma":0.010572129,"teacher_disagreement_score":0.004759539,"about_ca_system_score_codex":0.00073207,"about_ca_system_score_gemma":0.00041742978,"threshold_uncertainty_score":0.009463668},"labels":[],"label_agreement":null},{"id":"W2116208828","doi":"10.1007/s11269-012-9992-5","title":"River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia","year":2012,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Golder Associates (Canada)","funders":"Universiti Teknologi Petronas","keywords":"Conjugate gradient method; Algorithm; Gradient descent; Multilayer perceptron; Artificial neural network; Convergence (economics); Training (meteorology); Sediment; Levenberg–Marquardt algorithm; Hydrogeology; Computer science; Machine learning; Geology; Geomorphology; Geotechnical engineering; Meteorology; Geography","score_opus":0.044213029755571856,"score_gpt":0.2608464373813931,"score_spread":0.21663340762582128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116208828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99482155,0.000050508064,0.0041977353,0.00007406363,0.0000057032325,0.000011877889,0.00006181523,0.00006384696,0.0007128705],"genre_scores_gemma":[0.9957402,0.000040518196,0.0033778015,0.000005011574,0.0000018736923,0.0000052185283,0.000061144136,0.000005176219,0.0007631732],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978834,0.00007007431,0.000021012092,0.00004574265,0.000032928005,0.000041928808],"domain_scores_gemma":[0.99895823,0.00060490356,0.00009172157,0.00005422701,0.00024449735,0.000046499565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095147575,0.0005571715,0.00043009972,0.00039851328,0.0004177377,0.00067297113,0.00062867557,0.0008420869,0.0004914304],"category_scores_gemma":[0.0015973008,0.0003222002,0.00046317588,0.000545089,0.0003504732,0.0007204074,0.00031128345,0.00049003924,0.00010289763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044346714,0.00040311555,0.056535102,0.000092020106,0.000095687865,0.00084168155,0.00018459329,0.8962569,0.0027567518,0.000648989,0.00054698956,0.04119468],"study_design_scores_gemma":[0.000014469125,0.00008001831,0.008605081,0.0000048556917,0.000021140193,0.000027389315,0.00011717058,0.98903066,0.0018709339,0.00011783689,0.000098479504,0.000011968632],"about_ca_topic_score_codex":0.08899198,"about_ca_topic_score_gemma":0.06927977,"teacher_disagreement_score":0.08899198,"about_ca_system_score_codex":0.0013734755,"about_ca_system_score_gemma":0.0008561772,"threshold_uncertainty_score":0.17694795},"labels":[],"label_agreement":null},{"id":"W2119821103","doi":"10.1002/hyp.5656","title":"Characterization of soil moisture conditions at temporal scales from a few days to annual","year":2004,"lang":"en","type":"article","venue":"Hydrological Processes","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Golder Associates (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Streamflow; Environmental science; Water content; Watershed; Precipitation; Moisture; Wavelet; Self-organizing map; Hydrology (agriculture); Soil science; Computer science; Meteorology; Artificial neural network; Geology; Machine learning; Geography; Geotechnical engineering; Cartography","score_opus":0.014979272249635436,"score_gpt":0.23588991748353205,"score_spread":0.2209106452338966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119821103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933662,0.00005233109,0.0053340383,0.000018191817,0.0000027060642,0.0000042350334,0.00033081457,0.000052410145,0.0008389955],"genre_scores_gemma":[0.998798,0.000019730918,0.00089060306,0.0000018364501,0.0000020217815,0.0000022551894,0.00019247575,0.0000027599447,0.00009039104],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99996376,0.000004963838,0.0000028480904,0.000010863028,0.0000102226,0.0000073511064],"domain_scores_gemma":[0.9997837,0.000074046344,0.00004967384,0.000021947297,0.000046734975,0.000023962468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018450816,0.00008083248,0.000113350194,0.00083241926,0.00008979554,0.00031975337,0.000110222136,0.00013766185,0.00044813572],"category_scores_gemma":[0.00054979406,0.000055765784,0.000090234775,0.0005546673,0.00011510798,0.00029071353,0.00011238617,0.00012042596,0.0000853011],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004909598,0.00020997683,0.59890616,0.00012618022,0.00015798918,0.00036038554,0.0004060531,0.0639837,0.10424328,0.0020769476,0.00094692584,0.22809142],"study_design_scores_gemma":[0.0000078113335,0.000065755914,0.8458872,0.0000072413673,0.000024309049,0.000104490166,0.00019160121,0.14375497,0.008547911,0.0005562436,0.0008321492,0.00002038716],"about_ca_topic_score_codex":0.0022474707,"about_ca_topic_score_gemma":0.0032619005,"teacher_disagreement_score":0.0022474707,"about_ca_system_score_codex":0.00011560849,"about_ca_system_score_gemma":0.00008306806,"threshold_uncertainty_score":0.004468739},"labels":[],"label_agreement":null},{"id":"W2120998537","doi":"10.1139/l04-007","title":"A bimodal model for the high values of a river flow","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Goodness of fit; Flow (mathematics); Bivariate analysis; Statistics; Linear regression; Exponential function; Distribution (mathematics); Regression analysis; Econometrics; Regression; Applied mathematics; Mathematical analysis","score_opus":0.012504678477459763,"score_gpt":0.18434748763729106,"score_spread":0.1718428091598313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120998537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30619648,0.0005293409,0.67441815,0.0020164447,0.00013980891,0.00020243997,0.0019295792,0.0013506432,0.013217043],"genre_scores_gemma":[0.9786022,0.00021978411,0.011026743,0.00018938122,0.000062507665,0.00012885654,0.00045465078,0.000066523324,0.0092494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989988,0.0002327753,0.00003360015,0.00032380153,0.00015169181,0.0002593079],"domain_scores_gemma":[0.9965513,0.0019651086,0.00040046958,0.00032500958,0.0005330368,0.00022504685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035058067,0.0007665477,0.0010823826,0.001635638,0.0006855606,0.0016931737,0.002950198,0.002134567,0.0068875374],"category_scores_gemma":[0.012252027,0.00049229705,0.0009747457,0.0014015264,0.0023899602,0.0024408381,0.0011066751,0.002232624,0.0019092581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046058223,0.00019111375,0.022459233,0.00016991122,0.0001231983,0.0006772528,0.00084222085,0.7527186,0.0074979,0.1763087,0.0049250405,0.033626195],"study_design_scores_gemma":[0.000033051278,0.000071059694,0.005262128,0.000026552789,0.000029323926,0.00021373737,0.000083317216,0.9572211,0.00042638948,0.035326965,0.0012519711,0.000054369062],"about_ca_topic_score_codex":0.022455348,"about_ca_topic_score_gemma":0.017073998,"teacher_disagreement_score":0.022455348,"about_ca_system_score_codex":0.0018112952,"about_ca_system_score_gemma":0.0013137889,"threshold_uncertainty_score":0.044649243},"labels":[],"label_agreement":null},{"id":"W2121782086","doi":"10.1109/ijcnn.2012.6252383","title":"Downscaling temperature and precipitation using support vector regression with evolutionary strategy","year":2012,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Support vector machine; Random forest; Computer science; Benchmark (surveying); Artificial neural network; Artificial intelligence; Machine learning; Downscaling; Evolutionary algorithm; Regression; Linear regression; Feature selection; Symbolic regression; Genetic programming; Data mining; Mathematics; Statistics; Precipitation","score_opus":0.023353028169247947,"score_gpt":0.2574650239930481,"score_spread":0.23411199582380016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121782086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039443433,0.00018006559,0.95918936,0.00011147064,0.000026847445,0.000029341601,0.000015458472,0.00029299167,0.0007109426],"genre_scores_gemma":[0.49090004,0.00015598568,0.5072341,0.000111141955,0.000044316308,0.00010225684,0.000098500976,0.00006943375,0.001284159],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961406,0.00015446662,0.00002791578,0.000062310006,0.00010891782,0.000032357155],"domain_scores_gemma":[0.9990324,0.0006191988,0.00010330713,0.00006857151,0.00015116677,0.000025471467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012819647,0.00064305984,0.0009212304,0.00061154104,0.00021066803,0.00046646417,0.0008502351,0.00088273035,0.0007046705],"category_scores_gemma":[0.0028253952,0.0004089294,0.0007586527,0.00054824166,0.00027218807,0.00074626936,0.00044851843,0.00069986325,0.00024979064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053228137,0.00006105314,0.0017202741,0.00003616172,0.000071717885,0.0000743633,0.000041412943,0.8626164,0.004445484,0.0025608223,0.0003218393,0.1279973],"study_design_scores_gemma":[0.0000033640174,0.00001570308,0.00007468038,0.0000016380957,0.0000034771674,0.000007433083,0.0000018433014,0.9989625,0.00045313657,0.0003540744,0.00011974259,0.000002323009],"about_ca_topic_score_codex":0.0020500254,"about_ca_topic_score_gemma":0.0020299843,"teacher_disagreement_score":0.0020500254,"about_ca_system_score_codex":0.000212695,"about_ca_system_score_gemma":0.00040987445,"threshold_uncertainty_score":0.0067797303},"labels":[],"label_agreement":null},{"id":"W2125112475","doi":"10.1109/epec.2010.5697203","title":"Tidal currents forecasting using a hybrid of ANN and least squares model","year":2010,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Artificial neural network; Least-squares function approximation; Computer science; Algorithm; Artificial intelligence; Mathematics; Statistics","score_opus":0.046506790980023076,"score_gpt":0.2589074395570735,"score_spread":0.21240064857705043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125112475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27211916,0.0006416103,0.71585315,0.00036668262,0.00012830652,0.00014644767,0.00021839894,0.0017709153,0.008755313],"genre_scores_gemma":[0.83577985,0.0002876487,0.15960495,0.00007427867,0.00004201322,0.000111278794,0.00018984951,0.00003904033,0.003871163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997346,0.00007221765,0.000019110275,0.000050751405,0.000104273655,0.000019102768],"domain_scores_gemma":[0.9995647,0.00022294847,0.000039162438,0.000029202112,0.00013034715,0.000013577265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005008715,0.00040377167,0.0005997096,0.00042964402,0.00021779514,0.0005360832,0.00047997414,0.00046748843,0.0007712429],"category_scores_gemma":[0.0012967774,0.00025232093,0.00037209722,0.0005446312,0.0001365187,0.0008797072,0.00029250342,0.0004994779,0.00023566549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014237661,0.00013508837,0.003868928,0.00009234904,0.00013799219,0.00007654807,0.00006802167,0.86080265,0.010657065,0.0011791099,0.0006973947,0.1221424],"study_design_scores_gemma":[0.000004078298,0.000039554146,0.0005962204,0.0000030734448,0.000007913568,0.000010633028,0.0000054350635,0.99788445,0.00092128594,0.0002464242,0.00027459033,0.0000062995246],"about_ca_topic_score_codex":0.007228437,"about_ca_topic_score_gemma":0.009056089,"teacher_disagreement_score":0.007228437,"about_ca_system_score_codex":0.00037598354,"about_ca_system_score_gemma":0.00038360764,"threshold_uncertainty_score":0.014372706},"labels":[],"label_agreement":null},{"id":"W2128075723","doi":"10.1111/j.1752-1688.2001.tb05476.x","title":"MODELING TRANSIENT pH DEPRESSIONS IN COASTAL STREAMS OF BRITISH COLUMBIA USING NEURAL NETWORKS<sup>1</sup>","year":2001,"lang":"en","type":"article","venue":"JAWRA Journal of the American Water Resources Association","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Watershed; Environmental science; Hydrology (agriculture); Precipitation; Urbanization; Watershed area; Dry season; Geography; Ecology; Meteorology; Geology; Machine learning; Computer science; Cartography","score_opus":0.011879925410455277,"score_gpt":0.2174646000421632,"score_spread":0.20558467463170793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128075723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911378,0.000052704374,0.0063753175,0.00015947856,0.0000072567095,0.000029710289,0.00045229198,0.000160426,0.0016251013],"genre_scores_gemma":[0.9977368,0.000030362113,0.0012449635,0.000011623208,0.0000016362542,0.000015288228,0.00028451806,0.0000046836676,0.0006700547],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990904,0.000015721798,0.000005842189,0.000030395326,0.000014105299,0.00002489067],"domain_scores_gemma":[0.9996574,0.00016228421,0.000032219068,0.000011857967,0.00010667001,0.000029595218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026532236,0.0004248077,0.00022198987,0.0003086216,0.00045846976,0.0007748861,0.0007182748,0.0005045475,0.0011141887],"category_scores_gemma":[0.0012237774,0.00022841345,0.00021250366,0.00052815734,0.0002780959,0.0003579391,0.00029492506,0.00044862254,0.0001326409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110137364,0.00008976317,0.04257535,0.00003259342,0.000045672463,0.00009136736,0.000057244597,0.9419894,0.00075984054,0.00018349708,0.00063125865,0.01343397],"study_design_scores_gemma":[0.000009057489,0.000012130632,0.009586813,0.00000279324,0.0000074274017,0.0000036621536,0.000036521247,0.989786,0.00028779052,0.00013634253,0.00012712956,0.000004263758],"about_ca_topic_score_codex":0.710742,"about_ca_topic_score_gemma":0.6780737,"teacher_disagreement_score":0.289258,"about_ca_system_score_codex":0.0047658407,"about_ca_system_score_gemma":0.0025648703,"threshold_uncertainty_score":0.581923},"labels":[],"label_agreement":null},{"id":"W2132417139","doi":"10.5194/hess-14-1931-2010","title":"Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology - Part 1: Concepts and methodology","year":2010,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":205,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Genetic programming; Computer science; Data mining; Support vector machine; Evapotranspiration; Sampling (signal processing); Process (computing); Regression; Hydrological modelling; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.11230977228939426,"score_gpt":0.3235866012903875,"score_spread":0.21127682900099326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132417139","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8657465,0.0005334306,0.12313195,0.0006174395,0.00019400835,0.0011793411,0.0032900271,0.0013090894,0.003998127],"genre_scores_gemma":[0.8747386,0.0003157865,0.12054127,0.0001011414,0.00003691688,0.0010434128,0.002496497,0.00006395354,0.00066242245],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849224,0.00070109696,0.0001272903,0.00027297996,0.000342922,0.00006349477],"domain_scores_gemma":[0.9920672,0.0051503973,0.00040503012,0.0012057805,0.001043732,0.00012789834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004368027,0.00076962216,0.00039862268,0.0007175496,0.00037490533,0.0012258027,0.0010740622,0.0010122441,0.0010050165],"category_scores_gemma":[0.011941154,0.0004068381,0.0007094601,0.0012414077,0.00042497896,0.0015536146,0.0007102733,0.0012686894,0.00026166515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028161663,0.00635113,0.029860776,0.0011531012,0.00045947052,0.00019218335,0.0005460918,0.6972805,0.027893372,0.012984543,0.004710613,0.21575205],"study_design_scores_gemma":[0.00026926334,0.002030695,0.0063879522,0.000052933898,0.000065331296,0.000057317455,0.00014685628,0.9523607,0.03232515,0.0032966197,0.0029391672,0.00006814592],"about_ca_topic_score_codex":0.003789311,"about_ca_topic_score_gemma":0.0019850715,"teacher_disagreement_score":0.004368027,"about_ca_system_score_codex":0.0009774528,"about_ca_system_score_gemma":0.0008455483,"threshold_uncertainty_score":0.023100615},"labels":[],"label_agreement":null},{"id":"W2134712296","doi":"10.1109/iccms.2009.70","title":"Implementing an Intuitive Reasoner for Predicting Continuous Weather Variables","year":2009,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Semantic reasoner; Computer science; Variable (mathematics); Data mining; Linear regression; Regression analysis; Regression; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.01686146746513032,"score_gpt":0.2645346955752567,"score_spread":0.2476732281101264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134712296","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007229108,0.000036002322,0.9802317,0.000117999,0.000030784227,0.00017277786,0.00016897547,0.011061156,0.0009516359],"genre_scores_gemma":[0.10310082,0.00008472512,0.8940467,0.00021071848,0.00001947069,0.00025859562,0.0005940168,0.00031173776,0.0013731605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760276,0.0005392659,0.0003289385,0.00052891125,0.0008375753,0.00016256204],"domain_scores_gemma":[0.9962171,0.0021966458,0.00026292916,0.00059562613,0.00064954866,0.00007813067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044361004,0.0010410353,0.00064291985,0.0009992413,0.00037671512,0.002526978,0.00300534,0.0012866424,0.004825905],"category_scores_gemma":[0.010967094,0.000707195,0.0013162035,0.0005653298,0.0009786083,0.0028171127,0.0012907463,0.0019226421,0.0014124231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013728132,0.0009398418,0.0076016486,0.0016591978,0.0005382278,0.0016425112,0.0020224613,0.17817445,0.07474077,0.106459804,0.014003673,0.6108447],"study_design_scores_gemma":[0.00030571563,0.00037258584,0.0014996048,0.00019475195,0.00022849161,0.00058920705,0.00022224196,0.84772587,0.069213085,0.049523078,0.029963871,0.0001614381],"about_ca_topic_score_codex":0.002064803,"about_ca_topic_score_gemma":0.0021388433,"teacher_disagreement_score":0.004825905,"about_ca_system_score_codex":0.0005129087,"about_ca_system_score_gemma":0.001709823,"threshold_uncertainty_score":0.023460627},"labels":[],"label_agreement":null},{"id":"W2137644833","doi":"10.1007/s12205-009-0205-6","title":"Performance of an Artificial Neural Network model for simulating saltwater intrusion process in coastal aquifers when training with noisy data","year":2009,"lang":"en","type":"article","venue":"KSCE Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Artificial neural network; Training (meteorology); MATLAB; Process (computing); Saltwater intrusion; Computer science; Backpropagation; Test data; Aquifer; Transfer function; Artificial intelligence; Data modeling; Data mining; Machine learning; Engineering; Groundwater; Geotechnical engineering; Meteorology","score_opus":0.04045895344704177,"score_gpt":0.25253384951640134,"score_spread":0.2120748960693596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137644833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9587202,0.00019682391,0.038184196,0.00028054227,0.0000774267,0.00002818731,0.00011380479,0.0002556862,0.0021431919],"genre_scores_gemma":[0.9967533,0.00002680456,0.002618999,0.00002031057,0.0000057260413,0.00001120134,0.00006756362,0.000007825138,0.00048827607],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998286,0.00005397266,0.000018533527,0.000045476118,0.000026800017,0.000026602238],"domain_scores_gemma":[0.9983089,0.001166127,0.0001027479,0.00006881951,0.00029413393,0.000059216858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001001722,0.0007179559,0.00051323243,0.00033611353,0.0005137777,0.0007012329,0.00067908526,0.0014531694,0.00075592735],"category_scores_gemma":[0.0036805365,0.00044414954,0.0003708157,0.0002951698,0.00053871964,0.00083550886,0.00041006654,0.00075903523,0.0001290482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006986535,0.000031861287,0.0018381721,0.000011020021,0.00001627424,0.000019115303,0.000014208647,0.9938691,0.00057674194,0.0000832953,0.00007175889,0.0033987137],"study_design_scores_gemma":[0.0000018381746,0.0000075183675,0.00014387725,6.138867e-7,0.0000017941263,7.129284e-7,0.0000016362899,0.999632,0.00018230578,0.000021209917,0.0000054741126,0.0000010577011],"about_ca_topic_score_codex":0.046435356,"about_ca_topic_score_gemma":0.021451313,"teacher_disagreement_score":0.046435356,"about_ca_system_score_codex":0.0010661838,"about_ca_system_score_gemma":0.0007763803,"threshold_uncertainty_score":0.09233016},"labels":[],"label_agreement":null},{"id":"W2139662623","doi":"10.1139/l08-090","title":"River flow forecasting using different artificial neural network algorithms and wavelet transform","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Wavelet; Backpropagation; Wavelet transform; Computer science; Feedforward neural network; Algorithm; Discrete wavelet transform; Streamflow; Artificial intelligence; Pattern recognition (psychology); Geography","score_opus":0.022293288657697016,"score_gpt":0.19407425548038076,"score_spread":0.17178096682268373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139662623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21994281,0.0022259536,0.77274895,0.00034450725,0.0001461685,0.00007608641,0.00014212076,0.0006467426,0.0037266568],"genre_scores_gemma":[0.6876005,0.0021316067,0.3076303,0.000060558592,0.00007019977,0.00010670217,0.00034345573,0.000047867154,0.0020088344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957436,0.00013954635,0.00004355595,0.000060836785,0.00015630371,0.000025358926],"domain_scores_gemma":[0.9991689,0.00041093945,0.00007712941,0.00005455822,0.00027217082,0.000016292914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017761152,0.00057996984,0.0007062178,0.0010277869,0.00017853735,0.00066879473,0.0006483998,0.00063045765,0.00043938993],"category_scores_gemma":[0.0036782469,0.0002058203,0.0006011554,0.0017140851,0.00026597021,0.0012984885,0.00036798575,0.0006063733,0.00014872017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017884298,0.00011535173,0.0033057982,0.00022316903,0.00018405364,0.000077779,0.00006662594,0.6775478,0.004828303,0.004421002,0.00052851095,0.3085228],"study_design_scores_gemma":[0.000007735716,0.000025885778,0.0005946639,0.00000780804,0.000017202272,0.000010282835,0.0000080124355,0.997387,0.0010321658,0.0006658595,0.00023708897,0.0000063285734],"about_ca_topic_score_codex":0.004922459,"about_ca_topic_score_gemma":0.0036353406,"teacher_disagreement_score":0.004922459,"about_ca_system_score_codex":0.00043232413,"about_ca_system_score_gemma":0.00045517788,"threshold_uncertainty_score":0.009787619},"labels":[],"label_agreement":null},{"id":"W2140806992","doi":"10.1109/icsmc.2007.4414103","title":"Inductive transfer applied to stream discharge modeling","year":2007,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Acadia University","funders":"","keywords":"STREAMS; Transfer function; Transfer (computing); Data modeling; Nova scotia; Computer science; Flood myth; Artificial neural network; Transfer of learning; Streamflow; Discharge; Environmental science; Machine learning; Engineering; Database; Geology","score_opus":0.026398175973476014,"score_gpt":0.246097588245157,"score_spread":0.219699412271681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140806992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018278554,0.00029404473,0.97580826,0.00013043766,0.000035562643,0.000040039635,0.00006195335,0.00076869066,0.004582482],"genre_scores_gemma":[0.84883296,0.00067191856,0.13882774,0.00008282504,0.00010695127,0.0002502009,0.00019027073,0.00014076324,0.010896392],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996717,0.00012797289,0.000017533464,0.000048479367,0.00010154237,0.00003275923],"domain_scores_gemma":[0.99928504,0.0004699166,0.000046336485,0.00006484234,0.000116830015,0.000017027929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075907895,0.0004984608,0.00045434298,0.000596774,0.00032945062,0.0006008553,0.00074931997,0.00049356994,0.0023011107],"category_scores_gemma":[0.0027957775,0.00024567053,0.0004683415,0.0009780839,0.00047797823,0.0007080413,0.00078820955,0.0008068563,0.0005454339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022043449,0.000026305073,0.0004912221,0.000041034196,0.000024704827,0.00008371638,0.000060626862,0.9235462,0.0016604554,0.01066985,0.00039640616,0.06297744],"study_design_scores_gemma":[0.0000010375769,0.0000052987953,0.000053232365,0.0000016740238,0.0000017267414,0.000006383405,0.0000029247633,0.99510753,0.0005118772,0.0038730511,0.00043323176,0.0000020204639],"about_ca_topic_score_codex":0.011389433,"about_ca_topic_score_gemma":0.0044821827,"teacher_disagreement_score":0.011389433,"about_ca_system_score_codex":0.00088572304,"about_ca_system_score_gemma":0.00068055437,"threshold_uncertainty_score":0.022646308},"labels":[],"label_agreement":null},{"id":"W2142157592","doi":"10.1139/a10-021","title":"State-of-the-art and recent progress in phytoplankton succession modelling","year":2010,"lang":"en","type":"article","venue":"Environmental Reviews","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Phytoplankton; Ecological succession; Biomass (ecology); Statistic; Environmental science; Goodness of fit; Ecology; Computer science; Statistics; Mathematics; Machine learning; Biology; Nutrient","score_opus":0.019290517420128293,"score_gpt":0.24773484739804896,"score_spread":0.22844432997792066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142157592","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03142525,0.67118937,0.25365806,0.008496538,0.0016013135,0.00007560379,0.0003929449,0.0008783876,0.0322825],"genre_scores_gemma":[0.16414475,0.71729124,0.10716658,0.000605041,0.0028308886,0.000092882285,0.0007244051,0.00019068658,0.00695355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985605,0.0004924202,0.0001533017,0.00031476564,0.00040621316,0.00007283424],"domain_scores_gemma":[0.991441,0.006469697,0.00046861634,0.0005593175,0.0008963382,0.00016503909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005549122,0.0007474341,0.0011079505,0.0021063106,0.00044058127,0.002978558,0.0025004821,0.0014958576,0.002890984],"category_scores_gemma":[0.008415802,0.00043507133,0.0008870482,0.0040405504,0.0012837352,0.003935708,0.0010999852,0.0013664569,0.0013668538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012596308,0.00013016276,0.0050541325,0.005539134,0.00011418909,0.00009339113,0.00040345063,0.06191301,0.0034142688,0.042620566,0.00606655,0.87452525],"study_design_scores_gemma":[0.000038956085,0.00045974867,0.0107804695,0.0032532301,0.0003417175,0.00071736984,0.00091283704,0.37307268,0.00991722,0.0843332,0.5159225,0.00025005912],"about_ca_topic_score_codex":0.0039168694,"about_ca_topic_score_gemma":0.0024717352,"teacher_disagreement_score":0.005549122,"about_ca_system_score_codex":0.000990121,"about_ca_system_score_gemma":0.0012640951,"threshold_uncertainty_score":0.029346883},"labels":[],"label_agreement":null},{"id":"W2142921995","doi":"10.1175/jhm-d-13-0140.1","title":"Application Potential of Four Nontraditional Similarity Metrics in Hydrometeorology","year":2014,"lang":"en","type":"article","venue":"Journal of Hydrometeorology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Environment and Climate Change Canada","funders":"National Oceanic and Atmospheric Administration; China Meteorological Administration; National Natural Science Foundation of China","keywords":"Hydrometeorology; Similarity (geometry); Metric (unit); Pearson product-moment correlation coefficient; Correlation coefficient; Statistics; Computer science; Mean squared error; Index (typography); Correlation; Mathematics; Data mining; Artificial intelligence; Meteorology; Precipitation","score_opus":0.011320980388045557,"score_gpt":0.21971937699042346,"score_spread":0.2083983966023779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142921995","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096195,0.18925987,0.68528944,0.0018884749,0.000751579,0.00034054863,0.0009226656,0.00067773287,0.024674723],"genre_scores_gemma":[0.75505096,0.042435627,0.1979548,0.00034952437,0.0006804345,0.00035312818,0.0009577443,0.00012790528,0.0020898392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930265,0.0026367528,0.000786433,0.00077669165,0.002640617,0.00013301827],"domain_scores_gemma":[0.9837848,0.01061086,0.0015818874,0.00088437827,0.0028361273,0.00030189138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006096649,0.00091781357,0.0013651722,0.009124896,0.00051717606,0.00305538,0.0017209945,0.0012290681,0.0013030798],"category_scores_gemma":[0.023901688,0.00028212738,0.0011935123,0.0076215807,0.0012881984,0.003062444,0.0017184624,0.00096319575,0.00034158982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019501374,0.00017315545,0.029326573,0.003942594,0.0009523605,0.0003357162,0.0006745021,0.07702972,0.004816139,0.111182705,0.005234847,0.7661367],"study_design_scores_gemma":[0.00009284582,0.0012948428,0.049063392,0.0023752246,0.00087371137,0.00215258,0.0014301827,0.54995334,0.015278079,0.28230795,0.09468424,0.0004935608],"about_ca_topic_score_codex":0.0024958265,"about_ca_topic_score_gemma":0.0013495667,"teacher_disagreement_score":0.009124896,"about_ca_system_score_codex":0.0015071988,"about_ca_system_score_gemma":0.0012619729,"threshold_uncertainty_score":0.032242537},"labels":[],"label_agreement":null},{"id":"W2146931174","doi":"10.7202/018783ar","title":"Utilisation des réseaux de neurones et de la régularisation bayésienne en modélisation de la température de l’eau en rivière","year":2008,"lang":"fr","type":"article","venue":"Revue des sciences de l eau","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Physics; Humanities; Philosophy; Forestry; Geography","score_opus":0.052888738762201466,"score_gpt":0.3118516089442814,"score_spread":0.2589628701820799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146931174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061401706,0.00092526095,0.93422496,0.0003097691,0.00015097472,0.00007169155,0.00016644798,0.0008818384,0.0018672232],"genre_scores_gemma":[0.6315786,0.0010559473,0.35827586,0.0001454257,0.00010724809,0.00031599443,0.000369037,0.00024226513,0.007909706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916136,0.00026817672,0.000056130022,0.00025450753,0.00018182815,0.000077954464],"domain_scores_gemma":[0.99878746,0.00063675485,0.000106718566,0.000106397434,0.0003289421,0.000033771477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026423302,0.0012415414,0.0013745754,0.00064355065,0.0004618827,0.0012061634,0.001191516,0.0014948588,0.001728644],"category_scores_gemma":[0.0050829975,0.0007936368,0.0017837536,0.0006866885,0.0009065135,0.0014880289,0.0007178235,0.0018556206,0.0007244753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012932814,0.000036444188,0.0017592361,0.00013144937,0.00011309243,0.00007203704,0.00013864382,0.90923476,0.006782321,0.0060977144,0.0004908336,0.07501419],"study_design_scores_gemma":[0.000008876128,0.000032584972,0.00051083736,0.000017076665,0.000014896764,0.000017122946,0.000010394332,0.9944185,0.002161671,0.0019856074,0.00080579735,0.000016679556],"about_ca_topic_score_codex":0.025853472,"about_ca_topic_score_gemma":0.014740396,"teacher_disagreement_score":0.025853472,"about_ca_system_score_codex":0.0011953481,"about_ca_system_score_gemma":0.0015526245,"threshold_uncertainty_score":0.051406026},"labels":[],"label_agreement":null},{"id":"W2147733258","doi":"10.2166/nh.2012.040","title":"Downscaling of precipitation on a lake basin: evaluation of rule and decision tree induction algorithms","year":2012,"lang":"en","type":"article","venue":"Hydrology research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Downscaling; Commit; Decision tree; Precipitation; Climatology; Environmental science; Algorithm; Arid; Scale (ratio); Computer science; Meteorology; Machine learning; Geology; Geography; Cartography","score_opus":0.1548218177192235,"score_gpt":0.40263452213223816,"score_spread":0.24781270441301467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147733258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9539039,0.00040636613,0.04217223,0.00016809267,0.000033180826,0.00010562075,0.00033511958,0.00072592805,0.0021495332],"genre_scores_gemma":[0.95003664,0.00016418539,0.04884305,0.00003718073,0.000012521115,0.00005256721,0.00052453467,0.000037386813,0.00029180525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995597,0.0001772364,0.000046491015,0.0000828118,0.00009205915,0.000041623156],"domain_scores_gemma":[0.99616146,0.0028165143,0.00020070533,0.0002044349,0.00052900554,0.000087866836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025473214,0.00063190464,0.00067419856,0.00067210523,0.00029568071,0.00043487485,0.00085749035,0.00059882825,0.0006850551],"category_scores_gemma":[0.006141962,0.00020578204,0.0004362695,0.00080713775,0.0002584082,0.000901342,0.0004866321,0.00061622524,0.00013637896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004920475,0.00029643474,0.013321684,0.000110640874,0.00011122093,0.00005452106,0.00007256234,0.8640833,0.0021612083,0.00048154304,0.00053184485,0.11828294],"study_design_scores_gemma":[0.000024642832,0.00008982206,0.0015882866,0.0000032836558,0.000014088519,0.0000051368374,0.000015246009,0.99616927,0.0018812722,0.00014021159,0.00006531267,0.0000035418614],"about_ca_topic_score_codex":0.012243402,"about_ca_topic_score_gemma":0.0093687065,"teacher_disagreement_score":0.012243402,"about_ca_system_score_codex":0.000663765,"about_ca_system_score_gemma":0.0008620412,"threshold_uncertainty_score":0.024344265},"labels":[],"label_agreement":null},{"id":"W2148300238","doi":"10.1007/s10666-015-9468-0","title":"Predicting Nitrate Concentration and Its Spatial Distribution in Groundwater Resources Using Support Vector Machines (SVMs) Model","year":2015,"lang":"en","type":"article","venue":"Environmental Modeling & Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":118,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Support vector machine; Groundwater; Nitrate; Aquifer; Water quality; Environmental science; Soil science; Hydrology (agriculture); Machine learning; Computer science; Engineering; Chemistry; Geotechnical engineering; Ecology","score_opus":0.03776025100581817,"score_gpt":0.27109576401941476,"score_spread":0.2333355130135966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148300238","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8249741,0.00045703104,0.17169204,0.0003131902,0.00011418837,0.000019024608,0.00046051366,0.00045023474,0.0015197207],"genre_scores_gemma":[0.99405116,0.0000788591,0.0050107683,0.000015139126,0.00002189124,0.000009169883,0.00016760753,0.0000040465306,0.00064129784],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998385,0.000024264718,0.000014357982,0.000058790578,0.00003629631,0.000027811095],"domain_scores_gemma":[0.9996542,0.000158029,0.000050021008,0.000016714595,0.00010192605,0.000019118545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003428959,0.0003756858,0.0006024256,0.00038819283,0.00020393229,0.00045027907,0.00052921736,0.0006865217,0.00048051064],"category_scores_gemma":[0.00082590105,0.00021185263,0.0005428856,0.0006766417,0.00016242574,0.0005755257,0.00021933914,0.0004332053,0.00012484893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003064153,0.00020885072,0.037532594,0.000086343636,0.000103072976,0.00017204283,0.00004306353,0.86718225,0.006044244,0.0009407699,0.0017652906,0.08561502],"study_design_scores_gemma":[0.0000019612196,0.000008742935,0.0011395545,7.2398404e-7,0.0000037982488,0.000004754662,0.0000039373763,0.9983896,0.00028352448,0.00013361251,0.00002797355,0.0000018824476],"about_ca_topic_score_codex":0.01478936,"about_ca_topic_score_gemma":0.008836628,"teacher_disagreement_score":0.01478936,"about_ca_system_score_codex":0.00039979332,"about_ca_system_score_gemma":0.00049473596,"threshold_uncertainty_score":0.029406607},"labels":[],"label_agreement":null},{"id":"W2148808859","doi":"10.5194/hess-16-1151-2012","title":"Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia","year":2012,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"Ministério da Ciência, Tecnologia e Inovação; Kementerian Sains, Teknologi dan Inovasi","keywords":"Artificial neural network; Computer science; Perceptron; Multilayer perceptron; Radial basis function; Data mining; Activation function; Artificial intelligence","score_opus":0.04857763577447536,"score_gpt":0.25368065729000505,"score_spread":0.2051030215155297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148808859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.914682,0.0011253981,0.07619254,0.0005180955,0.00014270876,0.00005787705,0.00051562133,0.0003465472,0.006419154],"genre_scores_gemma":[0.99598193,0.00015293721,0.002257464,0.000012107567,0.00000864624,0.00002181427,0.00012420195,0.0000046688183,0.0014362826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982363,0.000046503865,0.000014570608,0.00005796365,0.000030803996,0.000026586991],"domain_scores_gemma":[0.9997247,0.000093837705,0.000033432327,0.000010762369,0.00012049656,0.000016777212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055543496,0.00064094464,0.0004972547,0.00053375924,0.0002796945,0.0008068541,0.00091524917,0.0006808197,0.0011156922],"category_scores_gemma":[0.0009839062,0.00027581427,0.00048772042,0.00043568187,0.00026729365,0.00079288316,0.0003605091,0.0005838664,0.00012589715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007470241,0.000035325746,0.0037515566,0.00003874117,0.000029334595,0.00006628431,0.000019120069,0.98746955,0.0006092825,0.00044256763,0.00024859185,0.007214855],"study_design_scores_gemma":[0.0000021962585,0.000012747137,0.000544685,0.0000023671623,0.0000048207107,0.0000031342825,0.0000061188616,0.9991829,0.00012068316,0.00008012962,0.00003770586,0.000002566604],"about_ca_topic_score_codex":0.039025977,"about_ca_topic_score_gemma":0.021175109,"teacher_disagreement_score":0.039025977,"about_ca_system_score_codex":0.0011345721,"about_ca_system_score_gemma":0.000853841,"threshold_uncertainty_score":0.07759762},"labels":[],"label_agreement":null},{"id":"W2149006894","doi":"10.1139/s02-014","title":"Developing artificial neural network models of water treatment processes: a guide for utilities","year":2002,"lang":"en","type":"article","venue":"Journal of Environmental Engineering and Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Process (computing); Computer science; Key (lock); Artificial intelligence; Process modeling; Unit operation; Machine learning; Biochemical engineering; Work in process; Engineering; Operations management","score_opus":0.040643011640211675,"score_gpt":0.22203223474139347,"score_spread":0.1813892231011818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149006894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012431155,0.010291019,0.9656771,0.002150594,0.0005133626,0.00047478348,0.0025536015,0.0033786132,0.013717755],"genre_scores_gemma":[0.00888494,0.017870089,0.9377548,0.0005624918,0.00032037505,0.0019814475,0.0035881756,0.00052709406,0.028510485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997166,0.00009056084,0.00004344498,0.00003394173,0.00010477667,0.00001058333],"domain_scores_gemma":[0.99900347,0.00047548304,0.00007105374,0.000061872364,0.0003455291,0.000042645075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012940395,0.0020641466,0.0011025313,0.0017901746,0.00040004626,0.0012785041,0.002328325,0.0023794726,0.013185711],"category_scores_gemma":[0.002849594,0.0014527846,0.0007511514,0.0016612635,0.00051632663,0.0019056104,0.0009898957,0.0027826924,0.009198573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060873223,0.00029255866,0.0007562765,0.0018831757,0.00011488929,0.00046562703,0.00025349646,0.27232805,0.0060415114,0.057854276,0.19163477,0.46831453],"study_design_scores_gemma":[0.00006782187,0.00012363898,0.0009540318,0.0009034905,0.00003826878,0.00025956196,0.0001304245,0.4437581,0.002580411,0.10930159,0.44178906,0.000093662675],"about_ca_topic_score_codex":0.005492475,"about_ca_topic_score_gemma":0.009488469,"teacher_disagreement_score":0.013185711,"about_ca_system_score_codex":0.000774203,"about_ca_system_score_gemma":0.0014424936,"threshold_uncertainty_score":0.044110596},"labels":[],"label_agreement":null},{"id":"W2151186326","doi":"10.5194/hess-16-2253-2012","title":"Record extension for short-gauged water quality parameters using a newly proposed robust version of the Line of Organic Correlation technique","year":2012,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Monte Carlo method; Skewness; Ordinary least squares; Percentile; Statistics; Robust regression; Variance (accounting); Econometrics; Computer science; Regression; Mathematics; Accounting","score_opus":0.06660578083599136,"score_gpt":0.27294798493867223,"score_spread":0.20634220410268087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151186326","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01928591,0.0002278517,0.97883123,0.00006389561,0.000048676393,0.000040243922,0.00020290149,0.00058096094,0.0007183453],"genre_scores_gemma":[0.27864772,0.0004737137,0.7167659,0.00009409783,0.00015501879,0.00014659467,0.0012293892,0.00026054317,0.0022270258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874926,0.00028179944,0.00008508588,0.0002670233,0.0005339562,0.00008281089],"domain_scores_gemma":[0.99603623,0.0011594516,0.0009628403,0.000607382,0.0011462931,0.000087884444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001821458,0.00066840736,0.00054667157,0.0014626106,0.00031234176,0.00078634295,0.0009785496,0.0005426593,0.001566747],"category_scores_gemma":[0.0070737656,0.00023220146,0.00097569806,0.0023263355,0.000346589,0.0011986312,0.0010309117,0.0009376067,0.00071756355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037087334,0.00018162424,0.01707699,0.00040245827,0.00042326192,0.00042686932,0.0002893164,0.15256825,0.034082826,0.014624316,0.0043849866,0.77516824],"study_design_scores_gemma":[0.000034966914,0.0002762458,0.011427849,0.00004520806,0.00013836607,0.00043833765,0.000076620534,0.9541768,0.016956031,0.003812565,0.012487275,0.00012979054],"about_ca_topic_score_codex":0.0028568413,"about_ca_topic_score_gemma":0.0030820975,"teacher_disagreement_score":0.0028568413,"about_ca_system_score_codex":0.00028794515,"about_ca_system_score_gemma":0.0009267199,"threshold_uncertainty_score":0.009632885},"labels":[],"label_agreement":null},{"id":"W2154250668","doi":"10.1139/s03-071","title":"An exploration of artificial neural network rainfall-runoff forecasting combined with wavelet decomposition","year":2004,"lang":"en","type":"article","venue":"Journal of Environmental Engineering and Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Morlet wavelet; Wavelet; Artificial neural network; Wavelet transform; Surface runoff; Computer science; Series (stratigraphy); Artificial intelligence; Environmental science; Discrete wavelet transform; Geology; Ecology","score_opus":0.01852569919110066,"score_gpt":0.21913622043707673,"score_spread":0.20061052124597606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154250668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58360314,0.0023819748,0.40593335,0.00073154684,0.000111618916,0.00005683034,0.00006884582,0.000412632,0.006700106],"genre_scores_gemma":[0.95385486,0.0006176311,0.044638343,0.000030139714,0.000029028124,0.000023400684,0.000043834963,0.000013111781,0.00074972725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969614,0.00015173359,0.0000125349725,0.000024658884,0.0000955807,0.000019457491],"domain_scores_gemma":[0.99961394,0.00028478843,0.000021144748,0.000017303784,0.00005310762,0.000009817422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011631902,0.00041143803,0.00039785184,0.0004454744,0.00009515069,0.00044649496,0.00026126305,0.00039919885,0.00046519953],"category_scores_gemma":[0.0023278897,0.00017174882,0.0002714513,0.00053154764,0.0001609827,0.0008376357,0.0002487359,0.00034489625,0.00009817445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006132846,0.00025688607,0.008249836,0.00021662735,0.00025176266,0.00017931366,0.00007559881,0.6443287,0.017609574,0.0050286786,0.00052247714,0.32266724],"study_design_scores_gemma":[0.000009443913,0.0001025864,0.0010694647,0.000008234354,0.000020889407,0.000023459059,0.000008100517,0.995388,0.002135881,0.00096131145,0.00026809477,0.000004619402],"about_ca_topic_score_codex":0.0013380776,"about_ca_topic_score_gemma":0.0013660274,"teacher_disagreement_score":0.0013380776,"about_ca_system_score_codex":0.00024632702,"about_ca_system_score_gemma":0.0002411838,"threshold_uncertainty_score":0.006151557},"labels":[],"label_agreement":null},{"id":"W2154740986","doi":"10.1175/2008jtecho569.1","title":"Development of an Atlantic Canadian Coastal Water Level Neural Network Model","year":2008,"lang":"en","type":"article","venue":"Journal of Atmospheric and Oceanic Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Fisheries and Oceans Canada","funders":"","keywords":"Artificial neural network; Environmental science; Term (time); Bathymetry; Water level; Oceanography; Climatology; Meteorology; Computer science; Geography; Geology; Machine learning; Cartography","score_opus":0.021469764082083693,"score_gpt":0.20591298762020765,"score_spread":0.18444322353812395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154740986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2068664,0.00070843415,0.7430579,0.000869279,0.00022366019,0.000254848,0.0018407113,0.0013875158,0.044791345],"genre_scores_gemma":[0.9203525,0.00027394778,0.06229245,0.00009024332,0.000026395885,0.00024259016,0.00088851555,0.000047251684,0.015786057],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998827,0.000013307732,0.000004908849,0.00003101689,0.000044471908,0.00002358592],"domain_scores_gemma":[0.9998504,0.000020740119,0.000010478075,0.000004395005,0.00010439151,0.00000950563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027465177,0.000548329,0.00027792918,0.00034583762,0.0004924301,0.00067276886,0.0011789179,0.0006466195,0.0016704027],"category_scores_gemma":[0.00051518634,0.00029708678,0.0003187441,0.00043349885,0.0002453035,0.0003553334,0.0004948508,0.00062194647,0.00034362677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011084587,0.000008387666,0.000966154,0.000010758447,0.000009519183,0.000035918034,0.000010064182,0.98801523,0.0005478892,0.00096498505,0.00056724163,0.008852811],"study_design_scores_gemma":[0.0000011136046,0.0000020528357,0.00013196176,0.0000014022667,0.0000024235073,0.0000016503623,0.0000021901728,0.99943405,0.00011103639,0.00010612379,0.00020454607,0.0000014581045],"about_ca_topic_score_codex":0.4687604,"about_ca_topic_score_gemma":0.39074695,"teacher_disagreement_score":0.5312396,"about_ca_system_score_codex":0.0026043765,"about_ca_system_score_gemma":0.003627389,"threshold_uncertainty_score":0.9320638},"labels":[],"label_agreement":null},{"id":"W2157041867","doi":"10.5194/hess-14-603-2010","title":"An experiment on the evolution of an ensemble of neural networks for streamflow forecasting","year":2010,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Ensemble learning; Artificial neural network; Confidence interval; Ensemble forecasting; Reliability (semiconductor); Computer science; Streamflow; Perceptron; Neural ensemble; Statistics; Artificial intelligence; Mathematics; Drainage basin","score_opus":0.027155535319845856,"score_gpt":0.2480457906401564,"score_spread":0.22089025532031054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157041867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932653,0.000100234305,0.005673039,0.000068398855,0.00003966089,0.000026229327,0.000094219264,0.00020599487,0.00052702177],"genre_scores_gemma":[0.99449545,0.000023613358,0.005037733,0.000024782486,0.000007897945,0.000024433662,0.00011574752,0.000011472487,0.0002588166],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995147,0.00016821323,0.000049648304,0.00010905063,0.00009418493,0.000064197186],"domain_scores_gemma":[0.9966382,0.0018914354,0.00015896093,0.00048349035,0.0006097583,0.00021818538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021644908,0.00051079737,0.0005943301,0.00037316736,0.00037438067,0.00045464153,0.0005490551,0.00095642835,0.00086720806],"category_scores_gemma":[0.0049345423,0.0003002772,0.0004505036,0.0003185442,0.00033358013,0.00078335626,0.0004999995,0.0010771444,0.00017977123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026153908,0.0019527818,0.029432608,0.00023741068,0.0004957496,0.00044438266,0.00043212553,0.7979658,0.061424427,0.0008593458,0.0015500607,0.102589846],"study_design_scores_gemma":[0.000051736333,0.0015210513,0.01002892,0.00001672724,0.000065205364,0.000051248997,0.00006241777,0.9646578,0.022814276,0.00034875763,0.00035896315,0.000022934706],"about_ca_topic_score_codex":0.0032800634,"about_ca_topic_score_gemma":0.0028376617,"teacher_disagreement_score":0.0032800634,"about_ca_system_score_codex":0.00036868892,"about_ca_system_score_gemma":0.00022763466,"threshold_uncertainty_score":0.011447072},"labels":[],"label_agreement":null},{"id":"W2158846206","doi":"10.1152/ajpheart.00510.2002","title":"Branching tree model with fractal vascular resistance explains fractal perfusion heterogeneity","year":2003,"lang":"en","type":"article","venue":"American Journal of Physiology-Heart and Circulatory Physiology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Fractal; Branching (polymer chemistry); Asymmetry; Fractal analysis; Fractal dimension; Statistical physics; Perfusion; Mathematics; Biological system; Physics; Mathematical analysis; Materials science; Biology; Cardiology; Medicine","score_opus":0.011593695082997181,"score_gpt":0.2247579593751649,"score_spread":0.21316426429216773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158846206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4533196,0.0009159378,0.5237815,0.0009722109,0.00010047203,0.00004649775,0.00021073462,0.00061057776,0.020042483],"genre_scores_gemma":[0.9870726,0.00024682048,0.009466615,0.00005581029,0.000045631554,0.00002946723,0.000052105217,0.000049490987,0.0029813347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987423,0.00003590307,0.0000045397696,0.000022041937,0.000030066045,0.000033279917],"domain_scores_gemma":[0.99932647,0.0002889948,0.0001371092,0.000054540345,0.00009155356,0.00010131097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004254121,0.00037576104,0.0005449677,0.00083109445,0.0003443796,0.0007123992,0.00069510227,0.0009541329,0.0013640437],"category_scores_gemma":[0.0014892238,0.0002342526,0.0006199607,0.0005035119,0.00084765785,0.0009788885,0.00042424919,0.00053615554,0.000255613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058273185,0.000035212655,0.0018360901,0.000038779606,0.00002571831,0.0004280903,0.00017127606,0.8256283,0.011058325,0.1532621,0.0011733182,0.00628449],"study_design_scores_gemma":[0.0000053486137,0.0000070106544,0.00024228936,0.0000021223073,0.0000041293692,0.000058157544,0.0000049979994,0.9796513,0.00011315648,0.01966478,0.00024006591,0.000006649573],"about_ca_topic_score_codex":0.0025801114,"about_ca_topic_score_gemma":0.001161484,"teacher_disagreement_score":0.0025801114,"about_ca_system_score_codex":0.00072237017,"about_ca_system_score_gemma":0.00038921073,"threshold_uncertainty_score":0.0052411556},"labels":[],"label_agreement":null},{"id":"W2159095923","doi":"10.2166/hydro.2005.0017","title":"Fuzzy set based error measure for hydrologic model evaluation","year":2005,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Measure (data warehouse); Mean squared error; Computer science; Set (abstract data type); Fuzzy logic; Model selection; Selection (genetic algorithm); Data mining; Process (computing); Fuzzy set; Field (mathematics); Approximation error; Machine learning; Artificial intelligence; Statistics; Mathematics; Algorithm","score_opus":0.07446884223505057,"score_gpt":0.3084995074916717,"score_spread":0.23403066525662114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159095923","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012996472,0.00066169264,0.98290956,0.000128209,0.00009989555,0.00013603388,0.00013290788,0.00022493783,0.002710408],"genre_scores_gemma":[0.32330555,0.0006546833,0.673452,0.000092800496,0.000103708546,0.00055501534,0.00047922897,0.000097654185,0.0012593628],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97988087,0.007242862,0.0018216778,0.0008776773,0.009871221,0.00030574683],"domain_scores_gemma":[0.95421237,0.031503327,0.0025593569,0.0030180877,0.008388032,0.000318816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02462258,0.001211468,0.001472233,0.0055427845,0.00072418986,0.0027653396,0.0018606439,0.0016828353,0.001458495],"category_scores_gemma":[0.06663841,0.00027630987,0.0012434088,0.0036093914,0.0012636146,0.0025548185,0.0015143299,0.0017521698,0.0003151252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043886926,0.00020692575,0.0058166413,0.0005206143,0.00031829308,0.00015938036,0.00029447913,0.6677325,0.00526562,0.08874167,0.0027487606,0.22775635],"study_design_scores_gemma":[0.000027164888,0.00025353555,0.0015770501,0.000105459374,0.000051198564,0.00013275261,0.00008754762,0.96570957,0.0052704555,0.023678206,0.00302933,0.000077702236],"about_ca_topic_score_codex":0.0024583042,"about_ca_topic_score_gemma":0.0015145376,"teacher_disagreement_score":0.02462258,"about_ca_system_score_codex":0.0018999198,"about_ca_system_score_gemma":0.0013310792,"threshold_uncertainty_score":0.13021815},"labels":[],"label_agreement":null},{"id":"W2166210698","doi":"10.5194/hess-13-1607-2009","title":"River flow forecasting with artificial neural networks using satellite observed precipitation pre-processed with flow length and travel time information: case study of the Ganges river basin","year":2009,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Precipitation; Flow (mathematics); Streamflow; Artificial neural network; Hydrological modelling; Environmental science; Computer science; Drainage basin; Meteorology; Geology; Machine learning; Climatology; Mathematics; Geography","score_opus":0.03461581209108301,"score_gpt":0.21544619200162382,"score_spread":0.1808303799105408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166210698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99602926,0.000065207336,0.0028498229,0.00009548474,0.000009129565,0.000013922624,0.00010145907,0.00007290066,0.0007627867],"genre_scores_gemma":[0.9973259,0.000053137872,0.0021774645,0.000008064579,0.000006691881,0.000011051075,0.000107204876,0.000003957261,0.00030651406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998074,0.00008343161,0.000012379661,0.000030100844,0.000042465836,0.000024292442],"domain_scores_gemma":[0.9992094,0.00052849366,0.00005499035,0.000055236436,0.0001185778,0.00003331239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005231086,0.0005060758,0.00032885408,0.00055870437,0.00031980456,0.00045896278,0.00047213765,0.0006306142,0.0004628521],"category_scores_gemma":[0.0013279092,0.00018172868,0.00035723177,0.00083282863,0.00030322134,0.00042103152,0.00028285835,0.00051125936,0.00006333504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002367073,0.00037591718,0.033017315,0.00007907845,0.00008030245,0.0012460931,0.00010018909,0.93400866,0.0025845862,0.0002702022,0.0004104187,0.027590511],"study_design_scores_gemma":[0.000020164201,0.00008348319,0.016062696,0.0000068267364,0.000019048162,0.000026905624,0.0000638152,0.9816632,0.0016670646,0.0001805794,0.00019568144,0.000010507995],"about_ca_topic_score_codex":0.0353977,"about_ca_topic_score_gemma":0.03231079,"teacher_disagreement_score":0.0353977,"about_ca_system_score_codex":0.000685108,"about_ca_system_score_gemma":0.00049618183,"threshold_uncertainty_score":0.07038337},"labels":[],"label_agreement":null},{"id":"W2167220065","doi":"10.7202/705507ar","title":"Short-term hydrological forecasts using linear regression / Prévisions hydrologiques à court terme obtenues en utilisant la régression linéaire","year":2005,"lang":"en","type":"article","venue":"Revue des sciences de l eau","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Term (time); Simple linear regression; Mathematics; Linear regression; Statistics; Correlation coefficient; Regression; Econometrics; Applied mathematics; Physics","score_opus":0.11674638574078253,"score_gpt":0.36819796444695535,"score_spread":0.25145157870617285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167220065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12048089,0.00030333435,0.870856,0.0002260565,0.000054609765,0.00009364444,0.0006899708,0.0032729101,0.004022657],"genre_scores_gemma":[0.7419323,0.00044885933,0.2507393,0.000050429608,0.0000694378,0.00014410999,0.0009898397,0.00013775866,0.0054880497],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923766,0.00037130425,0.000050473613,0.00012527868,0.00017528668,0.000039902065],"domain_scores_gemma":[0.99805105,0.001258059,0.00026672037,0.00014373823,0.00024788768,0.000032575597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002293629,0.00049541384,0.0005219832,0.0007051737,0.00021209983,0.00087425153,0.00056928385,0.00042745576,0.0023252587],"category_scores_gemma":[0.0053436314,0.000263349,0.00042569768,0.0009830194,0.00024025954,0.0013656528,0.0002941593,0.0007604003,0.00096542935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025373008,0.00007795928,0.0049838824,0.000117182644,0.00007942854,0.000038817772,0.000083684376,0.8322819,0.004491412,0.0038661421,0.0010385234,0.15268737],"study_design_scores_gemma":[0.000017676011,0.000058713005,0.0012846739,0.000008177971,0.000017720164,0.000015924128,0.00001230526,0.9934603,0.002567824,0.0015686572,0.00096487545,0.000023061693],"about_ca_topic_score_codex":0.012264797,"about_ca_topic_score_gemma":0.011347326,"teacher_disagreement_score":0.012264797,"about_ca_system_score_codex":0.00063956773,"about_ca_system_score_gemma":0.0007335323,"threshold_uncertainty_score":0.024386823},"labels":[],"label_agreement":null},{"id":"W2167953680","doi":"10.4138/atlgeol.2009.009","title":"Inductive Transfer Applied to Modeling River Discharge in Nova Scotia","year":2010,"lang":"en","type":"article","venue":"Atlantic Geology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Acadia University","funders":"Natural Sciences and Engineering Research Council of Canada; Acadia University","keywords":"Nova scotia; STREAMS; Discharge; Streamflow; Scope (computer science); Fluvial; Transfer function; Environmental science; Hydrology (agriculture); Computer science; Drainage basin; Geology; Geography; Cartography; Geomorphology; Oceanography; Engineering","score_opus":0.017497340637353438,"score_gpt":0.23092803468023151,"score_spread":0.21343069404287807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167953680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96992177,0.00012506933,0.025621338,0.00019197086,0.000023761562,0.00005809678,0.00018476664,0.00023667038,0.003636599],"genre_scores_gemma":[0.9933193,0.000044803106,0.004644163,0.000019217843,0.000003687525,0.000029364164,0.00013064781,0.00000943182,0.001799541],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998801,0.00003643412,0.0000082436145,0.000027656277,0.000021242025,0.00002635296],"domain_scores_gemma":[0.99956924,0.0002441774,0.000033043492,0.000021021557,0.00011424193,0.00001831163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005302082,0.0004146251,0.00020587505,0.00024827366,0.000367947,0.0004947117,0.0004919997,0.00035942177,0.0006979004],"category_scores_gemma":[0.0016568619,0.00020093574,0.0003045067,0.00029547105,0.00036853377,0.00021164911,0.00042894526,0.0004126671,0.00012297418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038440325,0.00002231285,0.0082258675,0.000012818436,0.000016588034,0.00009973639,0.000060874263,0.98067826,0.000805775,0.00020535135,0.00012763718,0.009706228],"study_design_scores_gemma":[0.000002889699,0.0000136623385,0.0035987056,0.0000027072838,0.0000032569799,0.0000051509046,0.000023690727,0.99561524,0.00048812083,0.00011901676,0.00012431368,0.0000032041985],"about_ca_topic_score_codex":0.54369956,"about_ca_topic_score_gemma":0.4650309,"teacher_disagreement_score":0.45630044,"about_ca_system_score_codex":0.0024751106,"about_ca_system_score_gemma":0.0017887052,"threshold_uncertainty_score":0.91797537},"labels":[],"label_agreement":null},{"id":"W2169204502","doi":"10.1111/j.1752-1688.2000.tb04291.x","title":"ARTIFICIAL NEURAL NETWORKS FOR SUBSURFACE DRAINAGE AND SUBIRRIGATION SYSTEMS IN ONTARIO, CANADA<sup>1</sup>","year":2000,"lang":"en","type":"article","venue":"JAWRA Journal of the American Water Resources Association","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Agriculture and Agri-Food Canada","funders":"","keywords":"Water table; Drainage; Evapotranspiration; Hydrology (agriculture); Artificial neural network; Loam; Environmental science; Table (database); Mean squared error; Water level; Soil science; Geology; Computer science; Geotechnical engineering; Soil water; Groundwater; Machine learning; Statistics; Mathematics; Data mining","score_opus":0.008067832635858904,"score_gpt":0.1904270787263428,"score_spread":0.18235924609048387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169204502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95339435,0.0005444049,0.03085353,0.0007777589,0.00004612195,0.000100948484,0.0018413933,0.00049564516,0.011945819],"genre_scores_gemma":[0.98830813,0.00018508274,0.0062042596,0.000019729398,0.000005257428,0.000033534598,0.0009274997,0.000012884969,0.0043036984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99988484,0.00001477451,0.0000069200064,0.000022159275,0.000040333354,0.000030974268],"domain_scores_gemma":[0.99964154,0.0000918287,0.000029765994,0.000008222695,0.0002074921,0.000021135127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002818204,0.0004291293,0.00018614998,0.0003504366,0.00064860407,0.00049567013,0.00054190675,0.0003818869,0.0019530738],"category_scores_gemma":[0.001117822,0.00015657693,0.00019662798,0.0006617334,0.00024735878,0.00029420754,0.00022998468,0.00028627104,0.00020862573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013443289,0.000047749105,0.035914842,0.0000791497,0.000033933895,0.00013695733,0.00011127334,0.91580737,0.0011333245,0.00088159874,0.0031249328,0.04259441],"study_design_scores_gemma":[0.000010460991,0.000012269682,0.009357925,0.000007099265,0.000008669233,0.000007496702,0.00005946109,0.988526,0.00050597,0.00033102324,0.0011672345,0.0000062913637],"about_ca_topic_score_codex":0.93884784,"about_ca_topic_score_gemma":0.93936706,"teacher_disagreement_score":0.06115216,"about_ca_system_score_codex":0.011777332,"about_ca_system_score_gemma":0.0066712284,"threshold_uncertainty_score":0.12302452},"labels":[],"label_agreement":null},{"id":"W2169739876","doi":"10.1111/j.1752-1688.2011.00588.x","title":"Predicting the Hypoxic-Volume in Chesapeake Bay with the Streeter-Phelps Model: A Bayesian Approach1","year":2011,"lang":"en","type":"article","venue":"JAWRA Journal of the American Water Resources Association","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Center for Sponsored Coastal Ocean Research; National Oceanic and Atmospheric Administration","keywords":"Chesapeake bay; Bayesian probability; Prior probability; Model selection; Environmental science; Computer science; Statistics; Mathematics; Artificial intelligence; Estuary; Oceanography; Geology","score_opus":0.012987638125007184,"score_gpt":0.18583208823317116,"score_spread":0.17284445010816396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169739876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8045049,0.0002781961,0.19076067,0.00095930294,0.000024141586,0.000105708205,0.0008228639,0.00017238437,0.002371791],"genre_scores_gemma":[0.98036516,0.00013052355,0.017920481,0.00006248169,0.000032707685,0.000068733665,0.00047368012,0.000017637221,0.0009285375],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946064,0.00021245523,0.000026469936,0.00017511426,0.000071477145,0.00005381703],"domain_scores_gemma":[0.99571097,0.0031867074,0.0005237421,0.00011247621,0.00032080626,0.000145318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031914224,0.00075057603,0.0008148976,0.0011765967,0.0005842767,0.0013963119,0.0015259149,0.0015562278,0.0013381636],"category_scores_gemma":[0.008547357,0.0007664983,0.00090501056,0.0006995921,0.0009102655,0.0012961265,0.0010924513,0.001150608,0.00017413391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006212165,0.00003568071,0.014402459,0.000021319502,0.00004860695,0.00007196492,0.000068708774,0.9770528,0.000496732,0.0026826167,0.00033292177,0.0047240304],"study_design_scores_gemma":[0.000007256626,0.000016990018,0.0024095762,0.000004813732,0.000010541758,0.000008806885,0.000015378886,0.99582195,0.00008348961,0.0015391608,0.00007020038,0.00001185807],"about_ca_topic_score_codex":0.040491164,"about_ca_topic_score_gemma":0.02807284,"teacher_disagreement_score":0.040491164,"about_ca_system_score_codex":0.0014259991,"about_ca_system_score_gemma":0.0011530943,"threshold_uncertainty_score":0.080510974},"labels":[],"label_agreement":null},{"id":"W2169793408","doi":"10.1623/hysj.52.3.508","title":"Seasonal reservoir inflow forecasting with low-frequency climatic indices: a comparison of data-driven methods","year":2007,"lang":"en","type":"article","venue":"Hydrological Sciences Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"","keywords":"Perceptron; Inflow; Artificial neural network; El Niño Southern Oscillation; Environmental science; Climatology; Multilayer perceptron; Series (stratigraphy); Time series; Computer science; Meteorology; Machine learning; Geography; Geology","score_opus":0.15602537363320654,"score_gpt":0.39754467212180755,"score_spread":0.24151929848860101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169793408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36115837,0.0012403768,0.62911576,0.00090415153,0.00021166685,0.00020081576,0.00067388546,0.0012748678,0.00522007],"genre_scores_gemma":[0.90320796,0.00035975658,0.094739355,0.00011264318,0.000056620458,0.00012026489,0.0006115669,0.00005007027,0.0007418253],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992316,0.00038530855,0.00006220163,0.000087586624,0.00020518877,0.000028127582],"domain_scores_gemma":[0.99610895,0.002647157,0.00021318054,0.00018837821,0.0007657593,0.000076600285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035672432,0.00056058704,0.0005820065,0.000896577,0.0001633963,0.0007915968,0.0008601045,0.0006338318,0.0006734475],"category_scores_gemma":[0.00861829,0.0004011182,0.00057206734,0.0006810715,0.00016468782,0.0010166265,0.0005188613,0.00057046686,0.0001743607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053859735,0.00035983842,0.01788932,0.00021740785,0.00036623023,0.0000645384,0.000083272025,0.7394329,0.0023656613,0.0024134878,0.0008171278,0.23545162],"study_design_scores_gemma":[0.000017939978,0.000027942979,0.0010665553,0.0000075271078,0.000010155672,0.000005302137,0.000005857998,0.99762946,0.00067013694,0.0003790586,0.00017289381,0.00000719453],"about_ca_topic_score_codex":0.006771967,"about_ca_topic_score_gemma":0.0065709413,"teacher_disagreement_score":0.006771967,"about_ca_system_score_codex":0.000599779,"about_ca_system_score_gemma":0.0008337339,"threshold_uncertainty_score":0.018865645},"labels":[],"label_agreement":null},{"id":"W2170460777","doi":"10.1007/s11269-015-1103-y","title":"Modeling the Relationship between Catchment Attributes and In-stream Water Quality","year":2015,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Water quality; Land cover; Hydrology (agriculture); Hydrogeology; Drainage basin; Environmental science; Land use; Linear regression; Regression analysis; Mathematics; Statistics; Geology; Geography; Ecology; Cartography; Civil engineering; Engineering","score_opus":0.11121156760448567,"score_gpt":0.288806920926414,"score_spread":0.17759535332192836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170460777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82167304,0.00022047774,0.17240584,0.0005846276,0.000084006715,0.000039292772,0.0009382389,0.00038783645,0.0036666396],"genre_scores_gemma":[0.99347997,0.0001092338,0.0050138007,0.00002104869,0.000023763061,0.00001605009,0.00020816912,0.000009895975,0.0011179666],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9998435,0.000042565815,0.00001102648,0.0000477295,0.000024799503,0.000030324829],"domain_scores_gemma":[0.99873537,0.000933305,0.00012434178,0.000045502875,0.00010912345,0.000052319378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006755933,0.00037548674,0.00041065257,0.000612257,0.0002317843,0.00083000626,0.00066109456,0.0006729301,0.0013222037],"category_scores_gemma":[0.0029241964,0.0003647307,0.0003448264,0.0014190705,0.00031867693,0.0011149028,0.0002678447,0.00084616133,0.00015043223],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002560984,0.000051451712,0.0114556635,0.000012719025,0.000029479048,0.000026344556,0.00001828405,0.98128295,0.00040768454,0.001203922,0.00016457765,0.0053213253],"study_design_scores_gemma":[0.0000012357605,0.0000032127557,0.00077980343,3.5874166e-7,0.0000037613502,0.000001823937,0.000002717806,0.99869883,0.00005246005,0.0004226853,0.000031798427,0.0000012022388],"about_ca_topic_score_codex":0.025942273,"about_ca_topic_score_gemma":0.027209012,"teacher_disagreement_score":0.025942273,"about_ca_system_score_codex":0.00080639205,"about_ca_system_score_gemma":0.0006978209,"threshold_uncertainty_score":0.051582515},"labels":[],"label_agreement":null},{"id":"W2170856142","doi":"10.5194/hess-15-841-2011","title":"Generalized versus non-generalized neural network model for multi-lead inflow forecasting at Aswan High Dam","year":2011,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"Ministério da Ciência, Tecnologia e Inovação; Natural Sciences and Engineering Research Council of Canada; Kementerian Sains, Teknologi dan Inovasi","keywords":"Generalization; Artificial neural network; Computer science; Inflow; Autocorrelation; Series (stratigraphy); Autoregressive model; Time series; Artificial intelligence; Recurrent neural network; Machine learning; Algorithm; Mathematics; Statistics","score_opus":0.1370527839266229,"score_gpt":0.2714770268651666,"score_spread":0.13442424293854371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170856142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91789794,0.00031847326,0.07567759,0.0007020448,0.00014716767,0.000040770832,0.00033918588,0.00030327032,0.0045735193],"genre_scores_gemma":[0.99534094,0.00007030734,0.0032955687,0.000017547223,0.000009134139,0.000015657763,0.00010198914,0.0000069679318,0.0011419384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998313,0.000068708214,0.000010139778,0.000039200728,0.000029364299,0.000021342781],"domain_scores_gemma":[0.99972934,0.00011937927,0.000027626409,0.000015909041,0.00008279908,0.000024932498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048809365,0.00048700525,0.0005225701,0.00038649995,0.0003855689,0.0006594178,0.0007436182,0.0007468594,0.00095375435],"category_scores_gemma":[0.00093533675,0.00019198425,0.00045777563,0.0005294878,0.00032662816,0.00080508186,0.00041435444,0.00074858277,0.00011293719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003208745,0.000020772552,0.0028996395,0.000017372791,0.000014716984,0.00008019686,0.000017269516,0.99090016,0.0004722885,0.0005731496,0.0002564235,0.004715905],"study_design_scores_gemma":[0.0000011237503,0.000003985553,0.00025001253,6.3868237e-7,0.0000012222054,0.0000015258289,0.000003171499,0.9995235,0.000050149356,0.00014299116,0.000020072916,0.000001655411],"about_ca_topic_score_codex":0.03380859,"about_ca_topic_score_gemma":0.039344624,"teacher_disagreement_score":0.03380859,"about_ca_system_score_codex":0.00104438,"about_ca_system_score_gemma":0.0008873275,"threshold_uncertainty_score":0.06722361},"labels":[],"label_agreement":null},{"id":"W2172724430","doi":"10.5194/hess-20-2267-2016","title":"Dissolved oxygen prediction using a possibility theory based fuzzy neural network","year":2016,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Università degli Studi di Ferrara; Ministry of Advanced Education; University of Victoria","keywords":"Fuzzy logic; Artificial neural network; Defuzzification; Computer science; Construct (python library); Neuro-fuzzy; Data mining; Artificial intelligence; Fuzzy set; Machine learning; Fuzzy control system; Fuzzy number","score_opus":0.025407480869917926,"score_gpt":0.2329276834398698,"score_spread":0.20752020256995188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172724430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32236442,0.0004334981,0.6713815,0.00043244104,0.000094055555,0.00006111691,0.00017181985,0.0003754011,0.0046857167],"genre_scores_gemma":[0.95217365,0.00007861363,0.046406303,0.000026952377,0.000016049351,0.000028722274,0.00006293566,0.0000049903833,0.0012018392],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982053,0.000044329583,0.000011016662,0.0000391545,0.000067533845,0.00001742563],"domain_scores_gemma":[0.9995227,0.00024978898,0.000040444793,0.000012737301,0.00015389774,0.00002041823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048325353,0.00029821365,0.0003255907,0.00061560737,0.0003199067,0.000654458,0.0005626981,0.00047231046,0.00084268406],"category_scores_gemma":[0.0013541101,0.00019164261,0.00035451524,0.00039287514,0.00034818164,0.0005158964,0.00028727474,0.00038447953,0.00009880737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010585361,0.00004284923,0.0037340506,0.00003978003,0.000045794786,0.00006744757,0.0000362288,0.9475347,0.0022833655,0.0019235099,0.0004315502,0.043754842],"study_design_scores_gemma":[0.000004199611,0.000007990725,0.00025609037,0.0000017970107,0.0000029020332,0.000002900268,0.0000020646276,0.99916244,0.00018373146,0.00031937868,0.00005436056,0.000002175339],"about_ca_topic_score_codex":0.03472231,"about_ca_topic_score_gemma":0.02675489,"teacher_disagreement_score":0.03472231,"about_ca_system_score_codex":0.0013563825,"about_ca_system_score_gemma":0.00071745313,"threshold_uncertainty_score":0.06904036},"labels":[],"label_agreement":null},{"id":"W2189249735","doi":"10.1139/l2012-011","title":"Application of artificial neural networks and adaptive neuro-fuzzy inference system models to short-term streamflow forecasting","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Tarbiat Modares University","keywords":"Adaptive neuro fuzzy inference system; Streamflow; Mean squared error; Artificial neural network; Autoregressive–moving-average model; Autoregressive model; Statistics; Flood forecasting; Computer science; Mathematics; Fuzzy logic; Artificial intelligence; Fuzzy control system; Geography; Cartography","score_opus":0.0323658291754915,"score_gpt":0.20536844179726957,"score_spread":0.17300261262177807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189249735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44879,0.0125943255,0.51941645,0.001454917,0.0005322253,0.00008304699,0.0004271138,0.0006481998,0.016053695],"genre_scores_gemma":[0.9507585,0.0023712018,0.044145282,0.00006375065,0.00008902787,0.000031663076,0.00017824884,0.000012704118,0.0023495895],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997328,0.00009787928,0.00002192141,0.00003867044,0.000089964815,0.000018748427],"domain_scores_gemma":[0.99966705,0.00019697913,0.000036296005,0.00001512718,0.00007464458,0.000009850168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006702397,0.00040597434,0.00027245967,0.00056488847,0.000184811,0.0005988411,0.00033324223,0.0005278667,0.00059955043],"category_scores_gemma":[0.0017892102,0.00016989735,0.00031895324,0.00062167126,0.00016270956,0.00069158635,0.00030878405,0.0004120236,0.00008871387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010691479,0.000097752825,0.008869273,0.00018312232,0.00021131549,0.00025599406,0.00008021198,0.8185787,0.004298006,0.0045660413,0.0009525912,0.16180012],"study_design_scores_gemma":[0.0000032484302,0.00002973138,0.0019201479,0.000012471486,0.000016245187,0.000020038353,0.000020073123,0.9948691,0.0006222546,0.0016528891,0.00082432677,0.000009462008],"about_ca_topic_score_codex":0.015565655,"about_ca_topic_score_gemma":0.017806081,"teacher_disagreement_score":0.015565655,"about_ca_system_score_codex":0.00043352484,"about_ca_system_score_gemma":0.00056496245,"threshold_uncertainty_score":0.030950129},"labels":[],"label_agreement":null},{"id":"W2201773709","doi":"10.1139/cjce-2014-0329","title":"Long lead forecasting of spring peak runoff using Mamdani-type fuzzy logic systems at Hay River, NWT","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alzheimer's Drug Discovery Foundation","keywords":"Snowmelt; Fuzzy logic; Environmental science; Surface runoff; Breakup; Hydrology (agriculture); Meteorology; Snow; Statistics; Computer science; Mathematics; Engineering; Geography; Ecology; Artificial intelligence","score_opus":0.051399409754707914,"score_gpt":0.21395051267986262,"score_spread":0.1625511029251547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2201773709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9868917,0.00004733938,0.010924331,0.00010119776,0.000008670589,0.000043991287,0.00018688694,0.00015886563,0.0016369026],"genre_scores_gemma":[0.9946826,0.000027080448,0.004560216,0.000004524596,9.4271854e-7,0.000010687797,0.00011534326,0.0000031695251,0.0005955086],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998543,0.000026920154,0.000006735657,0.000036275847,0.000048665603,0.000027055068],"domain_scores_gemma":[0.9998449,0.000047142108,0.000013662836,0.0000071854997,0.00006813681,0.000018853363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039893537,0.00034373833,0.00024005324,0.00026743158,0.0005380341,0.0006250446,0.00054526154,0.00031065816,0.00040199116],"category_scores_gemma":[0.0007876168,0.00013472786,0.00017237765,0.00031754634,0.00021868135,0.00021604291,0.00019943246,0.00032514153,0.00006535841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029470975,0.00016287512,0.027780844,0.00005931733,0.000033922483,0.0003453516,0.00023971958,0.9187338,0.014949142,0.0007299633,0.0006989053,0.035971485],"study_design_scores_gemma":[0.0000085995525,0.000031179294,0.0036792571,0.0000019152126,0.0000057971024,0.0000048675874,0.00007029653,0.99404114,0.001906244,0.00009309021,0.00015089283,0.000006583591],"about_ca_topic_score_codex":0.523094,"about_ca_topic_score_gemma":0.5643912,"teacher_disagreement_score":0.476906,"about_ca_system_score_codex":0.0028016677,"about_ca_system_score_gemma":0.0028546427,"threshold_uncertainty_score":0.9594292},"labels":[],"label_agreement":null},{"id":"W2256317226","doi":"10.2166/hydro.2013.042","title":"Multi-step streamflow forecasting using data-driven non-linear methods in contrasting climate regimes","year":2013,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Streamflow; Lead time; Environmental science; Watershed; Overfitting; Computer science; Wavelet; Artificial neural network; Climatology; Meteorology; Statistics; Econometrics; Mathematics; Artificial intelligence; Machine learning; Geology; Drainage basin; Geography; Engineering","score_opus":0.10805157162215141,"score_gpt":0.3563714897035554,"score_spread":0.24831991808140402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256317226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9604359,0.000098901706,0.03850245,0.0001361483,0.000018935887,0.000021591706,0.00015970248,0.00012860632,0.0004977353],"genre_scores_gemma":[0.9890022,0.00004580687,0.010592265,0.00000991522,0.000004546698,0.00001619155,0.00015363844,0.0000062268023,0.00016901598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983084,0.000073077215,0.000013953017,0.000038219805,0.000029459936,0.000014502119],"domain_scores_gemma":[0.9990237,0.00069353054,0.00007853025,0.000052061983,0.000116159616,0.000036092075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010263842,0.00028823523,0.0003911412,0.00038798933,0.00016303275,0.00046233885,0.0004079441,0.0004313625,0.00023078953],"category_scores_gemma":[0.0036401888,0.00018528332,0.00044253055,0.00051502313,0.00018475586,0.0006835903,0.00028925214,0.0005466197,0.00005062347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001318756,0.00010944972,0.017359229,0.00003111212,0.000052400985,0.000057229296,0.000054840817,0.9542153,0.002243961,0.0005093675,0.00017149094,0.025063772],"study_design_scores_gemma":[0.0000035099754,0.000011038326,0.002192112,0.0000011836777,0.0000021055444,0.000001904982,0.000006136622,0.99727505,0.0003232055,0.00015229412,0.000028941644,0.000002482398],"about_ca_topic_score_codex":0.009930088,"about_ca_topic_score_gemma":0.011031639,"teacher_disagreement_score":0.009930088,"about_ca_system_score_codex":0.0005047226,"about_ca_system_score_gemma":0.00050470384,"threshold_uncertainty_score":0.019744575},"labels":[],"label_agreement":null},{"id":"W2276221726","doi":"10.1002/2015wr016959","title":"Bootstrap rank‐ordered conditional mutual information (broCMI): A nonlinear input variable selection method for water resources modeling","year":2016,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Mutual information; Feature selection; Selection (genetic algorithm); Rank (graph theory); Nonparametric statistics; Variable (mathematics); Estimator; Parametric statistics; Mathematics; Kernel (algebra); Computer science; Data mining; Mathematical optimization; Statistics; Artificial intelligence","score_opus":0.06181744656260131,"score_gpt":0.33426972010694683,"score_spread":0.27245227354434554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2276221726","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00792296,0.000102091275,0.9908937,0.00009319562,0.000010883308,0.000036326477,0.00006200617,0.00033204467,0.0005467166],"genre_scores_gemma":[0.4479116,0.00018285942,0.5490395,0.00014809426,0.000089253976,0.00027799388,0.0005462054,0.00018459924,0.0016199613],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789774,0.0010729759,0.0000806736,0.00026155004,0.00058300904,0.00010398951],"domain_scores_gemma":[0.9949339,0.0033492458,0.00046875744,0.0003783568,0.00077206356,0.000097678945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036751984,0.0008492623,0.0012307198,0.001456796,0.00053529104,0.00083495426,0.001810573,0.00081241655,0.0018030695],"category_scores_gemma":[0.0115937935,0.0003456522,0.00090078695,0.0013304885,0.0008276511,0.0008811073,0.0012904771,0.0012716298,0.00032686867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022981512,0.00012475198,0.004127713,0.00017292732,0.00018129403,0.00017185998,0.00009116523,0.7195374,0.004566344,0.0325144,0.0029372058,0.23534505],"study_design_scores_gemma":[0.000003992472,0.0000114260165,0.00027996363,0.000004407483,0.000004368957,0.000010618971,0.00000292005,0.9963846,0.0006999991,0.0023359333,0.0002553365,0.000006369818],"about_ca_topic_score_codex":0.003877538,"about_ca_topic_score_gemma":0.00300381,"teacher_disagreement_score":0.003877538,"about_ca_system_score_codex":0.0008432769,"about_ca_system_score_gemma":0.0014005837,"threshold_uncertainty_score":0.019436538},"labels":[],"label_agreement":null},{"id":"W2283173098","doi":"10.2478/sggw-2014-0016","title":"Weekly urban water demand forecasting using a hybrid wavelet–bootstrap–artificial neural network approach","year":2014,"lang":"en","type":"article","venue":"Annals of Warsaw University of Life Sciences – SGGW Land Reclamation","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"","keywords":"Demand forecasting; Artificial neural network; Wavelet; Reliability (semiconductor); Computer science; Econometrics; Artificial intelligence; Operations research; Engineering; Mathematics","score_opus":0.1170432423732121,"score_gpt":0.25310433702390867,"score_spread":0.13606109465069655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2283173098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60012275,0.00016071206,0.39524323,0.00021299886,0.000056828005,0.000030042911,0.00025264864,0.00030833788,0.0036124648],"genre_scores_gemma":[0.9837546,0.000040096085,0.015624909,0.000009270474,0.0000091713255,0.000016466249,0.00010708821,0.000008293572,0.00043013395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999859,0.000051999825,0.00000920002,0.00002816855,0.000037302998,0.000014319344],"domain_scores_gemma":[0.9997261,0.0001340229,0.00002745861,0.000027295144,0.00007267475,0.000012387393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045519875,0.00026335128,0.00028528285,0.00048198755,0.00014479608,0.00028431293,0.00034571366,0.00031209082,0.00053700584],"category_scores_gemma":[0.0011336397,0.00014298447,0.00033195107,0.00053272437,0.000111794565,0.0005325437,0.00025068794,0.0003416012,0.000101621794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000735038,0.000064325315,0.0047869077,0.000024901314,0.000041852614,0.00006826849,0.000029840257,0.9425097,0.003201003,0.0009038121,0.00032436856,0.047971576],"study_design_scores_gemma":[7.8054927e-7,0.0000052307364,0.0004101752,6.379278e-7,0.0000014047329,0.0000022157203,0.0000030106191,0.9991943,0.0002024477,0.00013292921,0.000045276043,0.000001458418],"about_ca_topic_score_codex":0.005983483,"about_ca_topic_score_gemma":0.006254727,"teacher_disagreement_score":0.005983483,"about_ca_system_score_codex":0.00032043786,"about_ca_system_score_gemma":0.00023751953,"threshold_uncertainty_score":0.011897266},"labels":[],"label_agreement":null},{"id":"W2284019159","doi":"10.1002/2015wr017302","title":"Independent component analysis of local‐scale temporal variability in sediment‐water interface temperature","year":2015,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada; University of Saskatchewan; Simon Fraser University","funders":"SFU Community Trust Endowment Fund; Natural Sciences and Engineering Research Council of Canada; Pacific Institute for Climate Solutions; Watershed Watch Salmon Society","keywords":"Environmental science; Sediment; Groundwater; Hydrology (agriculture); Scale (ratio); Sediment–water interface; Surface water; Interface (matter); Inflow; Geology; Meteorology; Environmental engineering; Geography; Geomorphology; Oceanography","score_opus":0.049109665549533985,"score_gpt":0.31891592749108755,"score_spread":0.26980626194155355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284019159","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95936215,0.00012257116,0.037780236,0.000062689855,0.000041028252,0.000042340318,0.00069521734,0.00029688046,0.0015968938],"genre_scores_gemma":[0.9901764,0.0000670869,0.008371117,0.000005791197,0.000015784062,0.00003370492,0.0008419311,0.000025387955,0.0004628738],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981934,0.000039723585,0.000012338344,0.00004637855,0.00005064643,0.000031566673],"domain_scores_gemma":[0.99937797,0.00031761278,0.00006464188,0.000045977842,0.00016478573,0.000028905863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041391858,0.0003871311,0.00027105535,0.0012658812,0.0002534498,0.0004982252,0.00017516423,0.0001855756,0.0008028716],"category_scores_gemma":[0.0016040694,0.000097301534,0.0004477941,0.0016461227,0.00015553665,0.00025900584,0.00026064005,0.0003449025,0.00017572078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000801418,0.0006215996,0.31311217,0.00015195388,0.00058221695,0.00038053122,0.00060408475,0.14547165,0.062921576,0.0020111871,0.0047723507,0.4685693],"study_design_scores_gemma":[0.00001400859,0.00009867641,0.53482705,0.000014652902,0.00009314124,0.00006374188,0.00017137195,0.45796922,0.004786054,0.0006153901,0.0013066051,0.000040137562],"about_ca_topic_score_codex":0.00838062,"about_ca_topic_score_gemma":0.0077590453,"teacher_disagreement_score":0.00838062,"about_ca_system_score_codex":0.00027199145,"about_ca_system_score_gemma":0.00037031653,"threshold_uncertainty_score":0.01666367},"labels":[],"label_agreement":null},{"id":"W2286179031","doi":"10.1016/j.dss.2016.02.003","title":"A framework based on hidden Markov model with adaptive weighting for microcystin forecasting and early-warning","year":2016,"lang":"en","type":"article","venue":"Decision Support Systems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Research Foundation Singapore","keywords":"Weighting; Computer science; Warning system; Machine learning; Hidden Markov model; Artificial intelligence; Artificial neural network; Data mining","score_opus":0.03871776234724431,"score_gpt":0.2534854039126438,"score_spread":0.2147676415653995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2286179031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021163358,0.00010814996,0.9971969,0.000067922534,0.000028787543,0.000011248823,0.000021038892,0.00010916911,0.0003403784],"genre_scores_gemma":[0.3975616,0.0006973729,0.59650385,0.00015183205,0.00021395902,0.00027144206,0.00032909767,0.00014222499,0.004128574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999432,0.00017938137,0.0000403277,0.00014509924,0.00013565128,0.00006755307],"domain_scores_gemma":[0.9990546,0.00049938855,0.000075077325,0.000058038117,0.00025304934,0.00005984853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001699252,0.00069506455,0.001146669,0.0007936115,0.0006213878,0.0010691391,0.0022129389,0.0010429278,0.0020158554],"category_scores_gemma":[0.0031266164,0.0005150661,0.0009182037,0.0009863517,0.0005842925,0.002012603,0.001240604,0.0013897722,0.00041790277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006608047,0.00007983211,0.0006267263,0.00007824473,0.000088966204,0.00010569472,0.00008753572,0.85867375,0.0022138632,0.07018458,0.0013171766,0.06647755],"study_design_scores_gemma":[0.0000026299642,0.0000056820018,0.00002863739,0.0000018384851,0.000005567533,0.0000041090375,0.000002671426,0.9936034,0.00009580107,0.006038492,0.00020740132,0.0000038399735],"about_ca_topic_score_codex":0.018981868,"about_ca_topic_score_gemma":0.013630661,"teacher_disagreement_score":0.018981868,"about_ca_system_score_codex":0.00090380927,"about_ca_system_score_gemma":0.0020212654,"threshold_uncertainty_score":0.037742794},"labels":[],"label_agreement":null},{"id":"W2288701971","doi":"10.1007/s40808-016-0079-9","title":"Comparison of methods used for quantifying prediction interval in artificial neural network hydrologic models","year":2016,"lang":"en","type":"article","venue":"Modeling Earth Systems and Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hydrograph; Prediction interval; Artificial neural network; Interval (graph theory); Watershed; Bayesian probability; Hydrological modelling; Computer science; Statistics; Data mining; Mathematics; Artificial intelligence; Machine learning; Geography; Drainage basin; Geology; Cartography; Climatology","score_opus":0.21465417422875613,"score_gpt":0.35190931721741536,"score_spread":0.13725514298865923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288701971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38051113,0.005966281,0.60537386,0.0003702667,0.00024855923,0.00016895233,0.0010410425,0.001496894,0.0048229774],"genre_scores_gemma":[0.8470918,0.0016975175,0.14903846,0.00006083262,0.00006845344,0.00018006602,0.000988446,0.00024631267,0.0006280563],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667335,0.001526036,0.00049252284,0.0003285631,0.0008489798,0.00013050593],"domain_scores_gemma":[0.9568995,0.03589406,0.0017480411,0.001636222,0.003586385,0.00023576981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01129279,0.0010229986,0.0009829107,0.0029031648,0.00038874036,0.0018420097,0.0015951517,0.0011874626,0.00087505905],"category_scores_gemma":[0.037360948,0.00037233302,0.0009299487,0.0021612695,0.0004184922,0.0017897043,0.0009012359,0.0012537958,0.00013683017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024234997,0.00040326768,0.03973774,0.0011294115,0.0013195473,0.0001365564,0.00046027746,0.57536036,0.006607859,0.008593839,0.0011863819,0.36264125],"study_design_scores_gemma":[0.000048453872,0.0001898012,0.0073072133,0.00008747328,0.00016599796,0.00004100592,0.00006901089,0.9841314,0.0054279068,0.0019684427,0.0005116802,0.000051674884],"about_ca_topic_score_codex":0.007786222,"about_ca_topic_score_gemma":0.00540741,"teacher_disagreement_score":0.01129279,"about_ca_system_score_codex":0.00091117097,"about_ca_system_score_gemma":0.00082264584,"threshold_uncertainty_score":0.059722662},"labels":[],"label_agreement":null},{"id":"W2288971867","doi":"","title":"The Management And Analysis Of Infrastructure Time Series Data: An Environmental Time Series Database","year":2006,"lang":"en","type":"article","venue":"Proceedings of the Joint CIB W78, W102, ICCCBE, ICCC, and DMUCE International Conference on Computing and Decision Making in Civil and Building Engineering, Montreal, Canada, 14-16 June","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Data management; Data quality; Time series; Database; Data mining; Data science; Engineering; Machine learning","score_opus":0.008506366794021234,"score_gpt":0.21589151395135953,"score_spread":0.2073851471573383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288971867","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08220722,0.0022519717,0.6771498,0.004653653,0.00058644096,0.0015885558,0.16780382,0.03854717,0.025211304],"genre_scores_gemma":[0.33015773,0.0026576316,0.42519516,0.00045848257,0.000407514,0.0010809596,0.22726957,0.0015067598,0.01126618],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722725,0.00041440717,0.0005217074,0.00053735374,0.0011582724,0.00014097248],"domain_scores_gemma":[0.9908646,0.0016872179,0.0007284973,0.0029828676,0.0030752155,0.00066166004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004892481,0.0005266349,0.0007023384,0.0052074357,0.0009374401,0.0038990187,0.0020717306,0.00063671655,0.0024154717],"category_scores_gemma":[0.011061274,0.000383529,0.00049955765,0.010008925,0.00047833144,0.003035508,0.0012722058,0.0011378478,0.0022740804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006259926,0.00053673197,0.047441393,0.00047729487,0.00032206805,0.00074556953,0.0009360897,0.027728083,0.01740198,0.028210772,0.20261371,0.6729603],"study_design_scores_gemma":[0.00016876844,0.00024722354,0.081102856,0.00018525585,0.0002953691,0.00063148147,0.0009382863,0.36846974,0.037061978,0.02051149,0.49013594,0.00025160337],"about_ca_topic_score_codex":0.031015214,"about_ca_topic_score_gemma":0.022227013,"teacher_disagreement_score":0.031015214,"about_ca_system_score_codex":0.0017792255,"about_ca_system_score_gemma":0.0031185925,"threshold_uncertainty_score":0.06166935},"labels":[],"label_agreement":null},{"id":"W2289152296","doi":"10.1007/s00477-016-1213-y","title":"Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River, Iran","year":2016,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":179,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Adaptive neuro fuzzy inference system; Wavelet; Haar; Artificial intelligence; Statistics; Haar wavelet; Mathematics; Discrete wavelet transform; Salinity; Coefficient of determination; Computational intelligence; Pattern recognition (psychology); Artificial neural network; Wavelet transform; Computer science; Geology; Fuzzy logic; Fuzzy control system","score_opus":0.10809845732041415,"score_gpt":0.389054215941687,"score_spread":0.28095575862127287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2289152296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97373974,0.00010254691,0.023303675,0.0003652495,0.000032777963,0.000035817608,0.00013836277,0.00016761674,0.0021143092],"genre_scores_gemma":[0.9951056,0.00006215925,0.0042928946,0.000007980238,0.0000050061835,0.000008492593,0.000053661846,0.0000061887727,0.00045796178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973756,0.00008811459,0.000018033179,0.00004408716,0.000061329556,0.00005086082],"domain_scores_gemma":[0.99944466,0.00030651558,0.00004949836,0.000040753614,0.00013557526,0.000022995968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096153945,0.0004883371,0.00049802766,0.0005133247,0.000450854,0.0008433697,0.0009714141,0.0008610709,0.00063675595],"category_scores_gemma":[0.0016017862,0.0002291787,0.0006034686,0.00085237576,0.00032235443,0.00074277964,0.00044401854,0.00060893054,0.00008748622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019110706,0.00046545267,0.030290779,0.00007693139,0.00011770014,0.001173842,0.00022158089,0.9101116,0.0030225273,0.001903561,0.0011956596,0.051229205],"study_design_scores_gemma":[0.0000127428175,0.00006462881,0.0032253969,0.000002543387,0.000023593537,0.000030727962,0.00014802176,0.994935,0.00082761375,0.00046991612,0.0002528183,0.0000071203135],"about_ca_topic_score_codex":0.033163246,"about_ca_topic_score_gemma":0.02564631,"teacher_disagreement_score":0.033163246,"about_ca_system_score_codex":0.0010294282,"about_ca_system_score_gemma":0.0009730003,"threshold_uncertainty_score":0.06594044},"labels":[],"label_agreement":null},{"id":"W2296250040","doi":"10.1109/icmla.2015.87","title":"Prediction of SPEI Using MLR and ANN: A Case Study for Wilsons Promontory Station in Victoria","year":2015,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Southern Queensland","keywords":"Promontory; Mean squared error; Evapotranspiration; Artificial neural network; Linear regression; Statistics; Regression; Coefficient of determination; Precipitation; Mathematics; Computer science; Artificial intelligence; Meteorology; Geography; Ecology; Cartography","score_opus":0.1329588816235091,"score_gpt":0.3115383113126274,"score_spread":0.17857942968911827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296250040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9983681,0.000032227756,0.0005597221,0.000111039146,0.0000021554918,0.000021223117,0.000113165836,0.000022817709,0.0007695735],"genre_scores_gemma":[0.9976943,0.000037505197,0.0014764755,0.0000130663475,0.0000022699799,0.000008337028,0.00014429023,0.0000044050935,0.0006194519],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996635,0.00009656818,0.000028844057,0.00006500529,0.000085752676,0.000060314178],"domain_scores_gemma":[0.9992105,0.0003376528,0.00009430139,0.00006272967,0.00018969076,0.000105179235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089173234,0.00035823273,0.00029149704,0.0004558036,0.0007868839,0.00064813544,0.0008876849,0.0006160121,0.00045732834],"category_scores_gemma":[0.0024510836,0.00026449823,0.00035352656,0.000848316,0.0003564894,0.00059764204,0.00045200574,0.0005708816,0.000112089176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048617978,0.00079582987,0.48515308,0.00022229947,0.00017521672,0.0062206034,0.0023325954,0.4174089,0.009659263,0.0013809305,0.0013574342,0.074807614],"study_design_scores_gemma":[0.000033324668,0.00027862118,0.20088275,0.000027280916,0.000032145177,0.00023068106,0.0022477382,0.79236007,0.0022588621,0.00042787948,0.0011804367,0.00004019308],"about_ca_topic_score_codex":0.34660128,"about_ca_topic_score_gemma":0.45339724,"teacher_disagreement_score":0.34660128,"about_ca_system_score_codex":0.0034739247,"about_ca_system_score_gemma":0.0016145025,"threshold_uncertainty_score":0.6891677},"labels":[],"label_agreement":null},{"id":"W2314233999","doi":"10.2478/v10025-012-0038-4","title":"Comparison of machine learning methods for runoff forecasting in mountainous watersheds with limited data / Porównanie metod uczenia maszynowego do prognozowania spływu w zlewniach górskich na podstawie ograniczonych danych","year":2012,"lang":"en","type":"article","venue":"Journal of Water and Land Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Surface runoff; Watershed; Support vector machine; Hydrology (agriculture); Precipitation; Antecedent moisture; Environmental science; Runoff curve number; Machine learning; Meteorology; Computer science; Geography; Engineering; Ecology","score_opus":0.07779298667317963,"score_gpt":0.3349514647251872,"score_spread":0.2571584780520076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314233999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78771406,0.0013112462,0.20758745,0.0003792489,0.00006405999,0.00007371727,0.00022218289,0.00047843833,0.0021695874],"genre_scores_gemma":[0.9687669,0.00032818742,0.030279195,0.000015963575,0.000016447004,0.00003704817,0.00016302579,0.000013154668,0.00038008014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994124,0.00030987742,0.000057660673,0.00006893594,0.00011520642,0.00003587896],"domain_scores_gemma":[0.9973572,0.0019302499,0.00015134466,0.00012120846,0.00038436303,0.00005558067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002267853,0.0004170555,0.0006127701,0.001211678,0.00015676876,0.0005426849,0.0004854223,0.0004377676,0.0006073493],"category_scores_gemma":[0.0048959204,0.0001783762,0.0004871413,0.0009441197,0.00014961055,0.0006723375,0.0002999027,0.00047276609,0.0001269619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038237948,0.00019838095,0.022941194,0.00014837035,0.00021223318,0.00007197934,0.00006934964,0.7886658,0.0018143653,0.0007837743,0.00046127048,0.1842509],"study_design_scores_gemma":[0.000006009807,0.00004418911,0.0028364519,0.000006320245,0.00000959665,0.0000066858306,0.000021791178,0.99645644,0.00034247714,0.00018093134,0.00008524767,0.0000038884764],"about_ca_topic_score_codex":0.0069144126,"about_ca_topic_score_gemma":0.0047171623,"teacher_disagreement_score":0.0069144126,"about_ca_system_score_codex":0.00038736235,"about_ca_system_score_gemma":0.00047939824,"threshold_uncertainty_score":0.013748348},"labels":[],"label_agreement":null},{"id":"W2315555627","doi":"10.4296/cwrj3602849","title":"The Influence of Air Temperature on Water Temperature and the Concentration of Dissolved Oxygen in Newfoundland Rivers","year":2011,"lang":"en","type":"article","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Government of Newfoundland and Labrador; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Environmental science; Air temperature; Water quality; Hydrology (agriculture); Oxygen; Current (fluid); Limiting oxygen concentration; Meteorology; Chemistry; Ecology; Geography; Geology; Oceanography","score_opus":0.009055067193724448,"score_gpt":0.17861572994978858,"score_spread":0.16956066275606413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315555627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99127823,0.00040464223,0.005412244,0.0003577841,0.000014039911,0.000007499315,0.00043606004,0.00014573192,0.0019437049],"genre_scores_gemma":[0.9971988,0.0001856227,0.0012436273,0.000018745459,0.0000041969697,0.000005243781,0.00030252017,0.000010706968,0.0010306694],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997801,0.000059369373,0.000012580506,0.00005627373,0.00003721041,0.00005449043],"domain_scores_gemma":[0.9992963,0.00041014078,0.00011573833,0.00003714668,0.00011278943,0.000027777436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042807843,0.00023436632,0.00019872766,0.00032501045,0.00024608287,0.00079895486,0.00034410704,0.00022973944,0.00035428483],"category_scores_gemma":[0.0023166034,0.00015686145,0.00032682906,0.00037625388,0.0003641812,0.00041110616,0.00023538547,0.0003226099,0.00008067131],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024563234,0.0000699833,0.5214232,0.00008345478,0.00024642088,0.00027480358,0.00031944236,0.42197546,0.0063818353,0.0011131068,0.0016825238,0.04618411],"study_design_scores_gemma":[0.000012292672,0.00005155669,0.4622103,0.000020110141,0.00009509542,0.00005100874,0.00022877162,0.5322302,0.0024906744,0.0003401995,0.0022258973,0.00004389703],"about_ca_topic_score_codex":0.77636796,"about_ca_topic_score_gemma":0.76637125,"teacher_disagreement_score":0.22363204,"about_ca_system_score_codex":0.0036057488,"about_ca_system_score_gemma":0.001560979,"threshold_uncertainty_score":0.44989806},"labels":[],"label_agreement":null},{"id":"W2316412822","doi":"10.1061/40644(2002)90","title":"Implementation in PCSWMM Using Genetic Algorithms for Auto Calibration and Design-Optimization","year":2002,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Calibration; Computer science; Software; Genetic algorithm; Storm Water Management Model; Hydrological modelling; Storm; Control engineering; Algorithm; Systems engineering; Machine learning; Engineering; Programming language","score_opus":0.07541198769566901,"score_gpt":0.2930139327859023,"score_spread":0.2176019450902333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316412822","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008182992,0.000032422326,0.9789017,0.00006579107,0.00003493544,0.0000781728,0.00009347409,0.008780877,0.003829648],"genre_scores_gemma":[0.10659589,0.000058546175,0.88926184,0.00007933098,0.000014291708,0.00034902286,0.0003118982,0.0010275433,0.0023016143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995389,0.00014644244,0.000024040732,0.000071681396,0.00018136836,0.00003759185],"domain_scores_gemma":[0.99875987,0.0006297714,0.000087378125,0.00023990459,0.000259488,0.000023632367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012220325,0.0009175739,0.00041438843,0.0007080744,0.00045025506,0.0006898551,0.0010121578,0.0008007143,0.005789793],"category_scores_gemma":[0.003490987,0.0003815801,0.000526305,0.00059294497,0.0003613933,0.00050645607,0.00053639576,0.0009674947,0.0013670869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114524235,0.00012068505,0.0012619173,0.0001557962,0.00007426495,0.00008619634,0.00014839588,0.61122143,0.008290387,0.011255297,0.0056961062,0.36157498],"study_design_scores_gemma":[0.000039853665,0.00004013094,0.00017776208,0.000013776974,0.000011205151,0.000026928461,0.000012905491,0.9811491,0.0065962183,0.003770478,0.008152664,0.000008990181],"about_ca_topic_score_codex":0.0050416905,"about_ca_topic_score_gemma":0.0039311275,"teacher_disagreement_score":0.005789793,"about_ca_system_score_codex":0.00061128754,"about_ca_system_score_gemma":0.0010775544,"threshold_uncertainty_score":0.019368768},"labels":[],"label_agreement":null},{"id":"W2320684931","doi":"10.1061/40569(2001)54","title":"Developing Runoff Hydrograph using Artificial Neural Networks","year":2001,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"U.S. Army Corps of Engineers","keywords":"Hydrograph; Surface runoff; Artificial neural network; Precipitation; Runoff model; Computer science; Flow (mathematics); Environmental science; Watershed; Hydrology (agriculture); Meteorology; Mathematics; Machine learning; Geology; Geography; Geotechnical engineering","score_opus":0.063358267916262,"score_gpt":0.2748341516413704,"score_spread":0.21147588372510842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320684931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.108434975,0.00017227652,0.88263816,0.00018976984,0.000033242035,0.00014110799,0.00045434982,0.0021114675,0.005824689],"genre_scores_gemma":[0.74376744,0.00030177596,0.2504955,0.000068671805,0.000024736682,0.0002369899,0.0008821802,0.00008958738,0.0041331975],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998908,0.000019139967,0.000010796635,0.00002900422,0.00003776422,0.000012460162],"domain_scores_gemma":[0.999729,0.00013010798,0.00003087072,0.000010361915,0.000092130686,0.000007495749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024767808,0.0003919986,0.00022138197,0.00068052486,0.00020194835,0.00044684045,0.0003452879,0.0003646066,0.0014712506],"category_scores_gemma":[0.0009710777,0.00025711377,0.0003316047,0.0007611855,0.00014713852,0.00050801365,0.00022872945,0.0003696881,0.00027184756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012363453,0.000014705308,0.0011303654,0.00002176971,0.000010089274,0.000032461874,0.000016838025,0.960677,0.001137211,0.00071374356,0.0002897857,0.03594367],"study_design_scores_gemma":[0.0000010750983,0.000002946274,0.00029096144,0.0000024078363,0.0000013694888,0.0000027636722,0.000003649585,0.9987257,0.00037083344,0.00042787878,0.00016866703,0.0000018142399],"about_ca_topic_score_codex":0.023495143,"about_ca_topic_score_gemma":0.024431732,"teacher_disagreement_score":0.023495143,"about_ca_system_score_codex":0.00089575263,"about_ca_system_score_gemma":0.0008991379,"threshold_uncertainty_score":0.04671675},"labels":[],"label_agreement":null},{"id":"W2329020462","doi":"10.1061/40644(2002)239","title":"Two Neural Networks for Generation of High-Resolution Long-Term Storm Rainfall Compared to Ormsbee's Method—Case Study for Toronto","year":2002,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Artificial neural network; Computer science; Storm; Radial basis function; Term (time); Precipitation; Perceptron; Multilayer perceptron; Function (biology); Mean squared error; Meteorology; Algorithm; Artificial intelligence; Statistics; Mathematics; Geography","score_opus":0.09572348121053326,"score_gpt":0.3329193318867526,"score_spread":0.23719585067621934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2329020462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8750458,0.0007850275,0.11246247,0.00049770944,0.00005041688,0.00011755838,0.00029978814,0.0005315284,0.010209833],"genre_scores_gemma":[0.96977633,0.00017564632,0.028091956,0.000015508176,0.0000067169017,0.000030929645,0.00009107597,0.000011514372,0.00180033],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984384,0.000060348077,0.000008587582,0.000024560335,0.000036625028,0.000026100694],"domain_scores_gemma":[0.99959725,0.00025108835,0.000022982773,0.000021668908,0.000089347304,0.000017680857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005673081,0.0004027015,0.00031337974,0.00031802017,0.0003788876,0.00058355904,0.00048697903,0.0005233899,0.0010008257],"category_scores_gemma":[0.001344989,0.00017203268,0.00020579243,0.00077322207,0.00025788025,0.00033590078,0.0002630168,0.00031545342,0.000054168147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002286937,0.00005952022,0.0040577385,0.00006661907,0.000037626312,0.00031399744,0.00009373486,0.9328159,0.0019332317,0.0016954964,0.0005686605,0.05812883],"study_design_scores_gemma":[0.000012403436,0.00001657223,0.0011559951,0.0000022880638,0.000009904719,0.000008962721,0.00002423549,0.9974987,0.00088558573,0.0001570007,0.00022410181,0.0000043082255],"about_ca_topic_score_codex":0.20866266,"about_ca_topic_score_gemma":0.21665512,"teacher_disagreement_score":0.7913374,"about_ca_system_score_codex":0.0024330276,"about_ca_system_score_gemma":0.0008233692,"threshold_uncertainty_score":0.4148962},"labels":[],"label_agreement":null},{"id":"W2333985097","doi":"10.1061/40644(2002)195","title":"Thermal Enrichment of Stream Temperature by Urban Storm Waters","year":2002,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Surface runoff; Impervious surface; Environmental science; Hydrology (agriculture); Rainwater harvesting; STREAMS; Thermal pollution; Urban heat island; Storm; First flush; Water quality; Stormwater; Surface water; Environmental engineering; Meteorology; Ecology; Geology; Geography","score_opus":0.009487250801364169,"score_gpt":0.1882868761014684,"score_spread":0.17879962530010424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333985097","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89346653,0.0004665035,0.08979204,0.00032122777,0.00009212972,0.00008774872,0.0007762074,0.00070195657,0.01429572],"genre_scores_gemma":[0.99429,0.0003236153,0.0026802246,0.000016939935,0.000036163732,0.000035012337,0.00015226561,0.00003955524,0.0024262585],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9998932,0.000033659177,0.000005404087,0.000023533727,0.000020176898,0.000024120021],"domain_scores_gemma":[0.9998554,0.000060696704,0.000032911783,0.000010205449,0.000022173144,0.000018591665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014179212,0.00037330738,0.00032049653,0.00025076183,0.00024145693,0.0006199766,0.00036543215,0.00045069802,0.0014507269],"category_scores_gemma":[0.0005315543,0.00026562382,0.0003912909,0.00047142862,0.0003723921,0.00063266425,0.0002928229,0.0002784124,0.00019427908],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003366597,0.000021681604,0.0060614008,0.00001541558,0.000014342942,0.00006569218,0.000027514914,0.9873376,0.0009952302,0.0012795368,0.00033149763,0.003816343],"study_design_scores_gemma":[0.000009301202,0.000026010475,0.0032218876,0.000004017694,0.00001299587,0.000017000562,0.000019163308,0.9947832,0.00049520266,0.00064104254,0.00076376856,0.000006408848],"about_ca_topic_score_codex":0.019224767,"about_ca_topic_score_gemma":0.017747616,"teacher_disagreement_score":0.019224767,"about_ca_system_score_codex":0.0009894854,"about_ca_system_score_gemma":0.00049141987,"threshold_uncertainty_score":0.03822571},"labels":[],"label_agreement":null},{"id":"W2334329924","doi":"10.11159/ijepr.2012.003","title":"Drinking Water Source Contamination Early Warning System and Modelling in China: A Review","year":2012,"lang":"en","type":"review","venue":"International Journal of Environmental Pollution and Remediation","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Contamination; Warning system; Environmental science; China; Water source; Water contamination; Early warning system; Water resource management; Environmental planning; Computer science; Geography; Ecology; Biology; Telecommunications","score_opus":0.021445124831485505,"score_gpt":0.24951298219725576,"score_spread":0.22806785736577026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2334329924","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010061058,0.99398005,0.002979988,0.00020251368,0.00018450164,0.000020749525,0.00006662124,0.000028066235,0.0015314106],"genre_scores_gemma":[0.006243992,0.99112296,0.0017830456,0.0000530443,0.00013795066,0.000018363326,0.00009165408,0.0000040437744,0.0005449793],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99977034,0.00003224232,0.000038680453,0.000047653513,0.000094182695,0.00001689139],"domain_scores_gemma":[0.9994361,0.0002840968,0.00007762924,0.000016430982,0.00016492423,0.000020832087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007927502,0.0012109621,0.0014933201,0.0024177742,0.00025535896,0.00084284187,0.0012316399,0.0009021264,0.0017278534],"category_scores_gemma":[0.0012363348,0.0003681742,0.0009241914,0.004097212,0.00031285195,0.0013904461,0.0004548825,0.0005393187,0.00053298136],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040265073,0.00009286576,0.00096971303,0.01985585,0.00017151634,0.0001291148,0.00007597908,0.009741706,0.00088190456,0.004366498,0.011624311,0.95205027],"study_design_scores_gemma":[0.000044686312,0.0005799399,0.007390787,0.012370128,0.0012722427,0.0011029623,0.0003449485,0.027624885,0.004528422,0.010908483,0.9336373,0.00019523839],"about_ca_topic_score_codex":0.007995049,"about_ca_topic_score_gemma":0.0049783047,"teacher_disagreement_score":0.007995049,"about_ca_system_score_codex":0.0006222175,"about_ca_system_score_gemma":0.0017748373,"threshold_uncertainty_score":0.015897036},"labels":[],"label_agreement":null},{"id":"W2347140512","doi":"10.1016/j.jhydrol.2016.04.048","title":"Streamflow forecasting using functional regression","year":2016,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Streamflow; Functional data analysis; Regression; Linear regression; Computer science; Regression analysis; Artificial neural network; Flow (mathematics); Functional principal component analysis; Linear model; Econometrics; Mathematics; Statistics; Artificial intelligence; Machine learning; Geography; Cartography","score_opus":0.061038589304704724,"score_gpt":0.25650070869968433,"score_spread":0.1954621193949796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2347140512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22795369,0.00030834455,0.7671539,0.0003248036,0.00009566348,0.000024487994,0.00020463132,0.00077132985,0.0031631067],"genre_scores_gemma":[0.9672616,0.00012893601,0.030774858,0.000029158515,0.000041886753,0.000021471289,0.00023439214,0.000038690476,0.001468952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997453,0.000115787356,0.000017728307,0.000054164462,0.00004243721,0.000024499315],"domain_scores_gemma":[0.99850357,0.00097011914,0.000074961245,0.000087788474,0.000327025,0.000036600493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013183639,0.00046612968,0.00064033834,0.0007647426,0.00025791395,0.0005434054,0.0006286851,0.00046491963,0.001037139],"category_scores_gemma":[0.0035944392,0.0003097405,0.0005099076,0.0007348414,0.00025440755,0.0010785584,0.00032565245,0.000764985,0.00023322701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007474523,0.00004649179,0.0024165444,0.000021126778,0.000052585427,0.000028369224,0.000018539387,0.94054234,0.0011670025,0.0030059712,0.00052138325,0.052104868],"study_design_scores_gemma":[5.595964e-7,0.0000018088643,0.000087166096,3.477762e-7,0.0000010065589,7.6568176e-7,4.4166086e-7,0.9996352,0.000046541685,0.00020986235,0.000015680003,5.6732773e-7],"about_ca_topic_score_codex":0.017424867,"about_ca_topic_score_gemma":0.008967079,"teacher_disagreement_score":0.017424867,"about_ca_system_score_codex":0.00048280347,"about_ca_system_score_gemma":0.00045376152,"threshold_uncertainty_score":0.03464693},"labels":[],"label_agreement":null},{"id":"W2353795165","doi":"10.1007/s11434-010-4183-3","title":"Application of artificial neural networks in global climate change and ecological research: An overview","year":2010,"lang":"en","type":"article","venue":"Chinese Science Bulletin","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Artificial neural network; Climate change; Global warming; Global change; Computer science; Ecological forecasting; Term (time); General Circulation Model; Ecology; Environmental science; Artificial intelligence; Environmental resource management","score_opus":0.09234494236193655,"score_gpt":0.36331460387151177,"score_spread":0.27096966150957524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2353795165","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012375752,0.6673698,0.2570076,0.006685469,0.001368473,0.00012110035,0.00016608255,0.00019879885,0.054706976],"genre_scores_gemma":[0.11245931,0.77391374,0.09716627,0.00090835354,0.002607235,0.00011247208,0.00019007987,0.00004582624,0.01259672],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996208,0.000120665725,0.000042147993,0.00006684474,0.00013089187,0.000018638282],"domain_scores_gemma":[0.99917907,0.0005114635,0.000041274776,0.000034263285,0.00021214031,0.000021712747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012650616,0.0006669222,0.0005681003,0.0014462817,0.00022833832,0.0013675023,0.0006517768,0.001075429,0.0016532408],"category_scores_gemma":[0.0016542083,0.00025813287,0.00051118113,0.0027534214,0.00040116007,0.0011377676,0.0004783586,0.00085495104,0.00054066157],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009891681,0.00019023159,0.0036917385,0.0030258484,0.00028035848,0.00021837173,0.00010389779,0.035623163,0.0023738279,0.043820813,0.006703363,0.9038695],"study_design_scores_gemma":[0.000048977734,0.0003784697,0.009804283,0.0028629664,0.00052348094,0.0009424761,0.00039983098,0.31232437,0.009393719,0.17676952,0.48639762,0.00015418825],"about_ca_topic_score_codex":0.002900469,"about_ca_topic_score_gemma":0.0034008229,"teacher_disagreement_score":0.002900469,"about_ca_system_score_codex":0.00059773115,"about_ca_system_score_gemma":0.00072028185,"threshold_uncertainty_score":0.006690383},"labels":[],"label_agreement":null},{"id":"W2356635637","doi":"10.1007/s11269-016-1340-8","title":"Artificial Neural Network Rainfall-Discharge Model Assessment Under Rating Curve Uncertainty and Monthly Discharge Volume Predictions","year":2016,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Rating curve; Environmental science; Discharge; Streamflow; Extrapolation; Precipitation; Artificial neural network; Hydrology (agriculture); Statistics; Meteorology; Computer science; Mathematics; Drainage basin; Machine learning; Geology; Geography","score_opus":0.019688343854110543,"score_gpt":0.23627866566656558,"score_spread":0.21659032181245502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2356635637","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96810853,0.0001494342,0.028208712,0.00021239734,0.000029433142,0.000038596707,0.00062356953,0.00027009638,0.0023592233],"genre_scores_gemma":[0.99774253,0.000025191632,0.0015699856,0.000007779689,0.000003578669,0.000010139045,0.00018319902,0.0000059709505,0.0004516234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959105,0.00016598894,0.000032496126,0.00008498568,0.00008691274,0.000038640483],"domain_scores_gemma":[0.9970861,0.0020447199,0.00023567026,0.00011801366,0.0004334844,0.00008199599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002169186,0.0006084241,0.0005943935,0.00069351855,0.00026073077,0.0007375698,0.00062354014,0.00084385206,0.0009114037],"category_scores_gemma":[0.0046112966,0.0003589222,0.0004656927,0.00065439905,0.00030299192,0.0011318814,0.0003665604,0.0005608348,0.000115771974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092120994,0.000030735253,0.0020532208,0.000010386508,0.000021638816,0.000015463294,0.0000050998424,0.9944246,0.00025974194,0.00017679278,0.000098725606,0.0028114214],"study_design_scores_gemma":[0.0000026918872,0.00001194564,0.00058401964,5.5606e-7,0.000002913707,0.0000011395712,0.0000013725587,0.99918956,0.00011420812,0.00007822812,0.000011081486,0.0000021742055],"about_ca_topic_score_codex":0.023842689,"about_ca_topic_score_gemma":0.014115372,"teacher_disagreement_score":0.023842689,"about_ca_system_score_codex":0.0015443484,"about_ca_system_score_gemma":0.0006848214,"threshold_uncertainty_score":0.047407806},"labels":[],"label_agreement":null},{"id":"W2375764845","doi":"10.1515/jwld-2016-0003","title":"A wavelet-SARIMA-ANN hybrid model for precipitation forecasting","year":2016,"lang":"en","type":"article","venue":"Journal of Water and Land Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Wavelet; Precipitation; Series (stratigraphy); Wavelet transform; Artificial neural network; Meteorology; Environmental science; Computer science; Mathematics; Artificial intelligence; Geography; Geology","score_opus":0.03717630925865342,"score_gpt":0.23025017851582721,"score_spread":0.1930738692571738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2375764845","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37946913,0.0009698942,0.60393995,0.00049930334,0.00028328964,0.00010436637,0.00070773665,0.0012194646,0.012806866],"genre_scores_gemma":[0.96895444,0.00021756256,0.02541034,0.000039703616,0.000037057176,0.00008049185,0.00026641836,0.000019696408,0.004974299],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987435,0.000030914245,0.000010395633,0.0000354341,0.000030078465,0.000018903502],"domain_scores_gemma":[0.99977845,0.00010417675,0.000022694967,0.000011140251,0.00007375165,0.0000098582295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049205124,0.00044459733,0.00052694394,0.00046345431,0.00023514971,0.00065452163,0.0007583679,0.0005928676,0.0017378987],"category_scores_gemma":[0.00085052924,0.00025498163,0.0005130155,0.00061311154,0.0001662796,0.00063545373,0.000346164,0.00064989796,0.00034114264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008032007,0.00006914369,0.0014514163,0.000036541984,0.000049394363,0.00005307875,0.000017871786,0.96882015,0.0013568413,0.0008928908,0.00044788426,0.026724517],"study_design_scores_gemma":[0.0000017302992,0.0000075305556,0.00011714536,8.8467624e-7,0.0000023168363,0.0000023837379,0.0000011299836,0.9996296,0.000083742765,0.000097571705,0.00005471847,0.0000012303874],"about_ca_topic_score_codex":0.008037749,"about_ca_topic_score_gemma":0.0071700932,"teacher_disagreement_score":0.008037749,"about_ca_system_score_codex":0.00038609412,"about_ca_system_score_gemma":0.00051604497,"threshold_uncertainty_score":0.015981913},"labels":[],"label_agreement":null},{"id":"W2378184816","doi":"10.1007/s11270-016-2852-9","title":"A Novel Record-Extension Technique for Water Quality Variables Based on L-Moments","year":2016,"lang":"en","type":"article","venue":"Water Air & Soil Pollution","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Helwan University","keywords":"Ordinary least squares; Extension (predicate logic); Outlier; Missing data; Variance (accounting); Statistics; Regression; Moment (physics); Percentile; Computer science; Mathematics; Econometrics; Data mining; Accounting","score_opus":0.03077720454501487,"score_gpt":0.26129241798820474,"score_spread":0.23051521344318987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2378184816","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016385704,0.00019630232,0.98101074,0.00008817823,0.00008739171,0.000024429579,0.00022466951,0.0011442932,0.0008383533],"genre_scores_gemma":[0.3033444,0.00040944258,0.69095427,0.0000904696,0.000320647,0.00009511643,0.0009683421,0.00018798531,0.0036293755],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996896,0.00004950044,0.0000278419,0.00008376297,0.00011382065,0.000035491634],"domain_scores_gemma":[0.9991172,0.00030152284,0.0001360019,0.00016901738,0.00023181323,0.000044421122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005049779,0.0004919249,0.0005917357,0.0010216278,0.00044812352,0.00058387587,0.0009986265,0.00044702474,0.0020158093],"category_scores_gemma":[0.0023570566,0.00028347442,0.0005745312,0.0016778694,0.0002612013,0.0011662228,0.0006953713,0.0013161616,0.0010606258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048813064,0.00013284196,0.003061598,0.00013466498,0.000090189154,0.00014553203,0.00013366799,0.044687536,0.0666756,0.006697903,0.0036939573,0.8740584],"study_design_scores_gemma":[0.00002322029,0.00006436101,0.002675827,0.000013769655,0.00003691676,0.00013499496,0.000024840301,0.97122586,0.019058581,0.002423991,0.004275896,0.000041787913],"about_ca_topic_score_codex":0.0029860865,"about_ca_topic_score_gemma":0.0035457418,"teacher_disagreement_score":0.0029860865,"about_ca_system_score_codex":0.00023986655,"about_ca_system_score_gemma":0.00059885625,"threshold_uncertainty_score":0.0067434907},"labels":[],"label_agreement":null},{"id":"W2393170704","doi":"10.1515/jwld-2016-0004","title":"Water demand forecasting using extreme learning machines","year":2016,"lang":"en","type":"article","venue":"Journal of Water and Land Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Extreme learning machine; Artificial neural network; Transformation (genetics); Wavelet; Machine learning; Artificial intelligence; Computer science","score_opus":0.043198940997423385,"score_gpt":0.22400283306030863,"score_spread":0.18080389206288525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2393170704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66674215,0.00019062088,0.32762116,0.00036361866,0.000039317412,0.00003492334,0.00025922386,0.00042206558,0.0043268343],"genre_scores_gemma":[0.9892392,0.00003427925,0.010116436,0.0000149872685,0.000009974442,0.000013252784,0.00011932432,0.0000047368094,0.0004477659],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997501,0.00012055951,0.000013691277,0.000033236392,0.00006145656,0.00002089774],"domain_scores_gemma":[0.9992501,0.00048230702,0.00006606579,0.000050477804,0.00013159041,0.000019376479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006482333,0.00028977572,0.00040425154,0.00044722718,0.00013663266,0.00036600657,0.0004160802,0.00030136044,0.00068504363],"category_scores_gemma":[0.0023925889,0.00013980127,0.00027907308,0.0005209662,0.00017511862,0.0005128862,0.00026675343,0.00041339392,0.00011191745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003982975,0.000038299586,0.002376409,0.000014430277,0.000020447025,0.00002360656,0.000007916903,0.97698146,0.0006534792,0.0006633197,0.00024656777,0.018934242],"study_design_scores_gemma":[0.0000012189673,0.000004077167,0.00025993952,6.1058176e-7,7.0226815e-7,0.0000013000911,0.000001047319,0.9993094,0.00010541701,0.00029177495,0.000023674456,8.523295e-7],"about_ca_topic_score_codex":0.0074458243,"about_ca_topic_score_gemma":0.006346203,"teacher_disagreement_score":0.0074458243,"about_ca_system_score_codex":0.0004935975,"about_ca_system_score_gemma":0.00028661324,"threshold_uncertainty_score":0.014804959},"labels":[],"label_agreement":null},{"id":"W2398936495","doi":"10.1007/s00477-016-1265-z","title":"Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model","year":2016,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":226,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Extreme learning machine; Computational intelligence; Wavelet; Index (typography); Computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology); Artificial neural network","score_opus":0.06390041391793945,"score_gpt":0.3264049352160453,"score_spread":0.26250452129810586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398936495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26607808,0.0003276173,0.7297455,0.00033344922,0.00011989007,0.000033170763,0.00018470932,0.00029648695,0.0028810082],"genre_scores_gemma":[0.9623821,0.00017762143,0.035275042,0.000054271015,0.00004195475,0.000051598043,0.00016655972,0.00002200238,0.0018288866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998431,0.00004181797,0.000013173952,0.00004364609,0.00003380301,0.000024327623],"domain_scores_gemma":[0.9997234,0.00014467361,0.00003797287,0.000013364302,0.00006495813,0.000015605121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006194167,0.00038770615,0.00064778834,0.0004309661,0.0002457654,0.00062146387,0.00080102077,0.0009839925,0.0008447768],"category_scores_gemma":[0.0012033541,0.00022256761,0.0005790016,0.00072936044,0.0002781813,0.0009723637,0.00045975664,0.00091119093,0.00012566961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033822504,0.00003872746,0.00087798195,0.000020799975,0.000026633426,0.00003933996,0.000014082532,0.98114544,0.00094054133,0.0018054218,0.0002626858,0.014794668],"study_design_scores_gemma":[0.0000011827094,0.000002728136,0.000062348845,3.9032355e-7,0.0000014042209,0.0000015541931,8.179087e-7,0.99967265,0.00005744174,0.00018380197,0.000014856451,8.615981e-7],"about_ca_topic_score_codex":0.003132585,"about_ca_topic_score_gemma":0.0023613842,"teacher_disagreement_score":0.003132585,"about_ca_system_score_codex":0.0003570586,"about_ca_system_score_gemma":0.00046010653,"threshold_uncertainty_score":0.0062286854},"labels":[],"label_agreement":null},{"id":"W2414456746","doi":"10.1007/978-1-4615-4153-0_68","title":"Modeling the Deposition of Acid Fog to High-Elevation Forests: Liquid Water Content and Sulfate Concentration","year":2000,"lang":"en","type":"book-chapter","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Sulfate; Terrain; Elevation (ballistics); Deposition (geology); Environmental science; Acid deposition; Meteorology; Atmospheric sciences; Geography; Chemistry; Cartography; Geology; Soil science; Engineering","score_opus":0.0329198024041483,"score_gpt":0.21111973706218856,"score_spread":0.17819993465804027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2414456746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5597287,0.002496888,0.37844208,0.0017744821,0.00045551592,0.000064443964,0.001991739,0.0020338795,0.0530122],"genre_scores_gemma":[0.97134835,0.00097248866,0.018215591,0.00007525392,0.0001204958,0.00003055742,0.00042481563,0.00011617491,0.008696217],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99996245,0.000008442489,0.0000027446968,0.000011282936,0.000008914105,0.0000061632063],"domain_scores_gemma":[0.9998977,0.000057482837,0.000011842146,0.0000051774778,0.000018365927,0.000009503406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014463023,0.0005421617,0.00042043655,0.00024916077,0.0003235737,0.0007537542,0.0009671703,0.00079455244,0.001211656],"category_scores_gemma":[0.00044275858,0.00044064678,0.00042087163,0.0005993302,0.000313268,0.0009801311,0.00028627514,0.00061410456,0.00015960468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009506803,0.0000112116595,0.00094467663,0.000012572387,0.000013230597,0.000021960765,0.0000130778035,0.99236226,0.000725749,0.0017642749,0.00039475018,0.0037266978],"study_design_scores_gemma":[0.0000030524034,0.0000020374057,0.00025772568,0.0000010226281,0.000004247707,0.00000358155,0.0000036309289,0.9981249,0.00027055127,0.0011029616,0.0002234752,0.0000027948122],"about_ca_topic_score_codex":0.055276565,"about_ca_topic_score_gemma":0.03535392,"teacher_disagreement_score":0.055276565,"about_ca_system_score_codex":0.0008526503,"about_ca_system_score_gemma":0.0007309661,"threshold_uncertainty_score":0.10990965},"labels":[],"label_agreement":null},{"id":"W2416868720","doi":"10.2166/wst.2002.0539","title":"Model-based advanced process control of coagulation","year":2002,"lang":"en","type":"article","venue":"Water Science & Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; Suncor Energy (Canada); University of British Columbia","funders":"","keywords":"Process (computing); Control (management); Process control; Artificial neural network; Scale (ratio); Engineering; Coagulation; Quality (philosophy); Process engineering; Computer science; Artificial intelligence","score_opus":0.01534985509093919,"score_gpt":0.23396783749709288,"score_spread":0.21861798240615368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2416868720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07228329,0.00096103776,0.9123702,0.00034072966,0.00015129943,0.000081999555,0.00010684411,0.002114391,0.011590306],"genre_scores_gemma":[0.97337645,0.00032030398,0.02312686,0.000030652132,0.000022626788,0.00007306886,0.00007335429,0.000031282965,0.0029453242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978286,0.000038513088,0.0000119392425,0.000048918555,0.000096675365,0.00002109389],"domain_scores_gemma":[0.99978095,0.00007706413,0.000032474105,0.000015718195,0.00008557525,0.000008308128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041543812,0.00047508406,0.0004943511,0.00020670195,0.0002686421,0.0008390565,0.00050558354,0.00041031797,0.0011858237],"category_scores_gemma":[0.0007508347,0.00017372842,0.00030450645,0.00019562861,0.0003404571,0.00038264977,0.0003223993,0.00055210147,0.0002384701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011880886,0.0000498769,0.00037481397,0.000078713056,0.000027628827,0.000033572804,0.00004128982,0.92288923,0.017207604,0.0037149182,0.00074600184,0.054717593],"study_design_scores_gemma":[0.000007206378,0.00002775866,0.00010937963,0.0000019888066,0.000003998614,0.000004625482,0.0000015029219,0.99672455,0.0019703389,0.00047176247,0.00067383243,0.000003070118],"about_ca_topic_score_codex":0.011280451,"about_ca_topic_score_gemma":0.008376535,"teacher_disagreement_score":0.011280451,"about_ca_system_score_codex":0.00072794146,"about_ca_system_score_gemma":0.0007082222,"threshold_uncertainty_score":0.022429585},"labels":[],"label_agreement":null},{"id":"W2433271649","doi":"10.1109/oceansap.2016.7485552","title":"Bootstrapped ANN for forecasting seawater chlorophyll-a around the north Pacific Rim","year":2016,"lang":"en","type":"article","venue":"OCEANS 2016 - Shanghai","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"North Pacific Marine Science Organization","keywords":"Mariculture; Environmental science; Seawater; Eutrophication; Chlorophyll a; Outlier; Mean squared error; Oceanography; Plankton; Biomass (ecology); Salinity; Statistics; Nutrient; Fishery; Mathematics; Ecology; Geology; Fish <Actinopterygii>; Biology","score_opus":0.03384717906020867,"score_gpt":0.23207163865123534,"score_spread":0.19822445959102666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2433271649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7810571,0.00084878196,0.21107067,0.00034452465,0.00012873253,0.00003230592,0.00044796645,0.0009812119,0.0050887302],"genre_scores_gemma":[0.9895642,0.00011078713,0.0094560115,0.000023590548,0.000012570148,0.000014896845,0.00021752321,0.000008664148,0.00059173873],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998796,0.000037366328,0.000010129434,0.000026717551,0.00003179094,0.000014300712],"domain_scores_gemma":[0.99970067,0.00014284885,0.00003546283,0.000022611282,0.000084494815,0.000013887694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043496105,0.0003808231,0.00027302836,0.00032622236,0.00017185841,0.0002704869,0.00039938572,0.00030582526,0.00050517457],"category_scores_gemma":[0.0013154617,0.00016439836,0.00026484494,0.0003278583,0.0001068358,0.00041656932,0.00025971181,0.00046649572,0.000112609625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006257243,0.0000385234,0.005068023,0.000020348261,0.00003704579,0.000056427893,0.000016228434,0.96105987,0.0013306554,0.00027799397,0.00043461964,0.031597666],"study_design_scores_gemma":[0.0000010257926,0.000004385274,0.00059757626,0.0000010072354,0.000001920077,0.0000014061711,0.0000017768888,0.999161,0.00010546984,0.00008945194,0.000033789813,0.0000011367752],"about_ca_topic_score_codex":0.014216456,"about_ca_topic_score_gemma":0.010309186,"teacher_disagreement_score":0.014216456,"about_ca_system_score_codex":0.0003345614,"about_ca_system_score_gemma":0.00038096655,"threshold_uncertainty_score":0.028267384},"labels":[],"label_agreement":null},{"id":"W2463556800","doi":"10.18178/ijesd.2016.7.12.901","title":"Finer Scale Rainfall Projections for Kerala Meteorological Subdivision, India Based on Multivariate Empirical Mode Decomposition","year":2016,"lang":"en","type":"article","venue":"International Journal of Environmental Science and Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Centre for Engineering Research and Development; Indian Institute of Technology Bombay","keywords":"Subdivision; Multivariate statistics; Decomposition; Hilbert–Huang transform; Scale (ratio); Mode (computer interface); Environmental science; Climatology; Multivariate analysis; Geography; Mathematics; Statistics; Geology; Computer science; Ecology; Biology; Cartography","score_opus":0.024134093511033895,"score_gpt":0.33907793753338095,"score_spread":0.31494384402234704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463556800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9260696,0.00010816074,0.070765615,0.000104917,0.000010825635,0.000018658075,0.0008619289,0.0003579748,0.001702303],"genre_scores_gemma":[0.98114437,0.000077984085,0.017787078,0.000006423706,0.000005605646,0.000014351507,0.0006606426,0.000016704817,0.00028676091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999573,0.000011607379,0.0000024426176,0.000011989436,0.0000083179975,0.000008383397],"domain_scores_gemma":[0.99991775,0.00002472799,0.000014766235,0.000012752742,0.000023852243,0.0000062004956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014012025,0.00021970145,0.00013250449,0.0004619437,0.00009131741,0.00028026922,0.00024106128,0.000101717,0.00047277106],"category_scores_gemma":[0.0004846977,0.00008495577,0.00029349566,0.0005217014,0.000060941107,0.00026625974,0.00020403168,0.00019664636,0.00010074214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000106454,0.000060062306,0.055321846,0.00005421517,0.000059011138,0.00020499791,0.00010705059,0.84584403,0.008997258,0.0030720902,0.0010564014,0.08511666],"study_design_scores_gemma":[0.0000037851632,0.000007946889,0.017446483,0.0000024920766,0.0000067490573,0.000014360482,0.000030507996,0.9810579,0.0006492718,0.0004433962,0.00033041587,0.0000067198735],"about_ca_topic_score_codex":0.012389098,"about_ca_topic_score_gemma":0.0131087,"teacher_disagreement_score":0.012389098,"about_ca_system_score_codex":0.00016757827,"about_ca_system_score_gemma":0.00032478865,"threshold_uncertainty_score":0.024633944},"labels":[],"label_agreement":null},{"id":"W2465694013","doi":"10.2166/ws.2015.066","title":"Development of artificial neural networks based confidence intervals and response surfaces for the optimization of coagulation performance","year":2015,"lang":"en","type":"article","venue":"Water Science & Technology Water Supply","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Alum; Turbidity; Interval (graph theory); Artificial neural network; Mean squared error; Coagulation; Confidence interval; Statistics; Carbon dioxide; Response surface methodology; Mathematics; Environmental science; Computer science; Machine learning; Chemistry; Ecology","score_opus":0.03179629015219974,"score_gpt":0.24768816164068783,"score_spread":0.2158918714884881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2465694013","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061793327,0.00059281744,0.9339453,0.00016169074,0.00003659583,0.00008959607,0.00014249385,0.0010660817,0.0021721018],"genre_scores_gemma":[0.73419017,0.0003727998,0.26353273,0.000060792,0.000030354622,0.00036181463,0.00046196367,0.00015574289,0.00083356956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959294,0.0021668174,0.0003390366,0.0003436898,0.0010880333,0.00013299884],"domain_scores_gemma":[0.98183167,0.013713945,0.0014067064,0.0005920086,0.0023503425,0.00010522369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009960155,0.0010097052,0.00095491915,0.0023472982,0.00022958529,0.0013144948,0.0014368116,0.0009815262,0.0009014648],"category_scores_gemma":[0.036491018,0.0005031104,0.00093701854,0.0014550844,0.00049112673,0.0011662296,0.00093748525,0.0014877291,0.00021467252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118952856,0.000058988222,0.0020719764,0.00012241951,0.00008373194,0.000035389614,0.000055586806,0.93369675,0.0017384932,0.003763004,0.00032147378,0.057933174],"study_design_scores_gemma":[0.00000523708,0.000035755347,0.00047339822,0.000013159453,0.0000058722035,0.000008092018,0.0000071813515,0.9972133,0.0010548588,0.0009482427,0.00022408682,0.00001074323],"about_ca_topic_score_codex":0.0041081714,"about_ca_topic_score_gemma":0.0018733534,"teacher_disagreement_score":0.009960155,"about_ca_system_score_codex":0.000981028,"about_ca_system_score_gemma":0.00078219594,"threshold_uncertainty_score":0.05267501},"labels":[],"label_agreement":null},{"id":"W2469821678","doi":"10.1016/j.measurement.2016.06.042","title":"Discharge forecasting using an Online Sequential Extreme Learning Machine (OS-ELM) model: A case study in Neckar River, Germany","year":2016,"lang":"en","type":"article","venue":"Measurement","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":88,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extreme learning machine; Flood myth; Mean squared error; Flood forecasting; Support vector machine; Computer science; Artificial neural network; Flooding (psychology); Ensemble forecasting; Coefficient of determination; Machine learning; Data mining; Artificial intelligence; Statistics; Mathematics; Geography","score_opus":0.30117023107441526,"score_gpt":0.30567662153705055,"score_spread":0.00450639046263529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469821678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98466176,0.00008652338,0.0128718605,0.00026253937,0.00001703337,0.000028353923,0.00031360297,0.00021256543,0.0015457984],"genre_scores_gemma":[0.99702495,0.000039143448,0.0021272225,0.0000076278093,0.0000041052836,0.000009664671,0.00013082642,0.000009699628,0.000646818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997031,0.00010957141,0.000023290417,0.00006807895,0.000039675164,0.00005627154],"domain_scores_gemma":[0.999318,0.0004487366,0.000053862335,0.00004197656,0.0000973014,0.0000401063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008540262,0.0007359466,0.00070075184,0.0005359008,0.0005989956,0.0010780755,0.0009899187,0.0016156274,0.0007703376],"category_scores_gemma":[0.0015745508,0.00036463107,0.0005547249,0.0008701145,0.00065977336,0.000933059,0.00047809695,0.0007317732,0.0001232758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013497789,0.00013936897,0.008022805,0.000029593533,0.000038053713,0.00068383577,0.00006602923,0.9820256,0.00081583025,0.0010190115,0.0004910718,0.0065338407],"study_design_scores_gemma":[0.000016183321,0.000029735693,0.0019024021,0.000002067636,0.000010925357,0.000014983964,0.000046282385,0.99717075,0.00036179673,0.00034157652,0.00009443533,0.000008910531],"about_ca_topic_score_codex":0.09481816,"about_ca_topic_score_gemma":0.059446387,"teacher_disagreement_score":0.09481816,"about_ca_system_score_codex":0.0015932977,"about_ca_system_score_gemma":0.0010781767,"threshold_uncertainty_score":0.18853253},"labels":[],"label_agreement":null},{"id":"W2480282550","doi":"10.5194/hess-2016-347","title":"Acclimatizing Fast Orthogonal Search (FOS) Model for River Stream-flow Forecasting","year":2016,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"Universiti Kebangsaan Malaysia","keywords":"Computer science; Process (computing); Flow (mathematics); Data mining; Mathematics","score_opus":0.08206298163789638,"score_gpt":0.27215467345646505,"score_spread":0.19009169181856866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2480282550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08335093,0.00040330162,0.90927356,0.0002548749,0.00008264773,0.00006745543,0.00013919904,0.0002786426,0.0061494047],"genre_scores_gemma":[0.93993974,0.00030347117,0.054491114,0.00006378463,0.00003320889,0.00015611947,0.00021638772,0.000039950588,0.0047563007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997563,0.000077623234,0.000014394627,0.000043653497,0.00007347062,0.000034631266],"domain_scores_gemma":[0.99973136,0.00011600646,0.000035253266,0.00000983687,0.00009440706,0.000013107455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006221715,0.0005621079,0.0006391034,0.0003599699,0.00034139463,0.00054370204,0.00074177905,0.00061250234,0.0018021282],"category_scores_gemma":[0.0011118572,0.00022041546,0.0006036032,0.00043408913,0.0003311441,0.0006931472,0.00047054153,0.00070027116,0.0001984864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029736728,0.000018711647,0.00077942334,0.000029860434,0.000018340143,0.00003341092,0.000022437021,0.98286563,0.0008964035,0.0033985327,0.00033756642,0.0115698865],"study_design_scores_gemma":[0.0000014387716,0.0000054969073,0.00004124525,7.567606e-7,0.0000011621776,0.0000018366316,0.0000010312851,0.99967813,0.000057518027,0.0001503984,0.000060024195,9.621191e-7],"about_ca_topic_score_codex":0.017757345,"about_ca_topic_score_gemma":0.00914784,"teacher_disagreement_score":0.017757345,"about_ca_system_score_codex":0.00042714356,"about_ca_system_score_gemma":0.00096377,"threshold_uncertainty_score":0.035308003},"labels":[],"label_agreement":null},{"id":"W2487421346","doi":"10.82308/26292","title":"Analyzing trends in temperature, streamflow and precipitation over Southern Ontario and Québec using the discreet wavelet transform","year":2013,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Streamflow; Precipitation; Environmental science; Climatology; Trend analysis; Series (stratigraphy); Wavelet; Discrete wavelet transform; Climate change; Wavelet transform; Time series; Principal component analysis; Statistics; Mathematics; Meteorology; Geography; Geology; Computer science; Drainage basin","score_opus":0.014704591095679708,"score_gpt":0.21577225982701145,"score_spread":0.20106766873133175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2487421346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98295915,0.00020166545,0.008663306,0.00015240186,0.000011954045,0.000034474022,0.0039491393,0.00009308296,0.003934805],"genre_scores_gemma":[0.9881813,0.00021214143,0.0071828454,0.000019944613,0.0000041657495,0.000021446825,0.0017496571,0.000014654421,0.0026138336],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9999063,0.000005354835,0.000004490834,0.000020623527,0.00004274847,0.000020431013],"domain_scores_gemma":[0.9996401,0.000048582522,0.0000436386,0.000013187441,0.00023253188,0.000022007014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017259245,0.00016541839,0.00010269335,0.0007825721,0.00051096024,0.00059632905,0.00022925367,0.00013553823,0.0009638871],"category_scores_gemma":[0.00081319304,0.00006283033,0.00013278186,0.0022004806,0.00017547699,0.00018253432,0.00014301528,0.00017277754,0.00009238024],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024199819,0.00009179777,0.59412116,0.00019133941,0.00014508258,0.00048198007,0.0019351401,0.045945376,0.048440736,0.0025239408,0.005969125,0.29991233],"study_design_scores_gemma":[0.0000067537358,0.000017130933,0.92828345,0.00001636019,0.00002257058,0.00003588023,0.00079381274,0.064122364,0.0022076182,0.00016415806,0.00430891,0.000021053711],"about_ca_topic_score_codex":0.97597337,"about_ca_topic_score_gemma":0.9854292,"teacher_disagreement_score":0.024026632,"about_ca_system_score_codex":0.0047921618,"about_ca_system_score_gemma":0.0048425687,"threshold_uncertainty_score":0.048336208},"labels":[],"label_agreement":null},{"id":"W2492623139","doi":"","title":"Bias correction of ANN based statistically ownscaled precipitation data for the Chaliyar river basin","year":2013,"lang":"en","type":"article","venue":"International Journal of Innovative Research in Science Engineering and Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Downscaling; Environmental science; Precipitation; Climatology; Rain gauge; Drainage basin; Scale (ratio); GCM transcription factors; Correlation coefficient; Structural basin; Hydrological modelling; Climate change; Climate model; Atmospheric research; Meteorology; General Circulation Model; Geography; Geology; Statistics","score_opus":0.09333360076858832,"score_gpt":0.37583914806495683,"score_spread":0.2825055472963685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492623139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98799664,0.00006834285,0.009416216,0.000045659464,0.000033167227,0.000029710673,0.0007810953,0.00039106997,0.001237979],"genre_scores_gemma":[0.9897363,0.000050809158,0.008304209,0.000010676782,0.0000071861214,0.000027992877,0.0013619241,0.000024678007,0.00047615854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998691,0.000028021685,0.000015947648,0.000046050038,0.00002267818,0.000018134533],"domain_scores_gemma":[0.9996013,0.00013618112,0.00004753716,0.00006522133,0.00013846927,0.000011327433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048055206,0.000314414,0.00017267658,0.00042197134,0.00020103196,0.0002844512,0.00033251548,0.00018956768,0.0007248555],"category_scores_gemma":[0.001298332,0.00017988677,0.00035366238,0.00054934644,0.00009147786,0.00029003472,0.00020214388,0.00027983612,0.00016732392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030917916,0.00019127634,0.16149296,0.0000904931,0.00019686086,0.00026355623,0.00009868642,0.70570946,0.011630072,0.0005376339,0.0015707837,0.1179091],"study_design_scores_gemma":[0.000019678473,0.000029233584,0.064379774,0.0000074530744,0.00002184493,0.000018386872,0.000024488318,0.9305615,0.004354828,0.00015756949,0.00041065377,0.000014491949],"about_ca_topic_score_codex":0.02719177,"about_ca_topic_score_gemma":0.025774354,"teacher_disagreement_score":0.02719177,"about_ca_system_score_codex":0.0005869905,"about_ca_system_score_gemma":0.0007342999,"threshold_uncertainty_score":0.054066956},"labels":[],"label_agreement":null},{"id":"W2515412127","doi":"10.1016/j.jenvman.2016.07.069","title":"Groundwater level prediction using a SOM-aided stepwise cluster inference model","year":2016,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; McMaster University","funders":"National Key Research and Development Program of China; China Postdoctoral Science Foundation","keywords":"Arid; Environmental science; Cluster analysis; Groundwater; Hydrology (agriculture); Computer science; Machine learning; Ecology; Engineering","score_opus":0.045945335170280155,"score_gpt":0.24345113156983356,"score_spread":0.1975057963995534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515412127","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08446699,0.00010396861,0.9120952,0.000104200786,0.0000550331,0.00005271833,0.00033615035,0.001402788,0.0013829562],"genre_scores_gemma":[0.73320496,0.000076856646,0.2637541,0.000051779232,0.00003638881,0.00011568686,0.000678079,0.00008548538,0.0019967272],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999783,0.000053239633,0.00001832949,0.00006867148,0.00004527473,0.00003151265],"domain_scores_gemma":[0.9991387,0.00043093867,0.000043643922,0.00006253492,0.00028688478,0.000037249087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091909384,0.00051388325,0.00087136653,0.00076054735,0.0006504107,0.00075921643,0.0015527066,0.00069588306,0.0016863701],"category_scores_gemma":[0.0020162815,0.0004716361,0.0010326849,0.0010988666,0.00025407862,0.00073578313,0.00061157136,0.0009968665,0.000461241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023244698,0.00011751318,0.0031822242,0.00003604928,0.00013042973,0.000044021534,0.00004314024,0.89672744,0.0021930893,0.0014422465,0.0009900075,0.09486137],"study_design_scores_gemma":[0.0000020920013,0.0000031207373,0.00008183243,4.793736e-7,0.00000330397,0.0000011268831,0.0000010844738,0.9995857,0.00013234426,0.00016530466,0.000022214947,0.0000014625625],"about_ca_topic_score_codex":0.031899408,"about_ca_topic_score_gemma":0.03380186,"teacher_disagreement_score":0.031899408,"about_ca_system_score_codex":0.00054599566,"about_ca_system_score_gemma":0.0014355957,"threshold_uncertainty_score":0.06342745},"labels":[],"label_agreement":null},{"id":"W2515552876","doi":"","title":"A New Wavelet Based Approach to Assess Hydrological Models","year":2014,"lang":"en","type":"article","venue":"2014 AGU Fall Meeting","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Wavelet; Computer science; Artificial intelligence; Environmental science","score_opus":0.05183380909433727,"score_gpt":0.2465586928622782,"score_spread":0.19472488376794092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515552876","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017927598,0.00009095898,0.97979957,0.00005250103,0.000050657294,0.000023966475,0.00013340071,0.00022704649,0.0016942869],"genre_scores_gemma":[0.4472005,0.00048473882,0.54663825,0.00007762465,0.0001768053,0.00013992534,0.0008553779,0.00027738517,0.0041494304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994823,0.00010723869,0.00005189489,0.00008783866,0.00023017186,0.000040496652],"domain_scores_gemma":[0.9987243,0.00047203095,0.00013260554,0.00016084922,0.0004394294,0.00007074345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011568089,0.00075249834,0.0005534648,0.0024898117,0.00032081598,0.0013999202,0.00080574374,0.00082830683,0.0020280327],"category_scores_gemma":[0.004611581,0.00031763536,0.00063753355,0.001703942,0.00036208713,0.0021546246,0.0008972321,0.0010582559,0.0006159786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023844265,0.00028426724,0.0077941427,0.00020877112,0.00025167083,0.0002608292,0.00017399518,0.41956604,0.055363115,0.054558028,0.003373358,0.4579274],"study_design_scores_gemma":[0.0000052664386,0.00003176823,0.0008433132,0.0000055999067,0.000021181871,0.000027542372,0.000016722635,0.99162537,0.0017363651,0.004930389,0.00074461696,0.000011952689],"about_ca_topic_score_codex":0.0016982001,"about_ca_topic_score_gemma":0.0012627761,"teacher_disagreement_score":0.0024898117,"about_ca_system_score_codex":0.0003559559,"about_ca_system_score_gemma":0.0003923188,"threshold_uncertainty_score":0.0067843795},"labels":[],"label_agreement":null},{"id":"W2517531326","doi":"","title":"Forecasting Urban Water Demand via Machine Learning Methods Coupled with a Bootstrap Rank-Ordered Conditional Mutual Information Input Variable Selection Method","year":2014,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mutual information; Feature selection; Variable (mathematics); Rank (graph theory); Selection (genetic algorithm); Computer science; Artificial intelligence; Machine learning; Econometrics; Data mining; Mathematics","score_opus":0.01785113444025988,"score_gpt":0.2577239810642298,"score_spread":0.2398728466239699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517531326","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13799752,0.00011643796,0.85888165,0.0002939241,0.000055528384,0.00006955169,0.00023218257,0.0010423355,0.0013107994],"genre_scores_gemma":[0.8775273,0.0000669946,0.1201013,0.00008230956,0.00009744877,0.0001530217,0.00065291027,0.00006893671,0.0012497196],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919003,0.00044484076,0.000044741966,0.00010385532,0.00014774252,0.00006877529],"domain_scores_gemma":[0.99538064,0.0034792905,0.0002310192,0.00018661961,0.00063048507,0.00009196086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022583737,0.00061898795,0.0011930134,0.000922377,0.0004975819,0.000741872,0.001229472,0.0008565256,0.0018078983],"category_scores_gemma":[0.00713833,0.0005597099,0.0008053837,0.000890309,0.00050209736,0.0010907702,0.00085891574,0.0010682152,0.00034060742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014529102,0.00011141783,0.0015277037,0.000029916004,0.000054749256,0.000037095822,0.000021317053,0.9518248,0.0007225114,0.0029463677,0.00092252553,0.04165621],"study_design_scores_gemma":[0.0000021349322,0.0000029152022,0.000054591408,3.2390176e-7,9.74842e-7,5.901461e-7,5.371732e-7,0.99965847,0.0000685119,0.00019715277,0.0000128286765,9.781853e-7],"about_ca_topic_score_codex":0.008603387,"about_ca_topic_score_gemma":0.007956389,"teacher_disagreement_score":0.008603387,"about_ca_system_score_codex":0.00060686294,"about_ca_system_score_gemma":0.0012001118,"threshold_uncertainty_score":0.017106652},"labels":[],"label_agreement":null},{"id":"W2518119950","doi":"10.1007/s11269-016-1489-1","title":"Probabilistic Prediction for Monthly Streamflow through Coupling Stepwise Cluster Analysis and Quantile Regression Methods","year":2016,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Regina","funders":"Science and Engineering Research Board; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Quantile; Probabilistic logic; Statistics; Streamflow; Linear regression; Standard deviation; Quantile regression; Regression; Mathematics; Regression analysis; Stepwise regression; Prediction interval; Calibration; Probabilistic forecasting; Geography","score_opus":0.022614397117446207,"score_gpt":0.28180607966094123,"score_spread":0.259191682543495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2518119950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031525344,0.000061032326,0.96742547,0.000055472923,0.000014711511,0.00003814027,0.000105447056,0.00048348802,0.00029099543],"genre_scores_gemma":[0.7153177,0.00013481505,0.28209665,0.00004232494,0.00004239321,0.0001891002,0.000710316,0.00015059857,0.0013160977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896586,0.0005284906,0.000053596985,0.00018912651,0.00018813567,0.00007482406],"domain_scores_gemma":[0.9955329,0.0030371733,0.00025532173,0.00034065646,0.0007601389,0.000073938114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035248485,0.0006214864,0.0008106561,0.0010790742,0.0004656918,0.0005933625,0.0013737306,0.0004912503,0.0015176104],"category_scores_gemma":[0.008993805,0.00049791473,0.0009958238,0.0014868822,0.00029652988,0.0010580824,0.00083325134,0.0012587334,0.00040960533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012409434,0.00010390604,0.00474419,0.00003938634,0.00014569993,0.000025487492,0.00006444748,0.9089256,0.0012750779,0.005358795,0.0008711129,0.0783222],"study_design_scores_gemma":[0.0000025184077,0.0000050494764,0.00030067065,9.959939e-7,0.000004714855,0.0000017847985,0.000002013301,0.99835265,0.00013644519,0.0011458411,0.00004465023,0.0000026789628],"about_ca_topic_score_codex":0.012828151,"about_ca_topic_score_gemma":0.011636448,"teacher_disagreement_score":0.012828151,"about_ca_system_score_codex":0.0005590538,"about_ca_system_score_gemma":0.0011590061,"threshold_uncertainty_score":0.025506973},"labels":[],"label_agreement":null},{"id":"W2528751116","doi":"","title":"Dissipation of Thermal Enrichment of Stormwater Management Ponds","year":2013,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Albert Einstein College of Medicine, Yeshiva University","keywords":"Stormwater management; Stormwater; Thermal management of electronic devices and systems; Environmental science; Dissipation; Hydrology (agriculture); Environmental engineering; Surface runoff; Geotechnical engineering; Engineering; Ecology; Physics; Biology","score_opus":0.011645421370994901,"score_gpt":0.20814498092767167,"score_spread":0.19649955955667678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528751116","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904749,0.000026961341,0.0074093896,0.00001448738,0.0000041504422,0.000019476409,0.00009117217,0.000056112152,0.0019034178],"genre_scores_gemma":[0.9989034,0.000013522966,0.00054624776,0.000002028028,5.740755e-7,0.000007754752,0.00003666855,0.0000036330955,0.00048613947],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9998142,0.000018861525,0.0000080110885,0.00003593818,0.00006620939,0.000056746398],"domain_scores_gemma":[0.99986506,0.00003202857,0.000029373163,0.000017190416,0.00004281337,0.000013576047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020760974,0.0002114458,0.00028299162,0.00013124451,0.00032840416,0.00057588785,0.00021707843,0.00015310243,0.0017559981],"category_scores_gemma":[0.0005628212,0.00017019699,0.0002502891,0.00027169572,0.0002635261,0.00032603982,0.0003639301,0.00018604935,0.00015392978],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058531156,0.00016399087,0.10087947,0.00030511827,0.00006835974,0.0007891466,0.00051112444,0.3592447,0.46555948,0.0012006018,0.00078790233,0.06990482],"study_design_scores_gemma":[0.000058726906,0.0008081854,0.39805993,0.000025882864,0.00006194498,0.00020401852,0.0010375595,0.42548397,0.16961138,0.0011504269,0.0034586533,0.00003929937],"about_ca_topic_score_codex":0.005186964,"about_ca_topic_score_gemma":0.010510156,"teacher_disagreement_score":0.005186964,"about_ca_system_score_codex":0.00084684324,"about_ca_system_score_gemma":0.0004579537,"threshold_uncertainty_score":0.0103135705},"labels":[],"label_agreement":null},{"id":"W2535399616","doi":"10.14288/1.0305711","title":"Short-term hydro-meteorological forecasting with extreme learning machines","year":2016,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Meteorology; Environmental science; Climatology; Weather forecasting; Computer science; Geography; Geology","score_opus":0.02243686273586998,"score_gpt":0.17762912564932948,"score_spread":0.1551922629134595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2535399616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19545203,0.0009342189,0.7948241,0.0003607833,0.00008348396,0.00008162935,0.00026807652,0.0011500984,0.006845538],"genre_scores_gemma":[0.8736369,0.00035186816,0.12370228,0.000043043772,0.00005990124,0.00009233842,0.00029946523,0.000043253516,0.0017709957],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996482,0.00012062646,0.000024447807,0.00005719359,0.0001249647,0.00002457856],"domain_scores_gemma":[0.9992034,0.0005291983,0.000060394894,0.000067922,0.00012546951,0.000013675702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008112511,0.00064679387,0.00054701813,0.0003455973,0.00023452009,0.00071791554,0.00063938886,0.00060403947,0.0011535706],"category_scores_gemma":[0.0028132522,0.0003323719,0.0005892908,0.0006575358,0.00029828984,0.0010390853,0.0006273393,0.0014232214,0.00022660909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038821905,0.00003915244,0.0013711727,0.00003319347,0.000035716355,0.000018829778,0.000026337673,0.9526053,0.00075219694,0.0018898176,0.00038704186,0.0428024],"study_design_scores_gemma":[0.0000027193719,0.000014331976,0.00023370016,0.0000024427165,0.0000017947265,0.0000027614951,0.000002503937,0.99800473,0.0003783328,0.0011713572,0.00018251987,0.0000027960673],"about_ca_topic_score_codex":0.0040203314,"about_ca_topic_score_gemma":0.003432617,"teacher_disagreement_score":0.0040203314,"about_ca_system_score_codex":0.0004964489,"about_ca_system_score_gemma":0.00047030495,"threshold_uncertainty_score":0.007993877},"labels":[],"label_agreement":null},{"id":"W2543665400","doi":"10.1016/j.jhydrol.2016.10.048","title":"Application of multi-scale wavelet entropy and multi-resolution Volterra models for climatic downscaling","year":2016,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Science and Technology Department of Ningxia","keywords":"Downscaling; Principal component analysis; Wavelet; Cluster analysis; Computer science; Precipitation; Environmental science; Statistics; Mathematics; Meteorology; Artificial intelligence; Geography","score_opus":0.029837617593344176,"score_gpt":0.2677538424816919,"score_spread":0.23791622488834768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2543665400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21540959,0.00049123896,0.7807805,0.0003334115,0.0001665485,0.000030073585,0.0001328052,0.00039489815,0.0022609204],"genre_scores_gemma":[0.9172873,0.0002159214,0.08155114,0.000029120189,0.000051778454,0.000020165964,0.00008045159,0.0000727529,0.000691342],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998753,0.000043378677,0.00001195215,0.000020233727,0.000037812864,0.00001133817],"domain_scores_gemma":[0.99949706,0.00029737054,0.00004203773,0.000053776206,0.00009018841,0.000019479849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082934217,0.00032347042,0.00039436977,0.00053769595,0.00024085863,0.0006041344,0.00030914368,0.00041719704,0.0007763684],"category_scores_gemma":[0.0028904483,0.00025400546,0.00046699005,0.00051082944,0.00016427346,0.0010188372,0.00046925643,0.0006503267,0.00011384566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104415245,0.000087381086,0.002233331,0.000045835946,0.00009105939,0.00007243206,0.00004310186,0.89006025,0.0102262655,0.008273628,0.00038901484,0.088373266],"study_design_scores_gemma":[0.0000015502201,0.000002741644,0.00021979617,7.794349e-7,0.0000031850734,0.0000023373673,0.0000011289045,0.99889886,0.00035313563,0.0004698349,0.000044944394,0.0000016683905],"about_ca_topic_score_codex":0.002344756,"about_ca_topic_score_gemma":0.0025275948,"teacher_disagreement_score":0.002344756,"about_ca_system_score_codex":0.0002589693,"about_ca_system_score_gemma":0.00039706356,"threshold_uncertainty_score":0.004662156},"labels":[],"label_agreement":null},{"id":"W2558716939","doi":"","title":"Flow and Sediment Prediction at Ungauged Basins Using Artificial Intelligence Models and Entropy Index","year":2016,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Index (typography); Entropy (arrow of time); Sediment; Flow (mathematics); Geology; Hydrology (agriculture); Environmental science; Geotechnical engineering; Computer science; Mathematics; Geomorphology; Physics; Thermodynamics; Geometry","score_opus":0.029187003367531536,"score_gpt":0.2247376555598014,"score_spread":0.19555065219226986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2558716939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9850739,0.000040189814,0.014142891,0.0000642082,0.0000038060623,0.000006852062,0.000071842325,0.00006025294,0.0005360569],"genre_scores_gemma":[0.9981681,0.000023739629,0.0015143384,0.000003442351,0.0000018527052,0.0000037865716,0.000075123164,0.0000030797237,0.00020644742],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992144,0.000019278461,0.0000058124297,0.000021516607,0.00001735342,0.000014525054],"domain_scores_gemma":[0.99966216,0.00018201908,0.00007122248,0.000011784823,0.000051402665,0.000021438858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027344257,0.00035380016,0.00023414877,0.0005664185,0.00022308301,0.0005274279,0.0002993234,0.00023656894,0.00023065029],"category_scores_gemma":[0.0011566497,0.00022011659,0.00032321454,0.0005331323,0.00036286275,0.00040590565,0.00021684737,0.00026014552,0.000041656644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003340033,0.000023631903,0.028508924,0.0000080219,0.000019660618,0.000046316436,0.00003386706,0.9635526,0.0008830711,0.00025480578,0.00007610887,0.0065595773],"study_design_scores_gemma":[0.0000010859924,0.0000045712877,0.0047006146,6.009202e-7,0.0000017183739,0.0000016085708,0.000005791222,0.9950311,0.0001254217,0.000110490946,0.000015302428,0.0000017074096],"about_ca_topic_score_codex":0.09672687,"about_ca_topic_score_gemma":0.08082944,"teacher_disagreement_score":0.09672687,"about_ca_system_score_codex":0.0013336265,"about_ca_system_score_gemma":0.0008526568,"threshold_uncertainty_score":0.19232768},"labels":[],"label_agreement":null},{"id":"W2560338233","doi":"","title":"A New Selection Metric for Multi-Objective Hydrologic Model Calibration","year":2014,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Calibration; Metric (unit); Selection (genetic algorithm); Model selection; Computer science; Hydrological modelling; Environmental science; Mathematics; Statistics; Artificial intelligence; Geology; Engineering; Operations management","score_opus":0.03574679330487407,"score_gpt":0.2632339800298319,"score_spread":0.22748718672495782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560338233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017424578,0.00033590046,0.9786774,0.00017418627,0.00010413882,0.00009655279,0.0003376982,0.00079968123,0.0020498047],"genre_scores_gemma":[0.37590244,0.00029714213,0.6170399,0.00030681925,0.00023139457,0.00050345284,0.0023346846,0.00073275145,0.0026512903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99509805,0.0019621998,0.0005017529,0.0005267347,0.0017229491,0.00018834826],"domain_scores_gemma":[0.9888995,0.0047081476,0.0009175864,0.0010368706,0.004064119,0.00037372918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007533453,0.0017808406,0.0019017345,0.0040979283,0.0007910938,0.0021991513,0.0019455893,0.0017026204,0.0027073054],"category_scores_gemma":[0.019414445,0.0004318091,0.0012258074,0.0031820359,0.00074091885,0.0023060488,0.0021732333,0.0016568248,0.000626127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033842376,0.00031292127,0.0074066524,0.00032730974,0.00048289401,0.00014626948,0.00008101986,0.5395137,0.009164972,0.010065854,0.008672741,0.42348722],"study_design_scores_gemma":[0.000020612046,0.000116411815,0.0012686421,0.000020124355,0.000035494897,0.000054677643,0.000019355322,0.9922443,0.0019849576,0.0028953245,0.0013179625,0.000022096063],"about_ca_topic_score_codex":0.0033008703,"about_ca_topic_score_gemma":0.0032469742,"teacher_disagreement_score":0.007533453,"about_ca_system_score_codex":0.0010435933,"about_ca_system_score_gemma":0.0014978031,"threshold_uncertainty_score":0.039841175},"labels":[],"label_agreement":null},{"id":"W2562380678","doi":"10.14796/jwmm.c413","title":"Improving Operational Water Quality Forecasting with Ensemble Data Assimilation","year":2016,"lang":"en","type":"article","venue":"Journal of Water Management Modeling","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Environmental Research; University of Texas at Arlington; National Science Foundation","keywords":"Data assimilation; Assimilation (phonology); Computer science; Environmental science; Quality (philosophy); Water quality; Meteorology; Geography","score_opus":0.09872408788273863,"score_gpt":0.2722508972305022,"score_spread":0.1735268093477636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562380678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26769128,0.0001979064,0.72831684,0.00029570045,0.00007419466,0.000040677776,0.00023865605,0.0016937351,0.0014509409],"genre_scores_gemma":[0.8743269,0.0001143469,0.12451007,0.00005871699,0.000040778174,0.0000489297,0.00045386623,0.00008569816,0.0003607604],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967027,0.00009330042,0.000024605204,0.00006598487,0.00009852083,0.000047298097],"domain_scores_gemma":[0.99897194,0.0004300921,0.00010697428,0.00019671604,0.00025497354,0.00003941494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013065651,0.0005450025,0.0006464469,0.00054256775,0.0003045924,0.0006681007,0.00069999194,0.000661525,0.00064376905],"category_scores_gemma":[0.004343908,0.00033107214,0.0006141116,0.0008075632,0.00021501195,0.0015112594,0.00091484946,0.0010620529,0.00017112045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048225138,0.00006497143,0.0048196223,0.000013751124,0.000057919082,0.000020333915,0.00003965511,0.9275822,0.0031559751,0.0006322972,0.00052929664,0.06303572],"study_design_scores_gemma":[0.00000254678,0.0000049629125,0.00038476038,5.953516e-7,0.0000025168956,0.0000010091888,0.0000021159165,0.9990682,0.00029004703,0.00015838373,0.0000822985,0.0000026554853],"about_ca_topic_score_codex":0.025946118,"about_ca_topic_score_gemma":0.021925675,"teacher_disagreement_score":0.025946118,"about_ca_system_score_codex":0.00045711218,"about_ca_system_score_gemma":0.0008871986,"threshold_uncertainty_score":0.051590204},"labels":[],"label_agreement":null},{"id":"W2584492552","doi":"","title":"Prediction of rainfall-runoff processes through black-box techniques","year":2015,"lang":"en","type":"other","venue":"DR-NTU (Nanyang Technological University)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Surface runoff; Black box; Environmental science; Hydrology (agriculture); Meteorology; Geology; Geography; Computer science; Artificial intelligence; Geotechnical engineering","score_opus":0.029764027598710625,"score_gpt":0.21118861261059485,"score_spread":0.18142458501188422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584492552","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114816375,0.00029152076,0.8804195,0.0000822647,0.00002798376,0.00013740739,0.00034111526,0.0010109274,0.002872872],"genre_scores_gemma":[0.8798697,0.00049166573,0.11601503,0.00003174065,0.000016461368,0.00025057193,0.00031483942,0.0000692834,0.0029406974],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996891,0.000094120274,0.000018627044,0.000087278524,0.00008831837,0.00002259828],"domain_scores_gemma":[0.9994618,0.00035245728,0.00006687466,0.000037413458,0.00007167313,0.0000097161055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008344814,0.0006628266,0.0006273856,0.00045589506,0.00023373056,0.00061961304,0.00062581024,0.0005555874,0.0015528396],"category_scores_gemma":[0.0014148005,0.00033698286,0.00043625516,0.0004941419,0.00026044206,0.0010504108,0.00034453988,0.00042303582,0.0003213189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009935635,0.000053807686,0.002666462,0.0000839806,0.000044668162,0.00006907278,0.000069786416,0.9470187,0.0044112266,0.0022661164,0.00019301755,0.0430238],"study_design_scores_gemma":[0.0000028597158,0.000012100101,0.00037291224,0.0000040385303,0.0000034549807,0.000004991216,0.0000031028396,0.9980102,0.0009724022,0.0004233339,0.00018738279,0.0000031632019],"about_ca_topic_score_codex":0.0071111456,"about_ca_topic_score_gemma":0.005152943,"teacher_disagreement_score":0.0071111456,"about_ca_system_score_codex":0.00036485295,"about_ca_system_score_gemma":0.00059783884,"threshold_uncertainty_score":0.014139473},"labels":[],"label_agreement":null},{"id":"W2588382693","doi":"10.1016/j.asej.2016.10.014","title":"Scale dependent prediction of reference evapotranspiration based on Multi-Variate Empirical mode decomposition","year":2017,"lang":"en","type":"article","venue":"Ain Shams Engineering Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Saskatchewan","keywords":"Evapotranspiration; Hilbert–Huang transform; Wind speed; Mode (computer interface); Scale (ratio); Stepwise regression; Statistics; Mathematics; Environmental science; Meteorology; Computer science; Geography; Energy (signal processing); Ecology","score_opus":0.04671315125489393,"score_gpt":0.32993173101224493,"score_spread":0.283218579757351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588382693","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13160239,0.00021079274,0.8667592,0.00007229497,0.000029479697,0.000012513192,0.00012006096,0.0003273789,0.0008659431],"genre_scores_gemma":[0.8595953,0.00024734734,0.13872653,0.000019642983,0.000024476507,0.000028402183,0.00029931398,0.000060607847,0.0009983439],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99988544,0.000034422887,0.0000067141123,0.000032235883,0.000033001026,0.000008244161],"domain_scores_gemma":[0.99978966,0.00010179482,0.000030794727,0.000020623678,0.00004937686,0.00000783239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044800845,0.00040250056,0.00022321878,0.0003991092,0.00010020675,0.00026864416,0.00037816138,0.0002181994,0.00044754212],"category_scores_gemma":[0.0012003136,0.00012550902,0.0003931826,0.0003167167,0.00009562842,0.00062480423,0.0002250281,0.00043570198,0.00015911159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114063485,0.0000904396,0.01756414,0.00007925382,0.00009158801,0.00008694299,0.000079132675,0.71456486,0.022166647,0.0042382022,0.0009129147,0.2400118],"study_design_scores_gemma":[0.000001491491,0.000005703446,0.0013591525,0.0000016802325,0.0000025548266,0.000006830175,0.0000027092233,0.9974751,0.0006949068,0.00030404748,0.00014272424,0.0000031644015],"about_ca_topic_score_codex":0.0022214372,"about_ca_topic_score_gemma":0.002071355,"teacher_disagreement_score":0.0022214372,"about_ca_system_score_codex":0.00014199656,"about_ca_system_score_gemma":0.00022942226,"threshold_uncertainty_score":0.004417062},"labels":[],"label_agreement":null},{"id":"W2588810797","doi":"10.1007/s00477-017-1394-z","title":"Multi-step water quality forecasting using a boosting ensemble multi-wavelet extreme learning machine model","year":2017,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":126,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extreme learning machine; Partial autocorrelation function; Adaptive neuro fuzzy inference system; Autocorrelation; Computer science; Mean squared error; Boosting (machine learning); Artificial intelligence; Wavelet; Discrete wavelet transform; Machine learning; Time series; Wavelet transform; Data mining; Statistics; Mathematics; Algorithm; Artificial neural network; Fuzzy logic; Autoregressive integrated moving average; Fuzzy control system","score_opus":0.2678065094809721,"score_gpt":0.41087592807290346,"score_spread":0.14306941859193134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588810797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15955964,0.0003448259,0.8376283,0.00016422938,0.00015311921,0.000024906363,0.00007543288,0.0002729726,0.001776607],"genre_scores_gemma":[0.938629,0.00016492106,0.059922006,0.000046614223,0.00005925687,0.000034166427,0.00011982059,0.000019410123,0.0010048302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997298,0.00007435235,0.000019454363,0.000058264402,0.000081703,0.00003642416],"domain_scores_gemma":[0.9994844,0.00020411285,0.000048378057,0.000062008745,0.00016952967,0.000031519015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010795817,0.00039159786,0.0011151758,0.00036607357,0.00033599685,0.0005760528,0.0009191223,0.00080365536,0.0006370279],"category_scores_gemma":[0.0015860376,0.00031479012,0.0010077457,0.0005660097,0.00023508671,0.0008510197,0.0005751783,0.000980012,0.00018854254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009845906,0.000089767775,0.0015845527,0.000028274684,0.0000974603,0.000049094808,0.000022736493,0.94914734,0.0034461145,0.0019708627,0.0004651118,0.043000296],"study_design_scores_gemma":[0.0000013533473,0.0000050944423,0.000104431376,5.13758e-7,0.0000037381697,0.000002466485,5.550478e-7,0.99960953,0.000101964375,0.00014538711,0.000023725328,0.000001197798],"about_ca_topic_score_codex":0.0023191695,"about_ca_topic_score_gemma":0.0019148636,"teacher_disagreement_score":0.0023191695,"about_ca_system_score_codex":0.00025944677,"about_ca_system_score_gemma":0.00047254644,"threshold_uncertainty_score":0.0057094097},"labels":[],"label_agreement":null},{"id":"W2597784382","doi":"","title":"Influence of Diffuse and Discrete Groundwater Discharge on River Thermal Regimes in Present and Future Climates","year":2015,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Groundwater; Environmental science; Hydrology (agriculture); Water resource management; Geology; Geotechnical engineering","score_opus":0.01663036506991093,"score_gpt":0.2366974324580505,"score_spread":0.22006706738813958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597784382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99798465,0.00008246727,0.00034864453,0.00011179624,0.0000107858295,0.0000024094754,0.00033341613,0.00001568041,0.001110109],"genre_scores_gemma":[0.99963415,0.000039398317,0.00007298247,0.000004805716,0.000006227665,0.0000010298678,0.00013602023,0.0000023388288,0.000103076985],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998524,0.00004777606,0.000013041631,0.000036452922,0.000020482392,0.000029874893],"domain_scores_gemma":[0.99894303,0.00057190156,0.00014337443,0.000059293536,0.00014836955,0.00013400415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000555138,0.0001466174,0.00023604621,0.0005385767,0.00028748024,0.0007754738,0.00020925267,0.00039041493,0.0010450399],"category_scores_gemma":[0.002263146,0.000154028,0.00034670316,0.00059874525,0.00047282493,0.0006122511,0.0004193034,0.00038946737,0.000116933275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008051006,0.00010568873,0.9065809,0.000059822152,0.0001460297,0.00018605021,0.00024755188,0.065821424,0.006827511,0.0013122185,0.00062717625,0.017280418],"study_design_scores_gemma":[0.000016084909,0.00007131426,0.9375489,0.00000855198,0.00004543003,0.00004598883,0.00030591476,0.06036193,0.0006039969,0.0004891983,0.00048647576,0.000016151744],"about_ca_topic_score_codex":0.017013421,"about_ca_topic_score_gemma":0.03025064,"teacher_disagreement_score":0.017013421,"about_ca_system_score_codex":0.00061058154,"about_ca_system_score_gemma":0.00022032026,"threshold_uncertainty_score":0.033828795},"labels":[],"label_agreement":null},{"id":"W2606562683","doi":"10.3808/jei.201600345","title":"Short-Term Peak Flow Rate Prediction and Flood Risk Assessment Using Fuzzy Linear Regression","year":2016,"lang":"en","type":"article","venue":"Journal of Environmental Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Calibration; Flood myth; Linear regression; Fuzzy logic; Regression; Sensitivity (control systems); Mathematics; Computer science; Engineering; Artificial intelligence; Geography","score_opus":0.018631590278118067,"score_gpt":0.25743226537581393,"score_spread":0.23880067509769587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606562683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39142144,0.00043872718,0.6043115,0.00023401929,0.000031907897,0.000060950835,0.0003240557,0.00112892,0.002048484],"genre_scores_gemma":[0.9494008,0.000109264394,0.049109608,0.000018979485,0.000010098893,0.000028840272,0.00017168584,0.00001729856,0.0011334785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940884,0.00012673905,0.000041594856,0.00015972058,0.00020609974,0.000057066143],"domain_scores_gemma":[0.9991148,0.00045472372,0.00014387895,0.000038676106,0.00022084183,0.000027119604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016012973,0.0006892765,0.0005538136,0.0012352725,0.00026920566,0.00095503236,0.0009563846,0.0006412782,0.0005658641],"category_scores_gemma":[0.003034596,0.00030878285,0.0006333795,0.0007871557,0.0002879479,0.0007933597,0.00036300407,0.0005849531,0.00013015587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117439275,0.000058790385,0.0099357385,0.00003793053,0.000068082816,0.000076309516,0.00005050846,0.9211993,0.0030694648,0.0007938885,0.00027929372,0.064313166],"study_design_scores_gemma":[0.000002437561,0.000022235678,0.0018999097,0.0000032512332,0.000006946469,0.000008989338,0.00001032186,0.9972024,0.00054855726,0.00020737704,0.00007903285,0.000008603109],"about_ca_topic_score_codex":0.0590581,"about_ca_topic_score_gemma":0.038178213,"teacher_disagreement_score":0.0590581,"about_ca_system_score_codex":0.0011607087,"about_ca_system_score_gemma":0.0010652569,"threshold_uncertainty_score":0.11742866},"labels":[],"label_agreement":null},{"id":"W2606780533","doi":"10.1002/2016ms000830","title":"Fully nonlinear statistical and machine‐learning approaches for hydrological frequency estimation at ungauged sites","year":2017,"lang":"en","type":"article","venue":"Journal of Advances in Modeling Earth Systems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Pacific Institute for Climate Solutions; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonlinear system; Quantile; Computer science; Artificial neural network; Linear model; Machine learning; Artificial intelligence; Mathematics; Statistics","score_opus":0.06639370173454329,"score_gpt":0.2908321233278244,"score_spread":0.2244384215932811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606780533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.329662,0.00032664769,0.66705704,0.0002698838,0.00002918049,0.000051285988,0.00024486898,0.0003357211,0.0020233411],"genre_scores_gemma":[0.94807595,0.00012613644,0.050560076,0.000020650026,0.000020119334,0.000039935032,0.0001989039,0.000041713523,0.00091657933],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938524,0.00038095535,0.000023524688,0.00009395806,0.00007394931,0.000042321873],"domain_scores_gemma":[0.99822706,0.001191888,0.00021142742,0.00011522143,0.00021310154,0.000041216383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017665809,0.0005716891,0.0005044823,0.0010993017,0.00023018848,0.0006835405,0.0007093209,0.00045396853,0.001038456],"category_scores_gemma":[0.0036157968,0.00027307807,0.0008875927,0.0011144637,0.000411164,0.00071068696,0.0007587192,0.0007081385,0.00021636533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004145203,0.000030914067,0.00647104,0.000037516562,0.000051976633,0.0000632971,0.000052672833,0.96127546,0.0008643697,0.0019602731,0.00017686494,0.028974062],"study_design_scores_gemma":[5.7523215e-7,0.0000031315076,0.0009689827,0.0000015677881,0.0000017005558,0.0000037356772,0.0000061512005,0.9984068,0.000073349205,0.00048625312,0.00004499047,0.0000028521567],"about_ca_topic_score_codex":0.01351325,"about_ca_topic_score_gemma":0.012413551,"teacher_disagreement_score":0.01351325,"about_ca_system_score_codex":0.0005011609,"about_ca_system_score_gemma":0.00075933,"threshold_uncertainty_score":0.026869178},"labels":[],"label_agreement":null},{"id":"W2607052725","doi":"10.1515/jwld-2017-0012","title":"Assessing the suitability of extreme learning machines (ELM) for groundwater level prediction","year":2017,"lang":"en","type":"article","venue":"Journal of Water and Land Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Extreme learning machine; Groundwater; Evapotranspiration; Environmental science; Aquifer; Hydrology (agriculture); Water resources; Univariate; Irrigation; Support vector machine; Multivariate statistics; Water resource management; Computer science; Machine learning; Artificial neural network; Engineering; Geotechnical engineering; Ecology","score_opus":0.08890593218605962,"score_gpt":0.29321665942445163,"score_spread":0.204310727238392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607052725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8894433,0.00039435618,0.107483774,0.00037382726,0.00005502207,0.000072691146,0.00026270247,0.00029362136,0.0016206816],"genre_scores_gemma":[0.99187684,0.000043666823,0.007751302,0.000017207292,0.000009267733,0.000021617674,0.00011359489,0.000003840509,0.00016274961],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988166,0.0006954211,0.000094008894,0.00014295246,0.00014829305,0.000102770646],"domain_scores_gemma":[0.99358976,0.0053352257,0.00027024437,0.00019438035,0.00049319817,0.00011710585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037244838,0.00066540233,0.00077826885,0.0013684065,0.00029480446,0.0008074297,0.000653236,0.00081937556,0.0006744742],"category_scores_gemma":[0.009650085,0.0002111724,0.00070420327,0.0009284759,0.0002692367,0.0008806499,0.0005165433,0.00070178974,0.00015140993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030277533,0.00022206276,0.03268611,0.000051570587,0.00016255511,0.0000759296,0.000039813243,0.9125946,0.00079138385,0.0005649029,0.00039801854,0.052110296],"study_design_scores_gemma":[0.0000034108336,0.000064751104,0.0022403712,0.0000032364653,0.000006039857,0.00000628916,0.000013647942,0.9971789,0.00020323016,0.00024930004,0.000027192955,0.0000036468566],"about_ca_topic_score_codex":0.005390324,"about_ca_topic_score_gemma":0.0027510487,"teacher_disagreement_score":0.005390324,"about_ca_system_score_codex":0.0005639104,"about_ca_system_score_gemma":0.0005756436,"threshold_uncertainty_score":0.01969719},"labels":[],"label_agreement":null},{"id":"W2609487750","doi":"10.1080/07011784.2017.1290552","title":"Regional monthly runoff forecast in southern Canada using ANN, <i>K</i>-means, and <i>L</i>-moments techniques","year":2017,"lang":"en","type":"article","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Surface runoff; Environmental science; Hydrology (agriculture); Climatology; Mathematics; Meteorology; Geography; Geology; Ecology; Geotechnical engineering; Biology","score_opus":0.022799904782814864,"score_gpt":0.20837016194203736,"score_spread":0.18557025715922248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609487750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9657814,0.0003156056,0.028862037,0.00015715633,0.0000175616,0.000032451215,0.0012105462,0.0003977066,0.003225437],"genre_scores_gemma":[0.98784083,0.00014810277,0.009796103,0.000011987409,0.0000035232804,0.000010048653,0.00080080365,0.000015558286,0.001373069],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99988616,0.000012584457,0.0000059505965,0.0000296217,0.000036359434,0.00002932891],"domain_scores_gemma":[0.9998547,0.000020324398,0.0000165277,0.0000065193785,0.00009035,0.000011527427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026165068,0.000369344,0.00024742153,0.00050651544,0.0004422031,0.0005276811,0.00028703766,0.00016577398,0.0005342586],"category_scores_gemma":[0.0005955075,0.00012137395,0.00041124175,0.0009344483,0.00014175089,0.00018550802,0.00018487021,0.00020702582,0.000108169144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015985024,0.00004745473,0.066720776,0.00006760744,0.00009051519,0.0001634744,0.000117729694,0.84692067,0.0048729917,0.00053743954,0.0019299339,0.0783716],"study_design_scores_gemma":[0.0000070793003,0.000012121141,0.033721488,0.0000070855954,0.000022526954,0.000013612798,0.000098406636,0.9641757,0.00099538,0.00014988946,0.0007848782,0.000011867384],"about_ca_topic_score_codex":0.91813225,"about_ca_topic_score_gemma":0.91089046,"teacher_disagreement_score":0.081867754,"about_ca_system_score_codex":0.003950672,"about_ca_system_score_gemma":0.0062330575,"threshold_uncertainty_score":0.16469973},"labels":[],"label_agreement":null},{"id":"W2609833776","doi":"10.2495/sdp-v12-n7-1117-1131","title":"Forecasting extreme monthly rainfall events in regions of Queensland, Australia using artificial neural networks","year":2017,"lang":"en","type":"article","venue":"International Journal of Sustainable Development and Planning","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"B. Macfie Family Foundation","keywords":"Flooding (psychology); Climatology; Environmental science; Meteorology; Extreme weather; Geography; Climate change; Geology; Oceanography","score_opus":0.10909208550313378,"score_gpt":0.30617903766714827,"score_spread":0.1970869521640145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609833776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966518,0.0001017556,0.0017921348,0.000091221045,0.0000060277935,0.0000140276225,0.00037178243,0.000047996407,0.0009232917],"genre_scores_gemma":[0.99797684,0.00008646361,0.0011660544,0.0000070820033,0.0000046439154,0.000009717865,0.00035504482,0.0000021359187,0.00039199318],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986434,0.00003080766,0.000012789206,0.00004017954,0.000030085166,0.00002187023],"domain_scores_gemma":[0.99953866,0.00013291987,0.000156205,0.000021285541,0.00010667321,0.00004430593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031198192,0.00030172584,0.00016451314,0.0007693527,0.00027738942,0.00037824592,0.00035478914,0.00025716994,0.00044808336],"category_scores_gemma":[0.001214539,0.00018652326,0.00019140849,0.0010179286,0.00021970541,0.00031508013,0.00036630745,0.00021834404,0.00007464124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024960173,0.00017500976,0.326428,0.00012808287,0.00012934276,0.0008446668,0.00083838135,0.61416996,0.007035156,0.0006400828,0.0015372884,0.047824357],"study_design_scores_gemma":[0.000019077763,0.000055683275,0.36418,0.000019688141,0.000026637572,0.000047538808,0.00039981137,0.6334046,0.0006372948,0.00041658498,0.00077434635,0.000018758126],"about_ca_topic_score_codex":0.15628912,"about_ca_topic_score_gemma":0.20542222,"teacher_disagreement_score":0.15628912,"about_ca_system_score_codex":0.0013153452,"about_ca_system_score_gemma":0.0005879707,"threshold_uncertainty_score":0.31075877},"labels":[],"label_agreement":null},{"id":"W2616081160","doi":"10.1080/19475705.2017.1327464","title":"Real-time prediction of water level change using adaptive neuro-fuzzy inference system","year":2017,"lang":"en","type":"article","venue":"Geomatics Natural Hazards and Risk","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Incheon National University","keywords":"Adaptive neuro fuzzy inference system; Inference system; Artificial neural network; Neuro-fuzzy; Computer science; Machine learning; Data mining; Artificial intelligence; Fuzzy logic; Fuzzy control system","score_opus":0.05265431899161907,"score_gpt":0.2617476224457841,"score_spread":0.20909330345416502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616081160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35902435,0.00043344146,0.63272697,0.00022169927,0.00009675131,0.00007787462,0.0003130402,0.0014061235,0.0056997957],"genre_scores_gemma":[0.9771253,0.000107515334,0.021787373,0.000014121759,0.000008399051,0.000030423742,0.000110776644,0.000007771439,0.0008083843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998728,0.00001760558,0.000011406294,0.000030349616,0.000053456224,0.000014407663],"domain_scores_gemma":[0.9998223,0.00007700618,0.000024067234,0.000009439572,0.00006032635,0.000006879201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032273296,0.00033540465,0.00032312798,0.0003096233,0.00026473968,0.00038273877,0.000379999,0.0003621771,0.00063677237],"category_scores_gemma":[0.00093128014,0.00013167835,0.00025098928,0.00032399045,0.00012841335,0.00038546638,0.00019058661,0.00036982296,0.00013845236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012247941,0.00008451551,0.004808846,0.000068157315,0.00004149548,0.00010706976,0.000075310134,0.88491637,0.010496161,0.0007748995,0.00076262467,0.09774209],"study_design_scores_gemma":[0.0000019470758,0.000009721129,0.0006450004,0.0000013688864,0.0000033425274,0.0000038738704,0.0000034230304,0.9986615,0.0004927228,0.00009684546,0.00007766886,0.000002535995],"about_ca_topic_score_codex":0.028823143,"about_ca_topic_score_gemma":0.024427334,"teacher_disagreement_score":0.028823143,"about_ca_system_score_codex":0.0004446352,"about_ca_system_score_gemma":0.0004595323,"threshold_uncertainty_score":0.05731076},"labels":[],"label_agreement":null},{"id":"W2619656986","doi":"10.3390/w9060381","title":"Optimising Fuzzy Neural Network Architecture for Dissolved Oxygen Prediction and Risk Analysis","year":2017,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Fuzzy logic; Computer science; Neuro-fuzzy; Data mining; Environmental science; Fuzzy control system; Machine learning; Artificial intelligence","score_opus":0.015269884092887659,"score_gpt":0.2333985336522131,"score_spread":0.21812864955932545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619656986","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08969984,0.0004183867,0.9069744,0.00019855474,0.00004317371,0.000054807795,0.00003895167,0.00025182558,0.0023201117],"genre_scores_gemma":[0.8865172,0.00021911292,0.11089434,0.00004786754,0.000031881667,0.000109529974,0.000059614227,0.000016475193,0.0021038973],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998012,0.00006177909,0.0000122358115,0.00004427393,0.000050988776,0.00002944732],"domain_scores_gemma":[0.99967694,0.00016145839,0.00003205927,0.000008998506,0.00010775838,0.000012850525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008632109,0.00064386846,0.00055161153,0.00052154454,0.00036013348,0.00057692593,0.00074674736,0.00078969134,0.00070405763],"category_scores_gemma":[0.0014170253,0.0003322208,0.00040767103,0.00046105156,0.0003117025,0.0005671416,0.00047631946,0.00069228467,0.0001132981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020826827,0.000018743152,0.00051276886,0.000013334242,0.000019676554,0.000017686174,0.000015755166,0.97649574,0.00095570344,0.0007473953,0.000117409785,0.021065021],"study_design_scores_gemma":[0.0000014206294,0.0000069122175,0.00006011476,0.0000012426285,0.0000022592221,0.0000017959894,0.0000015125723,0.99956554,0.0001273138,0.00020077964,0.000029803185,0.0000012637593],"about_ca_topic_score_codex":0.014317489,"about_ca_topic_score_gemma":0.013590114,"teacher_disagreement_score":0.014317489,"about_ca_system_score_codex":0.00089062087,"about_ca_system_score_gemma":0.0007372887,"threshold_uncertainty_score":0.02846831},"labels":[],"label_agreement":null},{"id":"W2721810300","doi":"10.14796/jwmm.r206-10","title":"Real Time Flow Prediction using Fuzzy Logic Models","year":2000,"lang":"en","type":"article","venue":"Journal of Water Management Modeling","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fuzzy logic; Computer science; Artificial intelligence","score_opus":0.03688157462857427,"score_gpt":0.2352627038848738,"score_spread":0.19838112925629953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2721810300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122841105,0.00044592324,0.8650148,0.0003628912,0.0001110021,0.000058317477,0.00039337337,0.001750303,0.009022311],"genre_scores_gemma":[0.9365993,0.0002923459,0.058844484,0.000051846193,0.00002809591,0.000079596226,0.00028748158,0.000035086177,0.003781598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997899,0.00004731508,0.0000142480685,0.000046526828,0.000077994795,0.000023986875],"domain_scores_gemma":[0.99965084,0.00015848351,0.000050423118,0.000020832988,0.00010453833,0.000014933188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004540451,0.0004511044,0.00037998,0.00062625296,0.00029215866,0.0008869865,0.00063482084,0.00055663346,0.001986994],"category_scores_gemma":[0.0011634694,0.00024136047,0.00042244286,0.0005601982,0.0002743911,0.0010104587,0.00023074595,0.0005470299,0.0003436779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048175694,0.000031836298,0.00047915737,0.000018536119,0.000016021646,0.000025467969,0.000019028805,0.97229284,0.0016797516,0.002288543,0.00036231012,0.022738416],"study_design_scores_gemma":[0.000004139974,0.0000064789406,0.00007949304,0.00000157093,0.00000208401,0.000002623722,0.0000016051666,0.9988508,0.00027791667,0.0006364051,0.00013418513,0.0000027329213],"about_ca_topic_score_codex":0.020415949,"about_ca_topic_score_gemma":0.01268801,"teacher_disagreement_score":0.020415949,"about_ca_system_score_codex":0.00091991597,"about_ca_system_score_gemma":0.0007511925,"threshold_uncertainty_score":0.04059428},"labels":[],"label_agreement":null},{"id":"W2735794055","doi":"10.1007/s40996-017-0068-x","title":"A New Approach for Parameter Estimation of Autoregressive Models Using Adaptive Network-Based Fuzzy Inference System (ANFIS)","year":2017,"lang":"en","type":"article","venue":"Iranian Journal of Science and Technology Transactions of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of California, Davis; Ryerson University","keywords":"Adaptive neuro fuzzy inference system; Fuzzy inference system; Autoregressive model; Inference; Computer science; Estimation; Artificial intelligence; Inference system; Estimation theory; Machine learning; Fuzzy logic; Econometrics; Mathematics; Fuzzy control system; Engineering; Algorithm","score_opus":0.030161834974819973,"score_gpt":0.24751876755017352,"score_spread":0.21735693257535355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735794055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026973318,0.00019890282,0.9962291,0.000036873626,0.00004607093,0.000019335666,0.000012767267,0.00015436343,0.0006051323],"genre_scores_gemma":[0.32246307,0.0007413388,0.672028,0.00009602121,0.00015370187,0.00018759904,0.00014253108,0.00005941347,0.0041283406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996499,0.00006486063,0.00003507023,0.00009600692,0.00013408005,0.000020117732],"domain_scores_gemma":[0.9997358,0.00011205331,0.000028592496,0.000015572965,0.00009963034,0.00000836272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006685688,0.000748454,0.00072935247,0.0006247935,0.0004369627,0.0006519694,0.0010067443,0.0010552478,0.001315958],"category_scores_gemma":[0.0011960645,0.00037556372,0.00072959403,0.00045259963,0.0003006926,0.0010212162,0.0004981974,0.0012963915,0.00032590746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012510216,0.00012755084,0.0009799374,0.00031154882,0.00019979058,0.0002724938,0.00029004365,0.46513885,0.03051697,0.012431184,0.0016754613,0.4879311],"study_design_scores_gemma":[0.000006180047,0.00002734739,0.0001839751,0.000012947865,0.000020973132,0.000041066687,0.000011044456,0.9952809,0.0018872372,0.0013036256,0.001213947,0.0000106247435],"about_ca_topic_score_codex":0.006863495,"about_ca_topic_score_gemma":0.0068549584,"teacher_disagreement_score":0.006863495,"about_ca_system_score_codex":0.00034184943,"about_ca_system_score_gemma":0.0005367241,"threshold_uncertainty_score":0.0136470795},"labels":[],"label_agreement":null},{"id":"W2738937980","doi":"10.1002/met.1661","title":"Forecasting soil temperature based on surface air temperature using a wavelet artificial neural network","year":2017,"lang":"en","type":"article","venue":"Meteorological Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ste. Anne's Hospital","funders":"","keywords":"Artificial neural network; Environmental science; Wavelet transform; Frost (temperature); Meteorology; Air temperature; Surface air temperature; Wavelet; Computer science; Precipitation; Machine learning; Artificial intelligence; Geography","score_opus":0.049723444329044665,"score_gpt":0.2720255723570545,"score_spread":0.22230212802800983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738937980","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7570441,0.00034522614,0.23869531,0.00019315448,0.00012308701,0.00003751995,0.00028217948,0.00039933895,0.0028801733],"genre_scores_gemma":[0.9831166,0.00018084848,0.0158056,0.000011037584,0.000013485821,0.00002073172,0.00016778646,0.00000617751,0.0006775832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999925,0.000015875488,0.00000685249,0.000020972298,0.000019691695,0.000011717824],"domain_scores_gemma":[0.9998379,0.00007258098,0.000024640376,0.000008682081,0.00004776666,0.000008362465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026524876,0.0003637123,0.00027820014,0.0003799575,0.00012565355,0.00034251722,0.00031572272,0.00030920442,0.00047561736],"category_scores_gemma":[0.0007353612,0.00014716125,0.00029918874,0.00051131466,0.00008628644,0.00045694315,0.00018686449,0.00035835258,0.000106597065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001108516,0.00010166263,0.011365811,0.000044504653,0.000056222147,0.00006966869,0.000030989035,0.92041135,0.0045926054,0.00045605234,0.0004290911,0.062331174],"study_design_scores_gemma":[0.0000013216352,0.0000072642056,0.0007000527,9.079282e-7,0.0000030386434,0.0000018011542,0.00000242863,0.99900717,0.00019227277,0.000055435587,0.000027066351,0.0000012339477],"about_ca_topic_score_codex":0.007996603,"about_ca_topic_score_gemma":0.0064973035,"teacher_disagreement_score":0.007996603,"about_ca_system_score_codex":0.000304751,"about_ca_system_score_gemma":0.00028801875,"threshold_uncertainty_score":0.015900075},"labels":[],"label_agreement":null},{"id":"W274788335","doi":"10.1007/s11269-015-0978-y","title":"Plunging Flow Depth Estimation in a Stratified Dam Reservoir Using Neuro-Fuzzy Technique","year":2015,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Hydrogeology; Inflow; Flow (mathematics); Turbulence; Geology; Mean squared error; Entrainment (biomusicology); Arithmetic underflow; Nonlinear system; Mechanics; Geotechnical engineering; Mathematics; Statistics; Geometry; Computer science","score_opus":0.039796998330483155,"score_gpt":0.25927372660313497,"score_spread":0.2194767282726518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W274788335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7996817,0.000117144045,0.1984123,0.00008963648,0.000017397486,0.000021397822,0.00008041263,0.00016364644,0.0014164438],"genre_scores_gemma":[0.9908524,0.000029052153,0.008802095,0.0000041979433,0.0000031001966,0.000005511755,0.00001976514,0.0000020117361,0.00028193768],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99994946,0.0000076118245,0.0000046447244,0.000014594945,0.000013380448,0.000010353473],"domain_scores_gemma":[0.999841,0.000065386695,0.000025666526,0.000009532875,0.000040925126,0.000017610611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017389398,0.00025250792,0.00028731392,0.00036138762,0.0003102737,0.00032644637,0.00034773248,0.00041816258,0.00032877573],"category_scores_gemma":[0.0004659027,0.00023440475,0.00024909189,0.0004172766,0.0001805487,0.00047925132,0.00027547812,0.00027285403,0.000045428187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024708195,0.000095463656,0.016162885,0.00005170453,0.000040621995,0.000313421,0.000099622135,0.89437175,0.027909275,0.0009043659,0.0002368928,0.059566975],"study_design_scores_gemma":[0.0000019800548,0.000012463748,0.0011304324,9.668081e-7,0.000004397517,0.0000045037245,0.0000071890017,0.9978492,0.00086946914,0.00009460571,0.000021321976,0.0000033966244],"about_ca_topic_score_codex":0.01223263,"about_ca_topic_score_gemma":0.010814902,"teacher_disagreement_score":0.01223263,"about_ca_system_score_codex":0.0004030362,"about_ca_system_score_gemma":0.00041825388,"threshold_uncertainty_score":0.024322867},"labels":[],"label_agreement":null},{"id":"W2751199820","doi":"10.2495/sdp-v12-n8-1282-1298","title":"Application of artificial neural networks to forecasting monthly rainfall one year in advance for locations within the Murray Darling basin, Australia","year":2017,"lang":"en","type":"article","venue":"International Journal of Sustainable Development and Planning","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Met Office; B. Macfie Family Foundation","keywords":"Artificial neural network; Structural basin; Hydrology (agriculture); Meteorology; Climatology; Environmental science; Geology; Artificial intelligence; Geography; Computer science; Geotechnical engineering; Geomorphology","score_opus":0.04454013578671389,"score_gpt":0.2953984695377647,"score_spread":0.2508583337510508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751199820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9727076,0.00031800635,0.021968435,0.0003289552,0.000053896478,0.000087017565,0.00035371838,0.00023204728,0.0039502117],"genre_scores_gemma":[0.9883696,0.00012463432,0.010214752,0.000018391876,0.0000085531465,0.000026496931,0.00026461013,0.000012453053,0.00096054893],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997639,0.00007922264,0.000019536219,0.000048458318,0.0000583266,0.000030635958],"domain_scores_gemma":[0.999506,0.00021426198,0.0000584104,0.000025002448,0.0001596866,0.000036732894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064371165,0.000569079,0.0003286162,0.00077289314,0.00031489605,0.0006913745,0.0005186353,0.00042546098,0.0004744532],"category_scores_gemma":[0.002468543,0.00035140026,0.00031317337,0.0009107101,0.00016762284,0.00044742823,0.0004999733,0.00050650194,0.00007814955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005200647,0.00006251736,0.012950577,0.000031143543,0.000051035655,0.00011553147,0.00007975994,0.9642602,0.0008413883,0.00018841146,0.00029663648,0.021070823],"study_design_scores_gemma":[0.000005015022,0.000015980917,0.0052113654,0.000004082378,0.0000068915338,0.000004990899,0.000033685727,0.9940904,0.00027252012,0.00012937158,0.00021998138,0.0000056513645],"about_ca_topic_score_codex":0.14399578,"about_ca_topic_score_gemma":0.17752843,"teacher_disagreement_score":0.14399578,"about_ca_system_score_codex":0.0015719517,"about_ca_system_score_gemma":0.0013991285,"threshold_uncertainty_score":0.2863152},"labels":[],"label_agreement":null},{"id":"W2751512204","doi":"10.1002/2016wr019981","title":"Information theory‐based decision support system for integrated design of multivariable hydrometric networks","year":2017,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Streamflow; Multivariable calculus; Mutual information; Computer science; Entropy (arrow of time); Information theory; Optimal design; Bayesian network; Data mining; Mathematical optimization; Mathematics; Machine learning; Artificial intelligence; Engineering; Statistics; Control engineering","score_opus":0.0720373437083821,"score_gpt":0.3252005159347391,"score_spread":0.253163172226357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751512204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011682559,0.000059908667,0.9867423,0.000053714994,0.00001312274,0.0000988905,0.000034912435,0.00036784812,0.0009467563],"genre_scores_gemma":[0.6981817,0.000087186105,0.29988638,0.00010741914,0.000026046877,0.0006670865,0.00014171634,0.00002897233,0.00087359507],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987386,0.0004264233,0.00010023624,0.00022368385,0.0003964488,0.000114653325],"domain_scores_gemma":[0.9977385,0.001209645,0.00025036608,0.000079718644,0.0006523741,0.000069401794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029735381,0.0010135826,0.0011306297,0.0011451592,0.0006285761,0.0014052485,0.0010261764,0.0009400101,0.0028163104],"category_scores_gemma":[0.004980483,0.00049345987,0.0007182183,0.0006305646,0.000514594,0.0008342532,0.0008879801,0.0009066184,0.0002832472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012363828,0.00008847641,0.0003990838,0.0000887939,0.00004469145,0.000048617243,0.0000506013,0.93863815,0.0024900706,0.004263949,0.00042312712,0.0533409],"study_design_scores_gemma":[0.000012187157,0.000032491862,0.00004491735,0.000004181978,0.0000070393944,0.0000030782498,0.0000029854918,0.998692,0.00037325182,0.000703728,0.00012070442,0.0000034193076],"about_ca_topic_score_codex":0.006072328,"about_ca_topic_score_gemma":0.005349349,"teacher_disagreement_score":0.006072328,"about_ca_system_score_codex":0.001307485,"about_ca_system_score_gemma":0.0019331834,"threshold_uncertainty_score":0.015725791},"labels":[],"label_agreement":null},{"id":"W2755901084","doi":"10.2166/hydro.2017.129","title":"Bed material load estimation in channels using machine learning and meta-heuristic methods","year":2017,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Particle swarm optimization; Support vector machine; Heuristic; Computer science; Decision tree; Set (abstract data type); Bed load; Field (mathematics); Mathematical optimization; Tree (set theory); Logarithm; Data mining; Machine learning; Artificial intelligence; Mathematics; Sediment transport","score_opus":0.05434771808020506,"score_gpt":0.34650699621608333,"score_spread":0.2921592781358783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755901084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18959804,0.00034235755,0.8069079,0.00020372978,0.000034767476,0.00006368991,0.00009682153,0.0003462272,0.002406441],"genre_scores_gemma":[0.9336793,0.000121138,0.06530124,0.000028172963,0.000016929516,0.000059133232,0.00006583301,0.000016524544,0.00071175466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997583,0.00011957872,0.000016098063,0.00003633219,0.000041154057,0.00002859254],"domain_scores_gemma":[0.99913824,0.00060453964,0.000100067235,0.00003343924,0.00009894793,0.000024768968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083003554,0.00050310604,0.0007396854,0.0010229729,0.00027506554,0.00085903605,0.00071726553,0.00088754186,0.0006579389],"category_scores_gemma":[0.0015910092,0.0004056898,0.00069413544,0.00071428565,0.00036319724,0.00074509607,0.00028347765,0.0004039898,0.0001268975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010654923,0.000013142027,0.00040257498,0.000008727551,0.000010606847,0.000008200903,0.000004685876,0.99438655,0.00017254328,0.00034090327,0.000028480137,0.0046129576],"study_design_scores_gemma":[0.0000010771735,0.0000033620433,0.000029997043,6.7271003e-7,8.004507e-7,7.31942e-7,0.0000011077689,0.9997949,0.000045604917,0.000109304354,0.000011893452,6.485927e-7],"about_ca_topic_score_codex":0.009511751,"about_ca_topic_score_gemma":0.005272901,"teacher_disagreement_score":0.009511751,"about_ca_system_score_codex":0.00062987505,"about_ca_system_score_gemma":0.00078045,"threshold_uncertainty_score":0.018912733},"labels":[],"label_agreement":null},{"id":"W2766193180","doi":"10.1080/02626667.2017.1393686","title":"Probabilistic and ensemble simulation approaches for input uncertainty quantification of artificial neural network hydrological models","year":2017,"lang":"en","type":"article","venue":"Hydrological Sciences Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Uncertainty quantification; Probabilistic logic; Computer science; Artificial neural network; Uncertainty analysis; Identification (biology); Sensitivity analysis; Ensemble forecasting; Machine learning; Hydrological modelling; Artificial intelligence; Data mining; Simulation","score_opus":0.20305174434111592,"score_gpt":0.3201226734359925,"score_spread":0.11707092909487657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766193180","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0138221,0.00020899049,0.98425055,0.000099355675,0.000013651748,0.000021827127,0.00004343393,0.000085948435,0.0014540848],"genre_scores_gemma":[0.7439605,0.0006563533,0.25388375,0.000065299595,0.000058124202,0.00025477543,0.00021063413,0.00009192889,0.00081862573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985788,0.00083863427,0.00006831062,0.00010916839,0.00034442567,0.000060736445],"domain_scores_gemma":[0.99731296,0.0018758667,0.00027974034,0.00015885358,0.00033046422,0.000042037533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031866385,0.0008357777,0.0007046749,0.0011750523,0.00042027424,0.00092487846,0.000909432,0.0007734608,0.0007730843],"category_scores_gemma":[0.007147843,0.00054714724,0.0008650635,0.0012232601,0.00048487127,0.0015648619,0.0012867386,0.0011116539,0.00008945582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004590967,0.0000055166943,0.00025044422,0.000009546057,0.000022636204,0.000006304055,0.0000063231723,0.990148,0.00014723375,0.0040615015,0.000041597086,0.005296307],"study_design_scores_gemma":[5.174543e-7,0.0000025166248,0.00006356578,0.0000023234347,0.0000025917163,0.0000017869878,0.0000013695119,0.99765825,0.000082196224,0.002107524,0.000074956166,0.0000022566346],"about_ca_topic_score_codex":0.005288358,"about_ca_topic_score_gemma":0.005248246,"teacher_disagreement_score":0.005288358,"about_ca_system_score_codex":0.00086132897,"about_ca_system_score_gemma":0.0009381353,"threshold_uncertainty_score":0.016852796},"labels":[],"label_agreement":null},{"id":"W2766664988","doi":"","title":"Using a time-lagged method to enhance Numerical Weather Prediction for urban drainage applications","year":2017,"lang":"en","type":"article","venue":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kruger (Canada)","funders":"","keywords":"Meteorology; Drainage; Environmental science; Computer science; Econometrics; Climatology; Statistics; Geography; Mathematics; Geology; Ecology; Biology","score_opus":0.02242911137224518,"score_gpt":0.2771378148937882,"score_spread":0.254708703521543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766664988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21323813,0.00046361831,0.77935314,0.00026999516,0.0007200146,0.00006217023,0.0004983368,0.0015200422,0.003874511],"genre_scores_gemma":[0.76455694,0.0003331015,0.2311157,0.00008906893,0.00012046741,0.00006975351,0.00052803743,0.00013633625,0.0030505606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999106,0.000024510868,0.000009683606,0.000021234046,0.000024449586,0.00000955811],"domain_scores_gemma":[0.9994438,0.00024055658,0.00003852265,0.000051977888,0.00019478376,0.000030371277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050646527,0.00036152714,0.00025879996,0.0004238991,0.00027649433,0.0006117366,0.00052832026,0.00039559498,0.0024134594],"category_scores_gemma":[0.0017064925,0.0002545012,0.00030750962,0.0006513244,0.00016077039,0.0009312565,0.00030854478,0.0005969498,0.00037363925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032872477,0.0004545836,0.0073990026,0.00018578142,0.00009348342,0.00012612554,0.000086635475,0.7509879,0.055466015,0.0047331015,0.001976643,0.1781621],"study_design_scores_gemma":[0.0000055016353,0.000015955473,0.0003231886,0.0000024416063,0.0000045288634,0.0000039036963,0.000003213504,0.9970812,0.0019349918,0.00019055494,0.0004299176,0.0000046073387],"about_ca_topic_score_codex":0.007063675,"about_ca_topic_score_gemma":0.009656362,"teacher_disagreement_score":0.007063675,"about_ca_system_score_codex":0.00021192901,"about_ca_system_score_gemma":0.0005870045,"threshold_uncertainty_score":0.014045119},"labels":[],"label_agreement":null},{"id":"W2768460349","doi":"10.3808/jei.201700371","title":"Comparing A Bayesian and Fuzzy Number Approach to Uncertainty Quantification in Short-Term Dissolved Oxygen Prediction","year":2017,"lang":"en","type":"article","venue":"Journal of Environmental Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; University of Victoria","keywords":"Bayesian probability; Fuzzy logic; Autoregressive model; Measure (data warehouse); Statistics; Mean squared error; Computer science; Term (time); Regression analysis; Data mining; Bayesian inference; Mathematics; Artificial intelligence","score_opus":0.03718616984858123,"score_gpt":0.26410156482102415,"score_spread":0.22691539497244292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768460349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24892025,0.0011251908,0.7431709,0.0006212892,0.0001101356,0.000086719905,0.0002033989,0.00057441834,0.0051876735],"genre_scores_gemma":[0.86179525,0.00037534247,0.13616215,0.00009097944,0.000047049856,0.00006850311,0.00020045324,0.000044572505,0.0012156452],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901235,0.00036563957,0.00006697679,0.00014362841,0.0003626783,0.00004874409],"domain_scores_gemma":[0.9970061,0.00200562,0.00018065018,0.00011442573,0.0006198245,0.00007342226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003002003,0.0007291645,0.0006869847,0.0011339049,0.0002933323,0.0011153442,0.0010057306,0.00089220493,0.00060607516],"category_scores_gemma":[0.0073192264,0.00035934418,0.0006992739,0.00062817754,0.00044597365,0.0018691915,0.00071937975,0.00063382485,0.00013218774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024042088,0.00007941164,0.0040554916,0.00008594343,0.00012270226,0.000034300494,0.00006695171,0.89485425,0.0020755744,0.0037467072,0.00030118664,0.09433702],"study_design_scores_gemma":[0.000006758243,0.00003270859,0.0008773025,0.0000071168183,0.000011821664,0.000008221719,0.000011443556,0.9973585,0.00054261717,0.0009708025,0.00015843389,0.0000141218125],"about_ca_topic_score_codex":0.020302355,"about_ca_topic_score_gemma":0.014195215,"teacher_disagreement_score":0.020302355,"about_ca_system_score_codex":0.0011289063,"about_ca_system_score_gemma":0.0010548979,"threshold_uncertainty_score":0.04036838},"labels":[],"label_agreement":null},{"id":"W2792586183","doi":"10.2166/wst.2018.107","title":"River flood prediction using fuzzy neural networks: an investigation on automated network architecture","year":2018,"lang":"en","type":"article","venue":"Water Science & Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria; University of Calgary; York University","funders":"","keywords":"Flood myth; Data mining; Computer science; Artificial neural network; Feature selection; Fuzzy logic; Selection (genetic algorithm); Artificial intelligence; Machine learning; Geography","score_opus":0.018917973518619177,"score_gpt":0.2364661161678986,"score_spread":0.2175481426492794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792586183","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58438814,0.000550235,0.40543786,0.00068270037,0.000036945505,0.00013755474,0.000070998605,0.00026363943,0.008432021],"genre_scores_gemma":[0.9684336,0.00013962502,0.030525455,0.00002659253,0.000014972229,0.000041476436,0.00003287032,0.000008671907,0.00077667274],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999624,0.0001718256,0.00001904943,0.00006273391,0.00008315625,0.00003921002],"domain_scores_gemma":[0.99683595,0.0024477602,0.00015104875,0.000086937514,0.00044263076,0.000035643614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020009074,0.00036957907,0.00037889753,0.00068527774,0.0005098425,0.00069604523,0.0006382743,0.00065305614,0.00090587325],"category_scores_gemma":[0.006973728,0.0002464433,0.00033941973,0.00052231346,0.0004879078,0.0014359355,0.00037473417,0.000504441,0.000057657806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046699388,0.000034580513,0.0025182308,0.0000150612905,0.000016753313,0.000036845533,0.000039217302,0.9689388,0.00047887667,0.004041021,0.000113653514,0.02372029],"study_design_scores_gemma":[0.0000014700058,0.0000072702974,0.00020660304,0.0000013230213,0.0000016541709,0.0000029477565,0.0000034969805,0.9988586,0.00007369582,0.0008194603,0.00002244665,0.0000010612226],"about_ca_topic_score_codex":0.016884476,"about_ca_topic_score_gemma":0.011836154,"teacher_disagreement_score":0.016884476,"about_ca_system_score_codex":0.001068685,"about_ca_system_score_gemma":0.00071343285,"threshold_uncertainty_score":0.033572376},"labels":[],"label_agreement":null},{"id":"W2792618445","doi":"10.1007/s11270-018-3715-3","title":"A New Approach to Predict Daily pH in Rivers Based on the “à trous” Redundant Wavelet Transform Algorithm","year":2018,"lang":"en","type":"article","venue":"Water Air & Soil Pollution","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mean squared error; Linear regression; Wavelet; Series (stratigraphy); Artificial neural network; Wavelet transform; Coefficient of determination; Statistics; Mathematics; Algorithm; Regression; Artificial intelligence; Computer science; Geology","score_opus":0.014017105705687613,"score_gpt":0.2081008682292775,"score_spread":0.1940837625235899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792618445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011562708,0.00011385675,0.9874008,0.00006846063,0.00006185392,0.000019122841,0.000022792425,0.00018977239,0.0005604832],"genre_scores_gemma":[0.23690705,0.00040020526,0.7587281,0.00009241871,0.00013011046,0.00010425945,0.00018816502,0.000055558816,0.0033941527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982136,0.000026843076,0.000016713979,0.000044475415,0.00007441124,0.000016315546],"domain_scores_gemma":[0.9997929,0.000052983007,0.00002101315,0.000018854054,0.00010314862,0.000011206242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042799604,0.0004606037,0.0005443554,0.00072743796,0.00027920931,0.0005408925,0.0007606112,0.000645354,0.0008776873],"category_scores_gemma":[0.00075331546,0.0002468445,0.0005630702,0.00069441367,0.00027357193,0.00091695564,0.00035923335,0.00077995524,0.00041737923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017624912,0.00019794086,0.0019492847,0.00013898962,0.00014795522,0.00011623831,0.0000922947,0.2619893,0.04265241,0.010900351,0.00226751,0.6793714],"study_design_scores_gemma":[0.0000065693425,0.000021597536,0.00024089763,0.0000022444108,0.000009312828,0.000018238345,0.0000047522285,0.99678385,0.0019047142,0.00054198736,0.00046090523,0.000005045067],"about_ca_topic_score_codex":0.0027993573,"about_ca_topic_score_gemma":0.002246438,"teacher_disagreement_score":0.0027993573,"about_ca_system_score_codex":0.00024553237,"about_ca_system_score_gemma":0.00058825716,"threshold_uncertainty_score":0.0055660605},"labels":[],"label_agreement":null},{"id":"W2796858542","doi":"10.7939/r3vc9t","title":"Neural networks modelling of stream nitrogen using remote sensing information: model development and application","year":2009,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Forest Resource Improvement Association of Alberta; Ontario Innovation Trust","keywords":"Artificial neural network; Computer science; Remote sensing; Environmental science; Nitrogen; Artificial intelligence; Geology; Chemistry","score_opus":0.01476958884835139,"score_gpt":0.17029511393652624,"score_spread":0.15552552508817485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796858542","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5071693,0.0011771111,0.47493318,0.00058433163,0.00010594454,0.00021471639,0.00057346944,0.0006504907,0.01459157],"genre_scores_gemma":[0.9602973,0.00048094502,0.03343543,0.000049713526,0.000026983345,0.00026473016,0.00026771484,0.00002803954,0.00514912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998567,0.00004487608,0.000009686944,0.00003467791,0.000035021025,0.00001902365],"domain_scores_gemma":[0.99964786,0.00020284308,0.000036574496,0.000010472796,0.00009087601,0.000011258279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005921781,0.0006925473,0.00045531397,0.00038923448,0.0003353629,0.000640368,0.00091672374,0.0012057349,0.0010547086],"category_scores_gemma":[0.0010440099,0.00037140262,0.00054027827,0.000559926,0.000338336,0.0006705946,0.0004441155,0.0006784151,0.00018420492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008854598,0.000011687043,0.00036551317,0.000007895687,0.0000064205806,0.000012413819,0.000005672814,0.99667656,0.0001401458,0.00022081823,0.000042653483,0.002501436],"study_design_scores_gemma":[6.1228616e-7,0.0000021517212,0.00005974168,8.1586984e-7,9.657402e-7,6.1556074e-7,8.542759e-7,0.99977833,0.000053502834,0.000076513956,0.000025059206,8.1047386e-7],"about_ca_topic_score_codex":0.039492168,"about_ca_topic_score_gemma":0.022635264,"teacher_disagreement_score":0.039492168,"about_ca_system_score_codex":0.0010708602,"about_ca_system_score_gemma":0.00083613856,"threshold_uncertainty_score":0.07852459},"labels":[],"label_agreement":null},{"id":"W2797692099","doi":"10.5194/hess-2018-168","title":"HESS Opinions: Deep learning as a promising avenue toward knowledge discovery in water sciences","year":2018,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Big data; Transformative learning; Data science; Variety (cybernetics); Deep learning; Computer science; Field (mathematics); Artificial intelligence; Set (abstract data type); Stakeholder; Political science; Sociology; Data mining; Mathematics","score_opus":0.03507288553710524,"score_gpt":0.2978376948507449,"score_spread":0.26276480931363966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797692099","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00085028243,0.0087442715,0.0058408524,0.9403037,0.035567746,0.00001532844,0.00031819916,0.000075329306,0.008284285],"genre_scores_gemma":[0.12223612,0.03555457,0.013847435,0.6963913,0.09305608,0.00012037966,0.00046958376,0.00029067745,0.038033962],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944765,0.0019296001,0.0004592436,0.0009202048,0.001940908,0.000273532],"domain_scores_gemma":[0.9639214,0.01544535,0.0022230982,0.0018440568,0.014077353,0.0024887207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072023715,0.0007012977,0.00068779645,0.0013367415,0.0023094963,0.009307045,0.0018014765,0.012673962,0.015709452],"category_scores_gemma":[0.029360278,0.00023487903,0.00067132775,0.0014766747,0.0063467384,0.006719424,0.0030603544,0.012513369,0.0062863682],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016779396,0.000028605373,0.000835189,0.00042396135,0.000093751914,0.00038286217,0.0005996653,0.0008430336,0.0008418062,0.13236557,0.8200133,0.04340458],"study_design_scores_gemma":[0.00005330393,0.00004280976,0.0005483936,0.00077430654,0.00005442046,0.0002846445,0.001469393,0.0029070063,0.0016368777,0.2934971,0.69860274,0.00012897307],"about_ca_topic_score_codex":0.002915664,"about_ca_topic_score_gemma":0.0032201216,"teacher_disagreement_score":0.015709452,"about_ca_system_score_codex":0.0032686933,"about_ca_system_score_gemma":0.0032593403,"threshold_uncertainty_score":0.052553356},"labels":[],"label_agreement":null},{"id":"W2803907192","doi":"10.1016/j.jenvman.2018.05.072","title":"Novel hybrid linear stochastic with non-linear extreme learning machine methods for forecasting monthly rainfall a tropical climate","year":2018,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":106,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Tropical climate; Extreme learning machine; Environmental science; Climatology; Meteorology; Econometrics; Mathematics; Statistics; Computer science; Machine learning; Geography; Ecology; Artificial neural network; Geology; Biology","score_opus":0.03572237126299856,"score_gpt":0.280844081035535,"score_spread":0.24512170977253642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803907192","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06423075,0.0004040144,0.93289596,0.00018042882,0.00012542977,0.000040549567,0.000054639037,0.00036970145,0.0016986509],"genre_scores_gemma":[0.84337217,0.00018153239,0.15275356,0.00011595735,0.00017229054,0.000121678124,0.00020099747,0.00005140088,0.0030303395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937916,0.00025298723,0.00005286031,0.00009199548,0.00015799062,0.00006491422],"domain_scores_gemma":[0.99878484,0.00073523546,0.00009699257,0.0000650654,0.0002644751,0.000053449567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016088983,0.0006666137,0.000923804,0.00050059584,0.0003942489,0.00086207496,0.0013807531,0.00096606143,0.0016014285],"category_scores_gemma":[0.002806732,0.00046379754,0.0007930324,0.00064970134,0.00037377246,0.000872888,0.0010279851,0.00092315074,0.0002395242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001622863,0.00013961564,0.0012947202,0.000067337074,0.00012518096,0.00005566523,0.000036512763,0.91838104,0.0018474569,0.002878682,0.00062733586,0.074384175],"study_design_scores_gemma":[0.0000028443906,0.000009621366,0.000057244062,7.7083797e-7,0.0000024245192,0.0000020530874,0.0000010885838,0.9996043,0.0000797728,0.00020222293,0.00003623628,0.0000014997465],"about_ca_topic_score_codex":0.0037555047,"about_ca_topic_score_gemma":0.004874136,"teacher_disagreement_score":0.0037555047,"about_ca_system_score_codex":0.0003302138,"about_ca_system_score_gemma":0.00075540197,"threshold_uncertainty_score":0.008508742},"labels":[],"label_agreement":null},{"id":"W2805094882","doi":"10.1007/s11600-018-0168-4","title":"Reservoir water level forecasting using group method of data handling","year":2018,"lang":"en","type":"article","venue":"Acta Geophysica","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Mean squared error; Group (periodic table); Water level; Statistics; Hydrology (agriculture); Data mining; Mathematics; Computer science; Petroleum engineering; Geology; Geography; Geotechnical engineering; Chemistry; Cartography","score_opus":0.21829187397597424,"score_gpt":0.34216364504044716,"score_spread":0.12387177106447292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805094882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04176068,0.00010765759,0.9553202,0.00008509523,0.00011931823,0.000057000765,0.00021573663,0.0011579713,0.0011764753],"genre_scores_gemma":[0.5799119,0.00016545645,0.41544518,0.000050175597,0.00019619995,0.000246698,0.0008423119,0.00012194108,0.0030201247],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943286,0.00013666124,0.000049504197,0.0001441455,0.0001788919,0.000057751557],"domain_scores_gemma":[0.9984498,0.00060992775,0.000114566734,0.00022732378,0.0005339697,0.000064402564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009488866,0.0005597928,0.0013447375,0.0012981299,0.0006954117,0.00086687144,0.0010849775,0.0006677162,0.0024883482],"category_scores_gemma":[0.0032652586,0.00030056335,0.00080502545,0.0023683344,0.00028001735,0.0014366611,0.00067631167,0.0010037774,0.0005206361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005501725,0.00026099908,0.0048646806,0.00015129312,0.00020353161,0.00013342356,0.00025394658,0.36745307,0.010228584,0.0064438526,0.0048154993,0.604641],"study_design_scores_gemma":[0.000017904142,0.0000496641,0.00060770666,0.00000330742,0.000023805453,0.000013364809,0.000019220088,0.99485934,0.0018731119,0.0017670089,0.0007543061,0.0000113205415],"about_ca_topic_score_codex":0.0077423374,"about_ca_topic_score_gemma":0.004364151,"teacher_disagreement_score":0.0077423374,"about_ca_system_score_codex":0.00035807613,"about_ca_system_score_gemma":0.00082996127,"threshold_uncertainty_score":0.015394568},"labels":[],"label_agreement":null},{"id":"W2885506667","doi":"10.1007/s11600-018-0183-5","title":"Forecasting surface water-level fluctuations of a small glacial lake in Poland using a wavelet-based artificial intelligence method","year":2018,"lang":"en","type":"article","venue":"Acta Geophysica","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mean squared error; Artificial neural network; Mean absolute error; Range (aeronautics); Statistics; Surface water; Environmental science; Wavelet transform; Glacial lake; Water level; Scope (computer science); Wavelet; Hydrology (agriculture); Meteorology; Econometrics; Computer science; Physical geography; Mathematics; Geology; Artificial intelligence; Geography; Glacier; Engineering; Cartography","score_opus":0.10188004100318102,"score_gpt":0.29868486398118144,"score_spread":0.19680482297800042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885506667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98577255,0.000042912696,0.013645172,0.000046060468,0.0000045104725,0.000013510884,0.00005900051,0.00004109953,0.00037522934],"genre_scores_gemma":[0.9954953,0.000046769113,0.004238661,0.0000023926618,0.0000015620956,0.00000710374,0.000055654964,0.000002609206,0.00015003],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999391,0.000012412254,0.000007313759,0.000017190147,0.000011902123,0.000012111596],"domain_scores_gemma":[0.99986243,0.00005799499,0.00003060569,0.000008428179,0.000030502393,0.000009924687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029023914,0.0003095941,0.00027670898,0.00048554328,0.00015759563,0.00044716024,0.0002820198,0.0002905484,0.00023556262],"category_scores_gemma":[0.000856218,0.00015022309,0.00036131975,0.00050120126,0.00019001738,0.00031059867,0.00031074352,0.00023454693,0.00003839813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017907681,0.00008191395,0.048659865,0.000090070476,0.00008762644,0.00051839714,0.00017741993,0.9012033,0.0128061455,0.00050561834,0.00026232746,0.035428256],"study_design_scores_gemma":[0.0000048887146,0.000024141384,0.013866664,0.000003452724,0.0000117655945,0.000010166447,0.000054211516,0.9850772,0.0007964421,0.00009173989,0.000054319313,0.000005146595],"about_ca_topic_score_codex":0.017175307,"about_ca_topic_score_gemma":0.013094685,"teacher_disagreement_score":0.017175307,"about_ca_system_score_codex":0.00031136774,"about_ca_system_score_gemma":0.00039908127,"threshold_uncertainty_score":0.03415072},"labels":[],"label_agreement":null},{"id":"W2890873614","doi":"10.1007/s11269-018-2099-x","title":"Enhancement of Model Reliability by Integrating Prediction Interval Optimization into Hydrogeological Modeling","year":2018,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Calgary","keywords":"Hydrogeology; Perturbation (astronomy); Interval (graph theory); Computer science; Reliability (semiconductor); Data mining; Mathematical optimization; Statistics; Mathematics; Geology","score_opus":0.01417174759341163,"score_gpt":0.2251945242782452,"score_spread":0.21102277668483357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890873614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14996225,0.00027953676,0.8429974,0.00033082874,0.00009408475,0.00004087415,0.0001781593,0.0015060927,0.0046107955],"genre_scores_gemma":[0.95267206,0.00009223403,0.04649232,0.000028447264,0.000029543653,0.000031471227,0.00011544316,0.00010731852,0.00043117354],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970657,0.00010862126,0.000025496973,0.000043774013,0.000090062815,0.000025450572],"domain_scores_gemma":[0.99787426,0.0009676105,0.00022320208,0.00038455022,0.0005026906,0.00004768122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013707392,0.000611153,0.0005813398,0.00050583325,0.00022594654,0.00083604496,0.0008717776,0.00045085634,0.0009673131],"category_scores_gemma":[0.006730298,0.00035738523,0.00049925275,0.0004331535,0.00020212866,0.0012758116,0.00056493527,0.0009377505,0.00021146696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036808164,0.000043955024,0.0018680476,0.000023704653,0.000039048984,0.000015370346,0.00001720606,0.972604,0.0021135125,0.0008029914,0.00021872966,0.022216711],"study_design_scores_gemma":[0.0000018373598,0.0000064400006,0.00015022747,0.0000013960165,0.0000060146144,0.0000024454584,0.0000017858183,0.9988697,0.00050100323,0.00037060125,0.00008644512,0.0000020442062],"about_ca_topic_score_codex":0.0050534564,"about_ca_topic_score_gemma":0.0034679738,"teacher_disagreement_score":0.0050534564,"about_ca_system_score_codex":0.0003528451,"about_ca_system_score_gemma":0.0006861603,"threshold_uncertainty_score":0.010048091},"labels":[],"label_agreement":null},{"id":"W2892229913","doi":"10.2166/wcc.2018.113","title":"Comparison of wavelet-based hybrid models for the estimation of daily reference evapotranspiration in different climates","year":2018,"lang":"en","type":"article","venue":"Journal of Water and Climate Change","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Wavelet; Evapotranspiration; Discrete wavelet transform; Cascade algorithm; Mathematics; Wavelet transform; Statistics; Computer science; Artificial intelligence; Ecology","score_opus":0.1306074132280913,"score_gpt":0.3243194616523446,"score_spread":0.1937120484242533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892229913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7348814,0.0005041948,0.26129156,0.00018979344,0.00007676045,0.00004253369,0.00018258992,0.00039072058,0.002440458],"genre_scores_gemma":[0.9844765,0.00014163337,0.014863024,0.00001254604,0.000009102325,0.000024506231,0.000091626076,0.000012203767,0.00036873986],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979013,0.000090060974,0.000020564412,0.00003560271,0.000041956202,0.000021684213],"domain_scores_gemma":[0.9992835,0.00046369588,0.00005771187,0.00003186326,0.00014279317,0.000020529778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015733473,0.0005064023,0.00055218383,0.00065374764,0.0001539082,0.00064645987,0.0008181043,0.00047531258,0.0004707077],"category_scores_gemma":[0.002225152,0.00023778214,0.0006962522,0.0005327335,0.00016056772,0.0007778154,0.00038519746,0.0004812353,0.00011471308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015363384,0.00007256879,0.003091804,0.000036660338,0.00008881729,0.000023428183,0.0000403826,0.9697832,0.0011219326,0.00060846517,0.00011376687,0.024865298],"study_design_scores_gemma":[0.0000032723096,0.000016603888,0.0003078419,0.0000014472979,0.0000070446695,0.0000018425799,0.000005011791,0.9993861,0.00015417475,0.00009191474,0.000022694994,0.0000021384192],"about_ca_topic_score_codex":0.008316125,"about_ca_topic_score_gemma":0.0040936335,"teacher_disagreement_score":0.008316125,"about_ca_system_score_codex":0.00042915018,"about_ca_system_score_gemma":0.0003799979,"threshold_uncertainty_score":0.016535461},"labels":[],"label_agreement":null},{"id":"W2895493807","doi":"10.14796/jwmm.c453","title":"Suspended Sediment Concentration Modeling Using Conventional and Machine Learning Approaches in the Thames River, London Ontario","year":2018,"lang":"en","type":"article","venue":"Journal of Water Management Modeling","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Toronto and Region Conservation Authority; Western University","funders":"","keywords":"Hydrology (agriculture); Sediment; Environmental science; Water resource management; Geology; Geomorphology; Geotechnical engineering","score_opus":0.0869297878418971,"score_gpt":0.24062254206985614,"score_spread":0.15369275422795903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895493807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957885,0.00016594928,0.0015336089,0.00010475218,0.000003888784,0.000015044639,0.0003333293,0.000020772077,0.0020341824],"genre_scores_gemma":[0.99714905,0.00014312842,0.0010532162,0.00000561753,0.0000016671332,0.000009431433,0.00025044306,0.0000036510344,0.0013839097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998963,0.00001696454,0.0000106337375,0.000026465288,0.0000333051,0.000016365282],"domain_scores_gemma":[0.9997954,0.00007209555,0.0000363945,0.000008679443,0.000071005976,0.000016434258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019360468,0.00027630117,0.00014604392,0.00037445422,0.0006140774,0.00071413623,0.0005024835,0.00035989186,0.00059068366],"category_scores_gemma":[0.00071737554,0.00016719729,0.00025348362,0.00085930625,0.0003411498,0.0003304418,0.00016415963,0.00016210267,0.000078127494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017674228,0.000077821394,0.22955707,0.00014815784,0.00009126503,0.0007695976,0.00060881634,0.73341084,0.005033371,0.0013944214,0.0011009163,0.02763096],"study_design_scores_gemma":[0.000019970204,0.0000476356,0.14274265,0.000021561867,0.00003559761,0.0000486558,0.00051396474,0.8532978,0.0015056889,0.00021869662,0.0015188251,0.000028868215],"about_ca_topic_score_codex":0.9152118,"about_ca_topic_score_gemma":0.9441321,"teacher_disagreement_score":0.0847882,"about_ca_system_score_codex":0.0074193985,"about_ca_system_score_gemma":0.0037020734,"threshold_uncertainty_score":0.17057502},"labels":[],"label_agreement":null},{"id":"W2898661956","doi":"10.5194/hess-22-5639-2018","title":"HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community","year":2018,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":348,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy; State Key Laboratory of Hydraulics and Mountain River Engineering; Sichuan University; National Science Foundation","keywords":"Grassroots; Computer science; Field (mathematics); Data science; Process (computing); Baseline (sea); Citizen science; Artificial intelligence; Nature versus nurture; Data sharing; Sociology; Political science; Mathematics","score_opus":0.021484881824571346,"score_gpt":0.27630756898279724,"score_spread":0.25482268715822587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898661956","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013537996,0.0021514352,0.0029820283,0.9180558,0.03769737,0.000033137265,0.00050649873,0.00020842376,0.037011653],"genre_scores_gemma":[0.14660345,0.010214553,0.008132618,0.4560892,0.053889845,0.00018943784,0.0011744349,0.00074997003,0.32295647],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952992,0.0011993863,0.00019279716,0.00076272245,0.0017815398,0.0007642814],"domain_scores_gemma":[0.9645457,0.0070512732,0.0019852181,0.0021549547,0.011542206,0.012720636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006757303,0.0005904608,0.0004033306,0.0009520384,0.0033410743,0.010861238,0.002134489,0.011719329,0.09101586],"category_scores_gemma":[0.034458086,0.0002728462,0.0005356052,0.0010401187,0.00404545,0.011478136,0.007609801,0.011685545,0.02012625],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005059142,0.000021358435,0.0005097526,0.00010397202,0.000013796292,0.00019099379,0.0002480685,0.0002961105,0.00039120708,0.060950547,0.9088854,0.02833809],"study_design_scores_gemma":[0.000017583807,0.000013425402,0.00022018098,0.00013332155,0.0000052747796,0.00005117611,0.0004793197,0.00073990255,0.00046394693,0.023790464,0.97406375,0.000021636002],"about_ca_topic_score_codex":0.0047566853,"about_ca_topic_score_gemma":0.007159799,"teacher_disagreement_score":0.09101586,"about_ca_system_score_codex":0.0048448304,"about_ca_system_score_gemma":0.010881687,"threshold_uncertainty_score":0.3044784},"labels":[],"label_agreement":null},{"id":"W2901448577","doi":"10.1007/s11356-018-3751-y","title":"Evaluation of the bias and precision of regression techniques and machine learning approaches in total dissolved solids modeling of an urban aquifer","year":2018,"lang":"en","type":"article","venue":"Environmental Science and Pollution Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multicollinearity; Linear regression; Statistics; Principal component regression; Total dissolved solids; Regression analysis; Regression; Artificial neural network; Principal component analysis; Water quality; Aquifer; Environmental science; Groundwater; Mathematics; Machine learning; Environmental engineering; Computer science; Engineering; Ecology","score_opus":0.2093558404692054,"score_gpt":0.36533151517448437,"score_spread":0.15597567470527895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901448577","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92435443,0.001875062,0.07094821,0.00035647908,0.00012523698,0.00004632147,0.00017889006,0.0005460562,0.0015693228],"genre_scores_gemma":[0.97288674,0.00025646694,0.026086982,0.000063515385,0.000029655634,0.000011781581,0.00017539151,0.00007104402,0.0004183948],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687696,0.0015699227,0.00034746036,0.00041448604,0.00067368516,0.000117486445],"domain_scores_gemma":[0.94664913,0.041760128,0.0018960797,0.0025852683,0.006829188,0.000280259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019021293,0.00069911097,0.0007205468,0.0011893433,0.0006033415,0.0014572754,0.00089879497,0.0015716784,0.0002733086],"category_scores_gemma":[0.04323616,0.00041676158,0.0008057192,0.0007872217,0.00070338266,0.0011130723,0.00086106436,0.00096117257,0.00012271167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002947275,0.00047740323,0.11158229,0.00040455972,0.0010831784,0.00022837294,0.0004295019,0.66978264,0.019143,0.0027326082,0.0007551434,0.19043404],"study_design_scores_gemma":[0.00009793808,0.00024680025,0.015237439,0.000042539097,0.00016074307,0.00007306723,0.00007844242,0.9681721,0.014776994,0.0007225789,0.0003566971,0.000034696423],"about_ca_topic_score_codex":0.017209768,"about_ca_topic_score_gemma":0.011865615,"teacher_disagreement_score":0.019021293,"about_ca_system_score_codex":0.0011587407,"about_ca_system_score_gemma":0.0014304353,"threshold_uncertainty_score":0.100595415},"labels":[],"label_agreement":null},{"id":"W2905216752","doi":"10.1029/2018wr023205","title":"A Stochastic Data‐Driven Ensemble Forecasting Framework for Water Resources: A Case Study Using Ensemble Members Derived From a Database of Deterministic Wavelet‐Based Models","year":2018,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weighting; Ensemble forecasting; Probabilistic forecasting; Computer science; Probabilistic logic; Ensemble learning; Wavelet; Data mining; Artificial intelligence; Machine learning","score_opus":0.2673468259155963,"score_gpt":0.3827477327181475,"score_spread":0.11540090680255122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905216752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46922162,0.00028323734,0.526099,0.00058902556,0.000047096997,0.000066169145,0.00047391234,0.00038055275,0.0028394596],"genre_scores_gemma":[0.9579246,0.00008814568,0.041224375,0.000020791584,0.00001303128,0.000030980696,0.00024579925,0.0000168084,0.0004355672],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966335,0.00013534939,0.000020425174,0.000051258365,0.00009510031,0.000034570603],"domain_scores_gemma":[0.999099,0.000456296,0.00005589363,0.00008799073,0.00026461153,0.00003617385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017129725,0.000464127,0.0005630565,0.00054098497,0.00048502543,0.00071691425,0.00081271346,0.0006685676,0.00045021428],"category_scores_gemma":[0.0024981343,0.00024363834,0.00057797605,0.0009343116,0.0002558771,0.0007582877,0.0005026732,0.0007824337,0.000073085495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020491834,0.000021950296,0.0014593555,0.000007769839,0.00002225753,0.000060406015,0.000026167047,0.9844068,0.00041447874,0.0017817364,0.0002658912,0.011512656],"study_design_scores_gemma":[9.667908e-7,0.0000034105115,0.00013012721,6.998767e-7,0.0000021184328,0.000002044375,0.000003811939,0.99939144,0.00011494292,0.0002869453,0.00006170049,0.0000017595249],"about_ca_topic_score_codex":0.048328422,"about_ca_topic_score_gemma":0.034500953,"teacher_disagreement_score":0.048328422,"about_ca_system_score_codex":0.0008807476,"about_ca_system_score_gemma":0.0010006964,"threshold_uncertainty_score":0.09609425},"labels":[],"label_agreement":null},{"id":"W2909151008","doi":"10.1080/19942060.2018.1564702","title":"Modeling monthly pan evaporation using wavelet support vector regression and wavelet artificial neural networks in arid and humid climates","year":2019,"lang":"en","type":"article","venue":"Engineering Applications of Computational Fluid Mechanics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":120,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Wavelet; Arid; Artificial neural network; Support vector machine; Wavelet transform; Pan evaporation; Evaporation; Environmental science; Regression; Computer science; Pattern recognition (psychology); Meteorology; Artificial intelligence; Mathematics; Geography; Statistics; Geology","score_opus":0.013445916449986611,"score_gpt":0.22951935294993608,"score_spread":0.21607343649994948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909151008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9320219,0.00039961628,0.065513976,0.000102108665,0.000033672153,0.000025310694,0.00021184402,0.0002066925,0.0014849706],"genre_scores_gemma":[0.9930575,0.00014140962,0.006197148,0.00000654976,0.000007988267,0.000012484049,0.00011939415,0.000008647316,0.0004490734],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998964,0.000029101968,0.000011272071,0.00002788271,0.00002099449,0.0000143129855],"domain_scores_gemma":[0.99986637,0.00006287185,0.000023304,0.00000827923,0.000033879514,0.0000052260543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037115306,0.00037682964,0.00035236502,0.0003673065,0.000121431134,0.00043333543,0.00036405592,0.00035931368,0.00033817298],"category_scores_gemma":[0.00068204483,0.00020376939,0.00052085525,0.0005271276,0.00010967485,0.00047494844,0.00020791224,0.00030283423,0.000069210546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008569867,0.00006959994,0.016933218,0.00007575622,0.00007969467,0.00011054699,0.00003342845,0.94774354,0.0047719083,0.0003453128,0.00021966222,0.029531574],"study_design_scores_gemma":[0.0000019701638,0.000009227673,0.0026604417,0.0000014237079,0.000004796183,0.0000043541577,0.000007143219,0.996799,0.0004009777,0.000058462076,0.000049962317,0.0000022813576],"about_ca_topic_score_codex":0.008961694,"about_ca_topic_score_gemma":0.00745567,"teacher_disagreement_score":0.008961694,"about_ca_system_score_codex":0.00022274065,"about_ca_system_score_gemma":0.00029382575,"threshold_uncertainty_score":0.017819107},"labels":[],"label_agreement":null},{"id":"W2911052303","doi":"10.1016/j.jhydrol.2019.01.010","title":"A reliable linear method for modeling lake level fluctuations","year":2019,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":67,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Adaptive neuro fuzzy inference system; Artificial neural network; Standardization; Preprocessor; Computer science; Environmental science; Meteorology; Fuzzy logic; Machine learning; Artificial intelligence; Fuzzy control system; Geography","score_opus":0.052029714515510556,"score_gpt":0.3113882921491326,"score_spread":0.259358577633622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911052303","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004409765,0.0000742733,0.99438936,0.000045968227,0.000026141299,0.000012007504,0.000060930015,0.00056411355,0.0004175287],"genre_scores_gemma":[0.32617804,0.00022743114,0.6659193,0.00009708545,0.00014647491,0.00026030684,0.00040576846,0.00033223227,0.006433379],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996105,0.00016462864,0.00002055864,0.00006751263,0.00011016128,0.000026730084],"domain_scores_gemma":[0.99796677,0.0012545767,0.00010173547,0.00012712883,0.00050404825,0.000045806555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012299698,0.00055614003,0.00048719306,0.00052875804,0.00044738816,0.0006125178,0.0010830273,0.00068067305,0.002572714],"category_scores_gemma":[0.0042043375,0.00044623646,0.00045138618,0.0007182299,0.00032082177,0.00076541555,0.0005434477,0.001231709,0.0009175382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014389565,0.00006575169,0.00076138513,0.00007555541,0.00006530088,0.000050274622,0.00004715672,0.82841915,0.0064743576,0.005674581,0.0021035133,0.15611897],"study_design_scores_gemma":[0.0000021098224,0.0000059735125,0.00003780467,8.5131194e-7,0.000002436289,0.0000018720873,9.2156193e-7,0.99911445,0.00029018,0.00037516325,0.00016588654,0.0000023806197],"about_ca_topic_score_codex":0.014531017,"about_ca_topic_score_gemma":0.012431903,"teacher_disagreement_score":0.014531017,"about_ca_system_score_codex":0.0004105966,"about_ca_system_score_gemma":0.0012056264,"threshold_uncertainty_score":0.028892875},"labels":[],"label_agreement":null},{"id":"W2920756880","doi":"10.1016/j.jhydrol.2019.02.027","title":"Integrated Markov chains and uncertainty analysis techniques to more accurately forecast floods using satellite signals","year":2019,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Markov chain; Computer science; Variable (mathematics); Markov model; Markov chain Monte Carlo; Satellite; Reliability (semiconductor); Statistics; Algorithm; Data mining; Monte Carlo method; Mathematics; Machine learning; Engineering","score_opus":0.03021617011421007,"score_gpt":0.2974079722248033,"score_spread":0.26719180211059324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920756880","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047146086,0.00024577143,0.95084107,0.00018336627,0.00007932596,0.000021577831,0.00014183033,0.00033476495,0.0010061743],"genre_scores_gemma":[0.81181407,0.00033707527,0.18496378,0.00009876736,0.00013605143,0.0000899577,0.00047458094,0.000076048316,0.0020096602],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996623,0.00011099917,0.00003394031,0.000059268983,0.00010211222,0.00003141568],"domain_scores_gemma":[0.99629325,0.0028300409,0.00021896187,0.00015019391,0.00043764632,0.000069821224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015080665,0.00044313417,0.0005512336,0.00095337594,0.00032230344,0.00080699247,0.00050262455,0.00049038057,0.0015000784],"category_scores_gemma":[0.0066135316,0.00053040765,0.00059099763,0.0008869476,0.00036752856,0.0015550333,0.00068478973,0.0015742554,0.00020610682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051709587,0.00003371295,0.0012183421,0.00001537364,0.00005725635,0.000018971024,0.000020943531,0.96167505,0.00071586925,0.006424585,0.00044692124,0.02932115],"study_design_scores_gemma":[0.0000022806923,0.0000033387066,0.000099603574,0.0000012861001,0.0000035913877,0.0000015555966,9.449858e-7,0.99814034,0.00014989232,0.0015253467,0.00006997248,0.0000017705139],"about_ca_topic_score_codex":0.01913918,"about_ca_topic_score_gemma":0.022936076,"teacher_disagreement_score":0.01913918,"about_ca_system_score_codex":0.000688469,"about_ca_system_score_gemma":0.0012597386,"threshold_uncertainty_score":0.03805554},"labels":[],"label_agreement":null},{"id":"W2935484715","doi":"10.1007/s13762-019-02361-z","title":"Evaluation of preprocessing techniques for improving the accuracy of stochastic rainfall forecast models","year":2019,"lang":"en","type":"article","venue":"International Journal of Environmental Science and Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Preprocessor; Autocorrelation; Partial autocorrelation function; Normalization (sociology); Data pre-processing; Computer science; Standardization; Data mining; Transformation (genetics); Time series; Stochastic modelling; Econometrics; Algorithm; Statistics; Machine learning; Artificial intelligence; Mathematics; Autoregressive integrated moving average","score_opus":0.023500778942060218,"score_gpt":0.28696428556896153,"score_spread":0.2634635066269013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935484715","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36040616,0.0008126058,0.6285746,0.00032634605,0.0002629675,0.0001507761,0.00086978165,0.006261102,0.0023356192],"genre_scores_gemma":[0.6981791,0.0004140799,0.2979007,0.000060982384,0.00008296934,0.000114908005,0.0016821814,0.00030207116,0.0012629362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996189,0.0000977728,0.000060906143,0.00006887644,0.00010539898,0.000048251353],"domain_scores_gemma":[0.99616647,0.0023111373,0.00021408236,0.00039398725,0.00086266233,0.00005175125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093403703,0.0008935912,0.00048138946,0.00087240624,0.00032553112,0.0008596011,0.000730932,0.00061928836,0.0021427476],"category_scores_gemma":[0.0063105235,0.00030665708,0.0005150435,0.0010269955,0.00019935527,0.0008625276,0.00044872222,0.0007883549,0.000588491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023232447,0.0005890545,0.005881044,0.0003916632,0.00018108032,0.00019429863,0.00013553562,0.27364704,0.124785185,0.0023170703,0.0028249668,0.58672976],"study_design_scores_gemma":[0.000043603966,0.00021016732,0.002383431,0.000010208912,0.000053946816,0.000036439567,0.000027745564,0.92665607,0.06910413,0.0005640919,0.0008971056,0.000012989769],"about_ca_topic_score_codex":0.0048049665,"about_ca_topic_score_gemma":0.002992523,"teacher_disagreement_score":0.0048049665,"about_ca_system_score_codex":0.00030660446,"about_ca_system_score_gemma":0.000754616,"threshold_uncertainty_score":0.0095540285},"labels":[],"label_agreement":null},{"id":"W2942272975","doi":"","title":"Application du modèle «Random Forest Regression» dans l'analyse fréquentielle régionale des évènements hydrologiques extrêmes.","year":2019,"lang":"fr","type":"article","venue":"EspaceINRS Institutional Digital Repository (Institut National de la Recherche Scientifique)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Forestry; Geography; Humanities; Philosophy","score_opus":0.06204250223205091,"score_gpt":0.2931629886230738,"score_spread":0.23112048639102287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942272975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07383868,0.0013357725,0.91628534,0.0005500724,0.00014883418,0.00011335477,0.0015184314,0.0039960626,0.0022133884],"genre_scores_gemma":[0.56822956,0.0008286141,0.42014393,0.0001597472,0.00009875925,0.000247625,0.0032671995,0.0005596533,0.0064648455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905246,0.00042476834,0.00004246409,0.00024362472,0.00016355065,0.000073113144],"domain_scores_gemma":[0.99689424,0.0021680375,0.0002338053,0.00019424017,0.0004469546,0.0000627242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032338658,0.0010240322,0.0007890347,0.0015494573,0.00038466905,0.0011128675,0.0008605365,0.00086618034,0.001955853],"category_scores_gemma":[0.0054915003,0.00048010203,0.0020111795,0.0014507856,0.00023495384,0.00095473084,0.00053510914,0.0011304676,0.0010158147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022172749,0.000121954945,0.02098037,0.0002245085,0.0005696755,0.00020951415,0.00015818715,0.7449422,0.0041205497,0.0031687464,0.005016203,0.22026639],"study_design_scores_gemma":[0.000008444456,0.00002317382,0.002948277,0.000012626488,0.000034676763,0.000040092313,0.000025311287,0.9926845,0.00068666047,0.0011221827,0.0023963503,0.00001769748],"about_ca_topic_score_codex":0.04631862,"about_ca_topic_score_gemma":0.044004396,"teacher_disagreement_score":0.04631862,"about_ca_system_score_codex":0.0007233946,"about_ca_system_score_gemma":0.0014563127,"threshold_uncertainty_score":0.09209806},"labels":[],"label_agreement":null},{"id":"W2944550430","doi":"10.1016/j.jhydrol.2019.05.016","title":"Towards a time and cost effective approach to water quality index class prediction","year":2019,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":131,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Institut Pengurusan dan Pemantauan Penyelidikan, Universiti Malaya; Universiti Kebangsaan Malaysia; Universiti Malaya","keywords":"Water quality; Biochemical oxygen demand; Decision tree; Index (typography); Quality (philosophy); Chemical oxygen demand; Environmental science; Computer science; Suspended solids; Hydrology (agriculture); Data mining; Environmental engineering; Engineering; Ecology","score_opus":0.011548893887822632,"score_gpt":0.24658947698920872,"score_spread":0.2350405831013861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944550430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014469781,0.0002089106,0.9823208,0.00033490994,0.00006917582,0.000060821156,0.00013939559,0.00090867217,0.001487645],"genre_scores_gemma":[0.31364444,0.00034392133,0.67899334,0.0002634046,0.00022434969,0.00019386005,0.00056009996,0.00012269712,0.00565394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993724,0.00015763214,0.000051307845,0.00009330003,0.00027226805,0.000053144937],"domain_scores_gemma":[0.9979631,0.0010881008,0.00010490997,0.00014856108,0.0006232945,0.00007211945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010082432,0.0005219509,0.00086839666,0.0016385762,0.00040505175,0.0015601856,0.0012379321,0.0009618038,0.002986186],"category_scores_gemma":[0.003988234,0.0003088129,0.0004335883,0.0015145751,0.000406577,0.0014959638,0.0010648455,0.0013848902,0.0010888807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027167797,0.00041887685,0.0031065384,0.000091393405,0.00012657934,0.00011814344,0.000081184786,0.3257364,0.017940085,0.014069663,0.0044882824,0.6335511],"study_design_scores_gemma":[0.000009047996,0.00001805382,0.00032029254,0.0000029722532,0.000011428156,0.000015775473,0.000019010606,0.99362165,0.0016067558,0.0037116283,0.0006577409,0.0000056817325],"about_ca_topic_score_codex":0.011064838,"about_ca_topic_score_gemma":0.010112606,"teacher_disagreement_score":0.011064838,"about_ca_system_score_codex":0.0006009008,"about_ca_system_score_gemma":0.0014684071,"threshold_uncertainty_score":0.02200085},"labels":[],"label_agreement":null},{"id":"W2944685396","doi":"10.1007/s00477-019-01680-4","title":"Stepwise extreme learning machine for statistical downscaling of daily maximum and minimum temperature","year":2019,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Climate Extremes; National Research Foundation of Korea; Government of Canada","keywords":"Downscaling; Extreme learning machine; Artificial neural network; Computer science; Artificial intelligence; Machine learning; Feature selection; Feedforward neural network; Feature (linguistics); Climate change; Algorithm","score_opus":0.0245642677246573,"score_gpt":0.3105415558625902,"score_spread":0.2859772881379329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944685396","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028583856,0.000093518596,0.9701508,0.00006298001,0.000028907643,0.000022609323,0.000069900125,0.00068174995,0.0003056436],"genre_scores_gemma":[0.59862584,0.00010565047,0.39841816,0.000066392386,0.000054601012,0.0002192462,0.00055765896,0.00015726207,0.0017951425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953854,0.0002061367,0.000042662992,0.00007582022,0.00009899663,0.000037811016],"domain_scores_gemma":[0.99718934,0.0020345529,0.00016505344,0.00019276909,0.000362824,0.000055539742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016144449,0.0004879652,0.00067254575,0.000534805,0.00033821198,0.00039339345,0.00089832227,0.0005828948,0.0015873762],"category_scores_gemma":[0.0062040547,0.00032643703,0.000733524,0.00064247946,0.00031738624,0.0004882423,0.00070045004,0.0013811918,0.00041208472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017376682,0.000111700974,0.0025823934,0.00007750306,0.000119614895,0.00010088195,0.00006478841,0.7644469,0.0057468642,0.0061637447,0.0017161181,0.21869569],"study_design_scores_gemma":[0.000002550768,0.000010364686,0.00017147126,0.000001228451,0.000002839553,0.0000048625484,0.0000011224905,0.9984144,0.000486805,0.00080698286,0.00009551753,0.0000018715714],"about_ca_topic_score_codex":0.0028812196,"about_ca_topic_score_gemma":0.003982414,"teacher_disagreement_score":0.0028812196,"about_ca_system_score_codex":0.0002569719,"about_ca_system_score_gemma":0.000758296,"threshold_uncertainty_score":0.008538127},"labels":[],"label_agreement":null},{"id":"W2960137824","doi":"10.1016/j.agrformet.2019.107647","title":"On the applicability of maximum overlap discrete wavelet transform integrated with MARS and M5 model tree for monthly pan evaporation prediction","year":2019,"lang":"en","type":"article","venue":"Agricultural and Forest Meteorology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":110,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mars Exploration Program; Mean squared error; Pan evaporation; Wind speed; Discrete wavelet transform; Relative humidity; Multivariate adaptive regression splines; Coefficient of determination; Correlation coefficient; Wavelet; Environmental science; Statistics; Meteorology; Mathematics; Wavelet transform; Evaporation; Linear regression; Computer science; Geography; Bayesian multivariate linear regression; Artificial intelligence","score_opus":0.007900965922045517,"score_gpt":0.1859478138807081,"score_spread":0.1780468479586626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960137824","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8115607,0.0012809441,0.1788492,0.00049513206,0.00010412606,0.000029049479,0.00020383766,0.0003449795,0.0071321093],"genre_scores_gemma":[0.98682433,0.0002534733,0.0122804055,0.000021434867,0.000027777984,0.00000676404,0.0001222208,0.000019792085,0.00044370364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982846,0.00006196588,0.000009291571,0.00003352271,0.00004713612,0.000019594618],"domain_scores_gemma":[0.9996598,0.00019935815,0.000015878788,0.000025112164,0.00008729786,0.000012582015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008800484,0.00027125468,0.0002814096,0.00031801197,0.00019975008,0.0005213895,0.00042989003,0.00037905158,0.0009149785],"category_scores_gemma":[0.0018460646,0.00011855509,0.0003219972,0.00046503125,0.00015262201,0.00073238084,0.00031317337,0.00045020098,0.00014838856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008884631,0.00024051248,0.015904384,0.00016279552,0.00021791639,0.00015762952,0.000086614295,0.6687032,0.025389206,0.0051270784,0.0019380952,0.2811841],"study_design_scores_gemma":[0.0000054040574,0.00001649216,0.0018048838,0.0000029899875,0.000011644367,0.000003691339,0.000010484024,0.99678206,0.0010011442,0.00022503221,0.00013358198,0.000002500769],"about_ca_topic_score_codex":0.0077124597,"about_ca_topic_score_gemma":0.0043176305,"teacher_disagreement_score":0.0077124597,"about_ca_system_score_codex":0.00017798392,"about_ca_system_score_gemma":0.00035153527,"threshold_uncertainty_score":0.015335143},"labels":[],"label_agreement":null},{"id":"W2965559850","doi":"10.2166/wst.2019.263","title":"Predictive models for wastewater flow forecasting based on time series analysis and artificial neural network","year":2019,"lang":"en","type":"article","venue":"Water Science & Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hydromantis Environmental Software Solutions (Canada); McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Vienna Science and Technology Fund; Ontario Water Consortium","keywords":"Autoregressive integrated moving average; Inflow; Artificial neural network; Wastewater; Mean squared error; Time series; Multilayer perceptron; Computer science; Engineering; Artificial intelligence; Machine learning; Statistics; Environmental engineering; Meteorology; Mathematics","score_opus":0.013834317177181444,"score_gpt":0.20541655851100965,"score_spread":0.1915822413338282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965559850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104784496,0.0022203238,0.8842589,0.0005444075,0.00026557822,0.000105768144,0.0006082214,0.0015014904,0.0057108756],"genre_scores_gemma":[0.9314591,0.0016962545,0.061073553,0.00008851028,0.00011526305,0.00024651273,0.00067527196,0.00005463918,0.004590855],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996729,0.00008597555,0.00003346131,0.0000827274,0.00009310095,0.00003180383],"domain_scores_gemma":[0.9992366,0.00047979382,0.00009715199,0.000026301062,0.00014707055,0.000013068337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009052913,0.0009871502,0.0008322856,0.000978344,0.00039430978,0.00089637755,0.001033019,0.00092063594,0.0012332646],"category_scores_gemma":[0.0024402265,0.00038913652,0.0006693824,0.0014376335,0.00030698118,0.001056342,0.00041465217,0.0013452497,0.00027657897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028359464,0.0000363635,0.00095468195,0.000040944753,0.000041771353,0.000031082713,0.000019778923,0.9744976,0.0005176447,0.0014561919,0.00038220378,0.021993283],"study_design_scores_gemma":[7.6865e-7,0.000003098242,0.00010581203,0.0000015554741,0.0000024086964,0.0000017214178,0.0000013509734,0.99944466,0.0000656822,0.0003090419,0.00006201651,0.0000019079052],"about_ca_topic_score_codex":0.028117556,"about_ca_topic_score_gemma":0.019775836,"teacher_disagreement_score":0.028117556,"about_ca_system_score_codex":0.0009303604,"about_ca_system_score_gemma":0.0008060387,"threshold_uncertainty_score":0.055907786},"labels":[],"label_agreement":null},{"id":"W2966421386","doi":"10.1007/s12665-019-8474-y","title":"Evaluation of data-driven models (SVR and ANN) for groundwater-level prediction in confined and unconfined systems","year":2019,"lang":"en","type":"article","venue":"Environmental Earth Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":105,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mean squared error; Groundwater; Support vector machine; Hydrogeology; Artificial neural network; Mean absolute percentage error; Aquifer; Coefficient of determination; Correlation coefficient; Predictive modelling; Computer science; Machine learning; Data mining; Statistics; Engineering; Mathematics; Geotechnical engineering","score_opus":0.12205074681081728,"score_gpt":0.2800154020876894,"score_spread":0.1579646552768721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966421386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9881072,0.00024617976,0.009882046,0.00012665107,0.00003418117,0.000025120633,0.0002922253,0.00027442316,0.0010120614],"genre_scores_gemma":[0.997262,0.000034335844,0.0021576537,0.000010410066,0.0000034060306,0.000010621848,0.00021233284,0.000007614613,0.00030157203],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995648,0.00017611028,0.000044955104,0.00008957681,0.00007150859,0.00005301145],"domain_scores_gemma":[0.9967265,0.00222262,0.00014752703,0.00014476554,0.00063951133,0.0001190484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021080642,0.00083956355,0.0007910975,0.0004920702,0.0002783365,0.00062781334,0.0007031909,0.0009012324,0.0006640887],"category_scores_gemma":[0.0041562538,0.0003305817,0.0005313501,0.0004255388,0.00030519292,0.0008705636,0.0005220332,0.0005739768,0.0000908275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067002233,0.00034701425,0.0064374674,0.000078820856,0.00009613208,0.000037191774,0.000026458973,0.97165334,0.0019161702,0.00021241038,0.00029447992,0.018230442],"study_design_scores_gemma":[0.00001591137,0.00013626179,0.0010684942,0.0000019518877,0.000010627407,0.000002448001,0.00000869737,0.9979144,0.0007654463,0.000037989128,0.0000343266,0.0000035387461],"about_ca_topic_score_codex":0.041082617,"about_ca_topic_score_gemma":0.027376508,"teacher_disagreement_score":0.041082617,"about_ca_system_score_codex":0.0010950821,"about_ca_system_score_gemma":0.00096932845,"threshold_uncertainty_score":0.08168697},"labels":[],"label_agreement":null},{"id":"W2966632903","doi":"10.3808/jeil.201900007","title":"Examination of Multiple Linear Regression (MLR) and Neural Network (NN) Models to Predict Eutrophication Levels in Lake Champlain","year":2019,"lang":"en","type":"article","venue":"Journal of Environmental Informatics Letters","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"New York State Department of Environmental Conservation","keywords":"Eutrophication; Linear regression; Environmental science; Secchi disk; Alkalinity; Hydrology (agriculture); Chlorophyll a; Empirical modelling; Phosphorus; Water quality; Regression analysis; Lake ecosystem; Nutrient; Ecosystem; Ecology; Statistics; Mathematics; Biology; Chemistry; Computer science; Geology","score_opus":0.021101907211298964,"score_gpt":0.2159192897070044,"score_spread":0.19481738249570546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966632903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97283155,0.00077321555,0.0221672,0.0009067859,0.000052034877,0.000035308025,0.00047335072,0.0004974858,0.0022629786],"genre_scores_gemma":[0.9869646,0.0001769669,0.011050911,0.00007901718,0.000017486203,0.00003860646,0.0005493685,0.000018986417,0.0011040387],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995016,0.00022793552,0.000033704182,0.0001213394,0.00007792889,0.00003743736],"domain_scores_gemma":[0.99785835,0.0015868354,0.00016799566,0.000050641767,0.00028975023,0.00004638657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027800854,0.00065538054,0.0003805607,0.00076325954,0.0002536744,0.00056199834,0.0005468855,0.00045407456,0.00058363774],"category_scores_gemma":[0.0037553567,0.00020748429,0.00045053434,0.00055319053,0.00019679546,0.0005952343,0.00038072403,0.0005730221,0.00012423542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007026022,0.00011264391,0.03207171,0.000051340667,0.00009337796,0.000059371116,0.00004831521,0.93936664,0.0005866404,0.00030985716,0.00071965746,0.02651014],"study_design_scores_gemma":[0.000002116508,0.000014652552,0.0028611498,0.0000042307174,0.000005113918,0.0000033587123,0.00000868776,0.9968118,0.00014687968,0.00006550305,0.000073035895,0.0000035030191],"about_ca_topic_score_codex":0.072501294,"about_ca_topic_score_gemma":0.06540262,"teacher_disagreement_score":0.072501294,"about_ca_system_score_codex":0.0012933254,"about_ca_system_score_gemma":0.0011503663,"threshold_uncertainty_score":0.1441586},"labels":[],"label_agreement":null},{"id":"W2969357546","doi":"10.1007/s11269-019-02346-0","title":"Lake Water-Level fluctuations forecasting using Minimax Probability Machine Regression, Relevance Vector Machine, Gaussian Process Regression, and Extreme Learning Machine","year":2019,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":98,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Extreme learning machine; Relevance vector machine; Machine learning; Computer science; Artificial intelligence; Perceptron; Artificial neural network; Overfitting; Gaussian process; Support vector machine; Kriging; Gaussian","score_opus":0.03978697126735987,"score_gpt":0.24472581049632128,"score_spread":0.20493883922896142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969357546","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13468456,0.0007146152,0.8618283,0.00056798075,0.00010685276,0.000034496556,0.000089481015,0.00055747014,0.0014162423],"genre_scores_gemma":[0.92531216,0.00025368435,0.07298454,0.000064432235,0.00012598904,0.000047625526,0.00013291671,0.00004355859,0.001035143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999126,0.00038518428,0.000059944545,0.00017776283,0.00019858888,0.000052615498],"domain_scores_gemma":[0.99787855,0.0013316025,0.00022375205,0.00011321718,0.00040169118,0.000051234623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022376827,0.00052649516,0.0012684128,0.0008952022,0.0003667444,0.0008775297,0.00081886165,0.00073030184,0.00044107295],"category_scores_gemma":[0.007219686,0.00031102746,0.00066333974,0.0011873427,0.00042771766,0.0014939394,0.0006383105,0.0013192364,0.00012132812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001492101,0.00011532417,0.004539791,0.00007347772,0.00015077772,0.000041968928,0.00005441064,0.86177593,0.0013600319,0.006744413,0.0014875524,0.12350713],"study_design_scores_gemma":[0.0000031159243,0.000008241812,0.00025603213,0.0000011115213,0.0000032881132,0.0000021962544,0.000001083857,0.99866855,0.000106367326,0.00091428566,0.00003343525,0.0000022871104],"about_ca_topic_score_codex":0.004736951,"about_ca_topic_score_gemma":0.0036834963,"teacher_disagreement_score":0.004736951,"about_ca_system_score_codex":0.00054899126,"about_ca_system_score_gemma":0.0006167549,"threshold_uncertainty_score":0.011834085},"labels":[],"label_agreement":null},{"id":"W2969704959","doi":"10.1088/1742-6596/1276/1/012006","title":"Prediction of reflection coefficient of a perforated Quarter Circle Breakwater using artificial neural network (ann)","year":2019,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Reflection coefficient; Quarter (Canadian coin); Breakwater; Reflection (computer programming); Geology; Acoustics; Artificial intelligence; Optics; Computer science; Geotechnical engineering; Physics; History","score_opus":0.04597653462537003,"score_gpt":0.2473990980427563,"score_spread":0.2014225634173863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969704959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9230965,0.00027842444,0.07295948,0.0001393374,0.000085857355,0.00003093159,0.00020003389,0.00036294313,0.0028464256],"genre_scores_gemma":[0.9951245,0.00006392917,0.0039003312,0.000009718225,0.0000021963804,0.000013342033,0.00007008542,0.0000055695996,0.00081029086],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987125,0.000018774806,0.00001123862,0.000035621182,0.000039115654,0.000023986036],"domain_scores_gemma":[0.9996643,0.00016963232,0.000047374375,0.000015020272,0.00009025022,0.000013412004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027813515,0.00057003176,0.0003680689,0.0004242057,0.0001946245,0.0004620412,0.0003881771,0.00074099057,0.0013635708],"category_scores_gemma":[0.0008324776,0.00023653623,0.0004518358,0.0002782919,0.00020272216,0.00038439102,0.00020113894,0.00040431417,0.00022458225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021274421,0.0001322204,0.012410603,0.00011499905,0.00005446384,0.00022434787,0.000052675718,0.9336849,0.020557908,0.00015152482,0.00042282132,0.03198084],"study_design_scores_gemma":[0.000002367869,0.000058511978,0.0022128567,0.0000047010153,0.00000589387,0.000010595195,0.000013700731,0.99478626,0.0027825488,0.00004693129,0.00007035573,0.0000051294664],"about_ca_topic_score_codex":0.005831595,"about_ca_topic_score_gemma":0.0044617793,"teacher_disagreement_score":0.005831595,"about_ca_system_score_codex":0.00037716515,"about_ca_system_score_gemma":0.00021912968,"threshold_uncertainty_score":0.011595309},"labels":[],"label_agreement":null},{"id":"W2969834763","doi":"10.1109/access.2019.2936989","title":"A Machine Learning Metasystem for Robust Probabilistic Nonlinear Regression-Based Forecasting of Seasonal Water Availability in the US West","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Los Alamos National Laboratory; Università degli Studi di Palermo; U.S. Department of Agriculture; Simon Fraser University; Environment and Climate Change Canada; Oregon State University","keywords":"Computer science; Probabilistic logic; Machine learning; Artificial intelligence; Ensemble learning","score_opus":0.05485155803790336,"score_gpt":0.27826282943495634,"score_spread":0.22341127139705297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969834763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031390335,0.00012234342,0.962946,0.00025742303,0.000026965705,0.00007153611,0.0001503401,0.0025704096,0.0024646346],"genre_scores_gemma":[0.61134917,0.00012214096,0.38564938,0.00016532924,0.000040566163,0.0002550432,0.0003435318,0.00017598063,0.00189884],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951994,0.00011635018,0.000049255897,0.00016315412,0.00010956094,0.00004167341],"domain_scores_gemma":[0.999203,0.00036306866,0.00009006098,0.00011451089,0.00019204234,0.000037320464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018620339,0.00073936227,0.0006303756,0.0006993545,0.00067791424,0.0013433006,0.0011352969,0.0010497071,0.0018147134],"category_scores_gemma":[0.003247235,0.00046179772,0.000996086,0.00052691536,0.00052775274,0.0013493269,0.001129422,0.0011319105,0.00048302257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082078346,0.000070221526,0.0026576056,0.000062744315,0.00013757365,0.000090165544,0.0000838745,0.90605,0.0038070749,0.010995333,0.00077668397,0.07518654],"study_design_scores_gemma":[0.000005228687,0.000015181001,0.00010240401,0.000004952404,0.000010883975,0.000007388257,0.000005342823,0.99703074,0.0008694074,0.0014995025,0.00044459224,0.0000043582195],"about_ca_topic_score_codex":0.007629174,"about_ca_topic_score_gemma":0.007464606,"teacher_disagreement_score":0.007629174,"about_ca_system_score_codex":0.0012514854,"about_ca_system_score_gemma":0.0015208285,"threshold_uncertainty_score":0.015169561},"labels":[],"label_agreement":null},{"id":"W2977392146","doi":"10.1590/2318-0331.241920180077","title":"Spectral analysis in determining water quality sampling intervals","year":2019,"lang":"en","type":"article","venue":"Revista Brasileira de Recursos Hídricos","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sampling (signal processing); Representativeness heuristic; Statistics; Nyquist frequency; Series (stratigraphy); Water quality; Calibration; Quality (philosophy); Executable; Nyquist–Shannon sampling theorem; Environmental science; Remote sensing; Computer science; Mathematics; Geography; Telecommunications; Geology","score_opus":0.04292958291424653,"score_gpt":0.31593332778621414,"score_spread":0.2730037448719676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977392146","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24604504,0.00034625182,0.74952173,0.000053262498,0.00004556204,0.00011385173,0.0002454654,0.00042049502,0.0032084093],"genre_scores_gemma":[0.9023289,0.00014300918,0.09686432,0.000012607842,0.000021035035,0.00007729872,0.00021730708,0.000032206768,0.00030318237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989951,0.00037346254,0.00009856778,0.00016589771,0.0003020973,0.000064755615],"domain_scores_gemma":[0.9945832,0.0037543904,0.0004049453,0.00031156588,0.0008793791,0.00006660276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022360713,0.00036234056,0.00032064627,0.00224692,0.00028989153,0.0005900968,0.00036202723,0.0003374728,0.0008662278],"category_scores_gemma":[0.012731558,0.00013248478,0.0003240575,0.001528251,0.00030727166,0.00093822146,0.00033850165,0.0003745131,0.00025111448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005893802,0.00019544181,0.07588559,0.00037578846,0.00010891791,0.00024790133,0.00074563106,0.28683034,0.039318614,0.010890155,0.00091621344,0.583896],"study_design_scores_gemma":[0.0000109967,0.00009584941,0.04117165,0.000047046124,0.000038166534,0.0001540234,0.00024922646,0.9402826,0.011709712,0.004227012,0.00197682,0.00003689538],"about_ca_topic_score_codex":0.0037400082,"about_ca_topic_score_gemma":0.0022152173,"teacher_disagreement_score":0.0037400082,"about_ca_system_score_codex":0.00034274618,"about_ca_system_score_gemma":0.00029025602,"threshold_uncertainty_score":0.011825621},"labels":[],"label_agreement":null},{"id":"W2978449927","doi":"10.5539/enrr.v9n3p117","title":"Classification and Regression Tree to Predict the Precipitation Labels of North-West Region in Bangladesh","year":2019,"lang":"en","type":"article","venue":"Environment and Natural Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cart; Precipitation; Regression; Agriculture; North west; Regression analysis; Geography; Environmental science; Statistics; Physical geography; Mathematics; Meteorology; Archaeology","score_opus":0.039182073609262194,"score_gpt":0.28970861086063726,"score_spread":0.2505265372513751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978449927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9259724,0.00047118438,0.052759666,0.0011267185,0.0001251997,0.00009985085,0.006962282,0.0008372513,0.011645471],"genre_scores_gemma":[0.97757256,0.00017341234,0.015068502,0.000041628326,0.000016739226,0.000041209274,0.0042060986,0.000030348485,0.0028495493],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972373,0.00011913214,0.000022080338,0.00004764329,0.000042865617,0.00004455385],"domain_scores_gemma":[0.99909806,0.00048543332,0.000069740956,0.00004963196,0.00024389666,0.00005318297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062513276,0.00046406855,0.000326683,0.0010573238,0.0002961352,0.0004980666,0.0004928269,0.00029861167,0.0027742353],"category_scores_gemma":[0.002397116,0.0001465774,0.0003929557,0.0016143664,0.00009345858,0.00049649144,0.00031078942,0.0006848678,0.0012578365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006427818,0.00032223965,0.15089379,0.00013802729,0.00026953494,0.00048082205,0.00030786128,0.5533039,0.003630569,0.0021676884,0.020142486,0.2677003],"study_design_scores_gemma":[0.000019333644,0.00004065483,0.025461951,0.000012679205,0.000021677653,0.000029121635,0.00020002882,0.97123814,0.0005356123,0.00087094796,0.0015541512,0.000015639103],"about_ca_topic_score_codex":0.060060173,"about_ca_topic_score_gemma":0.05041633,"teacher_disagreement_score":0.060060173,"about_ca_system_score_codex":0.00071654236,"about_ca_system_score_gemma":0.00062072044,"threshold_uncertainty_score":0.119421184},"labels":[],"label_agreement":null},{"id":"W2979639302","doi":"10.3808/jeil.201900012","title":"Prediction of Long-Term Near-Surface Temperature Based on NA-CORDEX Output","year":2019,"lang":"en","type":"article","venue":"Journal of Environmental Informatics Letters","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"","keywords":"Downscaling; Nonlinear autoregressive exogenous model; Artificial neural network; Mean squared error; Computer science; Perceptron; Multilayer perceptron; Nonlinear system; Environmental science; Precipitation; Climate model; Climate change; Meteorology; Climatology; Machine learning; Statistics; Mathematics; Geography; Geology","score_opus":0.01022349877231195,"score_gpt":0.1947180300868267,"score_spread":0.18449453131451474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979639302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98797995,0.000049583792,0.0074131778,0.00010883874,0.000026420992,0.00003243911,0.0010058546,0.00046768461,0.002916107],"genre_scores_gemma":[0.9941795,0.000027512846,0.004143287,0.000007705767,0.0000021521405,0.000015664393,0.0007019567,0.000011510414,0.0009107554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998919,0.000013144462,0.000007266618,0.000037589925,0.000034328234,0.000015775386],"domain_scores_gemma":[0.99965763,0.000058060574,0.000036424277,0.000028045031,0.00019867768,0.000021137826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033044684,0.00046101352,0.00021183286,0.0002319322,0.00029204282,0.00041639863,0.0003697572,0.0002798735,0.00082681957],"category_scores_gemma":[0.0010107418,0.00012700839,0.00021960093,0.00032008247,0.00017654235,0.00035257722,0.00022803417,0.000285995,0.00015218706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049863267,0.00018020114,0.12861137,0.000090399015,0.00007252469,0.00027125535,0.00016569304,0.78689384,0.022141842,0.0008072666,0.0032770808,0.05698993],"study_design_scores_gemma":[0.000010853903,0.000024457644,0.025334809,0.0000030522167,0.000008561027,0.0000057294324,0.000032152646,0.9698313,0.0042410223,0.000087559296,0.0004125099,0.000008051304],"about_ca_topic_score_codex":0.2954383,"about_ca_topic_score_gemma":0.3412874,"teacher_disagreement_score":0.2954383,"about_ca_system_score_codex":0.0018101877,"about_ca_system_score_gemma":0.00150441,"threshold_uncertainty_score":0.5874373},"labels":[],"label_agreement":null},{"id":"W2980597459","doi":"10.1007/s11269-019-02356-y","title":"Advancing Freshwater Lake Level Forecast Using King’s Castle Optimization with Training Sample Adaption and Adaptive Neuro-Fuzzy Inference System","year":2019,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Adaptive neuro fuzzy inference system; Training (meteorology); Sample (material); Inference system; Fuzzy inference system; Hydrogeology; Inference; Artificial intelligence; Fuzzy logic; Computer science; Environmental science; Machine learning; Hydrology (agriculture); Operations research; Fuzzy control system; Engineering; Meteorology; Geography; Geotechnical engineering","score_opus":0.038975203698990546,"score_gpt":0.2197270873361447,"score_spread":0.18075188363715416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980597459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1401056,0.0003293268,0.85384935,0.00021389991,0.0001315805,0.00006349851,0.0000761271,0.00038454685,0.004846031],"genre_scores_gemma":[0.9297429,0.000094960946,0.06799858,0.000059123406,0.000032098338,0.00007030954,0.00008006372,0.000020457966,0.0019015116],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998354,0.000037214497,0.000013210511,0.000041058283,0.00004598077,0.000027105225],"domain_scores_gemma":[0.9995627,0.0002026976,0.00003457817,0.000025297444,0.00015457008,0.00002021552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065438566,0.00043577992,0.0008454855,0.00040986686,0.0005083762,0.0006126889,0.000713353,0.0007884304,0.0011299062],"category_scores_gemma":[0.0015432633,0.0003506996,0.00058550114,0.0004084907,0.00030723415,0.0006072469,0.00052689627,0.0007151319,0.0001370587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007604688,0.00004943409,0.00072624575,0.000035345463,0.00003374586,0.0000315641,0.000038793267,0.95412207,0.0017000289,0.0010425078,0.00049258297,0.041651547],"study_design_scores_gemma":[0.0000021500205,0.000006128858,0.00008717583,7.8615193e-7,0.0000020649588,9.98663e-7,0.0000013378444,0.9996934,0.00010446943,0.00006676294,0.000033343655,0.0000013057307],"about_ca_topic_score_codex":0.02726739,"about_ca_topic_score_gemma":0.022813821,"teacher_disagreement_score":0.02726739,"about_ca_system_score_codex":0.0006055849,"about_ca_system_score_gemma":0.00094343,"threshold_uncertainty_score":0.05421734},"labels":[],"label_agreement":null},{"id":"W2981565882","doi":"10.20381/ruor-24028","title":"SARIMA Short to Medium-Term Forecasting and Stochastic Simulation of Streamflow, Water Levels and Sediments Time Series from the HYDAT Database","year":2019,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Streamflow; Term (time); Series (stratigraphy); Medium term; Environmental science; Database; Hydrology (agriculture); Computer science; Geography; Geology; Cartography; Geotechnical engineering; Economics","score_opus":0.06798907248507179,"score_gpt":0.30111219722404536,"score_spread":0.23312312473897356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981565882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86166185,0.00026874605,0.0955854,0.00044141608,0.0001241285,0.00023075387,0.020786362,0.0079765115,0.012924765],"genre_scores_gemma":[0.9222512,0.00022021623,0.05935094,0.000044360368,0.000014533425,0.000109652334,0.0141063845,0.00022187483,0.0036807896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998123,0.00001972603,0.000014295957,0.000037030855,0.00007475132,0.00004192625],"domain_scores_gemma":[0.9996111,0.00008755306,0.000028080389,0.000033051743,0.00019430407,0.000045875375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043152148,0.0005162762,0.00028296193,0.00046602706,0.0004437008,0.0006325545,0.0008610061,0.00028389366,0.0019375685],"category_scores_gemma":[0.0009742507,0.00022283153,0.00050935964,0.00078240177,0.0002631234,0.00041660073,0.00033064725,0.00053548417,0.00025992809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020747307,0.00012665386,0.020610416,0.00013780937,0.00007536029,0.00018131344,0.00013437051,0.929022,0.0053476407,0.0027743285,0.0074365563,0.03394606],"study_design_scores_gemma":[0.000011761191,0.000011477464,0.004469919,0.0000036698664,0.000008762542,0.000008724635,0.000020087884,0.9915377,0.0021332367,0.00018723459,0.0015948418,0.000012687927],"about_ca_topic_score_codex":0.6626929,"about_ca_topic_score_gemma":0.6529278,"teacher_disagreement_score":0.6626929,"about_ca_system_score_codex":0.002516245,"about_ca_system_score_gemma":0.004892911,"threshold_uncertainty_score":0.6785871},"labels":[],"label_agreement":null},{"id":"W2986218094","doi":"10.2166/wcc.2019.321","title":"Flood prediction based on weather parameters using deep learning","year":2019,"lang":"en","type":"article","venue":"Journal of Water and Climate Change","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Flood myth; Support vector machine; Artificial intelligence; Machine learning; Artificial neural network; Flood forecasting; Computer science; Deep learning; Meteorology; Internet of Things; Environmental science; Geography","score_opus":0.035637477658943796,"score_gpt":0.23424384689910913,"score_spread":0.19860636924016534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986218094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8367123,0.00066231337,0.1532807,0.00079823757,0.00018710202,0.00003944456,0.0012478459,0.001429844,0.0056421896],"genre_scores_gemma":[0.99471915,0.000092428425,0.0039842944,0.000029203407,0.000017779172,0.000007984787,0.00037893502,0.0000062411,0.0007638636],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999238,0.000013105578,0.00000649819,0.00001874595,0.000015858068,0.00002194878],"domain_scores_gemma":[0.99966955,0.00014798988,0.000044207896,0.00001993277,0.00009146558,0.00002685462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024517352,0.00043394804,0.00039484035,0.0005790692,0.00017731704,0.00044130386,0.0002967454,0.0003902544,0.0013061739],"category_scores_gemma":[0.00088908407,0.0002024697,0.0003324049,0.00048546065,0.00013862278,0.0006907001,0.000343435,0.000675964,0.0002497025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002728938,0.00019889738,0.018638203,0.000049232804,0.00007147186,0.00010051436,0.000027801421,0.8908724,0.0043120584,0.0005821851,0.0019667908,0.08290751],"study_design_scores_gemma":[0.000001890119,0.000005835857,0.0008828389,0.0000017048515,0.0000023142172,0.0000020967373,0.000002560965,0.9985177,0.00031844352,0.0002200562,0.000042665088,0.000002011764],"about_ca_topic_score_codex":0.009831847,"about_ca_topic_score_gemma":0.008776428,"teacher_disagreement_score":0.009831847,"about_ca_system_score_codex":0.0004093719,"about_ca_system_score_gemma":0.00046842205,"threshold_uncertainty_score":0.01954925},"labels":[],"label_agreement":null},{"id":"W2990607379","doi":"10.1016/j.scitotenv.2019.135539","title":"Ensemble modelling framework for groundwater level prediction in urban areas of India","year":2019,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":142,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Science and Engineering Research Board","keywords":"Groundwater; Urbanization; Support vector machine; Population; Environmental science; Artificial neural network; Water resource management; Hydrology (agriculture); Computer science; Machine learning; Engineering; Ecology; Geotechnical engineering","score_opus":0.027948060117023783,"score_gpt":0.21857879176443054,"score_spread":0.19063073164740676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990607379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5046075,0.0011320912,0.48255306,0.0008689743,0.00017917743,0.00003330423,0.0013619333,0.0011169461,0.008147024],"genre_scores_gemma":[0.9844824,0.00027796483,0.012464227,0.0000351628,0.000038811664,0.00003247704,0.00048747796,0.000024212946,0.0021572802],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998523,0.00004521849,0.000011370611,0.000034212684,0.00002646771,0.000030408735],"domain_scores_gemma":[0.9997706,0.00009142137,0.000022974793,0.000018035425,0.0000830627,0.000013901069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042241946,0.0003891434,0.00071736355,0.00046657937,0.0003586708,0.0006882279,0.0009771269,0.00050893135,0.0010029882],"category_scores_gemma":[0.0006269499,0.00022838033,0.0006043582,0.00087739556,0.00014761802,0.0005368466,0.0004912344,0.000685905,0.00016396955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015849184,0.000015094032,0.001121572,0.0000075539538,0.000036652924,0.0000191438,0.000012896951,0.9888876,0.00017871396,0.00078450184,0.00033055182,0.008589932],"study_design_scores_gemma":[5.73802e-7,0.0000020717273,0.00016956971,5.2785504e-7,0.0000035036549,0.0000014727694,0.0000030890026,0.999527,0.000027718874,0.00020621021,0.000057101963,0.0000012900639],"about_ca_topic_score_codex":0.06878188,"about_ca_topic_score_gemma":0.054854922,"teacher_disagreement_score":0.06878188,"about_ca_system_score_codex":0.00057003094,"about_ca_system_score_gemma":0.0008420279,"threshold_uncertainty_score":0.13676304},"labels":[],"label_agreement":null},{"id":"W2994025393","doi":"10.1038/s41597-019-0316-y","title":"CE-QUAL-W2 model of dam outflow elevation impact on temperature, dissolved oxygen and nutrients in a reservoir","year":2019,"lang":"en","type":"article","venue":"Scientific Data","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Global Institute for Water Security, University of Saskatchewan; Global Water Futures; University of Saskatchewan","keywords":"Outflow; Nutrient; Environmental science; Elevation (ballistics); Hydrology (agriculture); Oxygen; Oceanography; Ecology; Geology; Chemistry; Biology; Geotechnical engineering; Mathematics","score_opus":0.04989829200182872,"score_gpt":0.29832687360129106,"score_spread":0.24842858159946235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994025393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80998546,0.00027064653,0.016679682,0.0015466361,0.00021436485,0.00020862867,0.14556725,0.0037634852,0.021763843],"genre_scores_gemma":[0.93886507,0.00013414033,0.009026037,0.00019986299,0.000023725683,0.00017767012,0.048110012,0.00017130618,0.0032922907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998074,0.000034508877,0.00001272978,0.000057538415,0.000032068714,0.00005577724],"domain_scores_gemma":[0.9992712,0.00024361021,0.00005398972,0.00005796777,0.00026599696,0.00010722965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059226097,0.0009101025,0.0007152086,0.0006034692,0.0004770083,0.00092316436,0.0019447041,0.0013172532,0.004886778],"category_scores_gemma":[0.0015500771,0.0005162654,0.00096227217,0.0013676201,0.00052498025,0.00062963227,0.00045469526,0.00093149306,0.00057156547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078602854,0.00006880898,0.006307815,0.000038454386,0.000034885765,0.00004677812,0.000015227834,0.9854403,0.00038740376,0.0007457539,0.0054113525,0.0014246237],"study_design_scores_gemma":[0.00008866254,0.000014913654,0.002416693,0.0000056000868,0.000009838154,0.0000055399237,0.000019566516,0.9955859,0.00028043793,0.00028575238,0.0012731659,0.000013902658],"about_ca_topic_score_codex":0.3925209,"about_ca_topic_score_gemma":0.28883904,"teacher_disagreement_score":0.3925209,"about_ca_system_score_codex":0.0028534255,"about_ca_system_score_gemma":0.0036232704,"threshold_uncertainty_score":0.78047234},"labels":[],"label_agreement":null},{"id":"W2996139122","doi":"10.3390/w12010005","title":"Groundwater Estimation from Major Physical Hydrology Components Using Artificial Neural Networks and Deep Learning","year":2019,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; University of Prince Edward Island","funders":"","keywords":"Hydrology (agriculture); Environmental science; Evapotranspiration; Baseflow; Groundwater; Multilayer perceptron; Streamflow; Watershed; Artificial neural network; Geography; Machine learning; Drainage basin; Geology; Computer science; Cartography; Ecology","score_opus":0.017328628956624174,"score_gpt":0.22564273475929017,"score_spread":0.208314105802666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996139122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70135415,0.0009944024,0.29174635,0.00034246506,0.00005301322,0.000053534233,0.0014264153,0.0011399281,0.0028897435],"genre_scores_gemma":[0.9574493,0.000223337,0.040788528,0.000033835,0.000012292337,0.000021262518,0.00071452506,0.00002171576,0.0007351943],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998361,0.000027383461,0.0000160906,0.000045811372,0.000054217446,0.000020320844],"domain_scores_gemma":[0.9997205,0.00008709177,0.00005746843,0.000023913015,0.00009644695,0.000014585843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003600461,0.00051602925,0.00029803743,0.0010390814,0.00023033931,0.00059812324,0.00041559164,0.00041558925,0.00035810994],"category_scores_gemma":[0.0010991415,0.00030074592,0.00036347986,0.0012763762,0.00021825808,0.0007565795,0.0005409951,0.00048135966,0.00009514562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009920164,0.00012460772,0.10449645,0.00017146327,0.00023451095,0.00019409203,0.00013957331,0.63656396,0.016262298,0.0014644879,0.0012009745,0.23904839],"study_design_scores_gemma":[0.0000063918083,0.00001868394,0.019058125,0.000012287467,0.000017503597,0.000016180447,0.0000445506,0.9757474,0.0036728778,0.0008722206,0.0005177489,0.00001597569],"about_ca_topic_score_codex":0.051690478,"about_ca_topic_score_gemma":0.08519846,"teacher_disagreement_score":0.051690478,"about_ca_system_score_codex":0.0009858881,"about_ca_system_score_gemma":0.00089490414,"threshold_uncertainty_score":0.10277921},"labels":[],"label_agreement":null},{"id":"W2997275685","doi":"","title":"Using Fuzzy-Set Classification to Analyse Sea-Level Indicators With Respect to Glacial-Isostatic Adjustment","year":2004,"lang":"en","type":"article","venue":"Publication Database GFZ (GFZ German Research Centre for Geosciences)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Post-glacial rebound; Glacial period; Geology; Sea level; Set (abstract data type); Physical geography; Computer science; Geomorphology; Geography; Oceanography","score_opus":0.13148627693061712,"score_gpt":0.38431501400328927,"score_spread":0.25282873707267217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997275685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3131051,0.00025646135,0.6791641,0.0001837298,0.000049693102,0.00021035355,0.0012364993,0.00087502075,0.0049190153],"genre_scores_gemma":[0.63173795,0.00009834756,0.3659559,0.000034113255,0.00002776855,0.00014892187,0.0010850215,0.000020020594,0.0008919579],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917346,0.0001837915,0.00015706434,0.00012943364,0.00028044777,0.00007563288],"domain_scores_gemma":[0.9964753,0.0023855902,0.00025675606,0.00019988841,0.00060226984,0.00008023367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025748194,0.00035529208,0.0004969022,0.0045087994,0.00055871473,0.0015473386,0.00059980503,0.000475565,0.0015142887],"category_scores_gemma":[0.00675915,0.00014904626,0.0006560551,0.0030301893,0.00059951755,0.00092297216,0.00032284684,0.0003770149,0.00029517204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008035787,0.00027420436,0.06868181,0.00033577386,0.000279285,0.00035735543,0.0013740646,0.18519029,0.021023022,0.020041533,0.0021004516,0.6995387],"study_design_scores_gemma":[0.00004679961,0.000125016,0.026252644,0.000061827006,0.000114123584,0.000119149205,0.00037453132,0.9442322,0.010425738,0.0155819105,0.0025999611,0.00006606951],"about_ca_topic_score_codex":0.01310815,"about_ca_topic_score_gemma":0.008010914,"teacher_disagreement_score":0.01310815,"about_ca_system_score_codex":0.0009678984,"about_ca_system_score_gemma":0.0007099454,"threshold_uncertainty_score":0.02606374},"labels":[],"label_agreement":null},{"id":"W2998160069","doi":"10.2478/jwld-2019-0074","title":"A comparative study of fuzzy logic-based models for groundwater quality evaluation based on irrigation indices","year":2019,"lang":"en","type":"article","venue":"Journal of Water and Land Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Groundwater; Fuzzy logic; Aquifer; Context (archaeology); Irrigation; Quality (philosophy); Environmental science; Computer science; Hydrology (agriculture); Water resource management; Data mining; Artificial intelligence; Engineering; Geography; Geotechnical engineering","score_opus":0.09967020250907839,"score_gpt":0.329117204763366,"score_spread":0.2294470022542876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998160069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6811162,0.0009074587,0.30342618,0.00049212674,0.000094530784,0.0001569804,0.00020855771,0.0004895454,0.013108428],"genre_scores_gemma":[0.988777,0.00011656817,0.010352133,0.000022410519,0.00000945355,0.000038223105,0.000039387538,0.000007860449,0.00063695794],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948466,0.00027689445,0.000029909164,0.00006592783,0.00010109594,0.000041608007],"domain_scores_gemma":[0.9976184,0.0016947835,0.00014528056,0.00007485594,0.00041852513,0.00004807742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002038468,0.0005299147,0.00070113665,0.0010016593,0.00036062443,0.0012663341,0.00082315627,0.0007057253,0.0010943178],"category_scores_gemma":[0.0045385393,0.00023115333,0.0006903559,0.0006210811,0.0003220181,0.00095016044,0.0004132003,0.00043889097,0.00012471424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012027334,0.000071934264,0.0023559122,0.000033534852,0.000043314838,0.000034861157,0.000052556657,0.9787578,0.0004069883,0.0020498584,0.00018677075,0.015886214],"study_design_scores_gemma":[0.000003391633,0.000018289467,0.00013981792,0.0000024564213,0.0000058345872,0.0000020765563,0.000006444247,0.9994673,0.00007485635,0.00023569705,0.00004138713,0.0000024227147],"about_ca_topic_score_codex":0.027382871,"about_ca_topic_score_gemma":0.013291688,"teacher_disagreement_score":0.027382871,"about_ca_system_score_codex":0.0018266609,"about_ca_system_score_gemma":0.0008978149,"threshold_uncertainty_score":0.054446995},"labels":[],"label_agreement":null},{"id":"W3001996239","doi":"10.20944/preprints202001.0312.v1","title":"Hybrid Model of Singular Value Decomposition, ANFIS and Genetic Algorithm for Prediction of Sediment Transport in Sewers","year":2020,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Université Laval","funders":"","keywords":"Adaptive neuro fuzzy inference system; Dimensionless quantity; Singular value decomposition; Genetic algorithm; Mathematics; Froude number; Algorithm; Particle swarm optimization; Applied mathematics; Mathematical optimization; Computer science; Fuzzy logic; Geometry; Artificial intelligence; Mechanics; Physics; Fuzzy control system; Flow (mathematics)","score_opus":0.06986102980649314,"score_gpt":0.29500731530014623,"score_spread":0.2251462854936531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001996239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3047223,0.0012329882,0.6832239,0.00039102364,0.00015570779,0.00013989673,0.00017825684,0.0010342511,0.008921624],"genre_scores_gemma":[0.9709036,0.0003052507,0.025613762,0.00003765558,0.000021932552,0.00012578137,0.000113508475,0.000014669245,0.002863907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997856,0.00005177616,0.000019057778,0.000049941453,0.00006495672,0.000028664881],"domain_scores_gemma":[0.99974805,0.0001304656,0.000033801927,0.000008507725,0.00006857576,0.000010557222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004597312,0.0007577759,0.0007988582,0.00050617545,0.00044586865,0.0008381527,0.00075398164,0.001135754,0.0009169386],"category_scores_gemma":[0.0008007815,0.0003951261,0.00074529205,0.0004458869,0.00033643376,0.00053251704,0.00037604306,0.0007172166,0.00014899283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044399505,0.000031270785,0.0008887136,0.000034825713,0.000034989305,0.00006984522,0.000031531803,0.9874277,0.0012565099,0.00052294676,0.00013943881,0.009517866],"study_design_scores_gemma":[0.0000018469353,0.00001579815,0.00011001359,0.000002090905,0.0000034844445,0.0000035594908,0.0000033226547,0.9995926,0.00012704969,0.00009254668,0.0000459864,0.0000016811069],"about_ca_topic_score_codex":0.023239365,"about_ca_topic_score_gemma":0.014084377,"teacher_disagreement_score":0.023239365,"about_ca_system_score_codex":0.00062967575,"about_ca_system_score_gemma":0.0007940272,"threshold_uncertainty_score":0.046208203},"labels":[],"label_agreement":null},{"id":"W3002212774","doi":"10.1016/j.jhydrol.2020.124614","title":"Discussion of “Comparative assessment of time series and artificial intelligence models to estimate monthly streamflow: A local and external data analysis approach” by Saeid Mehdizadeh, Farshad Fathian, Mir Jafar Sadegh Safari and Jan F. Adamowski","year":2020,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Autoregressive model; Time series; Nonlinear system; Series (stratigraphy); Computer science; Heteroscedasticity; Streamflow; Artificial neural network; Nonlinear autoregressive exogenous model; Autoregressive integrated moving average; Artificial intelligence; Econometrics; Mathematics; Machine learning; Geology; Geography","score_opus":0.06165643001159349,"score_gpt":0.32241063613368304,"score_spread":0.26075420612208955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3002212774","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019910054,0.018323356,0.2150508,0.67941093,0.018820854,0.00046282727,0.0014786064,0.000744138,0.045798406],"genre_scores_gemma":[0.4364054,0.019603997,0.230331,0.23977716,0.041438878,0.0016682214,0.0018709245,0.0006923629,0.028212048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9852063,0.009644401,0.0009224904,0.00092456234,0.0030178674,0.0002842774],"domain_scores_gemma":[0.9204147,0.062420342,0.0018470155,0.0019941167,0.012785822,0.0005379586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03934174,0.00093353743,0.0009771186,0.0029913082,0.0017630955,0.007022025,0.0038128945,0.00608649,0.0046217046],"category_scores_gemma":[0.09369565,0.00035958167,0.0025483065,0.0032232795,0.0036396075,0.004628914,0.0020440044,0.0046421457,0.00091086765],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041407178,0.0002573195,0.011168958,0.0013875503,0.001452973,0.0008434981,0.0019969733,0.04893902,0.0018424923,0.46753925,0.31307116,0.15108673],"study_design_scores_gemma":[0.00021867859,0.00068511843,0.013918323,0.002640196,0.00077095197,0.0007893942,0.0043862653,0.1469018,0.007866002,0.3687723,0.45269302,0.00035791565],"about_ca_topic_score_codex":0.0100590335,"about_ca_topic_score_gemma":0.009909495,"teacher_disagreement_score":0.03934174,"about_ca_system_score_codex":0.002711975,"about_ca_system_score_gemma":0.0030527667,"threshold_uncertainty_score":0.20806146},"labels":[],"label_agreement":null},{"id":"W3004198865","doi":"10.3808/jeil.201900017","title":"A Comparison of Two Data-Driven Models to Predict Hypolimnetic Dissolved Oxygen Concentration: A Case Study of the Seymareh Reservoir in Iran","year":2019,"lang":"en","type":"article","venue":"Journal of Environmental Informatics Letters","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Berger (Canada); York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Hypolimnion; Artificial neural network; Upstream (networking); DPSIR; Water quality; Linear regression; Mean squared error; Computer science; Selection (genetic algorithm); Environmental science; Data mining; Hydrology (agriculture); Statistics; Machine learning; Mathematics; Engineering; Ecology; Eutrophication","score_opus":0.06944895141034266,"score_gpt":0.29969561540210443,"score_spread":0.23024666399176177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004198865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9774095,0.000231122,0.01937345,0.00034921235,0.000039386567,0.00008447945,0.00027022316,0.00019771268,0.002044826],"genre_scores_gemma":[0.99034685,0.000099691824,0.00869647,0.000018942057,0.0000067827104,0.00004601584,0.00023536314,0.00001059073,0.000539377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997873,0.00006236575,0.000018349001,0.000054994875,0.000044841992,0.000032230015],"domain_scores_gemma":[0.99924445,0.0004320722,0.00005277909,0.000028367485,0.00020787305,0.0000344475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008797953,0.0010303152,0.0005818335,0.0006182056,0.00043394906,0.0007844622,0.0010060463,0.00094432296,0.00038520189],"category_scores_gemma":[0.001313381,0.0003904155,0.0008743973,0.00041865217,0.0002432317,0.00064341637,0.00042669853,0.0007526206,0.000080774844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013584476,0.0002708398,0.020360509,0.000106338586,0.000097530785,0.0002489102,0.00010061648,0.9573912,0.001526716,0.00036759482,0.00037995935,0.01901392],"study_design_scores_gemma":[0.00001238397,0.0000561109,0.0022618852,0.00000427218,0.000015875179,0.000008677263,0.000050952247,0.9965964,0.00077058515,0.00010153514,0.00011347368,0.000007869419],"about_ca_topic_score_codex":0.06242861,"about_ca_topic_score_gemma":0.047882188,"teacher_disagreement_score":0.06242861,"about_ca_system_score_codex":0.0015983302,"about_ca_system_score_gemma":0.0014483401,"threshold_uncertainty_score":0.12413043},"labels":[],"label_agreement":null},{"id":"W3005619874","doi":"10.1007/s00477-020-01776-2","title":"Short-term water quality variable prediction using a hybrid CNN–LSTM deep learning model","year":2020,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":557,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mean squared error; Water quality; Coefficient of determination; Artificial intelligence; Correlation coefficient; Convolutional neural network; Computer science; Statistics; Machine learning; Mathematics","score_opus":0.07775161905009657,"score_gpt":0.35128500254372397,"score_spread":0.2735333834936274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005619874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3611546,0.0011382911,0.6236462,0.0008991421,0.00067394064,0.00006286237,0.001438143,0.0033272305,0.007659596],"genre_scores_gemma":[0.9752514,0.00019572262,0.019591475,0.00012965105,0.00005588989,0.000028655191,0.00060003914,0.000029979046,0.0041172355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990606,0.0000054526586,0.0000052839046,0.000037660964,0.000021242962,0.000024314866],"domain_scores_gemma":[0.9998671,0.000027279291,0.000014499989,0.000013962641,0.00006371465,0.000013360245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021879002,0.0006148123,0.00046522284,0.00029594018,0.00020335287,0.00042089686,0.00075583835,0.0006466623,0.0016197792],"category_scores_gemma":[0.0004823345,0.00030161857,0.00048593868,0.00042701024,0.00017342636,0.00071526313,0.00045002592,0.00078004814,0.00041090517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029292054,0.00024209415,0.0059911134,0.000074487616,0.0001642515,0.00015656075,0.000033101816,0.74375623,0.023751322,0.0012634343,0.0041217376,0.22015274],"study_design_scores_gemma":[0.000002425996,0.000009223101,0.00037741486,0.0000014742486,0.0000069818557,0.000004703992,0.000001199251,0.9984339,0.00090048363,0.0001698427,0.00008941362,0.0000029151568],"about_ca_topic_score_codex":0.022177748,"about_ca_topic_score_gemma":0.02431514,"teacher_disagreement_score":0.022177748,"about_ca_system_score_codex":0.0005263915,"about_ca_system_score_gemma":0.0008041426,"threshold_uncertainty_score":0.044097304},"labels":[],"label_agreement":null},{"id":"W3009328342","doi":"10.1007/s00521-020-04800-2","title":"Prediction of actual evapotranspiration by artificial neural network models using data from a Bowen ratio energy balance station","year":2020,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of the Environment, Conservation and Parks; University of Guelph","funders":"","keywords":"Sigmoid function; Mean squared error; Artificial neural network; Evapotranspiration; Activation function; Energy balance; Coefficient of determination; Correlation coefficient; Wind speed; Generalization; Approximation error; Computer science; Mathematics; Artificial intelligence; Algorithm; Statistics; Meteorology; Physics; Mathematical analysis","score_opus":0.11049745469484841,"score_gpt":0.2734038011234458,"score_spread":0.16290634642859741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009328342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9952661,0.00003733984,0.002273743,0.00008992927,0.00003423792,0.000010400691,0.0010099056,0.00014314234,0.0011352199],"genre_scores_gemma":[0.9961731,0.00003140336,0.0019165794,0.000008216107,0.000009036132,0.000008948165,0.0011682338,0.000009614069,0.00067487085],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999889,0.000016333635,0.000011810171,0.000035277797,0.000034621535,0.000013013943],"domain_scores_gemma":[0.9996376,0.00012182438,0.000034327848,0.000031568943,0.0001455399,0.000029134695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026732832,0.00047918464,0.00029011327,0.00063716754,0.0003541768,0.0003840108,0.00042714315,0.00056289363,0.00087351666],"category_scores_gemma":[0.00093638984,0.00023924118,0.00034286123,0.0008140431,0.00022656827,0.0007149595,0.00017531126,0.00048077153,0.0002996549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042718436,0.0005269698,0.1900313,0.00008847992,0.00016251707,0.00030843925,0.00012971259,0.75505865,0.0129214665,0.00064573693,0.0028240548,0.036875516],"study_design_scores_gemma":[0.000028267737,0.000041124178,0.039071955,0.000003149456,0.000015125911,0.0000144482565,0.0000319112,0.9578252,0.0024375927,0.0001734053,0.00034566433,0.000012278846],"about_ca_topic_score_codex":0.043536093,"about_ca_topic_score_gemma":0.06294553,"teacher_disagreement_score":0.043536093,"about_ca_system_score_codex":0.0008820296,"about_ca_system_score_gemma":0.00064794766,"threshold_uncertainty_score":0.086565375},"labels":[],"label_agreement":null},{"id":"W3009964072","doi":"10.1016/j.scitotenv.2020.137612","title":"Improving prediction of water quality indices using novel hybrid machine-learning algorithms","year":2020,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":426,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Random forest; Pruning; Water quality; Algorithm; Statistics; Mean squared error; Computer science; Pearson product-moment correlation coefficient; Decision tree; Tree (set theory); Data mining; Mathematics; Machine learning; Ecology","score_opus":0.03510598550374761,"score_gpt":0.2329694438179496,"score_spread":0.197863458314202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009964072","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17276677,0.00079372124,0.82226896,0.00019296257,0.00022789909,0.00004564293,0.00007618608,0.000940581,0.00268722],"genre_scores_gemma":[0.8535424,0.00022975571,0.14428338,0.00008391769,0.00010772039,0.000060821803,0.00016828839,0.000036847254,0.0014867865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973005,0.000063431165,0.000022484259,0.0000677068,0.00008606432,0.000030178358],"domain_scores_gemma":[0.9991014,0.00047616518,0.00006841106,0.000057068777,0.0002707718,0.000026284317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008136216,0.0006642738,0.0007371384,0.00064892066,0.00027361,0.0007762364,0.00085631874,0.0007236907,0.0006969131],"category_scores_gemma":[0.0017768551,0.00025496582,0.0005192665,0.0006739875,0.00026167012,0.00084293267,0.00042335957,0.00066502986,0.00022864268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019704782,0.0002713426,0.0034395407,0.00006728901,0.00018626353,0.000048315545,0.00003361043,0.76589525,0.009996222,0.0016206943,0.0011587479,0.21708569],"study_design_scores_gemma":[0.0000034263999,0.000011167201,0.00017734969,7.0642653e-7,0.000004929439,0.0000029919813,9.646703e-7,0.9991109,0.000505837,0.0001290073,0.000051035615,0.0000016515792],"about_ca_topic_score_codex":0.0044073146,"about_ca_topic_score_gemma":0.004411263,"teacher_disagreement_score":0.0044073146,"about_ca_system_score_codex":0.00036338548,"about_ca_system_score_gemma":0.0004669226,"threshold_uncertainty_score":0.008763313},"labels":[],"label_agreement":null},{"id":"W3011850987","doi":"10.2112/jcoastres-d-19-00142.1","title":"Evolutionary Prediction of the Trajectory of a Rosette Momentum Jet Group in Flowing Currents","year":2020,"lang":"en","type":"article","venue":"Journal of Coastal Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Dimensionless quantity; Trajectory; Genetic programming; Jet (fluid); Momentum (technical analysis); Evolutionary algorithm; Mechanics; Reynolds number; Mathematics; Physics; Computer science; Machine learning; Mathematical optimization; Turbulence; Economics","score_opus":0.09353076414482987,"score_gpt":0.31902402440818395,"score_spread":0.2254932602633541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011850987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89438915,0.00014582959,0.10300499,0.00018619523,0.00002840751,0.000038800626,0.00017992478,0.0001289604,0.001897723],"genre_scores_gemma":[0.9760901,0.00009197199,0.022803616,0.000015369184,0.0000042815004,0.000029464582,0.00026537653,0.00002058066,0.0006791677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99993336,0.000017459786,0.0000034815228,0.00001835128,0.000013614071,0.000013765868],"domain_scores_gemma":[0.9995271,0.00023710357,0.00006395032,0.000021480571,0.000114139104,0.00003618486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042335616,0.00044048345,0.00030628077,0.0005775864,0.00035904182,0.0005277598,0.0004855426,0.0006425207,0.00048029676],"category_scores_gemma":[0.0017412324,0.00027387985,0.0005162789,0.00040292807,0.00028237494,0.00052513264,0.00033930485,0.00048604063,0.00010121396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019710482,0.000021659396,0.008354923,0.000011591583,0.000013271412,0.00004732305,0.00004016749,0.9816419,0.0008864382,0.0003999798,0.00015263456,0.008410427],"study_design_scores_gemma":[0.0000012843498,0.000008279526,0.0009612555,0.000002004123,0.0000024717683,0.0000031197337,0.000012131862,0.9986412,0.00020507733,0.00010920405,0.00005165912,0.0000022781642],"about_ca_topic_score_codex":0.02465647,"about_ca_topic_score_gemma":0.01733311,"teacher_disagreement_score":0.02465647,"about_ca_system_score_codex":0.00068843545,"about_ca_system_score_gemma":0.0007714068,"threshold_uncertainty_score":0.049025893},"labels":[],"label_agreement":null},{"id":"W3012057477","doi":"10.1016/j.scitotenv.2020.138015","title":"A generalized linear stochastic model for lake level prediction","year":2020,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Agriculture and Agri-Food Canada; Université Laval","funders":"","keywords":"Mean squared error; Gene expression programming; Support vector machine; Adaptive neuro fuzzy inference system; Multilayer perceptron; Artificial neural network; Mathematics; Machine learning; Artificial intelligence; Computer science; Statistics; Fuzzy logic; Fuzzy control system","score_opus":0.06048756324680239,"score_gpt":0.23906569307801706,"score_spread":0.17857812983121468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012057477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022903511,0.00052905874,0.9724448,0.0006246368,0.00015579996,0.00003231132,0.0005322614,0.00065676303,0.0021210022],"genre_scores_gemma":[0.85918057,0.0008871172,0.118801154,0.00038339547,0.0003571012,0.00030828908,0.00146359,0.00018290957,0.0184358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929416,0.00028569222,0.000041413714,0.00018054781,0.00011734495,0.00008075244],"domain_scores_gemma":[0.9985965,0.0009514203,0.00010784495,0.00005226752,0.00024574125,0.00004631732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013160236,0.00061571423,0.0014122342,0.00048627483,0.0005183719,0.0009973666,0.0020378015,0.0013303263,0.0030851627],"category_scores_gemma":[0.0036132121,0.0006631457,0.00082454074,0.0014481271,0.00065425155,0.0010242942,0.0009206688,0.0016666823,0.0006559035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002568426,0.000011482944,0.00016845395,0.000016944461,0.000027516586,0.00001864392,0.000011880513,0.98768765,0.0001881099,0.004174756,0.0005030209,0.007165922],"study_design_scores_gemma":[0.0000029504172,0.000004240638,0.00003160309,7.58947e-7,0.0000031570783,0.0000014432683,7.143422e-7,0.9987148,0.000017631788,0.001122208,0.000098007135,0.0000024798464],"about_ca_topic_score_codex":0.051360436,"about_ca_topic_score_gemma":0.03378089,"teacher_disagreement_score":0.051360436,"about_ca_system_score_codex":0.00094828324,"about_ca_system_score_gemma":0.0017670821,"threshold_uncertainty_score":0.10212296},"labels":[],"label_agreement":null},{"id":"W3013434849","doi":"10.1029/2019wr026226","title":"Data Assimilation for Streamflow Forecasting Using Extreme Learning Machines and Multilayer Perceptrons","year":2020,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo; Université de Sherbrooke","funders":"","keywords":"Streamflow; Data assimilation; Artificial neural network; Perceptron; Computer science; State variable; Multilayer perceptron; Extreme learning machine; Testbed; Nonlinear system; Artificial intelligence; Machine learning; Meteorology; Drainage basin; Geography","score_opus":0.49395543428167216,"score_gpt":0.39091541686992737,"score_spread":0.10304001741174479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013434849","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57447165,0.00021701076,0.42137572,0.00036678047,0.00008605428,0.00004380501,0.00020103718,0.0011809844,0.0020570213],"genre_scores_gemma":[0.9662152,0.00003553371,0.033370215,0.000017310134,0.000010646478,0.000018908217,0.00007929228,0.0000128510965,0.00023998263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974567,0.00008450401,0.000018208557,0.000046643123,0.000077709374,0.000027263],"domain_scores_gemma":[0.9994025,0.0002735221,0.00007734044,0.000088801076,0.00013174371,0.000026024018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009732864,0.00037333372,0.0004728209,0.00045798055,0.00026095906,0.00046268187,0.00046776433,0.0005075613,0.00049508765],"category_scores_gemma":[0.0020632795,0.00023681039,0.00044706947,0.0005987119,0.0003387701,0.00086047826,0.0006128381,0.00097206223,0.00008118652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006436178,0.00006365552,0.0029553783,0.00001619087,0.000044301065,0.000026619438,0.000019271429,0.9700665,0.004157055,0.0010603251,0.00021374934,0.021312574],"study_design_scores_gemma":[0.0000012933776,0.000005011934,0.0002421813,5.601481e-7,0.0000011970369,8.1034744e-7,9.820674e-7,0.99886477,0.0006100539,0.0002442624,0.000027475668,0.0000014501991],"about_ca_topic_score_codex":0.009630833,"about_ca_topic_score_gemma":0.0056273695,"teacher_disagreement_score":0.009630833,"about_ca_system_score_codex":0.0006573986,"about_ca_system_score_gemma":0.00037634646,"threshold_uncertainty_score":0.019149542},"labels":[],"label_agreement":null},{"id":"W3014107227","doi":"","title":"Machine Learning for Streamflow Prediction: Current Status and Future Prospects","year":2019,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Streamflow; Current (fluid); Computer science; Machine learning; Environmental science; Artificial intelligence; Geography; Engineering; Cartography; Drainage basin","score_opus":0.011848441998578645,"score_gpt":0.23073832915245254,"score_spread":0.2188898871538739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014107227","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021211453,0.83473545,0.091752045,0.03447869,0.002245472,0.00006550044,0.000382015,0.0007164161,0.014413046],"genre_scores_gemma":[0.29511178,0.57870525,0.10024946,0.004328384,0.007612771,0.00015666832,0.0012406085,0.0001231813,0.012471882],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991424,0.00032815928,0.00004932598,0.00017073864,0.00023361009,0.000075845346],"domain_scores_gemma":[0.9931758,0.0050318376,0.00023675803,0.00020276806,0.0011327703,0.00022004617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058405697,0.0006767062,0.0013125094,0.00089644635,0.00026526267,0.0025772206,0.0012551347,0.0015997833,0.004844674],"category_scores_gemma":[0.0053533236,0.00020734269,0.00060442643,0.0020541414,0.0012143286,0.0038580273,0.00093380304,0.0020261065,0.0015907275],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028934932,0.00027973432,0.0039466233,0.0010907616,0.000111883324,0.000020739408,0.00004819638,0.008565014,0.0009842714,0.0087863,0.015441334,0.96043587],"study_design_scores_gemma":[0.00024853632,0.0016342741,0.015918339,0.0048924163,0.00046359733,0.00024065361,0.00071732554,0.44320637,0.008323761,0.15207137,0.37205055,0.000232701],"about_ca_topic_score_codex":0.0029740555,"about_ca_topic_score_gemma":0.0023712947,"teacher_disagreement_score":0.0058405697,"about_ca_system_score_codex":0.0007475526,"about_ca_system_score_gemma":0.0011063425,"threshold_uncertainty_score":0.03088826},"labels":[],"label_agreement":null},{"id":"W3017246359","doi":"10.2166/hydro.2020.095","title":"Deep learning convolutional neural network in rainfall–runoff modelling","year":2020,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":247,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Convolutional neural network; Surface runoff; Artificial intelligence; Evapotranspiration; Deep learning; Time series; Series (stratigraphy); Machine learning; Water resources; Artificial neural network; Data mining; Geology","score_opus":0.02431721850055275,"score_gpt":0.21427057863621574,"score_spread":0.189953360135663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017246359","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3252567,0.0020954078,0.6622262,0.0007585772,0.000116288924,0.000054232714,0.00037306958,0.0011773666,0.007942179],"genre_scores_gemma":[0.9772399,0.0002987534,0.020194015,0.00004395746,0.000014380701,0.000025586885,0.00012206798,0.00001657205,0.0020447236],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990106,0.000025172565,0.000006357984,0.000023590179,0.00002450096,0.00001924561],"domain_scores_gemma":[0.99981886,0.00008874103,0.000024621306,0.000010346731,0.00004925118,0.000008148846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036912557,0.0004302836,0.00032722938,0.00031526704,0.00016485578,0.00040625577,0.0006735351,0.00079534063,0.0009913883],"category_scores_gemma":[0.00072201056,0.00024591095,0.0003449247,0.0004588954,0.00027035104,0.0005762041,0.00036842978,0.0006274448,0.00015977003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001224533,0.000010813043,0.00037252097,0.000011279345,0.000008512415,0.000016187267,0.0000044250787,0.9914157,0.0007587663,0.00055146863,0.00009203128,0.0067459503],"study_design_scores_gemma":[3.4073742e-7,0.0000017659203,0.00004109549,6.730246e-7,8.058015e-7,8.555148e-7,3.8449295e-7,0.999673,0.00013625025,0.00011626794,0.000027953658,5.430173e-7],"about_ca_topic_score_codex":0.024841458,"about_ca_topic_score_gemma":0.013811806,"teacher_disagreement_score":0.024841458,"about_ca_system_score_codex":0.0009352098,"about_ca_system_score_gemma":0.00066672836,"threshold_uncertainty_score":0.049393713},"labels":[],"label_agreement":null},{"id":"W3019703102","doi":"10.1016/j.envsoft.2020.104718","title":"A stochastic wavelet-based data-driven framework for forecasting uncertain multiscale hydrological and water resources processes","year":2020,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Wavelet; Variable (mathematics); Probabilistic logic; Selection (genetic algorithm); Interval (graph theory); Decomposition; Streamflow; Econometrics; Computer science; Water resources; Mathematics; Statistics; Mathematical optimization; Artificial intelligence; Geography","score_opus":0.08482296300816525,"score_gpt":0.25163900807311707,"score_spread":0.16681604506495182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019703102","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006797433,0.000095530624,0.9924051,0.0000751452,0.000040784882,0.000008181245,0.00007434215,0.00012524241,0.0003782733],"genre_scores_gemma":[0.65694386,0.0006849494,0.33831745,0.00011338959,0.0001720911,0.00014508395,0.0007364985,0.00014731065,0.0027394413],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975806,0.00006298158,0.000020272028,0.00004795459,0.00008539305,0.00002532001],"domain_scores_gemma":[0.9994584,0.00026171037,0.000053732445,0.000040533778,0.00014687581,0.0000387134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026394,0.00041996085,0.0006666616,0.00044354686,0.00023373011,0.0008648883,0.0011397967,0.0007243179,0.0011941418],"category_scores_gemma":[0.0025514634,0.00038772426,0.0006442048,0.000855189,0.0003807182,0.00090206275,0.0007307422,0.0011081917,0.00027431446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035020686,0.000025762101,0.0002497445,0.000030631905,0.000030961437,0.00003632044,0.00001529729,0.9568626,0.0017670062,0.017331291,0.00063542224,0.022979882],"study_design_scores_gemma":[0.0000011566553,0.0000021753926,0.000015597674,5.989386e-7,0.0000012953171,0.0000012840007,4.606859e-7,0.99895835,0.000046205692,0.000899577,0.00007240173,9.491658e-7],"about_ca_topic_score_codex":0.0069798958,"about_ca_topic_score_gemma":0.0043713525,"teacher_disagreement_score":0.0069798958,"about_ca_system_score_codex":0.00041767376,"about_ca_system_score_gemma":0.0010482485,"threshold_uncertainty_score":0.013878524},"labels":[],"label_agreement":null},{"id":"W3020880410","doi":"10.5281/zenodo.10964841","title":"ExArch: Climate analytics on distributed exascale data archives","year":2014,"lang":"en","type":"article","venue":"AGUFM","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Environment Research Council; Sight Research UK; UK Research and Innovation","keywords":"Exascale computing; Analytics; Computer science; Database; Data science; Operating system; Supercomputer","score_opus":0.06660684717317593,"score_gpt":0.27021254548936946,"score_spread":0.20360569831619352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020880410","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14269947,0.0008538441,0.30762568,0.004013814,0.0011052235,0.0010398326,0.042211507,0.44407806,0.056372546],"genre_scores_gemma":[0.5820346,0.0006549993,0.29931384,0.00091842056,0.00047153718,0.00080149923,0.07191723,0.0154220965,0.028465712],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992435,0.000106299325,0.000035715053,0.00018042816,0.00034381912,0.000090335],"domain_scores_gemma":[0.99831307,0.00037154308,0.00006174452,0.0007528446,0.00027386675,0.00022700452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017648923,0.0014504084,0.0007052372,0.0012850349,0.0012598184,0.003074389,0.0030849015,0.0007458907,0.012286242],"category_scores_gemma":[0.003825841,0.00045310642,0.00072830264,0.0018233644,0.00086621,0.006140198,0.0026072343,0.0019936382,0.003613801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039212937,0.0015339482,0.019786805,0.0007293362,0.00095606025,0.0009323824,0.001962893,0.13064016,0.06838706,0.037847,0.4027576,0.3305455],"study_design_scores_gemma":[0.0007113354,0.0002335301,0.00560922,0.00006366136,0.00008395259,0.00015667007,0.0007424669,0.8137415,0.046591982,0.0375892,0.09430929,0.00016722018],"about_ca_topic_score_codex":0.015252689,"about_ca_topic_score_gemma":0.015327649,"teacher_disagreement_score":0.015252689,"about_ca_system_score_codex":0.0011720429,"about_ca_system_score_gemma":0.001362359,"threshold_uncertainty_score":0.041101575},"labels":[],"label_agreement":null},{"id":"W3020943814","doi":"10.1016/j.advwatres.2020.103595","title":"Multiscale groundwater level forecasting: Coupling new machine learning approaches with wavelet transforms","year":2020,"lang":"en","type":"article","venue":"Advances in Water Resources","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":190,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Groundwater; Artificial neural network; Computer science; Environmental science; Irrigation scheduling; Gradient boosting; Water resource management; Artificial intelligence; Hydrology (agriculture); Random forest; Soil science; Geology; Geotechnical engineering","score_opus":0.07660228442083965,"score_gpt":0.223181709638159,"score_spread":0.14657942521731937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020943814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0151863005,0.00041672649,0.9830828,0.00017348079,0.00006604322,0.000009499469,0.00003864369,0.00015344897,0.00087305857],"genre_scores_gemma":[0.5680822,0.0013879018,0.42821938,0.00011132355,0.00030302652,0.00005976825,0.00017654416,0.00010514662,0.0015546832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973565,0.000070807466,0.00002479243,0.00006125802,0.00008913838,0.000018312654],"domain_scores_gemma":[0.9989827,0.0006412042,0.000098524644,0.00012456464,0.00012661776,0.000026444792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095585897,0.00045083917,0.0007253368,0.0008142592,0.00015035206,0.00085830624,0.00061210553,0.00064097,0.0010825038],"category_scores_gemma":[0.004670668,0.00031389433,0.00050175027,0.0013494169,0.00035802458,0.0017013865,0.00081355305,0.0011143623,0.0002645522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103591665,0.00010858612,0.0018124649,0.000115166134,0.00013525003,0.00004566868,0.00006534977,0.50034654,0.010262647,0.025173955,0.0012576124,0.46057314],"study_design_scores_gemma":[0.0000026434802,0.000007343589,0.00020516104,0.0000028272368,0.000007044858,0.0000047304516,0.0000025875415,0.99456185,0.0004263355,0.0045426437,0.00023384295,0.000002973789],"about_ca_topic_score_codex":0.0015635979,"about_ca_topic_score_gemma":0.0016624911,"teacher_disagreement_score":0.0015635979,"about_ca_system_score_codex":0.00026285963,"about_ca_system_score_gemma":0.00027095174,"threshold_uncertainty_score":0.0050551295},"labels":[],"label_agreement":null},{"id":"W3033590996","doi":"10.3390/w12061622","title":"Predicting River Flow Using an AI-Based Sequential Adaptive Neuro-Fuzzy Inference System","year":2020,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Environment and Protected Areas; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Environment and Parks","keywords":"Adaptive neuro fuzzy inference system; Computer science; Neuro-fuzzy; Flood myth; Environmental science; Flow (mathematics); Inference system; Hydrology (agriculture); Data mining; Fuzzy logic; Artificial intelligence; Fuzzy control system; Engineering; Mathematics; Geography","score_opus":0.05975357002979701,"score_gpt":0.24956917316490773,"score_spread":0.18981560313511073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033590996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18148744,0.00022879803,0.81209266,0.00021186243,0.0000846129,0.0001202727,0.00016110268,0.0009696085,0.0046436437],"genre_scores_gemma":[0.9210334,0.0000957134,0.077331886,0.000029062414,0.000017285314,0.00006686788,0.00008603981,0.000007585745,0.0013321531],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998332,0.00002484489,0.000016302876,0.00004543597,0.000063822255,0.000016354825],"domain_scores_gemma":[0.99972636,0.00012874498,0.00003779209,0.000012021766,0.00008473835,0.000010366969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040086836,0.0004249723,0.00034796196,0.0003653299,0.00040168682,0.00047457195,0.00055246573,0.00038936437,0.0008826501],"category_scores_gemma":[0.001136103,0.0002159799,0.00031299933,0.0003101353,0.00021348087,0.00041560983,0.00023511497,0.00039946396,0.00012777904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012031785,0.0000953006,0.0027127368,0.00006308784,0.000049944443,0.00010735432,0.000080693346,0.8909533,0.007610798,0.0012111168,0.0004698144,0.09652549],"study_design_scores_gemma":[0.0000032962503,0.000017035816,0.00028425484,0.0000018921302,0.000005690198,0.000007064608,0.0000040071604,0.9988997,0.00045159686,0.00020754189,0.000115183226,0.0000027189724],"about_ca_topic_score_codex":0.035198472,"about_ca_topic_score_gemma":0.03998502,"teacher_disagreement_score":0.035198472,"about_ca_system_score_codex":0.0005237837,"about_ca_system_score_gemma":0.00089393824,"threshold_uncertainty_score":0.06998718},"labels":[],"label_agreement":null},{"id":"W3034823224","doi":"10.23977/acss.2020.040105","title":"Classification of Groundwater Quality using Artificial Neural Networks in Safwan and Al-Zubayr in Basra","year":2020,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Groundwater; Artificial neural network; Groundwater resources; Water resource management; Environmental science; Environmental resource management; Hydrology (agriculture); Computer science; Artificial intelligence; Engineering; Aquifer; Geotechnical engineering","score_opus":0.08178138337406413,"score_gpt":0.30939089732271075,"score_spread":0.22760951394864662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034823224","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99844956,0.000057089608,0.00085834775,0.000051188166,0.000008851286,0.000009189182,0.00011163179,0.000016272817,0.00043791413],"genre_scores_gemma":[0.9988612,0.000041260817,0.00069211813,0.00000791307,0.0000030623323,0.000007508695,0.00019911837,9.149504e-7,0.00018677844],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996929,0.000082623475,0.000029767354,0.00005854827,0.00006908258,0.000067041925],"domain_scores_gemma":[0.9996195,0.00010496741,0.00006917963,0.000013476251,0.00016388665,0.000028974788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036153887,0.0003595616,0.00027288627,0.0009683389,0.00042379103,0.00055748515,0.00037430823,0.00051181007,0.00040544852],"category_scores_gemma":[0.0006880629,0.00016295239,0.00028199106,0.0012588731,0.00027435788,0.00037279312,0.00026441552,0.00024515856,0.00010036129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007647013,0.0006642927,0.7771427,0.00021072688,0.0002620021,0.0013489157,0.0009353657,0.09641572,0.013644365,0.0006802912,0.0014879487,0.10644303],"study_design_scores_gemma":[0.000060827442,0.00027245205,0.5420812,0.000048070855,0.000066394045,0.0001504387,0.0027998653,0.44885343,0.0040862723,0.0005135604,0.001020045,0.00004743118],"about_ca_topic_score_codex":0.049463715,"about_ca_topic_score_gemma":0.07432345,"teacher_disagreement_score":0.049463715,"about_ca_system_score_codex":0.0012201163,"about_ca_system_score_gemma":0.0006534552,"threshold_uncertainty_score":0.0983516},"labels":[],"label_agreement":null},{"id":"W3039456968","doi":"10.1007/978-3-030-52243-8_7","title":"A New Approach to Estimate the Discharge Coefficient in Sharp-Crested Rectangular Side Orifices Using Gene Expression Programming","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Université Laval","funders":"","keywords":"Gene expression programming; Expression (computer science); Discharge coefficient; Body orifice; Computer science; Mathematics; Physics; Biology; Programming language; Artificial intelligence; Anatomy; Thermodynamics","score_opus":0.03596587286635721,"score_gpt":0.29977768522210935,"score_spread":0.26381181235575213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039456968","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004219095,0.00003478993,0.9944284,0.000027338274,0.000014600325,0.000015870266,0.000045744808,0.0003851157,0.0008290645],"genre_scores_gemma":[0.0857328,0.00012917948,0.9074466,0.00009519657,0.000028940403,0.00017529094,0.00024357588,0.00032050317,0.0058278777],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997223,0.00003476815,0.00001247015,0.00010121936,0.000105970495,0.000023196613],"domain_scores_gemma":[0.99965763,0.00018515634,0.000029200035,0.00002650567,0.00008943864,0.000012062363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043107517,0.00069028884,0.00064664654,0.0006884716,0.00037988092,0.0007472332,0.0014850236,0.0006190284,0.0016852234],"category_scores_gemma":[0.00091720995,0.0005447213,0.0008737152,0.00085037,0.0006707492,0.0007845186,0.000613726,0.0014386298,0.00064580893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005138606,0.00012418485,0.003087929,0.00014659383,0.000080178084,0.00011129449,0.00018597394,0.66219366,0.07228474,0.030594954,0.0020851656,0.22905388],"study_design_scores_gemma":[0.000002280489,0.000009880236,0.00023376304,0.000004252282,0.0000073250226,0.000023009423,0.00001191693,0.9911556,0.0049753683,0.0023492712,0.0012178875,0.000009460968],"about_ca_topic_score_codex":0.004983608,"about_ca_topic_score_gemma":0.006454383,"teacher_disagreement_score":0.004983608,"about_ca_system_score_codex":0.00066791923,"about_ca_system_score_gemma":0.0007183446,"threshold_uncertainty_score":0.009909213},"labels":[],"label_agreement":null},{"id":"W3040007109","doi":"10.3390/su12135374","title":"Genetic-Algorithm-Optimized Sequential Model for Water Temperature Prediction","year":2020,"lang":"en","type":"article","venue":"Sustainability","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Water quality; Turbidity; Computer science; Genetic algorithm; Environmental science; Artificial neural network; STREAMS; Quality (philosophy); Machine learning; Data mining; Ecology","score_opus":0.016216789225249603,"score_gpt":0.2398011898229957,"score_spread":0.2235844005977461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040007109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07887199,0.00069704396,0.91353756,0.00032831472,0.00014276637,0.00009112263,0.00027214573,0.0008926613,0.0051663816],"genre_scores_gemma":[0.9257533,0.00028460214,0.06851492,0.00010563704,0.000036490375,0.00024354969,0.00037865667,0.00005608137,0.004626793],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971,0.00008454187,0.000017204216,0.00008367734,0.0000557658,0.000048760732],"domain_scores_gemma":[0.9993724,0.0003877935,0.00006218501,0.000018415683,0.00014113072,0.000018005974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007178789,0.0009224205,0.00097643875,0.0005451813,0.00036425117,0.000654525,0.00088598003,0.0009813509,0.001838709],"category_scores_gemma":[0.001688183,0.00044968072,0.0007906277,0.00075367093,0.0004407888,0.00043832566,0.00048145713,0.0010155966,0.0003150231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019010831,0.000008545285,0.0002156344,0.000009004093,0.000012021502,0.000011585302,0.000006330212,0.9944488,0.00019646753,0.0003674337,0.000101994854,0.004603244],"study_design_scores_gemma":[0.0000027364858,0.0000063602088,0.000042260323,6.855596e-7,0.000001884402,0.0000014058562,6.344848e-7,0.9996902,0.000050945448,0.00015078524,0.000051389692,8.368868e-7],"about_ca_topic_score_codex":0.036216278,"about_ca_topic_score_gemma":0.020491162,"teacher_disagreement_score":0.036216278,"about_ca_system_score_codex":0.0008089943,"about_ca_system_score_gemma":0.001493778,"threshold_uncertainty_score":0.072010994},"labels":[],"label_agreement":null},{"id":"W3041052911","doi":"10.3390/w12071973","title":"Application of Artificial Neural Network and Information Entropy Theory to Assess Rainfall Station Distribution: A Case Study from Colombia","year":2020,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Universidad de La Sabana; Pontificia Universidad Javeriana; Universidad Tecnológica de Bolívar","keywords":"Artificial neural network; Entropy (arrow of time); Computer science; Probabilistic logic; Acronym; Meteorology; Artificial intelligence; Data mining; Environmental science; Geography","score_opus":0.02258828426636466,"score_gpt":0.2439907132812223,"score_spread":0.22140242901485763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041052911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988664,0.000330157,0.005546954,0.00022239504,0.000013561244,0.00007661895,0.0006206085,0.000063986154,0.004461819],"genre_scores_gemma":[0.9969717,0.00010027796,0.0023607567,0.000005882752,0.0000038657518,0.000011016882,0.00016780254,0.0000037982045,0.00037468475],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995956,0.00016518951,0.00003240878,0.00004611011,0.0001086751,0.000052014988],"domain_scores_gemma":[0.9990403,0.00052563584,0.0000891221,0.000045641173,0.00024345709,0.000055856563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055841554,0.00044946364,0.00029889852,0.0020092775,0.00037350156,0.0009450755,0.00047495842,0.0004428973,0.0006193196],"category_scores_gemma":[0.0021858197,0.0001170752,0.0002725779,0.0019472648,0.000356816,0.00045251098,0.00042753769,0.00022507722,0.000046377172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006550923,0.0004096788,0.35176444,0.0008839876,0.0002921661,0.007954109,0.0024067117,0.46665162,0.007314993,0.005689937,0.0024425355,0.15353473],"study_design_scores_gemma":[0.00005670973,0.00023133254,0.29708666,0.0001187824,0.00012813455,0.0005488871,0.0063176136,0.6845297,0.0050021205,0.0017838231,0.004076467,0.00011970957],"about_ca_topic_score_codex":0.1357037,"about_ca_topic_score_gemma":0.15363383,"teacher_disagreement_score":0.1357037,"about_ca_system_score_codex":0.0024686956,"about_ca_system_score_gemma":0.00057235156,"threshold_uncertainty_score":0.2698276},"labels":[],"label_agreement":null},{"id":"W3042922613","doi":"10.5194/egusphere-egu2020-4233","title":"Using a boundary-corrected wavelet transform coupled with machine learning and hybrid deep learning approaches for multi-step water level forecasting in Lakes Michigan and Ontario","year":2020,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo; McGill University","funders":"","keywords":"Artificial intelligence; Discrete wavelet transform; Support vector machine; Wavelet; Convolutional neural network; Computer science; Deep learning; Machine learning; Wavelet transform","score_opus":0.11960188000884134,"score_gpt":0.24156242102130823,"score_spread":0.1219605410124669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042922613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91890717,0.0004917328,0.063704066,0.0015226338,0.000073937015,0.00003452974,0.0021266858,0.0006437321,0.01249549],"genre_scores_gemma":[0.9829146,0.00012633635,0.0128099425,0.00003717879,0.00001261166,0.000013658334,0.0009129355,0.000030858155,0.003141922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99991083,0.000008090765,0.0000048556467,0.000023139999,0.000029373414,0.000023772574],"domain_scores_gemma":[0.99987805,0.000024024155,0.000018125185,0.000010894944,0.000053694806,0.000015275067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016785653,0.00031664423,0.00017335115,0.00028163585,0.00046661668,0.0006223364,0.00058774994,0.00043019955,0.0013585796],"category_scores_gemma":[0.00087103783,0.00015588824,0.00030369408,0.0005696521,0.00022364293,0.00051868847,0.00037806944,0.0003924355,0.00018785062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000329349,0.00009638527,0.10337387,0.00016248682,0.00012461375,0.0006758589,0.0005266994,0.60249114,0.024262473,0.00443924,0.010796204,0.25272164],"study_design_scores_gemma":[0.000009517756,0.0000102838285,0.02483541,0.000009607603,0.00001321431,0.000014209885,0.00013749773,0.9699229,0.002528717,0.0005794928,0.0019235795,0.000015588106],"about_ca_topic_score_codex":0.72561663,"about_ca_topic_score_gemma":0.80193734,"teacher_disagreement_score":0.72561663,"about_ca_system_score_codex":0.0028190555,"about_ca_system_score_gemma":0.0028995313,"threshold_uncertainty_score":0.5519985},"labels":[],"label_agreement":null},{"id":"W3046048985","doi":"10.3390/ijgi9080479","title":"Daily Water Level Prediction of Zrebar Lake (Iran): A Comparison between M5P, Random Forest, Random Tree and Reduced Error Pruning Trees Algorithms","year":2020,"lang":"en","type":"article","venue":"ISPRS International Journal of Geo-Information","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Forests","funders":"","keywords":"Mean squared error; Random forest; Pruning; Statistics; Standard deviation; Tree (set theory); Decision tree; Algorithm; Computer science; Correlation coefficient; Mathematics; Machine learning","score_opus":0.04662398621044315,"score_gpt":0.2698469896894758,"score_spread":0.22322300347903265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046048985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8955253,0.0021312619,0.09385766,0.000880763,0.0001862734,0.00008887154,0.0019404934,0.0026391537,0.0027503131],"genre_scores_gemma":[0.95271283,0.0004371629,0.042772926,0.000100605976,0.00004296359,0.00006576229,0.003062633,0.000082528604,0.00072252227],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997031,0.00007272833,0.000024395677,0.00010002236,0.000044574903,0.000055162523],"domain_scores_gemma":[0.9993273,0.0003332946,0.00006833047,0.000031941265,0.0001931868,0.000045855442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012544128,0.0012059704,0.0009012222,0.001019649,0.00040341308,0.00062164187,0.001154336,0.00079489214,0.0006321426],"category_scores_gemma":[0.0022862593,0.00027578874,0.0014379703,0.0008600172,0.00018096785,0.0008688134,0.00038975078,0.0008164552,0.00021046022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044344785,0.00020424227,0.03648705,0.00018635669,0.00024098712,0.00013738604,0.00009958578,0.8390829,0.0019693319,0.0004887845,0.003567838,0.11709212],"study_design_scores_gemma":[0.000020904467,0.000046846406,0.0045375205,0.000011038995,0.000034407345,0.000014253867,0.000031160995,0.99435437,0.0004939617,0.00021713224,0.00022817588,0.000010300362],"about_ca_topic_score_codex":0.044484474,"about_ca_topic_score_gemma":0.027394505,"teacher_disagreement_score":0.044484474,"about_ca_system_score_codex":0.0007370376,"about_ca_system_score_gemma":0.0013116497,"threshold_uncertainty_score":0.08845109},"labels":[],"label_agreement":null},{"id":"W3046393533","doi":"10.18280/isi.250311","title":"Deep Learning-Based Forecast and Warning of Floods in Klang River, Malaysia","year":2020,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Teknologi Malaysia","keywords":"Warning system; Geography; Meteorology; Cartography; Computer science; Telecommunications","score_opus":0.01383786558641682,"score_gpt":0.20793275868648223,"score_spread":0.19409489310006542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046393533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803432,0.00016489397,0.01649915,0.00034707636,0.000024088875,0.000015283737,0.00051798084,0.00029608596,0.0017922113],"genre_scores_gemma":[0.99683064,0.00005124661,0.0021620407,0.000008917266,0.0000022978945,0.000005153171,0.00018277238,0.0000036967294,0.0007532631],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999441,0.000014210325,0.000005901022,0.000013763903,0.000009504871,0.00001241678],"domain_scores_gemma":[0.99980336,0.000073267736,0.00003283646,0.000007626013,0.000061467574,0.000021349331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029143007,0.0002990168,0.00016204751,0.0003553849,0.00011638053,0.0003036822,0.00021333745,0.00027422607,0.0006337916],"category_scores_gemma":[0.0007357355,0.00012878675,0.00019770236,0.00019111123,0.00012849063,0.0004866709,0.00026140732,0.00038166015,0.000110703826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029352083,0.0000830444,0.04145542,0.000084701685,0.00004760246,0.00017701444,0.000104431754,0.89963335,0.0049155583,0.00090881734,0.0015451339,0.05075139],"study_design_scores_gemma":[0.0000042518436,0.00002409649,0.008112883,0.0000074877953,0.0000062608055,0.000007980393,0.000043843338,0.98999256,0.0014320281,0.00022689803,0.00013529863,0.0000064638216],"about_ca_topic_score_codex":0.028731145,"about_ca_topic_score_gemma":0.025557807,"teacher_disagreement_score":0.028731145,"about_ca_system_score_codex":0.0005826162,"about_ca_system_score_gemma":0.00063547585,"threshold_uncertainty_score":0.057127833},"labels":[],"label_agreement":null},{"id":"W3047702563","doi":"10.1007/s11269-020-02644-y","title":"A Comparative Study of Linear Stochastic with Nonlinear Daily River Discharge Forecast Models","year":2020,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Université Laval","funders":"","keywords":"Discharge; Flood myth; Nonlinear system; Time series; Environmental science; Meteorology; Statistics; Series (stratigraphy); Computer science; Mathematics; Geology; Drainage basin; Geography","score_opus":0.04212654556029443,"score_gpt":0.23882159028264954,"score_spread":0.1966950447223551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047702563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.937494,0.001309307,0.04701964,0.0007929996,0.00011116601,0.00004847058,0.0006098559,0.00043062904,0.012183963],"genre_scores_gemma":[0.99401546,0.00033324613,0.0037751764,0.000027701222,0.00002716059,0.000010897934,0.0002832337,0.000029664989,0.0014975847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993729,0.0003294923,0.000046635334,0.000088520515,0.00010964883,0.000052934847],"domain_scores_gemma":[0.99001384,0.008126965,0.00033482997,0.00026584545,0.00112407,0.00013456187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030423312,0.00043421288,0.0006070078,0.000747428,0.00033979156,0.00127219,0.00073873013,0.0005673371,0.0020133092],"category_scores_gemma":[0.008770109,0.00025703854,0.0005190876,0.00083238236,0.00035799938,0.0015497007,0.00043863937,0.00050480536,0.00022461588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048484083,0.00014425634,0.009656434,0.00012284852,0.00011503762,0.000052919295,0.000070348855,0.96258634,0.00076481426,0.0040930593,0.0005642088,0.021344945],"study_design_scores_gemma":[0.000008146095,0.00007403751,0.0014412575,0.000004266448,0.000017754011,0.000004550845,0.000023351946,0.99760157,0.00020235412,0.00044403956,0.00017148531,0.000007104568],"about_ca_topic_score_codex":0.04192272,"about_ca_topic_score_gemma":0.02265187,"teacher_disagreement_score":0.04192272,"about_ca_system_score_codex":0.0013233608,"about_ca_system_score_gemma":0.00094042846,"threshold_uncertainty_score":0.083357394},"labels":[],"label_agreement":null},{"id":"W3047730769","doi":"","title":"Primary weathering rates, water transit times and concentration-discharge relations: A theoretical analysis for the critical zone","year":2017,"lang":"en","type":"article","venue":"Lancaster EPrints (Lancaster University)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Svenska Forskningsrådet Formas; Kempe Foundation","keywords":"Weathering; Environmental science; Primary (astronomy); Transit (satellite); Geology; Geochemistry; Public transport; Waste management; Engineering","score_opus":0.016795337446983024,"score_gpt":0.23266584835910362,"score_spread":0.2158705109121206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047730769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5983592,0.0016846225,0.38504115,0.0011555187,0.000038113467,0.000087743225,0.00024261049,0.00030142223,0.013089528],"genre_scores_gemma":[0.99051476,0.0007035435,0.007030931,0.0000647803,0.0000347006,0.000046344812,0.0000600191,0.00004574957,0.0014990831],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999892,0.000014331554,0.0000036414872,0.000034794586,0.000020448771,0.000034662076],"domain_scores_gemma":[0.9993973,0.00029619518,0.00013196471,0.00003026583,0.00006922621,0.000075078875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054971676,0.000559352,0.0005037565,0.0014246005,0.0006627808,0.001016443,0.0011728711,0.0008650338,0.001644953],"category_scores_gemma":[0.0019317404,0.00042721746,0.0012243382,0.00046052245,0.0016506921,0.0017204751,0.001047205,0.00089291885,0.0001520107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008524781,0.00009277455,0.009541318,0.00016693257,0.000059779963,0.0005081786,0.00028657,0.67711365,0.024096366,0.27861747,0.0010669216,0.008364838],"study_design_scores_gemma":[0.0000073119286,0.000017097876,0.0010672201,0.000006271521,0.000014788882,0.000040140927,0.0000262618,0.9716049,0.00087886775,0.025946995,0.0003811561,0.00000917767],"about_ca_topic_score_codex":0.011082911,"about_ca_topic_score_gemma":0.0024567528,"teacher_disagreement_score":0.011082911,"about_ca_system_score_codex":0.0020943396,"about_ca_system_score_gemma":0.0009595553,"threshold_uncertainty_score":0.02203679},"labels":[],"label_agreement":null},{"id":"W3048739124","doi":"10.1007/978-3-319-48657-4_325-2","title":"Time Series Modeling","year":2018,"lang":"en","type":"book-chapter","venue":"Encyclopedia of earth sciences series/Encyclopedia of earth sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Series (stratigraphy); Computer science; Geology","score_opus":0.02256915996978862,"score_gpt":0.2341487972329997,"score_spread":0.21157963726321108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048739124","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030437172,0.00266181,0.9078703,0.0013368971,0.0010248049,0.00015780532,0.009966145,0.009833433,0.064105146],"genre_scores_gemma":[0.16823289,0.0099531105,0.5406089,0.0012451612,0.0015289927,0.0007904689,0.05033913,0.0035182969,0.22378312],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995315,0.00010411904,0.00004162635,0.00013543456,0.00016608577,0.000021309825],"domain_scores_gemma":[0.99916625,0.000325914,0.000051529478,0.00023027317,0.00020225425,0.000023716799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000774943,0.0011094343,0.00077470153,0.0007952717,0.00031585761,0.0017720482,0.0011173163,0.00078008237,0.03230239],"category_scores_gemma":[0.0033224453,0.00035001975,0.001092254,0.0014596295,0.00023424679,0.0016458029,0.00071146997,0.0010292076,0.020067548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056126853,0.00007914815,0.0016033953,0.00035361835,0.00020129849,0.00016981321,0.0000868544,0.21980767,0.0018320607,0.11768636,0.15368435,0.5044392],"study_design_scores_gemma":[0.000019433453,0.000026003545,0.0007602571,0.00008906372,0.000063390115,0.000116922645,0.000034437668,0.7037087,0.0017074925,0.09939963,0.19404648,0.0000281901],"about_ca_topic_score_codex":0.0051062047,"about_ca_topic_score_gemma":0.0028353687,"teacher_disagreement_score":0.03230239,"about_ca_system_score_codex":0.00048405532,"about_ca_system_score_gemma":0.0007711837,"threshold_uncertainty_score":0.10806221},"labels":[],"label_agreement":null},{"id":"W3083174013","doi":"10.1016/j.jhydrol.2020.125509","title":"Using ensembles of adaptive neuro-fuzzy inference system and optimization algorithms to predict reference evapotranspiration in subtropical climatic zones","year":2020,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":87,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University","funders":"","keywords":"Adaptive neuro fuzzy inference system; Particle swarm optimization; Computer science; Evapotranspiration; Machine learning; Artificial intelligence; Artificial neural network; Algorithm; Fuzzy logic; Fuzzy control system; Ecology","score_opus":0.07299319256522115,"score_gpt":0.28007431080834394,"score_spread":0.2070811182431228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083174013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8214523,0.0005985221,0.17463423,0.0001986761,0.00020549264,0.00004383318,0.00016028527,0.0003399549,0.0023667233],"genre_scores_gemma":[0.9850227,0.000060831844,0.014414911,0.000020646426,0.000015580059,0.000016952881,0.0000761239,0.000008763013,0.00036342148],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997453,0.000079220634,0.00003171106,0.00006303503,0.000045569963,0.000035172554],"domain_scores_gemma":[0.99899906,0.0005075927,0.00008010242,0.00006106687,0.00030853166,0.00004363845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013998268,0.00048735304,0.00067676423,0.000668768,0.00046449347,0.0007259121,0.0006780605,0.0007195488,0.00047275977],"category_scores_gemma":[0.003043079,0.00035768072,0.00057792815,0.0005699954,0.00022221224,0.000887019,0.0004420857,0.0006660247,0.00009676293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017839883,0.00011982706,0.0053835236,0.00002546168,0.00015216462,0.000037574093,0.000038906714,0.9467376,0.001262856,0.00035288054,0.00037208642,0.045338802],"study_design_scores_gemma":[0.0000028786549,0.00000866805,0.00061903795,0.0000013528784,0.000009034163,0.0000014598139,0.0000047438643,0.9990325,0.00019579905,0.00010038821,0.000021580938,0.0000026177129],"about_ca_topic_score_codex":0.024396036,"about_ca_topic_score_gemma":0.026986292,"teacher_disagreement_score":0.024396036,"about_ca_system_score_codex":0.00070825056,"about_ca_system_score_gemma":0.0006584034,"threshold_uncertainty_score":0.048508048},"labels":[],"label_agreement":null},{"id":"W3088163218","doi":"10.9734/jerr/2020/v17i117179","title":"Evapotranspiration Estimation Using Artificial Neural Network over South-Western Nigeria","year":2020,"lang":"en","type":"article","venue":"Journal of Engineering Research and Reports","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial neural network; Evapotranspiration; Mean squared error; Multilayer perceptron; Correlation coefficient; Radial basis function; Statistics; Perceptron; Mathematics; Wind speed; Environmental science; Meteorology; Geography; Artificial intelligence; Computer science; Ecology","score_opus":0.08626479507846449,"score_gpt":0.3176778152473189,"score_spread":0.23141302016885443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088163218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917964,0.0004708431,0.0060622,0.00012443375,0.000024988634,0.000014950552,0.00029957335,0.000059470298,0.0011471538],"genre_scores_gemma":[0.99592483,0.00023119201,0.0030308722,0.000009118133,0.0000045443576,0.000007935574,0.00037972536,0.0000031383363,0.00040877535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999912,0.000019370389,0.000013829484,0.000022070135,0.000018236546,0.0000144207925],"domain_scores_gemma":[0.9998379,0.000060453473,0.000028138746,0.0000079372085,0.000058497986,0.000007103876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028520776,0.00040717624,0.0003183675,0.0005266781,0.00020355349,0.00041037548,0.00021837381,0.0003469973,0.0002805898],"category_scores_gemma":[0.0006149093,0.0001666755,0.00024489925,0.0005794479,0.00010010027,0.00038955687,0.00017739872,0.00022783052,0.00008276002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004595489,0.00024941246,0.16302386,0.00033880147,0.00017041428,0.0011063943,0.00027352554,0.72786486,0.014073257,0.00051994214,0.0015012162,0.09041882],"study_design_scores_gemma":[0.000014820457,0.0000505073,0.053690616,0.0000433742,0.000030414185,0.00007588967,0.00023111614,0.94176596,0.0032938872,0.0002524491,0.00053175294,0.000019130961],"about_ca_topic_score_codex":0.024476951,"about_ca_topic_score_gemma":0.0253902,"teacher_disagreement_score":0.024476951,"about_ca_system_score_codex":0.00041098116,"about_ca_system_score_gemma":0.00037170583,"threshold_uncertainty_score":0.04866892},"labels":[],"label_agreement":null},{"id":"W3088901673","doi":"10.3390/w12102654","title":"Machine Learning-Based Water Level Prediction in Lake Erie","year":2020,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Queen's University","funders":"","keywords":"Mean squared error; Random forest; Multilayer perceptron; Decision tree; Linear regression; Machine learning; Water resources; Statistics; Water level; Perceptron; Computer science; Regression; Mean squared prediction error; Regression analysis; Artificial neural network; Environmental science; Artificial intelligence; Mathematics; Cartography; Ecology; Geography","score_opus":0.035100023305698475,"score_gpt":0.20719930972026346,"score_spread":0.17209928641456498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088901673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9901035,0.00015140137,0.007661385,0.00019623703,0.000008897054,0.000010820958,0.00041412454,0.00014964734,0.0013040878],"genre_scores_gemma":[0.9951544,0.000095510746,0.0036807032,0.000016515822,0.0000032591688,0.000009450273,0.00047322258,0.000007990735,0.0005591676],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984634,0.00003077736,0.000013162855,0.00004070713,0.000033220393,0.00003575617],"domain_scores_gemma":[0.9998325,0.000055863336,0.000031893567,0.000009277442,0.000060502927,0.000009804203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037098024,0.00026948148,0.00031966314,0.0005063065,0.000218343,0.00054014905,0.00030904115,0.00043354573,0.00040299702],"category_scores_gemma":[0.000959981,0.00014089988,0.0004068505,0.0008240525,0.00015749031,0.0005827939,0.00042007858,0.00032018102,0.0001297759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024783527,0.00013171902,0.16241586,0.00011694748,0.00012622241,0.0004549071,0.00023994713,0.76847595,0.0069127413,0.0008975721,0.0016381241,0.058342226],"study_design_scores_gemma":[0.000008818466,0.00002558316,0.03073698,0.00000968798,0.000016798434,0.0000122474785,0.00010270573,0.9671629,0.0012531035,0.0001928559,0.0004645727,0.000013709568],"about_ca_topic_score_codex":0.09613248,"about_ca_topic_score_gemma":0.10635609,"teacher_disagreement_score":0.90386754,"about_ca_system_score_codex":0.00096664426,"about_ca_system_score_gemma":0.00084095343,"threshold_uncertainty_score":0.1911459},"labels":[],"label_agreement":null},{"id":"W3092278000","doi":"10.5194/hess-25-2543-2021","title":"Resampling and ensemble techniques for improving ANN-based high-flow forecast accuracy","year":2021,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Resampling; Boosting (machine learning); Computer science; Random forest; Oversampling; Undersampling; AdaBoost; Artificial neural network; Ensemble learning; Machine learning; Regression; Data mining; Artificial intelligence; Jackknife resampling; Statistics; Mathematics; Support vector machine; Estimator","score_opus":0.026448957655581154,"score_gpt":0.2512165177998116,"score_spread":0.22476756014423044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092278000","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37845406,0.00092456513,0.6157773,0.00028584525,0.00016726302,0.00008757227,0.00020481969,0.0012697093,0.0028288683],"genre_scores_gemma":[0.90847224,0.00017359448,0.09036159,0.00006197285,0.00005313442,0.00004396772,0.0002778925,0.000042386782,0.0005130819],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994168,0.00022166346,0.000039389797,0.00008768661,0.00017951915,0.00005488104],"domain_scores_gemma":[0.9977646,0.001030648,0.00015970175,0.00026483863,0.00072466646,0.000055451812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027130973,0.0006902539,0.00073990994,0.00084493624,0.00036309127,0.0005044095,0.000563883,0.00043019545,0.0005769691],"category_scores_gemma":[0.00524309,0.00022134463,0.0006146148,0.00050292077,0.00020718714,0.0008244798,0.00054346526,0.000705045,0.00020551146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020995708,0.00012610582,0.011486353,0.000047346315,0.00018030588,0.000053371765,0.000079368234,0.7931528,0.0058888164,0.0009532762,0.0012130914,0.18660913],"study_design_scores_gemma":[0.0000043966656,0.00003734903,0.0016647509,0.000005191042,0.000014272474,0.000006599245,0.000008829788,0.9962298,0.0014942162,0.00031390073,0.00021542727,0.0000052449745],"about_ca_topic_score_codex":0.009720495,"about_ca_topic_score_gemma":0.012288625,"teacher_disagreement_score":0.009720495,"about_ca_system_score_codex":0.0005295312,"about_ca_system_score_gemma":0.0005832651,"threshold_uncertainty_score":0.019327879},"labels":[],"label_agreement":null},{"id":"W3092762910","doi":"10.5194/hess-25-2045-2021","title":"Rainfall–runoff prediction at multiple timescales with a single Long Short-Term Memory network","year":2021,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":253,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Global Water Futures; Horizon 2020 Framework Programme; Janssen Pharmaceuticals; Canada First Research Excellence Fund; Österreichische Forschungsförderungsgesellschaft; European Commission; Bundesministerium für Bildung, Wissenschaft und Forschung; Google; Compute Canada; Nvidia","keywords":"Benchmark (surveying); Process (computing); Temporal resolution; Flood myth; Deep learning; Reservoir computing; Long short term memory; Memory model","score_opus":0.0189434626163235,"score_gpt":0.20226832864859498,"score_spread":0.1833248660322715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092762910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6929374,0.0012658631,0.29724967,0.0013310062,0.00023832388,0.000039144757,0.0006924501,0.0013553726,0.004890837],"genre_scores_gemma":[0.97796977,0.00013492133,0.020167442,0.000078996825,0.00002876879,0.00002171218,0.00026683486,0.000011812409,0.0013197353],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998733,0.000020840107,0.000008037481,0.000052722982,0.000021246562,0.00002390506],"domain_scores_gemma":[0.9996643,0.00014521077,0.00004522146,0.00003048393,0.000091527756,0.000023363815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046417653,0.0005697248,0.0003539776,0.00039956623,0.00024955542,0.0004965383,0.00066352845,0.00046750891,0.0012538299],"category_scores_gemma":[0.001177311,0.00022971665,0.00033209161,0.00055286085,0.00020577517,0.001236757,0.0004402387,0.00095629896,0.0002016207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015749146,0.00009505522,0.004450486,0.000030775267,0.00007949268,0.000059518537,0.000028649069,0.902583,0.00310121,0.001248893,0.0015745662,0.086590886],"study_design_scores_gemma":[0.000002882793,0.0000069377816,0.00023253601,0.0000011233956,0.0000039711094,0.0000015813677,0.0000024265876,0.99893934,0.00030163824,0.00044010094,0.00006622626,0.0000012210612],"about_ca_topic_score_codex":0.018024215,"about_ca_topic_score_gemma":0.026795886,"teacher_disagreement_score":0.018024215,"about_ca_system_score_codex":0.0007323735,"about_ca_system_score_gemma":0.0009111945,"threshold_uncertainty_score":0.035838604},"labels":[],"label_agreement":null},{"id":"W3103222423","doi":"10.18280/ijdne.150505","title":"Application of Artificial Neural Network for Forecasting Nitrate Concentration as a Water Quality Parameter: A Case Study of Feitsui Reservoir, Taiwan","year":2020,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Tenaga Nasional; Tenaga Nasional Berhad","keywords":"Water quality; Nitrate; Artificial neural network; Environmental science; Hydropower; Environmental engineering; Hydrology (agriculture); Agriculture; Total dissolved solids; Engineering; Ecology; Machine learning; Computer science; Geotechnical engineering; Biology","score_opus":0.05412330315178153,"score_gpt":0.31072183458504915,"score_spread":0.2565985314332676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103222423","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99599874,0.000065324915,0.0027421182,0.00011563122,0.000007503103,0.000016449507,0.00008387772,0.000037618192,0.00093291025],"genre_scores_gemma":[0.99803704,0.000059333728,0.0013984597,0.000006598725,0.0000024694132,0.000011328836,0.00009731311,0.0000033086405,0.0003842009],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981314,0.000048804006,0.000022590631,0.000041163774,0.000040158444,0.00003405243],"domain_scores_gemma":[0.9995553,0.00022606431,0.000049342456,0.00002900306,0.000114657276,0.000025673684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056662917,0.00055483356,0.00041077202,0.0006635554,0.0004577575,0.00054464943,0.00072491734,0.00082528667,0.00041599394],"category_scores_gemma":[0.0010122962,0.00023751908,0.0005329146,0.0008304964,0.0002771478,0.00046772845,0.00039294385,0.00033556327,0.000052729407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022630132,0.0003779875,0.096129686,0.00013956946,0.00013600933,0.006120073,0.00033899015,0.8620418,0.006966647,0.000598923,0.0007186654,0.026205331],"study_design_scores_gemma":[0.000015241225,0.00010124529,0.013385503,0.0000074962254,0.00003178902,0.000069107184,0.0003135525,0.9838905,0.0017655287,0.00018584779,0.00021876658,0.00001543118],"about_ca_topic_score_codex":0.07506456,"about_ca_topic_score_gemma":0.058711737,"teacher_disagreement_score":0.07506456,"about_ca_system_score_codex":0.0010695889,"about_ca_system_score_gemma":0.00086516247,"threshold_uncertainty_score":0.14925528},"labels":[],"label_agreement":null},{"id":"W3123413142","doi":"10.18280/ria.340608","title":"Application of Artificial Neural Network and Genetic Algorithm Based Artificial Neural Network Models for River Flow Prediction","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Computer science; Genetic algorithm; Artificial intelligence; Algorithm; Machine learning","score_opus":0.044987160801618,"score_gpt":0.24508930713827906,"score_spread":0.20010214633666107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123413142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23542717,0.004892534,0.7425594,0.0009875809,0.00028667893,0.00015421928,0.0003078263,0.00089552486,0.014489129],"genre_scores_gemma":[0.9298544,0.0016713721,0.06328818,0.00009915763,0.000056578334,0.00012776414,0.00030009536,0.000029166164,0.0045733755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997564,0.00007685585,0.000021287215,0.000045553785,0.000077663375,0.00002219045],"domain_scores_gemma":[0.9995813,0.00025016413,0.00004336191,0.00001425881,0.00010141686,0.000009507713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053316256,0.000589848,0.00046993143,0.00055711064,0.00026586678,0.0008631065,0.00072809204,0.00091442675,0.0007950402],"category_scores_gemma":[0.0015474742,0.0002708102,0.0004861998,0.00087600085,0.00022642424,0.0008380445,0.00036535223,0.0007169679,0.00016327061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000369607,0.000051614243,0.0017054343,0.000057688238,0.000052281957,0.000053719683,0.000026071304,0.96626776,0.0008051151,0.0009561917,0.00031010486,0.02967706],"study_design_scores_gemma":[0.0000019624674,0.000015938302,0.00026156168,0.0000050779668,0.0000054659945,0.000004625407,0.0000043208656,0.99894387,0.00020733978,0.00037519092,0.00017108722,0.0000036704232],"about_ca_topic_score_codex":0.014731229,"about_ca_topic_score_gemma":0.009925068,"teacher_disagreement_score":0.014731229,"about_ca_system_score_codex":0.0004955237,"about_ca_system_score_gemma":0.00061127066,"threshold_uncertainty_score":0.029290974},"labels":[],"label_agreement":null},{"id":"W3125052912","doi":"10.3997/2214-4609.2020603008","title":"Impact of Conductive Metal Particles on Water Saturation Estimations","year":2020,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Schlumberger (Canada)","funders":"","keywords":"Electrical conductor; Saturation (graph theory); Materials science; Metal; Composite material; Metallurgy; Mathematics","score_opus":0.05973168228652851,"score_gpt":0.29315813688922976,"score_spread":0.23342645460270126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125052912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9294667,0.00037862587,0.062323764,0.00021301322,0.00017630961,0.000027481266,0.0003953834,0.0012650543,0.0057536284],"genre_scores_gemma":[0.993359,0.000049906794,0.0061377212,0.000015349793,0.000011920527,0.0000034080847,0.0000968192,0.000016332351,0.00030942046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997181,0.00009077447,0.000019693649,0.00006175694,0.00007455826,0.000035027228],"domain_scores_gemma":[0.9972963,0.0019042754,0.00010576185,0.00014933314,0.00047216562,0.000072109906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068873045,0.00038628432,0.00033011058,0.00060160196,0.0002705862,0.00085356773,0.0004168494,0.0005297221,0.0008949904],"category_scores_gemma":[0.0038034117,0.00016216622,0.00027593682,0.00067020964,0.00018433266,0.00092732045,0.00032366568,0.00039639263,0.00022173117],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016523411,0.00023973093,0.060383927,0.00017504647,0.00013728737,0.0002156635,0.00010837335,0.7461752,0.027761022,0.0009952185,0.0011619315,0.16099425],"study_design_scores_gemma":[0.00001765968,0.00006000058,0.0057266885,0.0000059880567,0.000029190069,0.000013530014,0.000032594508,0.984472,0.009048232,0.0003173952,0.000267475,0.000009213901],"about_ca_topic_score_codex":0.014917024,"about_ca_topic_score_gemma":0.00928249,"teacher_disagreement_score":0.014917024,"about_ca_system_score_codex":0.0003297287,"about_ca_system_score_gemma":0.0003023089,"threshold_uncertainty_score":0.029660404},"labels":[],"label_agreement":null},{"id":"W3129144742","doi":"10.1016/j.envsoft.2021.105159","title":"Deep learning, explained: Fundamentals, explainability, and bridgeability to process-based modelling","year":2021,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Leverage (statistics); Process (computing); Artificial intelligence; Data science; Computer science; Earth system science; Field (mathematics); Management science; Engineering; Ecology; Mathematics","score_opus":0.018973627250787578,"score_gpt":0.2316734991690357,"score_spread":0.21269987191824813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129144742","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012192268,0.0029295047,0.9661197,0.0085426755,0.00012164133,0.000033494718,0.00042719592,0.00038143338,0.009252124],"genre_scores_gemma":[0.7326011,0.0070862677,0.24828875,0.0014602318,0.00055678916,0.00027210783,0.0011288295,0.00030648342,0.008299462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989517,0.00046725216,0.0000665565,0.00022413413,0.00020712873,0.00008330473],"domain_scores_gemma":[0.9961241,0.0028133444,0.00030673356,0.00041904402,0.00023135694,0.00010547808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022297683,0.0009116199,0.00069323403,0.0011691204,0.00047615942,0.0027941759,0.0015695705,0.0014354311,0.004136629],"category_scores_gemma":[0.01070412,0.00051798864,0.0009793176,0.0013390344,0.0038994502,0.0058363215,0.002432988,0.0040247827,0.00048233222],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034035398,0.00003224568,0.0015632069,0.00016138054,0.000055536497,0.000091206355,0.00028079847,0.08042248,0.00037676573,0.8808257,0.002062901,0.034093723],"study_design_scores_gemma":[0.000005294814,0.000008316846,0.0002567846,0.00003777631,0.000006453612,0.000023111583,0.000024366273,0.15825444,0.0001850891,0.83721274,0.0039768866,0.000008749709],"about_ca_topic_score_codex":0.0061398554,"about_ca_topic_score_gemma":0.003830478,"teacher_disagreement_score":0.0061398554,"about_ca_system_score_codex":0.0020937677,"about_ca_system_score_gemma":0.0011731616,"threshold_uncertainty_score":0.015191376},"labels":[],"label_agreement":null},{"id":"W3134693883","doi":"","title":"LSTM-Based Rainfall-Runoff Modeling at Arbitrary Time Scales","year":2020,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Surface runoff; Environmental science; Computer science; Hydrology (agriculture); Meteorology; Geology; Geography; Geotechnical engineering","score_opus":0.02721374148222639,"score_gpt":0.2251649228363935,"score_spread":0.19795118135416712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134693883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13651969,0.00042288078,0.8447601,0.00060449215,0.00027718482,0.000035703302,0.0016398237,0.0051953206,0.010544753],"genre_scores_gemma":[0.89969116,0.00030722588,0.09232505,0.00012935698,0.00012058593,0.000059863047,0.0012627146,0.00024774382,0.0058562215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999255,0.000014268644,0.0000051827747,0.000024624002,0.00001849503,0.000012058197],"domain_scores_gemma":[0.9998522,0.00006497815,0.000013226263,0.00001792817,0.00004256927,0.000009054224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002130752,0.0003638491,0.00032643016,0.00025274156,0.00019934271,0.0005505494,0.00066860707,0.0005512431,0.0024072828],"category_scores_gemma":[0.001025886,0.0002490437,0.00028906303,0.0008115956,0.00018575633,0.0012361147,0.0003134643,0.00074732973,0.0004970043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003441928,0.000021900418,0.00042193956,0.000024869969,0.000018529212,0.000019077725,0.000017681372,0.9586908,0.003973903,0.003432938,0.0017377409,0.031606168],"study_design_scores_gemma":[9.605415e-7,0.0000011481648,0.00005639752,4.885851e-7,0.0000010165726,9.691724e-7,5.992222e-7,0.99892056,0.0002690134,0.00062551897,0.00012229309,0.0000011112337],"about_ca_topic_score_codex":0.013175272,"about_ca_topic_score_gemma":0.010544359,"teacher_disagreement_score":0.013175272,"about_ca_system_score_codex":0.00049342646,"about_ca_system_score_gemma":0.00060721126,"threshold_uncertainty_score":0.026197195},"labels":[],"label_agreement":null},{"id":"W3135011382","doi":"10.5194/egusphere-egu21-14324","title":"Bring the noise: Piecing together a discharge record from an automated salt dilution gauging setup and various other information sources","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Tributary; Dilution; Streamflow; Noise (video); STREAMS; Hydrology (agriculture); Environmental science; Salt lake; Salt water; Salt (chemistry); Water resources; Turbulence; Computer science; Geography; Meteorology; Chemistry; Environmental engineering; Engineering; Geology; Physics; Ecology; Cartography; Artificial intelligence; Biology; Computer network","score_opus":0.010665754795718314,"score_gpt":0.23751313533735977,"score_spread":0.22684738054164144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135011382","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39978936,0.00075993023,0.5433368,0.0027351342,0.0011709387,0.00038631159,0.005819931,0.023262965,0.022738585],"genre_scores_gemma":[0.721254,0.00042435096,0.26455128,0.0004671673,0.00034303791,0.000079832396,0.004529433,0.00097232393,0.0073785568],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994747,0.00007403532,0.00004226016,0.00010529347,0.00024847127,0.000055308512],"domain_scores_gemma":[0.99895084,0.00031794157,0.000105210376,0.00018090763,0.00035792857,0.00008718854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008008967,0.00070590153,0.0004326356,0.0023090632,0.0004737933,0.0017969743,0.0005465074,0.0006519675,0.002644778],"category_scores_gemma":[0.0039252336,0.00025711503,0.00031283437,0.0018850644,0.00030686794,0.001508015,0.0011219211,0.00075097854,0.0012487664],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008132546,0.0003264304,0.08190417,0.00039006505,0.00022682725,0.0018690419,0.0012589472,0.035238836,0.0645898,0.0024181816,0.015713679,0.79525065],"study_design_scores_gemma":[0.00012999367,0.00065997726,0.15453324,0.0002555007,0.0004158707,0.0014259472,0.0019093689,0.66160107,0.09735082,0.012331999,0.06903516,0.00035107232],"about_ca_topic_score_codex":0.0073944204,"about_ca_topic_score_gemma":0.011980296,"teacher_disagreement_score":0.0073944204,"about_ca_system_score_codex":0.00040301066,"about_ca_system_score_gemma":0.0005343533,"threshold_uncertainty_score":0.014702797},"labels":[],"label_agreement":null},{"id":"W3139023302","doi":"10.1016/j.jhydrol.2021.126196","title":"Coupling a hybrid CNN-LSTM deep learning model with a Boundary Corrected Maximal Overlap Discrete Wavelet Transform for multiscale Lake water level forecasting","year":2021,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":215,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Tabriz","keywords":"Coupling (piping); Artificial intelligence; Boundary (topology); Computer science; Pattern recognition (psychology); Wavelet; Wavelet transform; Geology; Mathematics; Materials science; Mathematical analysis","score_opus":0.027010322894283893,"score_gpt":0.23456740264784473,"score_spread":0.20755707975356083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139023302","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12267714,0.0005766167,0.86886287,0.0003943922,0.00035868576,0.00003519738,0.0002529153,0.0017688485,0.005073363],"genre_scores_gemma":[0.92361546,0.00018366039,0.071872585,0.00015996551,0.00006629207,0.00003292234,0.00032653866,0.000069063266,0.0036736373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999188,0.000008586555,0.0000048423944,0.000026618114,0.000022356759,0.000018696986],"domain_scores_gemma":[0.9999018,0.00002645466,0.000008378806,0.0000118385915,0.000038776252,0.000012802719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002424121,0.0004243523,0.00041647063,0.00023112599,0.00018403586,0.00039395923,0.0006737791,0.0005988586,0.0020871975],"category_scores_gemma":[0.0006067982,0.0002545303,0.00038924135,0.00033070814,0.0001388347,0.00072710635,0.00060740433,0.00071798393,0.0005099159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025477877,0.00021998039,0.0019783145,0.00008098077,0.00014274128,0.0001267426,0.000053358763,0.5871414,0.036230132,0.0036397341,0.0049892776,0.36514273],"study_design_scores_gemma":[0.0000019453164,0.0000079683,0.000097831406,0.0000014340471,0.000004926838,0.000003669988,0.0000015820334,0.99861205,0.00083521375,0.00029399185,0.00013760067,0.0000017878488],"about_ca_topic_score_codex":0.009441639,"about_ca_topic_score_gemma":0.013350896,"teacher_disagreement_score":0.009441639,"about_ca_system_score_codex":0.00032317665,"about_ca_system_score_gemma":0.00061836676,"threshold_uncertainty_score":0.018773377},"labels":[],"label_agreement":null},{"id":"W3139034298","doi":"","title":"Application of hydrometeorological indices for hydrologic forecasts within an artificial neural network framework","year":2020,"lang":"en","type":"article","venue":"AGU Fall Meeting Abstracts","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Hydrometeorology; Artificial neural network; Environmental science; Hydrological modelling; Meteorology; Climatology; Computer science; Hydrology (agriculture); Artificial intelligence; Geology; Precipitation; Geography","score_opus":0.04450727962414262,"score_gpt":0.26868429831426993,"score_spread":0.2241770186901273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139034298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17408445,0.0006096485,0.8142715,0.00071721204,0.00019851199,0.00006136304,0.0002463621,0.0003875598,0.009423359],"genre_scores_gemma":[0.92891544,0.00024599527,0.068320535,0.000041105068,0.000103433675,0.00003482389,0.00013692521,0.000027473876,0.0021743204],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982953,0.000054935394,0.000013085122,0.000034993234,0.00005107895,0.000016320706],"domain_scores_gemma":[0.9996543,0.00015338829,0.000040968484,0.000015858905,0.00011849899,0.000016960787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007830675,0.00033941292,0.00031861255,0.00043090814,0.00025586903,0.0008134414,0.00048533158,0.00047993113,0.0008671928],"category_scores_gemma":[0.0019622825,0.00015784889,0.00025424678,0.00050054025,0.0002156852,0.0006810744,0.0003883694,0.00057258666,0.00014023065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036152836,0.00003960643,0.0018553975,0.000018430263,0.00003688129,0.000034267618,0.000017085486,0.94872195,0.0018632155,0.0045692623,0.00036527,0.042442445],"study_design_scores_gemma":[9.599896e-7,0.0000026078953,0.00016762454,9.687302e-7,0.0000021341305,0.0000012117665,0.0000013228048,0.99905914,0.00014031478,0.0005550123,0.0000674597,0.0000012837471],"about_ca_topic_score_codex":0.014869921,"about_ca_topic_score_gemma":0.0117954,"teacher_disagreement_score":0.014869921,"about_ca_system_score_codex":0.00049061066,"about_ca_system_score_gemma":0.0006786641,"threshold_uncertainty_score":0.029566765},"labels":[],"label_agreement":null},{"id":"W3150510645","doi":"","title":"Comparison of Neural Networks to Ormsbee's Method for Rain Generation - applied to Toronto, Ontario","year":2008,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Radial basis function; Perceptron; Computer science; Multilayer perceptron; Function (biology); Backpropagation; Mean squared error; Meteorology; Storm; Algorithm; Artificial intelligence; Statistics; Mathematics; Geography","score_opus":0.07651078228024982,"score_gpt":0.32963964450920347,"score_spread":0.25312886222895364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3150510645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4035012,0.0053038956,0.500051,0.0011489354,0.00054575026,0.0005221853,0.002729329,0.004142898,0.082054794],"genre_scores_gemma":[0.849255,0.0017449218,0.118020065,0.00009316518,0.000051563533,0.00014742526,0.0015495105,0.00036075866,0.028777588],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976176,0.000050011942,0.000013952452,0.000036563182,0.00009657934,0.000041243664],"domain_scores_gemma":[0.9994642,0.00018270088,0.000018937602,0.000026082076,0.00029027107,0.00001781716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006134748,0.0004980161,0.0004231185,0.00069955847,0.000536131,0.0007569156,0.0007053202,0.0003622423,0.004960143],"category_scores_gemma":[0.0023369172,0.00016871998,0.0002843978,0.0014231286,0.00020728259,0.00043612876,0.00034100184,0.0002708771,0.00055858295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000307962,0.000051384355,0.0066220164,0.00020279772,0.00008546294,0.000097922,0.000147696,0.5903733,0.0015321245,0.0060117445,0.0073653045,0.38720235],"study_design_scores_gemma":[0.00001837157,0.000011934092,0.0026304917,0.000012114353,0.000012334487,0.000008349267,0.00004992153,0.9934695,0.00055012596,0.0006338037,0.0025973055,0.000005818542],"about_ca_topic_score_codex":0.76441103,"about_ca_topic_score_gemma":0.7860204,"teacher_disagreement_score":0.23558897,"about_ca_system_score_codex":0.0054605617,"about_ca_system_score_gemma":0.0047150967,"threshold_uncertainty_score":0.47395277},"labels":[],"label_agreement":null},{"id":"W3152509532","doi":"10.3390/su13094627","title":"A C-Vine Copula-Based Quantile Regression Method for Streamflow Forecasting in Xiangxi River Basin, China","year":2021,"lang":"en","type":"article","venue":"Sustainability","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"National Key Research and Development Program of China; Fundamental Research Funds for the Central Universities; Chinese Academy of Sciences","keywords":"Vine copula; Quantile; Streamflow; Copula (linguistics); Quantile regression; Environmental science; Regression; Econometrics; Statistics; Mathematics; Drainage basin; Geography; Cartography","score_opus":0.021051742333313198,"score_gpt":0.30723005785391233,"score_spread":0.28617831552059914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152509532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07069592,0.000617598,0.9259031,0.00019707305,0.0000338756,0.000037210528,0.00022983948,0.00062070566,0.0016646095],"genre_scores_gemma":[0.9207826,0.00058473344,0.075837396,0.00007377937,0.000033357435,0.00008115498,0.00053634983,0.000095424075,0.0019751107],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967694,0.00011970008,0.000019896146,0.000087774286,0.00005748374,0.000038256803],"domain_scores_gemma":[0.99962914,0.00016803703,0.000044177534,0.000022480146,0.00011922612,0.000016792657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010079531,0.0005622925,0.0005936705,0.0006925918,0.00021917064,0.000508709,0.000719058,0.0003992601,0.0011753221],"category_scores_gemma":[0.0022437314,0.00025683866,0.00055375026,0.0008577111,0.00016973398,0.0006013973,0.0003712702,0.0006261533,0.00021693629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051160645,0.000030687796,0.005058535,0.00005374829,0.00008101466,0.00007143535,0.00004842093,0.9022701,0.0015918569,0.0027904673,0.0012004656,0.08675215],"study_design_scores_gemma":[0.0000011735732,0.000004341855,0.00051996554,0.0000017258126,0.000003442652,0.0000040546684,0.0000035068115,0.9989831,0.00010915552,0.00024805745,0.000119115204,0.0000024934411],"about_ca_topic_score_codex":0.019709881,"about_ca_topic_score_gemma":0.010273658,"teacher_disagreement_score":0.019709881,"about_ca_system_score_codex":0.0005523451,"about_ca_system_score_gemma":0.00075595395,"threshold_uncertainty_score":0.039190292},"labels":[],"label_agreement":null},{"id":"W3153431051","doi":"10.31223/osf.io/wg7sn","title":"Non-crossing nonlinear regression quantiles by monotone composite quantile regression neural network, with application to rainfall extremes","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Quantile; Quantile regression; Statistics; Mathematics; Overfitting; Linear regression; Regression; Econometrics; Artificial neural network; Computer science; Artificial intelligence","score_opus":0.025527221661644752,"score_gpt":0.2947981855425977,"score_spread":0.26927096388095295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153431051","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21216378,0.0009947869,0.78192943,0.000547807,0.00006471519,0.000058221656,0.00020403341,0.00083678984,0.003200367],"genre_scores_gemma":[0.9325663,0.00029319082,0.06489661,0.00008880195,0.0000408622,0.000054649114,0.00020134113,0.000046550394,0.0018117358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997651,0.00007926664,0.0000110738365,0.000068422945,0.000044922923,0.000031188654],"domain_scores_gemma":[0.99924123,0.00042459177,0.000092471986,0.000033128174,0.00018221175,0.000026355117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001116688,0.00049316266,0.00047423528,0.0003635828,0.00024683672,0.00044961384,0.0006983016,0.0006825546,0.0008801319],"category_scores_gemma":[0.0030543895,0.00028088232,0.00051722885,0.0005122367,0.0003493853,0.0005347122,0.00064917584,0.00095199666,0.000121196426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006643546,0.000032181073,0.0021930458,0.000027868196,0.00003545763,0.000055077933,0.00003278332,0.95088494,0.0010578412,0.0017244312,0.0004063495,0.04348353],"study_design_scores_gemma":[7.6741213e-7,0.000004026754,0.00014603883,8.1400833e-7,0.0000013625679,0.0000024377377,0.0000011266884,0.9994512,0.00006462979,0.0002980573,0.000028272336,0.0000011740044],"about_ca_topic_score_codex":0.015996225,"about_ca_topic_score_gemma":0.011559626,"teacher_disagreement_score":0.015996225,"about_ca_system_score_codex":0.0007410245,"about_ca_system_score_gemma":0.00055465515,"threshold_uncertainty_score":0.03180623},"labels":[],"label_agreement":null},{"id":"W3153642306","doi":"10.5194/egusphere-egu21-6312","title":"Learning from mistakes - Assessing the performance and uncertainty in process-based models","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BGC Engineering (Canada); University of Calgary","funders":"","keywords":"Variable (mathematics); Process (computing); Set (abstract data type); Computer science; Cluster analysis; Field (mathematics); Data mining; Statistics; Mathematics; Artificial intelligence","score_opus":0.03304457753635645,"score_gpt":0.26294142682661187,"score_spread":0.22989684929025542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153642306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26395547,0.00032522436,0.73229146,0.0005965931,0.000041453648,0.00015688998,0.00021267698,0.0004442256,0.0019760432],"genre_scores_gemma":[0.92271215,0.00013675986,0.07644082,0.000049063598,0.000025030262,0.00009691837,0.00022246299,0.00004954569,0.0002671894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99030894,0.005455242,0.0008964151,0.0011342685,0.0018825432,0.00032264617],"domain_scores_gemma":[0.88750184,0.09635895,0.0063300137,0.004873461,0.0041819853,0.00075370295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0244316,0.0016259027,0.001204591,0.003008585,0.0006897532,0.0030946499,0.001681233,0.0016226928,0.0007444967],"category_scores_gemma":[0.09266604,0.0005832749,0.0010778691,0.0015737916,0.0018775058,0.0039562266,0.0030439645,0.001770588,0.00013969441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012456693,0.000070958085,0.016122205,0.000086011976,0.00017251493,0.000075165495,0.0002948565,0.9448164,0.00035512797,0.0075420337,0.00016609865,0.030174064],"study_design_scores_gemma":[0.0000036698577,0.000052735064,0.001447506,0.000019580237,0.00001480344,0.000016745724,0.000051744035,0.98719317,0.0005307968,0.010565864,0.000088149274,0.000015202349],"about_ca_topic_score_codex":0.006354002,"about_ca_topic_score_gemma":0.00357297,"teacher_disagreement_score":0.0244316,"about_ca_system_score_codex":0.0019260452,"about_ca_system_score_gemma":0.0018960246,"threshold_uncertainty_score":0.1292082},"labels":[],"label_agreement":null},{"id":"W3154077419","doi":"10.21203/rs.3.rs-285852/v1","title":"Hourly soil temperature prediction using integrated machine learning methods, GLUE uncertainty analysis, Taguchi search, and wavelet coherence analysis","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"GLUE; Taguchi methods; Wavelet; Coherence (philosophical gambling strategy); Computer science; Artificial intelligence; Machine learning; Environmental science; Engineering; Mathematics; Statistics; Mechanical engineering","score_opus":0.06721324625169033,"score_gpt":0.390427939492575,"score_spread":0.32321469324088464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154077419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7579455,0.00013249887,0.241008,0.000033321823,0.000017505861,0.000019422068,0.000046735753,0.00017548379,0.0006215302],"genre_scores_gemma":[0.98148316,0.000028034112,0.018295748,0.0000038259277,0.0000027624012,0.000013309531,0.00002951677,0.0000061684577,0.00013732814],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980646,0.000049062393,0.00001473941,0.000047701888,0.000063694744,0.00001836003],"domain_scores_gemma":[0.99975437,0.00010480711,0.000042562064,0.000017687888,0.00007058509,0.000010083196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052203494,0.0005087997,0.00048226304,0.00058040034,0.00015521041,0.00037817578,0.0003886918,0.000363449,0.00024404451],"category_scores_gemma":[0.000836952,0.00022227645,0.00061038166,0.0005067045,0.00013101405,0.0004623697,0.00020923911,0.00024446927,0.00005777361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016674069,0.00013905001,0.0231239,0.00008143026,0.00013234981,0.000066806315,0.00008904922,0.85498434,0.02387577,0.00042042314,0.00013515519,0.09678487],"study_design_scores_gemma":[0.000004413524,0.000042313444,0.0030543017,0.0000017282126,0.000012169082,0.0000058718133,0.000011097028,0.9950041,0.0017452033,0.00007933499,0.000035232057,0.0000042389593],"about_ca_topic_score_codex":0.0049720495,"about_ca_topic_score_gemma":0.0060097477,"teacher_disagreement_score":0.0049720495,"about_ca_system_score_codex":0.0002881253,"about_ca_system_score_gemma":0.0003445847,"threshold_uncertainty_score":0.009886205},"labels":[],"label_agreement":null},{"id":"W3154817805","doi":"10.1016/j.advwatres.2021.103920","title":"A workflow to address pitfalls and challenges in applying machine learning models to hydrology","year":2021,"lang":"en","type":"article","venue":"Advances in Water Resources","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Mitacs","keywords":"Computer science; Streamflow; Hydrological modelling; Machine learning; Feature selection; Dimensionality reduction; Artificial intelligence; Data mining; Model selection; Test set; Cross-validation; Data pre-processing; Workflow; Drainage basin","score_opus":0.049007493702548144,"score_gpt":0.25477653710598536,"score_spread":0.2057690434034372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154817805","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002567365,0.000096611126,0.8900575,0.0023118122,0.0005039239,0.00080405147,0.0042083147,0.09254354,0.0069068237],"genre_scores_gemma":[0.019272314,0.0002386999,0.9530826,0.0007382476,0.0001523521,0.00089781557,0.0073347418,0.0082981335,0.009985128],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99738973,0.00061857724,0.00048438797,0.00036744418,0.0009493412,0.00019053956],"domain_scores_gemma":[0.9777899,0.007876375,0.0006646874,0.0065039867,0.0058213687,0.0013438013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008146044,0.0020370327,0.001189472,0.0043128794,0.0021426303,0.007851234,0.0028162342,0.0024704144,0.027007231],"category_scores_gemma":[0.03184862,0.0011820591,0.0018978205,0.002774486,0.0010426998,0.0037388732,0.004758927,0.0036011552,0.021181608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006474522,0.00069235894,0.0056803403,0.00083540473,0.00020469252,0.0021124978,0.002277452,0.020636007,0.01722905,0.059728846,0.33554733,0.55440855],"study_design_scores_gemma":[0.00042545464,0.00013956113,0.0026806449,0.0006103369,0.00012019226,0.0010127107,0.00082269264,0.2147315,0.04872215,0.17699963,0.5534012,0.00033390286],"about_ca_topic_score_codex":0.009935519,"about_ca_topic_score_gemma":0.009404995,"teacher_disagreement_score":0.027007231,"about_ca_system_score_codex":0.0012754482,"about_ca_system_score_gemma":0.008903331,"threshold_uncertainty_score":0.090348184},"labels":[],"label_agreement":null},{"id":"W3156493712","doi":"10.5194/hess-2021-65","title":"Gaining Hydrological Insights Through Wilk's Feature Importance: A Test-Statistic Interpretation method for Reliable and Robust Inference","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Regina","funders":"National Key Research and Development Program of China; Western Economic Diversification Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Equifinality; Overfitting; Feature (linguistics); Statistic; Inference; Artificial intelligence; Machine learning; Computer science; Random forest; Statistics; Mathematics; Artificial neural network","score_opus":0.03121312430953003,"score_gpt":0.3015856282723847,"score_spread":0.27037250396285467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156493712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017163442,0.00011532867,0.98161525,0.00008021288,0.000029987003,0.000059805196,0.000092602044,0.00038484743,0.000458559],"genre_scores_gemma":[0.57633257,0.00017110237,0.42162916,0.00017339007,0.00018212396,0.00034202935,0.00045108327,0.00022023956,0.00049821654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99465585,0.0026078972,0.00037324085,0.00078511756,0.0013914477,0.00018640298],"domain_scores_gemma":[0.9638028,0.027445935,0.0026644368,0.0025137188,0.0031540857,0.0004190802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015115509,0.0010187047,0.0015710351,0.005754711,0.00065185997,0.00144219,0.0014697396,0.0012163342,0.0016258933],"category_scores_gemma":[0.054008245,0.00037963295,0.0013842119,0.003072526,0.0020387706,0.0020601156,0.0014442358,0.0025643469,0.0003202024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005965848,0.00043525407,0.05273619,0.0007388122,0.0010283396,0.0008173095,0.0006372908,0.28597748,0.020852156,0.07054281,0.0063655553,0.5592722],"study_design_scores_gemma":[0.000041425923,0.0002494137,0.009686788,0.000047240683,0.00008416175,0.00017454477,0.00008151078,0.94578886,0.0064492915,0.035410896,0.0019194991,0.00006627576],"about_ca_topic_score_codex":0.0013228266,"about_ca_topic_score_gemma":0.000986667,"teacher_disagreement_score":0.015115509,"about_ca_system_score_codex":0.00087732077,"about_ca_system_score_gemma":0.001204108,"threshold_uncertainty_score":0.079939425},"labels":[],"label_agreement":null},{"id":"W3158543373","doi":"10.1016/j.scitotenv.2021.147319","title":"Efficacy of machine learning techniques in predicting groundwater fluctuations in agro-ecological zones of India","year":2021,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Groundwater; Environmental science; Ecology; Water resource management; Environmental resource management; Geology; Biology; Geotechnical engineering","score_opus":0.011807880089516151,"score_gpt":0.22523661396854755,"score_spread":0.21342873387903138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158543373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97382486,0.00046899286,0.022187501,0.00033842522,0.000026506375,0.00003513403,0.0003071193,0.00039275948,0.0024187139],"genre_scores_gemma":[0.99604285,0.00012334359,0.0034980997,0.000013237601,0.000004042907,0.000006428362,0.00015031637,0.0000030554336,0.00015859578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997004,0.00009618131,0.000039972696,0.00005458308,0.00007098745,0.000037875572],"domain_scores_gemma":[0.998968,0.000698851,0.000114108225,0.000041727413,0.00014464441,0.00003268965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008190485,0.000527401,0.00033795155,0.0013149764,0.000190934,0.0008156644,0.00044411002,0.00045861883,0.00025749402],"category_scores_gemma":[0.0023920222,0.00015207115,0.0004781161,0.0008058153,0.00021550452,0.0005889943,0.00028890956,0.00048902456,0.00009902403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021989511,0.00019281925,0.1259784,0.00011469216,0.00012886543,0.00021467343,0.00018441262,0.78238714,0.0032840134,0.0005903129,0.0006286707,0.08607612],"study_design_scores_gemma":[0.0000034645782,0.00005628757,0.019900776,0.000011963087,0.000018680314,0.000030991796,0.00014556744,0.9783755,0.0010125618,0.0002722046,0.0001614173,0.00001067098],"about_ca_topic_score_codex":0.021260792,"about_ca_topic_score_gemma":0.016558114,"teacher_disagreement_score":0.021260792,"about_ca_system_score_codex":0.0005510327,"about_ca_system_score_gemma":0.000629433,"threshold_uncertainty_score":0.042274117},"labels":[],"label_agreement":null},{"id":"W3160202230","doi":"10.5194/egusphere-egu2020-22357","title":"CoSMoS v2.0: Making Time Series Generation Simple","year":2020,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Series (stratigraphy); Computer science; Transformation (genetics); Univariate; Simple (philosophy); Intermittency; Multivariate statistics; Meteorology; Machine learning; Turbulence; Geology","score_opus":0.042624451252486734,"score_gpt":0.240466352638505,"score_spread":0.19784190138601826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160202230","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033447233,0.00015919495,0.7946897,0.0002281424,0.00039043537,0.0001710356,0.012815706,0.18062769,0.0075734016],"genre_scores_gemma":[0.07581185,0.0006377815,0.77993137,0.00046572596,0.0002877124,0.0013898714,0.037743215,0.091039136,0.0126933465],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993606,0.00015956322,0.000095406205,0.00015377259,0.0001831271,0.000047470865],"domain_scores_gemma":[0.9980679,0.0009661448,0.000104873674,0.0004243651,0.00034774843,0.000088997826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024031536,0.0010094426,0.0007386383,0.0012081607,0.0003178513,0.0014728563,0.0022131284,0.0007158219,0.055645663],"category_scores_gemma":[0.010494181,0.0011139808,0.0013348965,0.0012831069,0.00040815945,0.0014966783,0.0015753072,0.0017439199,0.021511707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008292759,0.00013215512,0.0043355916,0.0011462264,0.0004753997,0.0008979566,0.0005072388,0.1379597,0.011384192,0.05403084,0.47889817,0.30940333],"study_design_scores_gemma":[0.0004446016,0.00007255319,0.0015439691,0.00015667157,0.00010419729,0.00039983154,0.000050889143,0.60611,0.017869214,0.055710085,0.317397,0.00014100461],"about_ca_topic_score_codex":0.0021079239,"about_ca_topic_score_gemma":0.0017366714,"teacher_disagreement_score":0.055645663,"about_ca_system_score_codex":0.0002834355,"about_ca_system_score_gemma":0.000733568,"threshold_uncertainty_score":0.1861533},"labels":[],"label_agreement":null},{"id":"W3162123554","doi":"10.1016/j.jhydrol.2021.126459","title":"Closure to the discussion of Ebtehaj et al. on “Comparative assessment of time series and artificial intelligence models to estimate monthly streamflow: A local and external data analysis approach”","year":2021,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Closure (psychology); Streamflow; Series (stratigraphy); Time series; Computer science; Environmental science; Geology; Machine learning; Geography; Drainage basin; Cartography","score_opus":0.06887578045069868,"score_gpt":0.35508753037394175,"score_spread":0.28621174992324305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162123554","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00161633,0.013142789,0.010236288,0.8477385,0.091741525,0.000084221436,0.0010191354,0.00017895638,0.034242257],"genre_scores_gemma":[0.02587892,0.005636879,0.0096614165,0.85698915,0.06593728,0.0002612504,0.00034036645,0.00023319802,0.0350615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99131095,0.0029432287,0.00071884383,0.0011179288,0.0032379625,0.0006711297],"domain_scores_gemma":[0.9600432,0.022520417,0.0018002412,0.0017106858,0.013272052,0.00065335113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011548065,0.00066074776,0.001084165,0.0020458465,0.0033061316,0.0057923216,0.0057969177,0.011134701,0.018929692],"category_scores_gemma":[0.080123425,0.0003639242,0.0016200066,0.0022123472,0.0035583575,0.005198146,0.0036849754,0.011605432,0.00934006],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053256983,0.00003535814,0.00053965865,0.00033067967,0.00007713595,0.00022063358,0.00077781314,0.00036448243,0.00024723008,0.10090058,0.88354456,0.012908605],"study_design_scores_gemma":[0.000023877888,0.000026305333,0.0014250097,0.00056026125,0.000057334288,0.00015778611,0.000894285,0.0010000981,0.0011333049,0.082388245,0.9122691,0.000064452106],"about_ca_topic_score_codex":0.01883253,"about_ca_topic_score_gemma":0.019037735,"teacher_disagreement_score":0.018929692,"about_ca_system_score_codex":0.0027695128,"about_ca_system_score_gemma":0.0037463387,"threshold_uncertainty_score":0.06332612},"labels":[],"label_agreement":null},{"id":"W3164523253","doi":"","title":"Conceptual Framework for Groundwater Vulnerability Assessment Using Physical, Experimental and Machine Learning Based Approaches in Coastal Aquifers of India","year":2020,"lang":"en","type":"article","venue":"Journal of the Indian Society of Coastal Agricultural Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Aquifer; Saltwater intrusion; Groundwater recharge; Groundwater; Vulnerability (computing); Environmental science; Water resource management; Hydrology (agriculture); Geology; Computer science; Geotechnical engineering","score_opus":0.1491710075609776,"score_gpt":0.3553649619234787,"score_spread":0.20619395436250113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164523253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046316706,0.0010948848,0.92195886,0.0020495297,0.00007140894,0.00040032956,0.0006864624,0.00031508066,0.02710672],"genre_scores_gemma":[0.799775,0.0015678562,0.19427249,0.00017163093,0.000050857732,0.0009188398,0.00036899094,0.000028618555,0.0028457558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953043,0.00017671897,0.000044833592,0.00008525124,0.00012172874,0.000041030187],"domain_scores_gemma":[0.9994223,0.00022459736,0.000110401874,0.00004511412,0.00016202817,0.000035564703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010989791,0.0006566716,0.00045499983,0.002076564,0.00061845104,0.0019805555,0.0022754234,0.0010625301,0.00192234],"category_scores_gemma":[0.0012591436,0.0003236274,0.0008176878,0.0014016024,0.0022275788,0.0015285179,0.0014829725,0.0007032238,0.00014867877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019377581,0.00010746752,0.0040856684,0.0002946544,0.000048199232,0.0003265377,0.0003017973,0.6331165,0.002876999,0.34168902,0.0006630875,0.0164707],"study_design_scores_gemma":[0.000015219281,0.00009303027,0.002022957,0.00008529483,0.000035165336,0.000099644,0.00048535477,0.86689955,0.0008400254,0.1253596,0.004017628,0.00004660881],"about_ca_topic_score_codex":0.01494606,"about_ca_topic_score_gemma":0.00941898,"teacher_disagreement_score":0.01494606,"about_ca_system_score_codex":0.0023921384,"about_ca_system_score_gemma":0.0025511454,"threshold_uncertainty_score":0.02971816},"labels":[],"label_agreement":null},{"id":"W3165551827","doi":"10.5194/egusphere-egu21-10152","title":"Exploring the potential of transfer entropy for identifying similarity of catchment dynamics","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Streamflow; Regionalisation; Surface runoff; Environmental science; Drainage basin; Similarity (geometry); Precipitation; Hydrology (agriculture); Mathematics; Computer science; Geography; Meteorology; Ecology; Geology; Cartography","score_opus":0.08781690472755412,"score_gpt":0.2694257381252654,"score_spread":0.18160883339771128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165551827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3143597,0.0012719374,0.67368835,0.0010474831,0.0000746178,0.00009194975,0.00041658452,0.00031812506,0.008731204],"genre_scores_gemma":[0.9656276,0.0002796012,0.032727808,0.000080120226,0.00007946701,0.000047391502,0.00023579341,0.000035257086,0.00088698126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875224,0.00067282905,0.0000596724,0.00022097591,0.00020940922,0.00008489469],"domain_scores_gemma":[0.9873166,0.010595426,0.0007222021,0.00070210936,0.00037918048,0.00028443077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003981313,0.00050652295,0.0007517439,0.0033504793,0.0004413173,0.0020276797,0.00066890696,0.0008845793,0.0017050672],"category_scores_gemma":[0.018727448,0.00021169816,0.00082516356,0.0018441763,0.001627615,0.0031122686,0.0022762972,0.001063054,0.00020596637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004546664,0.000265782,0.042071372,0.00030592064,0.0004662829,0.00045851263,0.00092294486,0.5320502,0.0052211178,0.20241402,0.0016800661,0.21368912],"study_design_scores_gemma":[0.000010100182,0.00011343251,0.0071957903,0.00002984454,0.000026852442,0.00007856505,0.00009673966,0.85559285,0.00095538335,0.13523926,0.0006260888,0.000034973757],"about_ca_topic_score_codex":0.0015230711,"about_ca_topic_score_gemma":0.0007907697,"teacher_disagreement_score":0.003981313,"about_ca_system_score_codex":0.00088823814,"about_ca_system_score_gemma":0.00049789855,"threshold_uncertainty_score":0.0210554},"labels":[],"label_agreement":null},{"id":"W3165975092","doi":"10.46488/nept.2021.v20i02.043","title":"Statistical Downscaling of Rainfall Under Climate Change in Krishna River Sub-basin of Andhra Pradesh, India Using Artificial Neural Network (ANN)","year":2021,"lang":"en","type":"article","venue":"Nature Environment and Pollution Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Downscaling; Climate change; Structural basin; Artificial neural network; Environmental science; Climatology; Geography; Physical geography; Water resource management; Geology; Oceanography; Artificial intelligence; Computer science; Geomorphology","score_opus":0.014913618804682454,"score_gpt":0.2507314066366191,"score_spread":0.23581778783193663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165975092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968021,0.000037639165,0.0021262066,0.00006832265,0.0000080567925,0.000009388512,0.00022573423,0.00007023745,0.00065225124],"genre_scores_gemma":[0.9974235,0.00003998063,0.002125738,0.000006813441,0.000002947513,0.000007046073,0.0002441529,0.0000045072848,0.00014531176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998884,0.000029184728,0.000013396778,0.000030602547,0.000024335432,0.000014083286],"domain_scores_gemma":[0.999723,0.00010898653,0.000053880212,0.00003313688,0.000068191555,0.0000128333595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024012101,0.00016155874,0.00014386782,0.00046244112,0.00018280114,0.0002795087,0.00032019388,0.00015227575,0.0002978173],"category_scores_gemma":[0.0007605673,0.00011371719,0.00026660875,0.0007027314,0.00016870759,0.00025090243,0.00020392238,0.0002908494,0.000059368776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002133424,0.00020934551,0.28445762,0.00013099246,0.0002334977,0.0006936463,0.00043790508,0.6148512,0.010797293,0.0009043558,0.0015585102,0.085512266],"study_design_scores_gemma":[0.000016664255,0.000073077,0.30557504,0.000014843986,0.000062977626,0.00010488501,0.000248844,0.6882039,0.004408744,0.0004310077,0.000833411,0.00002655844],"about_ca_topic_score_codex":0.03588363,"about_ca_topic_score_gemma":0.043222375,"teacher_disagreement_score":0.03588363,"about_ca_system_score_codex":0.00043362053,"about_ca_system_score_gemma":0.00042346772,"threshold_uncertainty_score":0.07134956},"labels":[],"label_agreement":null},{"id":"W3167890350","doi":"10.5194/egusphere-egu21-1644","title":"Improving Deep Learning hydrological time series modeling using Gaussian Filter preprocessing","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo; McGill University","funders":"","keywords":"Series (stratigraphy); Time series; Streamflow; Computer science; Filter (signal processing); Preprocessor; Autoregressive integrated moving average; Autoregressive model; Artificial intelligence; Noise (video); Machine learning; Statistics; Geography; Mathematics; Cartography; Geology; Drainage basin","score_opus":0.0226043929346843,"score_gpt":0.23445442248752787,"score_spread":0.21185002955284357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167890350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14578444,0.00054062065,0.8471571,0.0005895188,0.00011271939,0.000037209255,0.00037418422,0.0034247972,0.0019794053],"genre_scores_gemma":[0.86364293,0.00039288998,0.13097933,0.00026913668,0.000047396345,0.00006127357,0.0009379497,0.00013862865,0.003530536],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981695,0.00003188106,0.000012796066,0.000054939886,0.000046847952,0.000036602185],"domain_scores_gemma":[0.9994961,0.00024929878,0.0000494359,0.000051028324,0.00012749656,0.00002661115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008562094,0.0007434747,0.00047736353,0.00048704306,0.00020840207,0.000651154,0.0009411223,0.0008440157,0.0012958137],"category_scores_gemma":[0.0021310577,0.0002618603,0.0008217311,0.000615217,0.00025849443,0.0011526714,0.00055560196,0.0013930704,0.0005076874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006913211,0.000101299,0.002354053,0.000038727892,0.00005474336,0.00005950809,0.000036315625,0.881683,0.0044598114,0.0025964044,0.0016882957,0.1068587],"study_design_scores_gemma":[0.0000010381101,0.0000043683526,0.00008273664,8.699715e-7,0.0000017375957,0.0000011123179,0.0000011042639,0.99926025,0.00035196418,0.00022191784,0.0000718581,0.000001068897],"about_ca_topic_score_codex":0.026604274,"about_ca_topic_score_gemma":0.02447902,"teacher_disagreement_score":0.026604274,"about_ca_system_score_codex":0.0008349399,"about_ca_system_score_gemma":0.0014227966,"threshold_uncertainty_score":0.052898824},"labels":[],"label_agreement":null},{"id":"W3168508202","doi":"10.5194/egusphere-egu21-13303","title":"Improving hydrological forecasts through temporal hierarchal reconciliation","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mean squared error; Precipitation; Ordinary least squares; Mean absolute error; Exponential smoothing; Statistics; Environmental science; Moving average; Climatology; Econometrics; Meteorology; Mathematics; Computer science; Geology; Geography","score_opus":0.03255078774589145,"score_gpt":0.2471948996179172,"score_spread":0.21464411187202576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168508202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17915694,0.00073546334,0.8053814,0.0006087642,0.00022293687,0.00013519188,0.0029893923,0.0063063456,0.00446353],"genre_scores_gemma":[0.655753,0.00021467931,0.3345328,0.00016083231,0.000095274365,0.00012942344,0.0070802304,0.00043756588,0.0015960804],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874264,0.00045735834,0.00009136126,0.00037127946,0.000241599,0.000095849464],"domain_scores_gemma":[0.99772924,0.0006587182,0.00028200983,0.0005648327,0.000716966,0.00004821372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027747392,0.0007800537,0.00082039007,0.001882996,0.00054759067,0.0009469899,0.00094932335,0.000522884,0.0015023476],"category_scores_gemma":[0.007393161,0.00043646936,0.0010749522,0.0021004584,0.00030103538,0.0015230828,0.0013383974,0.00091568875,0.000652842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019092219,0.00012373281,0.014780506,0.00010688837,0.0002687932,0.000112660644,0.00036281496,0.5312049,0.0033949509,0.004280862,0.01197467,0.43319833],"study_design_scores_gemma":[0.000020793816,0.000025464122,0.004009312,0.000008784485,0.000037267488,0.000014351531,0.00006020765,0.98917514,0.0013779055,0.0026535946,0.0025930204,0.000024078248],"about_ca_topic_score_codex":0.014224224,"about_ca_topic_score_gemma":0.020438066,"teacher_disagreement_score":0.014224224,"about_ca_system_score_codex":0.0005917817,"about_ca_system_score_gemma":0.0014180872,"threshold_uncertainty_score":0.02828288},"labels":[],"label_agreement":null},{"id":"W3168593366","doi":"10.1007/s11600-021-00617-2","title":"Integrated preprocessing techniques with linear stochastic approaches in groundwater level forecasting","year":2021,"lang":"en","type":"article","venue":"Acta Geophysica","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Université Laval","funders":"","keywords":"Adaptive neuro fuzzy inference system; Multilayer perceptron; Akaike information criterion; Artificial neural network; Moving average; Autoregressive integrated moving average; Nonlinear system; Mean squared error; Computer science; Normalization (sociology); Statistics; Autoregressive–moving-average model; Mean absolute percentage error; Preprocessor; Time series; Autoregressive model; Data mining; Mathematics; Fuzzy logic; Artificial intelligence; Fuzzy control system","score_opus":0.09122146162597249,"score_gpt":0.24305012474581134,"score_spread":0.15182866311983884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168593366","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0125375055,0.00025930282,0.9852883,0.00014627518,0.00006940895,0.00001596756,0.000101276935,0.0009489825,0.0006330271],"genre_scores_gemma":[0.41861466,0.00061424554,0.57459575,0.00012667321,0.00023778393,0.00012990246,0.00079770223,0.00034777014,0.0045355055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995752,0.00013326669,0.00004132254,0.0000736864,0.00013215042,0.00004437051],"domain_scores_gemma":[0.9987318,0.00078137947,0.00007376233,0.00011233871,0.0002736646,0.000026941627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008550338,0.0005337381,0.00058722915,0.00080121466,0.00033847473,0.0010729276,0.00078900426,0.000549481,0.0025224558],"category_scores_gemma":[0.0033573392,0.000518932,0.00067618943,0.001473129,0.0003238629,0.001054483,0.0006067184,0.0013137244,0.0008357514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003011126,0.00013986434,0.0011911493,0.00012977915,0.00009884156,0.00007360357,0.00007847024,0.5288248,0.015959669,0.0132003,0.0023853623,0.43761706],"study_design_scores_gemma":[0.0000059862186,0.000019446225,0.0003200109,0.000003810475,0.000009383235,0.0000065556787,0.000006251537,0.9930112,0.002803935,0.0031147955,0.0006924253,0.0000062493605],"about_ca_topic_score_codex":0.008371614,"about_ca_topic_score_gemma":0.009453014,"teacher_disagreement_score":0.008371614,"about_ca_system_score_codex":0.0004311216,"about_ca_system_score_gemma":0.0011594401,"threshold_uncertainty_score":0.01664579},"labels":[],"label_agreement":null},{"id":"W3168747617","doi":"10.1088/1742-6596/1900/1/012015","title":"Rainfall forecasting in arid regions using an ensemble of artificial neural networks","year":2021,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Arid; Artificial neural network; Wilcoxon signed-rank test; Water resources; Correlation coefficient; Environmental science; Hydrology (agriculture); Meteorology; Statistics; Computer science; Mathematics; Artificial intelligence; Geography; Mann–Whitney U test; Engineering; Geology","score_opus":0.10249610097397863,"score_gpt":0.27636892806989266,"score_spread":0.17387282709591403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168747617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92675835,0.0005982958,0.06873673,0.00020865844,0.00008913413,0.000026470376,0.00028774387,0.0004027447,0.0028918942],"genre_scores_gemma":[0.99375606,0.00010680861,0.005616499,0.000014080859,0.000013446355,0.000006830117,0.00014855772,0.0000036228566,0.0003339608],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998078,0.000056509656,0.00001733056,0.000050176437,0.000042079082,0.000026227004],"domain_scores_gemma":[0.9995739,0.00017425462,0.000059969247,0.000033102817,0.00013603058,0.00002279193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083711196,0.0003774927,0.0005018531,0.00078704994,0.00020524707,0.00045559963,0.0004960544,0.00034290142,0.0004150892],"category_scores_gemma":[0.0012620239,0.00018574393,0.00038545404,0.0008214849,0.00009827851,0.00056316383,0.00030147424,0.0003416986,0.00009809379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015037876,0.00012212039,0.01848599,0.00003330956,0.00015095106,0.00008160676,0.00003160424,0.90832967,0.0017057552,0.00033816593,0.0005981235,0.06997239],"study_design_scores_gemma":[0.0000015384054,0.0000124069,0.001462593,0.0000020195478,0.0000073199453,0.0000028563668,0.000004695066,0.99820554,0.00016428079,0.00008453024,0.00005018612,0.0000020361174],"about_ca_topic_score_codex":0.012204556,"about_ca_topic_score_gemma":0.010189361,"teacher_disagreement_score":0.012204556,"about_ca_system_score_codex":0.00043362094,"about_ca_system_score_gemma":0.00030574686,"threshold_uncertainty_score":0.024267018},"labels":[],"label_agreement":null},{"id":"W3174631892","doi":"10.1061/(asce)ir.1943-4774.0001602","title":"Discussion of “Time-Series Prediction of Streamflows of Malaysian Rivers Using Data-Driven Techniques” by Siraj Muhammed Pandhiani, Parveen Sihag, Ani Bin Shabri, Balraj Singh, and Quoc Bao Pham","year":2021,"lang":"en","type":"article","venue":"Journal of Irrigation and Drainage Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Agriculture and Agri-Food Canada","funders":"","keywords":"Bin; Series (stratigraphy); Computer science; Geology; Algorithm; Paleontology","score_opus":0.013230261098562346,"score_gpt":0.2164305923091325,"score_spread":0.20320033121057016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174631892","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02699795,0.021108197,0.13949224,0.7163464,0.062219664,0.00014309288,0.00142649,0.0005875311,0.03167851],"genre_scores_gemma":[0.5242617,0.029961785,0.071295045,0.22803886,0.065957285,0.0004018647,0.001684274,0.00030159552,0.07809757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983328,0.0006418671,0.00016503214,0.00024252925,0.000540998,0.00007677335],"domain_scores_gemma":[0.996021,0.002145147,0.00015556549,0.00013986073,0.00142759,0.00011095753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041406834,0.00047391056,0.00042172923,0.0006838321,0.0011305009,0.003157303,0.0016863629,0.004201334,0.0016197421],"category_scores_gemma":[0.013019829,0.00025403503,0.001023408,0.0013852345,0.0011504331,0.0024150054,0.00089748687,0.003111467,0.0005344941],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030298182,0.00015615977,0.012161277,0.0011826106,0.00041822056,0.001972791,0.0020963443,0.095827036,0.0053445464,0.25016668,0.46529913,0.16507226],"study_design_scores_gemma":[0.00006358785,0.0001458848,0.009434827,0.0007511332,0.00011496487,0.00055283005,0.0015719455,0.13488804,0.008369893,0.084190555,0.7597288,0.00018761157],"about_ca_topic_score_codex":0.016229847,"about_ca_topic_score_gemma":0.009302117,"teacher_disagreement_score":0.016229847,"about_ca_system_score_codex":0.0014503746,"about_ca_system_score_gemma":0.0015353302,"threshold_uncertainty_score":0.03227073},"labels":[],"label_agreement":null},{"id":"W3176598223","doi":"10.18280/ijsdp.160310","title":"Application of Deep Learning Method for Daily Streamflow Time-Series Prediction: A Case Study of the Kowmung River at Cedar Ford, Australia","year":2021,"lang":"en","type":"article","venue":"International Journal of Sustainable Development and Planning","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"WaterNSW","keywords":"Streamflow; Mean squared error; Precipitation; Random forest; Climatology; Environmental science; Coefficient of determination; Computer science; Meteorology; Statistics; Mathematics; Machine learning; Geography; Drainage basin; Geology","score_opus":0.018320485046002772,"score_gpt":0.28205224307950355,"score_spread":0.2637317580335008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176598223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911045,0.0001406859,0.006337568,0.0003890149,0.000017073664,0.000037048427,0.00023230471,0.00012189187,0.0016197775],"genre_scores_gemma":[0.99335575,0.00010144975,0.005219295,0.000020943446,0.000005019548,0.000016422135,0.0001938936,0.0000071539944,0.0010800329],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997851,0.000049987884,0.000018541206,0.000056522607,0.0000534602,0.000036217785],"domain_scores_gemma":[0.9995828,0.00019010379,0.000034310848,0.000027944312,0.00012203037,0.000042749394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000632292,0.0004957318,0.00043041323,0.0006867874,0.00056885584,0.0006218659,0.00087018,0.0007525976,0.0006716621],"category_scores_gemma":[0.0012547068,0.00022268819,0.00041068508,0.00073877204,0.00034703303,0.00063151424,0.00039904777,0.00057583896,0.00009154122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018515445,0.00067814847,0.08770141,0.00019121837,0.00010802683,0.0033617865,0.0006856288,0.8011553,0.003989748,0.0018735952,0.0027165858,0.097353406],"study_design_scores_gemma":[0.000009497049,0.000043403586,0.013441645,0.000007947995,0.000013515676,0.000039592633,0.00023537558,0.98439145,0.0010179756,0.00030837907,0.00047916482,0.000012157018],"about_ca_topic_score_codex":0.20488007,"about_ca_topic_score_gemma":0.21644147,"teacher_disagreement_score":0.20488007,"about_ca_system_score_codex":0.0021170569,"about_ca_system_score_gemma":0.0014902998,"threshold_uncertainty_score":0.40737504},"labels":[],"label_agreement":null},{"id":"W3177344253","doi":"10.48550/arxiv.2106.14742","title":"TENT: Tensorized Encoder Transformer for Temperature Forecasting","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Transformer; Computer science; Encoder; Weather prediction; Exploit; Weather Research and Forecasting Model; Deep learning; Artificial intelligence; Artificial neural network; Weather forecasting; Recurrent neural network; Machine learning; Meteorology; Data mining; Geography; Engineering","score_opus":0.10126811679837054,"score_gpt":0.18538590248133432,"score_spread":0.08411778568296378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177344253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030407581,0.00058179686,0.9572257,0.0004328407,0.00019999479,0.00005458529,0.001281043,0.006328573,0.0034880226],"genre_scores_gemma":[0.8230892,0.0006372722,0.16477083,0.00024802948,0.00011608943,0.000112809124,0.0023154095,0.00031462594,0.008395704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998473,0.000029450333,0.000011357906,0.00004993896,0.000035705154,0.000026209662],"domain_scores_gemma":[0.9996019,0.00015152074,0.00004528829,0.000070272436,0.00010284116,0.000028257591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000431606,0.0008104448,0.0003502145,0.00041554405,0.00020595202,0.00056740624,0.00088746793,0.00046230646,0.0037382517],"category_scores_gemma":[0.001952807,0.00025464417,0.00046722897,0.0005653274,0.00032671445,0.0014899515,0.0006671574,0.0010673357,0.001277197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045336713,0.00014052136,0.0035685792,0.00017849082,0.00010698705,0.00019322011,0.00013428055,0.5675401,0.015846068,0.028071446,0.014617819,0.36914912],"study_design_scores_gemma":[0.000004362807,0.000020989619,0.00015175408,0.0000039486235,0.0000067174246,0.000017486864,0.000004564454,0.9910028,0.002109425,0.005729453,0.00094358943,0.0000049575606],"about_ca_topic_score_codex":0.010299596,"about_ca_topic_score_gemma":0.013958742,"teacher_disagreement_score":0.010299596,"about_ca_system_score_codex":0.0007524069,"about_ca_system_score_gemma":0.0010993452,"threshold_uncertainty_score":0.020479262},"labels":[],"label_agreement":null},{"id":"W3178601173","doi":"10.21203/rs.3.rs-603225/v1","title":"Application of Artificial Neural Networks to Project Reference Evapotranspiration under Climate Change Scenarios","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Dalhousie University; University of Prince Edward Island","funders":"","keywords":"Downscaling; Evapotranspiration; Climate change; Environmental science; Representative Concentration Pathways; Calibration; Climatology; Perceptron; Artificial neural network; General Circulation Model; Meteorology; Statistics; Computer science; Mathematics; Geography; Artificial intelligence; Geology","score_opus":0.21567858693500358,"score_gpt":0.4117741160617999,"score_spread":0.19609552912679634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178601173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95621157,0.0002918922,0.039042354,0.00025085144,0.000082281185,0.000073651434,0.0007056611,0.000477343,0.002864364],"genre_scores_gemma":[0.99074566,0.00006715422,0.008384669,0.000015352687,0.000006362574,0.00003967147,0.00031143468,0.00001167541,0.00041802818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973303,0.00011050373,0.000023477372,0.00005729611,0.000041304713,0.000034282184],"domain_scores_gemma":[0.99919623,0.0004244941,0.0000759171,0.000033791326,0.00023535306,0.000034196368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010844081,0.0007496139,0.00027203787,0.0010515703,0.0002542262,0.00065522623,0.00047570534,0.00064790965,0.0007942689],"category_scores_gemma":[0.0029266246,0.0002643815,0.00038423217,0.00095876167,0.00016087666,0.0004940743,0.00029888595,0.00046034472,0.00011305723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012480517,0.000081750164,0.012110286,0.00003272114,0.0000670263,0.000048842216,0.000026193964,0.9624233,0.0007824919,0.00020650477,0.0003460589,0.023750015],"study_design_scores_gemma":[0.0000035597377,0.000010104519,0.0021254555,0.0000021403641,0.0000044609696,0.0000015855614,0.000010945957,0.9974573,0.00026566078,0.0000755127,0.00004005954,0.0000031929526],"about_ca_topic_score_codex":0.04067276,"about_ca_topic_score_gemma":0.027647527,"teacher_disagreement_score":0.04067276,"about_ca_system_score_codex":0.0011276262,"about_ca_system_score_gemma":0.000652369,"threshold_uncertainty_score":0.080872},"labels":[],"label_agreement":null},{"id":"W3196258703","doi":"10.18280/ijdne.170218","title":"Forecasting the Water Level of the Euphrates River in Western Iraq Using Artificial Neural Networks (ANN)","year":2022,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Water level; Environmental science; Hydrology (agriculture); Agriculture; Flood myth; Geography; Engineering; Computer science; Geotechnical engineering; Machine learning; Cartography","score_opus":0.06177592890521461,"score_gpt":0.2661219911591099,"score_spread":0.2043460622538953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196258703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937735,0.00005610136,0.004346765,0.0001060633,0.000011985907,0.000010561015,0.00020105274,0.000058033987,0.0014359736],"genre_scores_gemma":[0.9966844,0.000060780472,0.0026097465,0.0000090341155,0.0000030945212,0.000007916604,0.00019766462,0.0000028634274,0.0004244859],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999275,0.00001816268,0.0000063773055,0.00001697837,0.000016965198,0.000014002358],"domain_scores_gemma":[0.9998487,0.00006366513,0.000026767786,0.0000085747515,0.00004406839,0.0000081326525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020346597,0.00021999699,0.00013161734,0.00024213447,0.00020039812,0.00028172473,0.00021573764,0.0002576124,0.00035287603],"category_scores_gemma":[0.0006038512,0.0001011227,0.00017830888,0.00038922593,0.00014720224,0.00025324762,0.00016681621,0.0002586431,0.000068467576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007612071,0.00010217201,0.07413341,0.000052809355,0.00005097293,0.00035098928,0.00017672083,0.885144,0.0048991963,0.00051238044,0.00094533636,0.033555847],"study_design_scores_gemma":[0.000005462909,0.000028529956,0.024249705,0.000005822417,0.000009010319,0.000015185113,0.00007701509,0.974098,0.0010252665,0.00013302687,0.00034533447,0.000007633683],"about_ca_topic_score_codex":0.049286902,"about_ca_topic_score_gemma":0.061363973,"teacher_disagreement_score":0.049286902,"about_ca_system_score_codex":0.0005855396,"about_ca_system_score_gemma":0.0004631754,"threshold_uncertainty_score":0.09800005},"labels":[],"label_agreement":null},{"id":"W3196409416","doi":"10.1016/j.envpol.2021.118116","title":"Real-time prediction of river chloride concentration using ensemble learning","year":2021,"lang":"en","type":"article","venue":"Environmental Pollution","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Chloride; Multilayer perceptron; Water quality; Artificial neural network; Machine learning; Perceptron; Artificial intelligence; Computer science; Environmental science; Hydrology (agriculture); Statistics; Mathematics; Chemistry; Geology; Ecology","score_opus":0.013706247221636495,"score_gpt":0.20875353565760113,"score_spread":0.19504728843596464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196409416","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7364943,0.00063499,0.2569988,0.0004574246,0.00024890978,0.00002525959,0.0005746655,0.0014736882,0.0030920112],"genre_scores_gemma":[0.9866072,0.00008594168,0.012449518,0.00002874985,0.000029307803,0.000011395194,0.0002905657,0.000012155134,0.0004852999],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979717,0.000039251983,0.000014816532,0.000060114355,0.000053201915,0.000035558067],"domain_scores_gemma":[0.9992823,0.0003286641,0.00006797902,0.000076412856,0.00020719235,0.000037455782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006012038,0.0005012691,0.0006979436,0.0006001101,0.00027504168,0.00046402635,0.00044460176,0.00059872726,0.00054905436],"category_scores_gemma":[0.0014632388,0.00023548627,0.00043421908,0.00081378093,0.00015960832,0.0007600913,0.0003710275,0.0008735249,0.00015486125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017516184,0.0001830216,0.010497952,0.000029369063,0.00014750782,0.0000612021,0.000027306949,0.8942777,0.005370682,0.00035745045,0.0011499583,0.087722726],"study_design_scores_gemma":[0.00000199146,0.0000075684566,0.0006326008,5.573223e-7,0.00000431923,0.0000024834185,0.0000013357055,0.99884075,0.00037186785,0.00010077542,0.000033857257,0.0000019141369],"about_ca_topic_score_codex":0.013523908,"about_ca_topic_score_gemma":0.011737912,"teacher_disagreement_score":0.013523908,"about_ca_system_score_codex":0.0004167471,"about_ca_system_score_gemma":0.0005005002,"threshold_uncertainty_score":0.026890397},"labels":[],"label_agreement":null},{"id":"W3196897376","doi":"10.1038/s41598-021-96751-4","title":"Streamflow prediction using an integrated methodology based on convolutional neural network and long short-term memory networks","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":279,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"University of Southern Queensland","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Residual; Artificial neural network; Convolution (computer science); Machine learning; Deep learning; Range (aeronautics); Flood forecasting; Streamflow; Pattern recognition (psychology); Data mining; Flood myth; Algorithm","score_opus":0.06876589877112961,"score_gpt":0.28847030947402325,"score_spread":0.21970441070289365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196897376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3123043,0.000990319,0.67939055,0.0003752612,0.00020064412,0.00009079075,0.00038544892,0.003234143,0.003028557],"genre_scores_gemma":[0.9418514,0.00020590881,0.055841703,0.00006430663,0.00003051864,0.000057176087,0.0003155957,0.000026664207,0.0016067256],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998425,0.000018638755,0.000011218519,0.000050492028,0.000044445485,0.000032620974],"domain_scores_gemma":[0.9997764,0.00005206872,0.000035288427,0.000018439265,0.00010272431,0.000015043504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005383339,0.0008780813,0.0005263564,0.0007067042,0.00024466048,0.0005386865,0.0007118067,0.0005962776,0.0009703203],"category_scores_gemma":[0.0006951284,0.00032837695,0.0005588335,0.0006187577,0.0002193268,0.0008825597,0.00042523592,0.00064571755,0.00019897641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014774069,0.00019286097,0.0057419455,0.000056166064,0.00017810667,0.0000903779,0.000027564542,0.8449767,0.011081488,0.0006936817,0.0009532367,0.13586009],"study_design_scores_gemma":[0.0000012838392,0.000010462788,0.0002719796,0.0000013066884,0.000005711987,0.0000022366246,0.0000012350847,0.99885356,0.0007369977,0.000075109194,0.00003831215,0.0000018157496],"about_ca_topic_score_codex":0.023750717,"about_ca_topic_score_gemma":0.023454417,"teacher_disagreement_score":0.023750717,"about_ca_system_score_codex":0.0007997112,"about_ca_system_score_gemma":0.0009988381,"threshold_uncertainty_score":0.04722494},"labels":[],"label_agreement":null},{"id":"W3199335793","doi":"10.1061/(asce)ir.1943-4774.0001638","title":"Discussion of “Model Development for Estimation of Sediment Removal Efficiency of Settling Basins Using Group Methods of Data Handling” by Faisal Ahmad, Mujib Ahmad Ansari, Ajmal Hussain, and Jahangeer Jahangeer","year":2021,"lang":"en","type":"article","venue":"Journal of Irrigation and Drainage Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Settling; Sediment; Estimation; Environmental science; Geology; Mathematics; Environmental engineering; Geomorphology; Economics; Management","score_opus":0.04769757137190654,"score_gpt":0.3217105402790771,"score_spread":0.27401296890717053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199335793","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071405913,0.00046945713,0.9790475,0.00814129,0.0013748567,0.000079351936,0.00022851797,0.00064317737,0.002875255],"genre_scores_gemma":[0.34101462,0.0015023084,0.6228806,0.0067646476,0.0028577263,0.0007691147,0.0011259762,0.0005142524,0.022570841],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.999052,0.0004887326,0.000064317326,0.00010391002,0.00024341722,0.000047591664],"domain_scores_gemma":[0.99783355,0.0011748081,0.000070310736,0.0001953566,0.00067646755,0.00004957321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041389866,0.00058915716,0.00057494425,0.00047177862,0.0006988791,0.0012791436,0.0019801133,0.0019043891,0.0030299358],"category_scores_gemma":[0.007637706,0.00031575825,0.0018922575,0.0006637059,0.00066096504,0.0016711918,0.00082948926,0.0020174927,0.0008895916],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118237855,0.00012780659,0.004095289,0.00032546234,0.0002403604,0.00048666602,0.0003289551,0.7409793,0.0039592297,0.12008715,0.042349976,0.08690156],"study_design_scores_gemma":[0.000021051996,0.00007635577,0.0007846102,0.000042705793,0.00004143548,0.00008093701,0.00006486011,0.93071365,0.004370767,0.039857835,0.023906467,0.000039260638],"about_ca_topic_score_codex":0.012462886,"about_ca_topic_score_gemma":0.00741173,"teacher_disagreement_score":0.012462886,"about_ca_system_score_codex":0.00066156784,"about_ca_system_score_gemma":0.0014987777,"threshold_uncertainty_score":0.02478069},"labels":[],"label_agreement":null},{"id":"W3200208466","doi":"10.21203/rs.3.rs-912383/v1","title":"Advanced Hybrid Machine Learning Algorithms for Multistep Lake Water Level Forecasting","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; McGill University; University of Waterloo; Ste. Anne's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Artificial intelligence; Algorithm","score_opus":0.1775023915818205,"score_gpt":0.37889548381112503,"score_spread":0.20139309222930454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200208466","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02073549,0.0005707814,0.97578645,0.00018164107,0.00012244612,0.000024664942,0.00008593604,0.00048448012,0.0020081121],"genre_scores_gemma":[0.53002983,0.00048221802,0.45779008,0.00014474207,0.00022167245,0.00019110818,0.00035134255,0.00015570255,0.010633286],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971527,0.00010231054,0.000021283982,0.00004990571,0.000086253596,0.000024936711],"domain_scores_gemma":[0.9986909,0.00089199026,0.00004637987,0.00009434175,0.00024804517,0.00002837203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009874419,0.000526949,0.00074198726,0.00064239954,0.00033140308,0.00078732154,0.000971683,0.0010132245,0.0034343433],"category_scores_gemma":[0.003313043,0.00035331934,0.0004828341,0.0011659702,0.00037833466,0.0011016106,0.00081689795,0.0013289447,0.00065369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011128291,0.00006486019,0.00045946534,0.000060513747,0.00007988264,0.000019281131,0.000040373823,0.7728844,0.002014514,0.0063864314,0.0017766855,0.2161023],"study_design_scores_gemma":[0.0000025502784,0.0000054477687,0.000045010238,0.0000011777323,0.0000019932838,0.0000016506509,0.000001242667,0.99845505,0.00015669702,0.0011736585,0.00015408284,0.0000013881512],"about_ca_topic_score_codex":0.006882425,"about_ca_topic_score_gemma":0.00595044,"teacher_disagreement_score":0.006882425,"about_ca_system_score_codex":0.00047588424,"about_ca_system_score_gemma":0.0005371624,"threshold_uncertainty_score":0.01368475},"labels":[],"label_agreement":null},{"id":"W3200863083","doi":"10.1016/j.jenvman.2021.113774","title":"The assessment of emerging data-intelligence technologies for modeling Mg+2 and SO4−2 surface water quality","year":2021,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Mean squared error; Multilayer perceptron; Support vector machine; Coefficient of determination; Wavelet; Water quality; Artificial neural network; Mathematics; Computer science; Statistics; Data mining; Artificial intelligence","score_opus":0.057465348627744835,"score_gpt":0.3267794619525717,"score_spread":0.26931411332482685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200863083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67590255,0.005922471,0.2830529,0.0054910113,0.0005090468,0.00022704642,0.0015376332,0.00092065503,0.026436612],"genre_scores_gemma":[0.95617193,0.0013369938,0.04101117,0.0001514017,0.0000631633,0.000034481945,0.00044022905,0.000017934983,0.00077267876],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996146,0.00013333982,0.000029169889,0.000056698882,0.00013857507,0.000027578384],"domain_scores_gemma":[0.9978404,0.0012254983,0.00015468328,0.00013393005,0.000552948,0.00009246891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021718256,0.0008064647,0.00046556312,0.0005936923,0.00024039153,0.0020877388,0.000879199,0.0008414917,0.001525394],"category_scores_gemma":[0.004742669,0.00021812723,0.00053052977,0.0005433244,0.00042155018,0.0032465637,0.0007092773,0.0007891192,0.00017923772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009428183,0.00045839482,0.0223317,0.00036679348,0.0003422052,0.00013520643,0.000071476425,0.78901786,0.007815822,0.022784812,0.0017121892,0.15402082],"study_design_scores_gemma":[0.00001864476,0.0001787791,0.001372482,0.000018570761,0.000047456528,0.0000125137285,0.00004434763,0.98962736,0.0029384852,0.004696904,0.0010365687,0.000007890112],"about_ca_topic_score_codex":0.0057604974,"about_ca_topic_score_gemma":0.003862747,"teacher_disagreement_score":0.0057604974,"about_ca_system_score_codex":0.0008706171,"about_ca_system_score_gemma":0.00077060045,"threshold_uncertainty_score":0.011485875},"labels":[],"label_agreement":null},{"id":"W3201096577","doi":"10.1080/19942060.2021.1966837","title":"Prediction of daily water level using new hybridized GS-GMDH and ANFIS-FCM models","year":2021,"lang":"en","type":"article","venue":"Engineering Applications of Computational Fluid Mechanics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Adaptive neuro fuzzy inference system; Group method of data handling; Gene expression programming; Predictive modelling; Computer science; Inference system; Machine learning; Data mining; Performance prediction; Artificial intelligence; Fuzzy logic; Fuzzy control system; Simulation","score_opus":0.03838096721465623,"score_gpt":0.2193454625154982,"score_spread":0.18096449530084197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201096577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.366848,0.0008092264,0.62363374,0.00039757608,0.00013772752,0.00011291566,0.00043816655,0.0007481298,0.006874483],"genre_scores_gemma":[0.9660154,0.00017312902,0.031601816,0.000037204685,0.000014597798,0.00007557001,0.00018807266,0.00001133635,0.0018829028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981874,0.00003526341,0.000015188691,0.000052814008,0.00005743271,0.00002062581],"domain_scores_gemma":[0.9998166,0.00007841619,0.000026407339,0.000009283224,0.000061501574,0.000007753524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044411144,0.00072178734,0.00047084416,0.00043983076,0.00027722574,0.0005336544,0.0008269862,0.0007754896,0.00077667483],"category_scores_gemma":[0.0007674712,0.00028674497,0.0007741289,0.00035630373,0.00022643027,0.00044230386,0.0003274878,0.0006290951,0.00012984795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039405983,0.000035010056,0.0017017426,0.00004320704,0.000051194475,0.000064394815,0.00004727789,0.9724452,0.0024515893,0.0004409809,0.00018829058,0.022491563],"study_design_scores_gemma":[0.0000016044221,0.000011680487,0.00029646876,0.0000020645004,0.00000482009,0.000004613419,0.0000055773635,0.99918956,0.0002864745,0.00010367339,0.00009094635,0.0000025418046],"about_ca_topic_score_codex":0.019257493,"about_ca_topic_score_gemma":0.01700141,"teacher_disagreement_score":0.019257493,"about_ca_system_score_codex":0.0005321821,"about_ca_system_score_gemma":0.00042755785,"threshold_uncertainty_score":0.0382908},"labels":[],"label_agreement":null},{"id":"W3201799535","doi":"10.82308/10836","title":"An ensemble wavelet-based stochastic data-driven framework for addressing nonlinearity, multiscale change, and uncertainty in water resources forecasting","year":2018,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wavelet; Computer science; Nonlinear system; Econometrics; Environmental science; Artificial intelligence; Mathematics","score_opus":0.12472995756511546,"score_gpt":0.3068138932524248,"score_spread":0.18208393568730935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201799535","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00853137,0.00020970673,0.9903126,0.0001149827,0.000039306382,0.000008145082,0.000050617655,0.00009587495,0.00063740474],"genre_scores_gemma":[0.5857539,0.0015780227,0.4070769,0.00015870105,0.00021662364,0.0001247698,0.00052111264,0.00016135297,0.00440863],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996007,0.00013213641,0.000025360343,0.00006822003,0.00013347245,0.00004010793],"domain_scores_gemma":[0.999405,0.00025637544,0.0000674882,0.000051825005,0.00018484019,0.000034526718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014295699,0.00059996685,0.00079645973,0.00056665234,0.0002750105,0.00091581314,0.0012443821,0.0007789243,0.0009888696],"category_scores_gemma":[0.0023393966,0.00034212234,0.00093533634,0.00080858846,0.00040556295,0.0012571483,0.0009646372,0.0011361289,0.00023510982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032824537,0.000020883614,0.0007352726,0.000049436632,0.00006653441,0.00004695812,0.00004647934,0.9266242,0.0022190323,0.024374986,0.0006220872,0.04516131],"study_design_scores_gemma":[8.020102e-7,0.0000049152322,0.000047041663,0.0000017207717,0.000003571365,0.0000030543742,0.0000020414432,0.9981838,0.000105647705,0.0013980847,0.00024703066,0.0000023206383],"about_ca_topic_score_codex":0.006357709,"about_ca_topic_score_gemma":0.0048417896,"teacher_disagreement_score":0.006357709,"about_ca_system_score_codex":0.00055529835,"about_ca_system_score_gemma":0.001046174,"threshold_uncertainty_score":0.01264137},"labels":[],"label_agreement":null},{"id":"W3203095355","doi":"10.1007/s00521-021-06550-1","title":"Hybrid models for suspended sediment prediction: optimized random forest and multi-layer perceptron through genetic algorithm and stochastic gradient descent methods","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Random forest; Algorithm; Perceptron; Computer science; Sediment; Multilayer perceptron; Genetic algorithm; Environmental science; Machine learning; Geology; Artificial neural network; Geomorphology","score_opus":0.05147506452192749,"score_gpt":0.31854035814559517,"score_spread":0.2670652936236677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203095355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07428118,0.0011405895,0.9214354,0.00024192597,0.00015672347,0.0000484906,0.00018500524,0.0009511885,0.0015595296],"genre_scores_gemma":[0.768808,0.0004603998,0.22601311,0.00014708267,0.000119447664,0.00015072593,0.00035213717,0.00014387212,0.0038051475],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994517,0.00021787993,0.00003950139,0.00012401752,0.00010406684,0.000062803],"domain_scores_gemma":[0.9988696,0.0006479708,0.00009893604,0.00005747041,0.00028231868,0.00004366722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023903046,0.0009803417,0.0018678051,0.00089304394,0.00050074904,0.0010808252,0.0019259425,0.0016139462,0.0011471355],"category_scores_gemma":[0.002777843,0.00061440194,0.0012614904,0.001264337,0.0004928591,0.0018041142,0.00063979725,0.0012558977,0.00038553672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092076145,0.00006310198,0.0005492529,0.000027221837,0.00006930264,0.000018515691,0.000012898699,0.97440547,0.00038866137,0.0012899328,0.00032902695,0.02275452],"study_design_scores_gemma":[0.000003391214,0.0000063429975,0.00004484789,0.0000010750182,0.00000382281,0.0000014754221,6.854901e-7,0.9996117,0.000058346315,0.0002442288,0.000022271528,0.000001957706],"about_ca_topic_score_codex":0.02123355,"about_ca_topic_score_gemma":0.020687435,"teacher_disagreement_score":0.02123355,"about_ca_system_score_codex":0.00089520524,"about_ca_system_score_gemma":0.0011792049,"threshold_uncertainty_score":0.042219937},"labels":[],"label_agreement":null},{"id":"W3206247424","doi":"10.1016/j.jglr.2021.09.011","title":"Linking multi-media modeling with machine learning to assess and predict lake chlorophyll a concentrations","year":2021,"lang":"en","type":"article","venue":"Journal of Great Lakes Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Department of Education","keywords":"Eutrophication; Environmental science; Chlorophyll a; Agriculture; Weather Research and Forecasting Model; Hydrology (agriculture); Climate change; Nutrient; Meteorology; Ecology; Geography","score_opus":0.11586411586120902,"score_gpt":0.3420888776879861,"score_spread":0.2262247618267771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206247424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68427354,0.0009824922,0.3045224,0.001634236,0.000550024,0.00009743264,0.0011583501,0.0021545258,0.004626971],"genre_scores_gemma":[0.9733881,0.00014104777,0.02501837,0.000084746614,0.000111940564,0.00003232872,0.00036662127,0.000028023946,0.0008286842],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972016,0.00008353753,0.00002774878,0.000085576496,0.0000453658,0.000037489677],"domain_scores_gemma":[0.9974999,0.0019178047,0.00017005722,0.00012139517,0.00022278092,0.00006798381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011686176,0.0009486218,0.00055739743,0.0016460598,0.0004680708,0.0017146416,0.00074276864,0.0012776338,0.0013387372],"category_scores_gemma":[0.0038129722,0.00045961075,0.0009979559,0.001020008,0.0003243777,0.0016641137,0.0007579507,0.0012357662,0.00035688098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020311274,0.0006581556,0.01798512,0.000052574247,0.00029909587,0.000077946774,0.00004171279,0.9191167,0.0026834123,0.00085389626,0.0008125552,0.05721566],"study_design_scores_gemma":[0.0000025117106,0.000006729486,0.0005076179,0.0000013896565,0.000008776377,0.0000020291086,0.0000032097953,0.9987154,0.00037255645,0.00034301463,0.00003335618,0.0000034017846],"about_ca_topic_score_codex":0.0175728,"about_ca_topic_score_gemma":0.012862548,"teacher_disagreement_score":0.0175728,"about_ca_system_score_codex":0.0008524493,"about_ca_system_score_gemma":0.0006305318,"threshold_uncertainty_score":0.034941018},"labels":[],"label_agreement":null},{"id":"W3208354647","doi":"10.1130/abs/2021am-366854","title":"LONG-TERM MONITORING OF METHANE CONCENTRATIONS IN A SHALE AQUIFER USING TOTAL DISSOLVED GAS PRESSURE (P<sub>TDG</sub>) PROBES: COMPARISON WITH DATA FROM GROUNDWATER SAMPLES","year":2021,"lang":"en","type":"article","venue":"Abstracts with programs - Geological Society of America","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Aquifer; Methane; Groundwater; Shale gas; Environmental science; Oil shale; Hydrology (agriculture); Environmental chemistry; Hydraulic fracturing; Petroleum engineering; Geology; Chemistry; Geotechnical engineering","score_opus":0.07070069326532455,"score_gpt":0.294436065696329,"score_spread":0.22373537243100447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208354647","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9993761,0.000017896253,0.00025258338,0.000011464595,0.0000018491029,0.0000023097678,0.0001654785,0.000011571892,0.00016067324],"genre_scores_gemma":[0.999062,0.00001865953,0.0004541883,0.0000069522453,0.000002416207,0.000004651994,0.00026616635,0.0000022334332,0.00018283611],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99992263,0.000009116748,0.0000040828722,0.000028072696,0.000021515116,0.000014663361],"domain_scores_gemma":[0.99980897,0.000044918597,0.000033869557,0.000011537501,0.00006718341,0.000033542008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023451138,0.00016497105,0.00017296034,0.00034938595,0.00048690868,0.00022524834,0.00019779419,0.00037293998,0.00025008086],"category_scores_gemma":[0.00028175427,0.00012923822,0.0001514157,0.00035538577,0.0002186232,0.00033455627,0.00022837166,0.00023641312,0.000094837356],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012329194,0.0003485011,0.72349775,0.000043397995,0.000088398265,0.00028378965,0.00036890584,0.0030130115,0.2553205,0.00006381934,0.0002737977,0.0154651785],"study_design_scores_gemma":[0.000019928353,0.0003816794,0.95479673,0.0000039186025,0.000049923834,0.000118232,0.00023055023,0.012761666,0.031206746,0.00004052285,0.00037762107,0.000012440638],"about_ca_topic_score_codex":0.018382259,"about_ca_topic_score_gemma":0.03311848,"teacher_disagreement_score":0.018382259,"about_ca_system_score_codex":0.0004952982,"about_ca_system_score_gemma":0.00025682198,"threshold_uncertainty_score":0.03655052},"labels":[],"label_agreement":null},{"id":"W3210625331","doi":"10.5281/zenodo.4095485","title":"Models and Predictions for \"Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network\"","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Term (time); Surface runoff; Environmental science; Meteorology; Computer science; Geography; Physics; Ecology","score_opus":0.04872614810696903,"score_gpt":0.2259776562196659,"score_spread":0.17725150811269685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210625331","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008628219,0.0009373434,0.1211943,0.0055316426,0.0020569821,0.00046689704,0.70087993,0.08479429,0.07551045],"genre_scores_gemma":[0.04846598,0.001184886,0.0861923,0.0014670889,0.00052406115,0.0010273572,0.7700891,0.019685127,0.0713641],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994005,0.000094124065,0.000045196077,0.00012696616,0.00027685743,0.000056325367],"domain_scores_gemma":[0.9989195,0.0002853099,0.000057015255,0.00024322713,0.00041699372,0.000077995006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012707562,0.0013288005,0.0006338324,0.00074673386,0.0004761685,0.0014798859,0.003001121,0.0016502441,0.10916952],"category_scores_gemma":[0.004130836,0.00079148664,0.0021401523,0.001431231,0.0002103182,0.0028628064,0.0014813923,0.0016257261,0.059502628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013965419,0.000070616275,0.0016471511,0.00041474722,0.00014768777,0.000060932474,0.0000411828,0.040107958,0.0010971392,0.007078248,0.9130743,0.036120355],"study_design_scores_gemma":[0.0004808624,0.00008677528,0.0046345987,0.0002516543,0.00015395661,0.00008862807,0.00007018356,0.26332408,0.00983996,0.024695527,0.6962452,0.00012855389],"about_ca_topic_score_codex":0.019816611,"about_ca_topic_score_gemma":0.016834304,"teacher_disagreement_score":0.10916952,"about_ca_system_score_codex":0.0011380928,"about_ca_system_score_gemma":0.0016931753,"threshold_uncertainty_score":0.3652084},"labels":[],"label_agreement":null},{"id":"W3210637362","doi":"10.1080/19942060.2021.1984992","title":"Artificial intelligence models for suspended river sediment prediction: state-of-the art, modeling framework appraisal, and proposed future research directions","year":2021,"lang":"en","type":"article","venue":"Engineering Applications of Computational Fluid Mechanics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Sediment; State (computer science); Marine engineering; Computer science; Environmental science; Engineering; Civil engineering; Artificial intelligence; Systems engineering; Hydrology (agriculture); Industrial engineering; Geology; Geotechnical engineering; Algorithm; Geomorphology","score_opus":0.03667051293614566,"score_gpt":0.2946404930902507,"score_spread":0.25796998015410505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210637362","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043094945,0.9229881,0.056303114,0.008032783,0.0006658489,0.000047087648,0.00009637684,0.00015415331,0.007403065],"genre_scores_gemma":[0.041590266,0.92392683,0.030502915,0.0007693631,0.0012426745,0.00010615888,0.0002199099,0.00002637292,0.001615431],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993349,0.00023870952,0.00007153061,0.00011021696,0.0001913687,0.00005342904],"domain_scores_gemma":[0.9972717,0.0018702042,0.00017241004,0.00008413428,0.0005284091,0.000073092866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032753758,0.0010386583,0.001247782,0.0022028752,0.00037987204,0.0031522976,0.0018666871,0.001565434,0.0018471887],"category_scores_gemma":[0.004445815,0.00045809735,0.0009452556,0.003226837,0.0010611321,0.003934144,0.0011372534,0.0023845942,0.0006621453],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013492559,0.00024416193,0.0028911352,0.010278096,0.0002636359,0.0002927346,0.00043806288,0.071303494,0.0012668434,0.15957023,0.01488009,0.7384365],"study_design_scores_gemma":[0.00003862384,0.0005128765,0.003618212,0.011135395,0.0005400668,0.00044092882,0.001123466,0.38470334,0.0019581248,0.29602933,0.29966396,0.00023569773],"about_ca_topic_score_codex":0.0032863163,"about_ca_topic_score_gemma":0.002376121,"teacher_disagreement_score":0.0032863163,"about_ca_system_score_codex":0.0011265938,"about_ca_system_score_gemma":0.0019005139,"threshold_uncertainty_score":0.017322063},"labels":[],"label_agreement":null},{"id":"W3210924576","doi":"","title":"Modelling Phosphorous Dynamics in a Wastewater Treatment Process using Bayesian Optimized LSTM","year":2021,"lang":"en","type":"article","venue":"Computers & Chemical Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kruger (Canada)","funders":"","keywords":"Bayesian probability; Dynamics (music); Wastewater; Process (computing); Process dynamics; Environmental science; Process engineering; Computer science; Sewage treatment; Artificial intelligence; Biological system; Biochemical engineering; Environmental engineering; Engineering; Physics; Biology","score_opus":0.01323797244743977,"score_gpt":0.2094156358640411,"score_spread":0.19617766341660134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210924576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69275147,0.00062725466,0.29862908,0.0009130354,0.0001489121,0.000044843902,0.00043754678,0.0007637097,0.0056842566],"genre_scores_gemma":[0.9922328,0.00009949825,0.006062329,0.00004367183,0.000012798283,0.000018395707,0.00008742762,0.000015733844,0.0014273435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999212,0.000014276315,0.000005870767,0.000026922315,0.000016285803,0.000015458341],"domain_scores_gemma":[0.99975973,0.00014454675,0.000031151296,0.0000084057865,0.000042249518,0.000013973677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028388825,0.00039696743,0.0005681387,0.0002190409,0.00030451978,0.0006390185,0.0006757849,0.0012355815,0.00086083426],"category_scores_gemma":[0.0008208745,0.00039345497,0.00044616734,0.0004458616,0.000452115,0.0008962644,0.00041717995,0.0008546799,0.00011003447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051905783,0.000024370338,0.0007412254,0.000023929966,0.00001732282,0.000022986444,0.000016271653,0.9922463,0.0024540664,0.0006071422,0.00011346924,0.0036810292],"study_design_scores_gemma":[0.0000023259038,0.0000033939016,0.00010661436,6.1601054e-7,0.0000016376141,0.0000013695508,0.0000015833689,0.9994293,0.00024513993,0.00018349262,0.000022454915,0.0000020724754],"about_ca_topic_score_codex":0.030729007,"about_ca_topic_score_gemma":0.016564328,"teacher_disagreement_score":0.030729007,"about_ca_system_score_codex":0.00085388124,"about_ca_system_score_gemma":0.0009945645,"threshold_uncertainty_score":0.061100245},"labels":[],"label_agreement":null},{"id":"W3211473442","doi":"10.1002/essoar.10508682.1","title":"DataStream's open data platform for sharing water quality data","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Walter and Duncan Gordon Foundation","funders":"","keywords":"World Wide Web; Computer science","score_opus":0.4522586006995949,"score_gpt":0.4265716329436709,"score_spread":0.025686967755923995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211473442","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044583385,0.00067324034,0.13115378,0.006890806,0.0013653917,0.001243035,0.6086036,0.14073928,0.10487251],"genre_scores_gemma":[0.042134315,0.001514778,0.17556272,0.0028515076,0.00043127962,0.0023209814,0.7198141,0.02863262,0.026737686],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9914738,0.0013179693,0.0013074172,0.001075926,0.004277353,0.0005474683],"domain_scores_gemma":[0.9701811,0.006962115,0.0014149771,0.012017646,0.00743694,0.001987114],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008353144,0.0010831553,0.0011395209,0.006504131,0.0014272206,0.00715873,0.004565884,0.002546747,0.04671489],"category_scores_gemma":[0.052406874,0.0010403066,0.0016004515,0.01623529,0.0014852732,0.009370331,0.007844031,0.003788582,0.032381784],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031994405,0.00007830127,0.003975555,0.0007396326,0.00015063917,0.00023520723,0.0007406374,0.0030252128,0.0030366362,0.05278775,0.87689435,0.05801614],"study_design_scores_gemma":[0.000102743696,0.000017762215,0.003163214,0.00025491253,0.000033931203,0.00012276611,0.00021797232,0.004335021,0.0031854208,0.027589375,0.9608476,0.00012935215],"about_ca_topic_score_codex":0.07267978,"about_ca_topic_score_gemma":0.065973885,"teacher_disagreement_score":0.9954341,"about_ca_system_score_codex":0.004712421,"about_ca_system_score_gemma":0.014478499,"threshold_uncertainty_score":0.15627694},"labels":[],"label_agreement":null},{"id":"W3216089282","doi":"10.5194/egusphere-egu21-3865","title":"GRQA: Global River Water Quality Archive","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Water quality; Environmental science; Metadata; Computer science; Hydrology (agriculture); Biology; Ecology; Geography; Engineering; Cartography","score_opus":0.0260401201035814,"score_gpt":0.27438303225716054,"score_spread":0.24834291215357915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216089282","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056265434,0.00011569943,0.0030753992,0.0006652346,0.00012071119,0.000116833726,0.96984476,0.0077753337,0.017723499],"genre_scores_gemma":[0.0048912507,0.0002905874,0.008230181,0.00040763125,0.000048033722,0.00027318264,0.97288674,0.002513664,0.010458619],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998415,0.00013035974,0.00017358163,0.00023399299,0.000895377,0.00015170367],"domain_scores_gemma":[0.9872292,0.0006769543,0.00064209837,0.0023653007,0.008383464,0.0007029802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027344846,0.0008176908,0.0008923226,0.0042630513,0.0008190868,0.0026948382,0.0037105267,0.0010290076,0.07047127],"category_scores_gemma":[0.009669486,0.00055304135,0.0004647116,0.009874386,0.0005594986,0.0022726473,0.0019407277,0.0019626953,0.050749317],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036149897,0.000013139857,0.0012215558,0.00018610262,0.000016016304,0.00002316079,0.00004181058,0.00074571325,0.00024193553,0.0017373459,0.9741931,0.021544045],"study_design_scores_gemma":[0.000052832373,0.0000064474075,0.0052043283,0.000096335876,0.000008398842,0.000019593821,0.000054042568,0.0016029091,0.000494015,0.0019713456,0.99045897,0.00003067236],"about_ca_topic_score_codex":0.33822966,"about_ca_topic_score_gemma":0.2624421,"teacher_disagreement_score":0.33822966,"about_ca_system_score_codex":0.0038572743,"about_ca_system_score_gemma":0.012991103,"threshold_uncertainty_score":0.6725219},"labels":[],"label_agreement":null},{"id":"W38598497","doi":"10.1007/978-3-540-79881-1_28","title":"Toward Bridging the Gap Between Data-Driven and Mechanistic Models: Cluster-Based Neural Networks for Hydrologic Processes","year":2008,"lang":"en","type":"book-chapter","venue":"Water science and technology library","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Artificial neural network; Modular design; Cluster analysis; Evapotranspiration; Computer science; Wind speed; Bridging (networking); Data mining; Field (mathematics); Artificial intelligence; Machine learning; Meteorology; Geography; Mathematics","score_opus":0.07099230902344184,"score_gpt":0.22870979274723008,"score_spread":0.15771748372378824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W38598497","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051904772,0.009735264,0.97336686,0.0021302772,0.0003782061,0.000018112078,0.00018777528,0.0006172185,0.008375854],"genre_scores_gemma":[0.22574048,0.027396461,0.7195342,0.0007977823,0.00087660155,0.00014421421,0.00079855346,0.000644965,0.024066623],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999008,0.000026486998,0.000006004469,0.000021400867,0.000039813523,0.000005548187],"domain_scores_gemma":[0.99950826,0.00033244633,0.000016477552,0.000043801738,0.00008645369,0.000012495929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006643248,0.00060330326,0.00047281274,0.00034606815,0.00018915927,0.0011072351,0.0012509992,0.00084134494,0.0021269165],"category_scores_gemma":[0.002192008,0.00050842663,0.0003542131,0.0010657752,0.0005995133,0.002095838,0.00068033644,0.0025174685,0.0007316069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047164216,0.0000614271,0.000470426,0.00032873097,0.000119695156,0.00004588093,0.0001436157,0.48858455,0.0017332523,0.1776598,0.028510617,0.3022949],"study_design_scores_gemma":[0.0000036253414,0.000005713736,0.00009971268,0.000020686113,0.000009634314,0.000009550372,0.000008251533,0.9009048,0.00044883136,0.091990344,0.0064917766,0.0000071511113],"about_ca_topic_score_codex":0.0062580267,"about_ca_topic_score_gemma":0.007844298,"teacher_disagreement_score":0.0062580267,"about_ca_system_score_codex":0.00059899985,"about_ca_system_score_gemma":0.00065129646,"threshold_uncertainty_score":0.012443244},"labels":[],"label_agreement":null},{"id":"W4200112963","doi":"10.18280/ijdne.160605","title":"Optimization of the Nonlinear Muskingum Model Parameters for the River Routing, Tigris River a Case Study","year":2021,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Particle swarm optimization; Harmony search; Flood myth; Computer science; Mathematical optimization; Genetic algorithm; Inflow; Mathematics; Meteorology; Geography","score_opus":0.021025887164942376,"score_gpt":0.26635967458730403,"score_spread":0.24533378742236164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200112963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9327805,0.00028625265,0.053575814,0.00038512304,0.000039965827,0.0000783992,0.00037792197,0.00020225196,0.012273848],"genre_scores_gemma":[0.9921874,0.0000805196,0.006080965,0.000009839097,0.0000032114965,0.000033057437,0.00010603378,0.000008007395,0.0014910077],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999895,0.000036340065,0.0000055857104,0.000019544705,0.000017861117,0.00002568721],"domain_scores_gemma":[0.9996439,0.00022802972,0.000036023124,0.00001417069,0.0000630714,0.00001483469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004733521,0.0006626826,0.0004336656,0.0005558989,0.00051963417,0.00074138015,0.00052915735,0.0010000474,0.001424437],"category_scores_gemma":[0.0009791408,0.00025630608,0.0005619041,0.00056817255,0.00030853215,0.00034614204,0.00038926268,0.00049081247,0.000104047416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022513115,0.00002691737,0.0018222725,0.000032819775,0.000011252163,0.00018517081,0.000028673456,0.99208623,0.00067671743,0.0006771781,0.00025795383,0.0041723675],"study_design_scores_gemma":[0.000007186266,0.000037601236,0.0012070755,0.000003938677,0.00001236883,0.000020005798,0.000052176678,0.997675,0.0004946784,0.00021472333,0.00026854625,0.000006646476],"about_ca_topic_score_codex":0.050749257,"about_ca_topic_score_gemma":0.04369806,"teacher_disagreement_score":0.050749257,"about_ca_system_score_codex":0.0011151651,"about_ca_system_score_gemma":0.001046472,"threshold_uncertainty_score":0.10090768},"labels":[],"label_agreement":null},{"id":"W4200255958","doi":"10.36334/modsim.2021.f5.khaiter","title":"An ML-based study of extreme weather events incorporating seasonality factor","year":2021,"lang":"en","type":"article","venue":"MODSIM2021, 24th International Congress on Modelling and Simulation.","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Mitacs","keywords":"Seasonality; Factor (programming language); Climatology; Meteorology; Computer science; Environmental science; Geography; Geology; Machine learning","score_opus":0.0952116341694376,"score_gpt":0.3202766622103635,"score_spread":0.22506502804092587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200255958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73123264,0.00025252553,0.26255018,0.00038590727,0.000060775976,0.00006180304,0.00069125055,0.0004743864,0.004290615],"genre_scores_gemma":[0.98347247,0.00005076211,0.0154092545,0.000018667359,0.00004468442,0.000018657089,0.0005339359,0.000019834606,0.00043164115],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947256,0.000238002,0.000039674112,0.000102741484,0.00009000318,0.000057032077],"domain_scores_gemma":[0.99691665,0.0021292188,0.00024850207,0.00016771936,0.00040602102,0.00013190281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019312808,0.00032366352,0.00045535408,0.0012874483,0.00026919207,0.0011344797,0.00059584476,0.00043838017,0.0011966547],"category_scores_gemma":[0.007629896,0.00021317496,0.00033848744,0.0014728239,0.0002666352,0.0015716194,0.00071362907,0.00062811706,0.0002848602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027679524,0.00017276382,0.09348746,0.0000647253,0.00015353275,0.00021091333,0.00013694049,0.826349,0.003346046,0.0053092656,0.00082472665,0.06966786],"study_design_scores_gemma":[0.0000033929362,0.000018202423,0.004920752,0.0000018872254,0.0000060646835,0.0000130624285,0.000020960815,0.99447167,0.00017164338,0.00026048906,0.00010761233,0.0000042181778],"about_ca_topic_score_codex":0.006215184,"about_ca_topic_score_gemma":0.004283107,"teacher_disagreement_score":0.006215184,"about_ca_system_score_codex":0.00036625282,"about_ca_system_score_gemma":0.00037707275,"threshold_uncertainty_score":0.01235801},"labels":[],"label_agreement":null},{"id":"W4200395259","doi":"10.1002/essoar.10509206.1","title":"Estimating the Autotrophic and Heterotrophic Respiration in the US Crop Fields using Knowledge Guided Machine Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Email authentication; Electronic mail; World Wide Web; Computer science; Operating system; Key (lock)","score_opus":0.0651660042421012,"score_gpt":0.30677415974242167,"score_spread":0.24160815550032047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200395259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9730248,0.0001240924,0.02585128,0.00009944277,0.000005736617,0.000010882906,0.00020962024,0.00023971459,0.0004344704],"genre_scores_gemma":[0.9915358,0.000027941018,0.00813627,0.0000130992275,0.000002187627,0.000007395983,0.00017289504,0.0000049642113,0.00009935887],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999411,0.000014917978,0.0000033986464,0.00002457636,0.0000074382856,0.000008575944],"domain_scores_gemma":[0.99973005,0.00015589794,0.00004036401,0.000019715833,0.000039022503,0.000014901095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040105186,0.0004460638,0.00022300902,0.0004797454,0.0002053849,0.00023509815,0.00035061338,0.00052345276,0.00023271723],"category_scores_gemma":[0.001016923,0.000248995,0.00034237764,0.00031396287,0.00026310835,0.0005477087,0.00016586535,0.0003070169,0.000047458998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023192031,0.00003414246,0.009912651,0.000008888901,0.000018512143,0.00002189571,0.000011765722,0.97733235,0.0014525326,0.00010573135,0.00010329401,0.010975104],"study_design_scores_gemma":[0.0000019272954,0.000005446137,0.0025701737,0.0000010917805,0.0000019689944,0.0000021433793,0.0000029197397,0.99687934,0.00038889155,0.00012073574,0.000023072462,0.0000022731756],"about_ca_topic_score_codex":0.043508522,"about_ca_topic_score_gemma":0.046243966,"teacher_disagreement_score":0.043508522,"about_ca_system_score_codex":0.0008334221,"about_ca_system_score_gemma":0.0005882123,"threshold_uncertainty_score":0.08651054},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4200408794","doi":"10.3808/jeil.202100074","title":"Outdoor Relative Humidity Prediction via Machine Learning Techniques","year":2021,"lang":"en","type":"article","venue":"Journal of Environmental Informatics Letters","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Machine learning; Support vector machine; Random forest; Artificial intelligence; Relative humidity; Perceptron; Computer science; Multilayer perceptron; Algorithm; Artificial neural network; Meteorology; Geography","score_opus":0.00956195999105344,"score_gpt":0.20322226066246793,"score_spread":0.1936603006714145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200408794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19195606,0.0012759089,0.79629797,0.0003358853,0.00016291295,0.000050981675,0.0003539667,0.0026749007,0.006891419],"genre_scores_gemma":[0.9328525,0.0003444558,0.06451843,0.00004183013,0.00007199428,0.000038514263,0.00024916756,0.000035558205,0.0018475305],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998462,0.000030413248,0.000010378817,0.000047837086,0.00004621709,0.000018864917],"domain_scores_gemma":[0.99973947,0.00013995019,0.00003771766,0.000019329034,0.0000559085,0.000007665344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029943843,0.000452318,0.00036772486,0.00075036834,0.0001744751,0.0004763585,0.00038466518,0.00043382004,0.0009591756],"category_scores_gemma":[0.0010976242,0.00015664517,0.0003833806,0.000703571,0.00013343795,0.00056963717,0.00023108105,0.00047671443,0.00039334883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086686494,0.00009799858,0.0058762827,0.00009695019,0.00006715467,0.000077126075,0.00004653323,0.6202589,0.008730571,0.0014127208,0.0015505021,0.3616985],"study_design_scores_gemma":[0.0000015069819,0.000009474041,0.0007997531,0.0000037829163,0.0000035049475,0.000008356077,0.000003990548,0.9975079,0.0010654374,0.0003780918,0.00021527517,0.000002748977],"about_ca_topic_score_codex":0.004947394,"about_ca_topic_score_gemma":0.0039721266,"teacher_disagreement_score":0.004947394,"about_ca_system_score_codex":0.00026926087,"about_ca_system_score_gemma":0.0002957636,"threshold_uncertainty_score":0.00983721},"labels":[],"label_agreement":null},{"id":"W4205286591","doi":"10.5351/kjas.2003.16.1.015","title":"Exploratory Analysis of Bioindex Data : Based on a Data Set from take Ontario","year":2003,"lang":"en","type":"article","venue":"Korean Journal of Applied Statistics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Correlogram; Variogram; Data set; Exploratory data analysis; Construct (python library); Set (abstract data type); Statistics; Component (thermodynamics); Geography; Econometrics; Computer science; Mathematics; Kriging","score_opus":0.09014663671023815,"score_gpt":0.27856668418239705,"score_spread":0.1884200474721589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205286591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98788995,0.000060969476,0.0010699675,0.000083850944,0.000004028259,0.00006574792,0.009106989,0.00007182562,0.0016467554],"genre_scores_gemma":[0.9762284,0.00010190315,0.004213425,0.00001608085,0.000005703438,0.0001076008,0.017759526,0.000016907692,0.0015503708],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99962604,0.000049454025,0.000026643256,0.000053868513,0.00017032708,0.00007359849],"domain_scores_gemma":[0.99811137,0.0005504424,0.00019689478,0.00018128302,0.00082648173,0.00013348245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004585712,0.00034829412,0.0002504815,0.0016025108,0.0008280658,0.00035967678,0.00037286812,0.0002027815,0.0011294548],"category_scores_gemma":[0.0026320557,0.00008650377,0.00030386553,0.0028269796,0.00036640352,0.00023272056,0.00047813318,0.00020344404,0.00018561506],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043865328,0.00020665908,0.91847795,0.00025537636,0.00015929464,0.0014034549,0.00432661,0.009878697,0.010207237,0.00073280843,0.0047485824,0.049164474],"study_design_scores_gemma":[0.000015634647,0.00007767148,0.979544,0.000019912904,0.000041821255,0.00013541935,0.0023729152,0.0085462835,0.0023741003,0.00017014315,0.0066707353,0.000031455224],"about_ca_topic_score_codex":0.68492377,"about_ca_topic_score_gemma":0.8792186,"teacher_disagreement_score":0.31507623,"about_ca_system_score_codex":0.0031979126,"about_ca_system_score_gemma":0.0034132572,"threshold_uncertainty_score":0.63386357},"labels":[],"label_agreement":null},{"id":"W4206622911","doi":"10.31807/tjwsm.831510","title":"A Flexible Water Quality Modelling Simulator Based on Matrix Algebra","year":2021,"lang":"en","type":"article","venue":"Turkish Journal of Water Science and Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Computer science; Water quality; Quality (philosophy); Software; Readability; Watershed; Component (thermodynamics); Simulation; Ecology; Machine learning","score_opus":0.031102698944948444,"score_gpt":0.28027912305093133,"score_spread":0.2491764241059829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206622911","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037178468,0.00014460685,0.92332673,0.0002458816,0.00014757601,0.00019491164,0.002989006,0.019640576,0.016132168],"genre_scores_gemma":[0.4860953,0.00045625214,0.486627,0.00018272376,0.000067448214,0.0008470037,0.006766428,0.0028463213,0.016111363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977046,0.000041171676,0.000020122885,0.000043230953,0.00009745424,0.000027517684],"domain_scores_gemma":[0.999688,0.000104818355,0.000022863742,0.000059298043,0.00008990787,0.00003509837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040861047,0.0005011246,0.0005135941,0.00040468937,0.000410752,0.00087348884,0.0014639845,0.0007311685,0.008230386],"category_scores_gemma":[0.0009825302,0.00037618648,0.00082064926,0.0006152768,0.0002968815,0.0010632125,0.000938432,0.001210363,0.0016895424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018223819,0.00016517004,0.0022627444,0.00020189634,0.00009483615,0.00023641471,0.00020674962,0.8830957,0.022073021,0.03592207,0.008746887,0.04681233],"study_design_scores_gemma":[0.000034927278,0.000019216848,0.00019432219,0.0000054421457,0.00000839802,0.000034491568,0.000007278744,0.9809229,0.0029256763,0.004893758,0.010940522,0.000013024537],"about_ca_topic_score_codex":0.006073715,"about_ca_topic_score_gemma":0.0038074267,"teacher_disagreement_score":0.008230386,"about_ca_system_score_codex":0.00047010975,"about_ca_system_score_gemma":0.001212519,"threshold_uncertainty_score":0.027533412},"labels":[],"label_agreement":null},{"id":"W4206850381","doi":"10.5194/hessd-3-201-2006","title":"Classification of heterogeneous precipitation fields for the assessment and possible improvement of lumped neural network models for streamflow forecasts","year":2006,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Coquitlam College; Université Laval; Golder Associates (Canada)","funders":"","keywords":"Orography; Precipitation; Artificial neural network; Surface runoff; Watershed; Environmental science; Streamflow; Rain gauge; Self-organizing map; Multilayer perceptron; Computer science; Meteorology; Perceptron; Machine learning; Geography; Cartography; Drainage basin","score_opus":0.0496349882062638,"score_gpt":0.2980658775427348,"score_spread":0.24843088933647098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206850381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34274364,0.00037877675,0.65345794,0.00021294931,0.000094512434,0.00009448612,0.00031426965,0.00092456595,0.0017789636],"genre_scores_gemma":[0.94507694,0.000065538385,0.053736158,0.000027731334,0.000019186306,0.000047078564,0.00018530228,0.00001618863,0.00082593906],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997098,0.00010932184,0.000025826972,0.00006483644,0.0000678105,0.000022317408],"domain_scores_gemma":[0.9991892,0.0004302806,0.0000863247,0.00012132971,0.00013954764,0.000033196433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013092839,0.0004231062,0.00053145067,0.00057917077,0.00018242226,0.00068762404,0.00046519155,0.00038405295,0.0012597247],"category_scores_gemma":[0.0032443746,0.00016921977,0.0003145339,0.00060630706,0.00020711683,0.0012088312,0.0004934968,0.00045798818,0.00016290361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001766532,0.00010393179,0.004171953,0.00005506547,0.00008268828,0.00003121137,0.000036534915,0.8766404,0.005029155,0.0014558255,0.00041643606,0.11180015],"study_design_scores_gemma":[0.0000021326439,0.00000851312,0.00043859432,0.0000016017858,0.0000035407977,0.0000017309195,0.0000027045232,0.99855286,0.00050365477,0.0004288347,0.000053804826,0.000001946797],"about_ca_topic_score_codex":0.0034947877,"about_ca_topic_score_gemma":0.004754884,"teacher_disagreement_score":0.0034947877,"about_ca_system_score_codex":0.0006118562,"about_ca_system_score_gemma":0.000286312,"threshold_uncertainty_score":0.0069488883},"labels":[],"label_agreement":null},{"id":"W4210738948","doi":"10.3390/w14030463","title":"Regression Tree Ensemble Rainfall–Runoff Forecasting Model and Its Application to Xiangxi River, China","year":2022,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Ensemble forecasting; Artificial neural network; Ensemble learning; Decision tree; Linear regression; Regression; Regression analysis; Computer science; Random forest; Statistics; Data mining; Artificial intelligence; Machine learning; Mathematics","score_opus":0.022227970357040217,"score_gpt":0.2280380268121621,"score_spread":0.20581005645512188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210738948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7085792,0.0010881895,0.28366596,0.0004889526,0.00009521933,0.00004579487,0.00036433135,0.00066539075,0.00500702],"genre_scores_gemma":[0.98580706,0.00041515578,0.01213465,0.000020324811,0.00001785412,0.000036197045,0.00020414416,0.000017689179,0.0013469199],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985266,0.000037497364,0.000010865138,0.000038964623,0.00003574091,0.000024247065],"domain_scores_gemma":[0.9998267,0.00006697184,0.00002039501,0.000012213449,0.00006133778,0.000012376536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005913641,0.0003835235,0.0006236251,0.00044965884,0.0003354496,0.00044246326,0.0005548346,0.0004813993,0.0007459159],"category_scores_gemma":[0.0009183602,0.00020365286,0.00054507423,0.00083706045,0.00010367492,0.00059532875,0.00032721818,0.00038979627,0.0000929869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023789844,0.00002536273,0.0028975704,0.00001757115,0.000033593205,0.000057150508,0.000023685596,0.973436,0.0004949633,0.0005358699,0.00031150185,0.022142915],"study_design_scores_gemma":[0.0000010537689,0.0000050285066,0.00032481222,7.505393e-7,0.000004072212,0.0000023798423,0.000002631453,0.99945515,0.00005190754,0.00009298964,0.000057842084,0.0000013840148],"about_ca_topic_score_codex":0.040881366,"about_ca_topic_score_gemma":0.021321883,"teacher_disagreement_score":0.040881366,"about_ca_system_score_codex":0.0004460623,"about_ca_system_score_gemma":0.00090870174,"threshold_uncertainty_score":0.08128685},"labels":[],"label_agreement":null},{"id":"W4210928746","doi":"10.20944/preprints202202.0101.v1","title":"A Comprehensive Study Of Artificial Intelligence Applications For Soil Temperature Prediction","year":2022,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Research Council Canada","keywords":"Gradient boosting; Ranging; Multilayer perceptron; Boosting (machine learning); Perceptron; Random forest; Range (aeronautics); Environmental science; Computer science; Artificial neural network; Machine learning; Predictive modelling; Artificial intelligence; Meteorology; Engineering; Geography","score_opus":0.17482731003953764,"score_gpt":0.3628125707809841,"score_spread":0.18798526074144647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210928746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09518403,0.19215365,0.6493893,0.0064905924,0.0011463779,0.00011783639,0.0004942597,0.0006350995,0.05438885],"genre_scores_gemma":[0.736715,0.1261062,0.12682995,0.00077252096,0.0013971361,0.0001079356,0.0005190859,0.00010940513,0.007442795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946815,0.0001635323,0.00003733866,0.0001079078,0.00019591395,0.000027266664],"domain_scores_gemma":[0.9986488,0.00089635706,0.0000833048,0.00008213986,0.00026452486,0.000024850602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093760894,0.0006750424,0.00043072336,0.00081692333,0.00023220657,0.0010748632,0.0004151689,0.0006606313,0.00096831407],"category_scores_gemma":[0.0032790068,0.00023502286,0.00076472876,0.0021809507,0.00041180666,0.0012156039,0.00044299904,0.00125873,0.00031698254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007108973,0.0001404091,0.0090721045,0.0015358127,0.00031724045,0.00023724457,0.00015800715,0.26944295,0.006019095,0.05695562,0.0069714403,0.64907897],"study_design_scores_gemma":[0.000010748394,0.00021187178,0.012600665,0.0005138843,0.00014463688,0.00028279936,0.00012909573,0.8608427,0.007211108,0.060034905,0.057954147,0.0000634461],"about_ca_topic_score_codex":0.001944274,"about_ca_topic_score_gemma":0.0010976221,"teacher_disagreement_score":0.001944274,"about_ca_system_score_codex":0.00039148662,"about_ca_system_score_gemma":0.0004117478,"threshold_uncertainty_score":0.0049586296},"labels":[],"label_agreement":null},{"id":"W4220766923","doi":"10.21203/rs.3.rs-1377902/v1","title":"Multilayer Perceptron-based Predictive Model for the Reconstruction of Missing Rainfall Data","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Korea Meteorological Administration; Chung-Ang University","keywords":"Missing data; Standard deviation; Multilayer perceptron; Statistics; Artificial neural network; Rain gauge; Mean squared error; Confusion matrix; Computer science; Data mining; Mathematics; Artificial intelligence; Radar","score_opus":0.2461490091125643,"score_gpt":0.42563049369822076,"score_spread":0.17948148458565646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220766923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13201131,0.0010397604,0.8615903,0.0004394805,0.00015312003,0.00006720766,0.00034502312,0.0011382175,0.003215592],"genre_scores_gemma":[0.9797992,0.00029867238,0.017806645,0.000054296608,0.000032277818,0.000085407606,0.00016716273,0.000019018305,0.0017372654],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994267,0.00017155625,0.000050978284,0.00013731464,0.000119497,0.000093979696],"domain_scores_gemma":[0.9990711,0.00053228217,0.000115570096,0.000038939994,0.00021624038,0.000025842393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019485562,0.0007454047,0.0010222543,0.00091646035,0.00040178525,0.0009034197,0.0013370259,0.00089962897,0.0015860255],"category_scores_gemma":[0.0033121833,0.00048034417,0.0008284564,0.0009659856,0.00046628522,0.00097606203,0.0006089955,0.0012860047,0.00027550414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007167995,0.000038451653,0.0012599152,0.000043485914,0.00005099985,0.00005520229,0.000025809875,0.98171026,0.00049722684,0.0010457513,0.00029741356,0.014903838],"study_design_scores_gemma":[0.0000013611808,0.0000055540227,0.000111220055,0.0000023483772,0.0000038221738,0.0000025466659,0.0000014712358,0.9995846,0.000058901118,0.000202266,0.00002420926,0.0000017033918],"about_ca_topic_score_codex":0.019760847,"about_ca_topic_score_gemma":0.0100582875,"teacher_disagreement_score":0.019760847,"about_ca_system_score_codex":0.0009608196,"about_ca_system_score_gemma":0.0010417089,"threshold_uncertainty_score":0.03929168},"labels":[],"label_agreement":null},{"id":"W4220799888","doi":"10.21203/rs.3.rs-1495339/v1","title":"Physics-Informed Data-driven Model for Predicting Streamflows: A Case Study of the Voshmgir Basin, Iran","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bedford Institute of Oceanography; University of Guelph","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Surface runoff; Field (mathematics); Water resources; Hydrological modelling; Structural basin; Computer science; Environmental science; Hydrology (agriculture); Predictive modelling; Meteorology; Support vector machine; Drainage basin; Runoff curve number; Climatology; Machine learning; Geography; Cartography; Mathematics; Engineering; Geology; Watershed","score_opus":0.26670572536560866,"score_gpt":0.432126320104211,"score_spread":0.16542059473860232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220799888","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9835112,0.00015081429,0.012988154,0.00046312434,0.000032585347,0.000052425512,0.0005688747,0.00026650875,0.0019662709],"genre_scores_gemma":[0.9956612,0.00006538285,0.0033660524,0.000018869485,0.0000084361145,0.000028715865,0.00031947927,0.000010007782,0.0005218463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987876,0.000031523665,0.000008541308,0.000034978275,0.000017778339,0.000028351862],"domain_scores_gemma":[0.9996575,0.00018518812,0.000028040293,0.000022782078,0.0000760801,0.000030524887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057298684,0.00071963546,0.0006249014,0.00042811132,0.00060709525,0.000798795,0.0011105114,0.001427065,0.0008796092],"category_scores_gemma":[0.001017886,0.00037808155,0.0008291186,0.00060634786,0.00046688257,0.00076901884,0.00051097217,0.0009369655,0.00010400654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004038386,0.000104931234,0.006888085,0.00002005832,0.00003215745,0.00021387421,0.00003812344,0.9865072,0.0005020566,0.00046714782,0.00043143376,0.004754492],"study_design_scores_gemma":[0.000010928247,0.000011728111,0.0014930934,0.0000016475883,0.0000062266085,0.000006507644,0.000026173935,0.99787986,0.0001607028,0.00028064643,0.00011732559,0.0000051103543],"about_ca_topic_score_codex":0.107654154,"about_ca_topic_score_gemma":0.071519434,"teacher_disagreement_score":0.107654154,"about_ca_system_score_codex":0.0015617023,"about_ca_system_score_gemma":0.002007054,"threshold_uncertainty_score":0.21405506},"labels":[],"label_agreement":null},{"id":"W4220861638","doi":"10.1007/s40009-022-01110-0","title":"Application of Machine Learning to Investigate the Impact of Climatic Variables on Marine Fish Landings","year":2022,"lang":"en","type":"article","venue":"National Academy Science Letters","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Fisheries and Oceans Canada","funders":"Universiti Tenaga Nasional; Kementerian Pendidikan","keywords":"Fish <Actinopterygii>; Marine fish; Decision tree; Random forest; Fishery; Environmental science; Linear regression; Regression analysis; Statistics; Regression; Value (mathematics); Mathematics; Computer science; Machine learning; Biology","score_opus":0.020049010726236233,"score_gpt":0.2776676361497191,"score_spread":0.2576186254234829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220861638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99534446,0.000038957653,0.0032641296,0.00013302015,0.000019338406,0.000007989716,0.000155314,0.000034439734,0.00100224],"genre_scores_gemma":[0.9986141,0.000018680055,0.001039097,0.000011762905,0.000008458697,0.0000040195923,0.00010509992,0.0000035586388,0.00019518952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996119,0.00021613637,0.000019401547,0.00005092436,0.0000540924,0.000047562244],"domain_scores_gemma":[0.99379855,0.0052287104,0.00033875564,0.00015333878,0.00033536056,0.00014528823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001652244,0.0003490775,0.00033790903,0.00088804355,0.0003497197,0.0005495947,0.0003902129,0.00048457648,0.001329001],"category_scores_gemma":[0.006201424,0.00016113535,0.0005510597,0.000942255,0.0002579459,0.00046662785,0.0002623031,0.0005019586,0.00013545257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051550526,0.00051566696,0.39990327,0.00004259567,0.0003812386,0.00015763848,0.00007262675,0.5669929,0.002453513,0.0010485712,0.00048586391,0.027430667],"study_design_scores_gemma":[0.000013830388,0.00009496937,0.059187487,0.00000249077,0.000024198038,0.000016670052,0.000041905067,0.939235,0.00067509303,0.00060654915,0.000093271876,0.00000863504],"about_ca_topic_score_codex":0.022147961,"about_ca_topic_score_gemma":0.011816327,"teacher_disagreement_score":0.022147961,"about_ca_system_score_codex":0.00069558504,"about_ca_system_score_gemma":0.00061239087,"threshold_uncertainty_score":0.044038057},"labels":[],"label_agreement":null},{"id":"W4220864256","doi":"10.2166/wst.2022.095","title":"An essential tool for WRRF modelling: a realistic and complete influent generator for flow rate and water quality based on data-driven methods","year":2022,"lang":"en","type":"article","venue":"Water Science & Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; CentrEau - Quebec Water Management Research Centre","funders":"","keywords":"Generator (circuit theory); Water quality; Range (aeronautics); Inlet; Automation; Data mining; Computer science; Multivariate statistics; Volumetric flow rate; Artificial neural network; Engineering; Environmental science; Machine learning","score_opus":0.08617119338889614,"score_gpt":0.3536946479374413,"score_spread":0.2675234545485452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220864256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077620586,0.00009525363,0.9856125,0.00015547156,0.000059616097,0.00009718506,0.0012852626,0.0016059112,0.0033267306],"genre_scores_gemma":[0.47528487,0.00052812346,0.5101059,0.0001699957,0.00009194584,0.0008673134,0.004138033,0.00082882214,0.007984981],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970967,0.00007107462,0.000023005708,0.00007209962,0.00010379058,0.000020329708],"domain_scores_gemma":[0.9996383,0.00012525567,0.0000428097,0.000081878665,0.000096446754,0.00001531589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006338179,0.00094603316,0.00070461846,0.000563616,0.00034564311,0.00096654333,0.0014255538,0.0010324676,0.0029865054],"category_scores_gemma":[0.0013295544,0.00042227336,0.00094049436,0.0005656562,0.0003674091,0.0010257268,0.00075329177,0.0016062977,0.0010891245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023930705,0.000036982117,0.00074339326,0.00010798369,0.00003109841,0.0000712461,0.00004724062,0.9642531,0.0035335433,0.008107452,0.0013509764,0.021693038],"study_design_scores_gemma":[0.0000054888624,0.0000124236885,0.00014714678,0.000010337713,0.0000045416173,0.000013836382,0.0000053385793,0.99161786,0.0012745003,0.002361023,0.0045381086,0.000009348692],"about_ca_topic_score_codex":0.009773562,"about_ca_topic_score_gemma":0.005966776,"teacher_disagreement_score":0.009773562,"about_ca_system_score_codex":0.0006354525,"about_ca_system_score_gemma":0.0010773183,"threshold_uncertainty_score":0.01943332},"labels":[],"label_agreement":null},{"id":"W4220884174","doi":"10.1007/s12237-022-01070-0","title":"Prediction of Coastal Water Temperature Using Statistical Models","year":2022,"lang":"en","type":"article","venue":"Estuaries and Coasts","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Institut National de Santé Publique du Québec; University of New Brunswick; Institut National de la Recherche Scientifique","funders":"","keywords":"Mean squared error; Linear regression; Sea surface temperature; Random forest; Wind speed; Artificial neural network; Environmental science; Regression; Regression analysis; Predictive modelling; Statistics; Meteorology; Machine learning; Mathematics; Computer science; Geography","score_opus":0.027049330341606594,"score_gpt":0.21064739850039801,"score_spread":0.18359806815879143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220884174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4806632,0.00045244678,0.5122489,0.00043265717,0.000114049726,0.000032611228,0.0007487993,0.0014398296,0.0038674774],"genre_scores_gemma":[0.97696143,0.00019245756,0.021473568,0.000018851642,0.000034961362,0.000027363714,0.0003197741,0.000023795443,0.0009477521],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986196,0.000046800364,0.000012721445,0.000028285463,0.0000355605,0.000014628028],"domain_scores_gemma":[0.99868995,0.0008734301,0.00013098714,0.00005937945,0.0002093628,0.000036865462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005401212,0.00040342327,0.0003996291,0.0006248829,0.0002062464,0.0005583575,0.0003700963,0.00028812065,0.0005022549],"category_scores_gemma":[0.0025647054,0.0002678138,0.00040162914,0.0010396264,0.00022995181,0.00069361366,0.00022153169,0.0005098979,0.000128406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020327847,0.000017152504,0.0028301326,0.000007997146,0.000019567378,0.00000886747,0.0000048745023,0.9864377,0.0003703864,0.000633425,0.00019805522,0.009451522],"study_design_scores_gemma":[9.905663e-7,0.0000022455135,0.00021808624,3.2350985e-7,0.0000014571159,6.3936125e-7,6.4387086e-7,0.9994721,0.00007200546,0.0002103996,0.000020453834,7.892784e-7],"about_ca_topic_score_codex":0.025370609,"about_ca_topic_score_gemma":0.021251442,"teacher_disagreement_score":0.025370609,"about_ca_system_score_codex":0.0005331638,"about_ca_system_score_gemma":0.00071898603,"threshold_uncertainty_score":0.050445855},"labels":[],"label_agreement":null},{"id":"W4220933802","doi":"10.18280/ijdne.170118","title":"Develop Evaporation Model Using Multiple Linear Regression in the Western Desert of Iraq –Horan Valley","year":2022,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Anbar","keywords":"Linear regression; Pan evaporation; Evaporation; Regression analysis; Arid; Mean squared error; Stepwise regression; Wind speed; Mathematics; Environmental science; Statistics; Meteorology; Geography; Ecology","score_opus":0.039863579237219546,"score_gpt":0.29268188386408645,"score_spread":0.2528183046268669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220933802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74504095,0.0012624318,0.23913868,0.00048494348,0.000072521354,0.00013237781,0.0006860925,0.0011002859,0.012081673],"genre_scores_gemma":[0.97461516,0.00044303804,0.020145033,0.00003919595,0.000023391338,0.0000816522,0.00037148668,0.000059965256,0.004221065],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985945,0.000036054196,0.000009751186,0.000040500614,0.00003152931,0.000022603683],"domain_scores_gemma":[0.99988973,0.00004403911,0.00001794595,0.000004532408,0.000039171475,0.000004489646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032427444,0.00042301224,0.00050049927,0.00026820882,0.00033046797,0.0007320861,0.00067257683,0.00048188138,0.0010296985],"category_scores_gemma":[0.00052796054,0.00021059914,0.0007733311,0.00043707335,0.0001404078,0.00046159994,0.0003303744,0.0004583033,0.00030621476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031268097,0.000063049185,0.011113179,0.00009736004,0.000057385205,0.0003238681,0.00008664924,0.9631833,0.0026820628,0.0010383249,0.00085467065,0.02046886],"study_design_scores_gemma":[0.000004879594,0.000011617646,0.0021739092,0.000004831529,0.000008309665,0.000021408528,0.000022985354,0.9967146,0.0003890491,0.00018457639,0.0004578642,0.0000061189467],"about_ca_topic_score_codex":0.020548536,"about_ca_topic_score_gemma":0.0132978605,"teacher_disagreement_score":0.020548536,"about_ca_system_score_codex":0.00042298887,"about_ca_system_score_gemma":0.0006450462,"threshold_uncertainty_score":0.04085785},"labels":[],"label_agreement":null},{"id":"W4220997640","doi":"10.18280/ijdne.170110","title":"Linear Regression Analysis Using Log Transformation Model for Rainfall Data in Water Resources Management Krueng Pase, Aceh, Indonesia","year":2022,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universitas Syiah Kuala","keywords":"Wind speed; Linear regression; Regression analysis; Watershed; Water resources; Environmental science; Agriculture; Statistics; Regression; Mathematics; Geography; Meteorology; Climatology; Hydrology (agriculture); Computer science; Ecology; Engineering","score_opus":0.03197905390430561,"score_gpt":0.2872254095097937,"score_spread":0.2552463556054881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220997640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26860607,0.0017882886,0.70918906,0.0013435503,0.0004995955,0.00056059397,0.002981095,0.0045103715,0.010521413],"genre_scores_gemma":[0.8669102,0.001555848,0.10945417,0.00013361487,0.00010475317,0.0007186248,0.003182861,0.0004518898,0.017487993],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.998431,0.000807735,0.00010213752,0.0003172943,0.0002426232,0.00009917859],"domain_scores_gemma":[0.99712974,0.0020063573,0.0002559123,0.00017061063,0.00039659083,0.000040848576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033657376,0.0007705241,0.00068418507,0.0008895709,0.0003216251,0.0012569891,0.0009365665,0.00044751677,0.00444824],"category_scores_gemma":[0.007754473,0.00032891147,0.0011133257,0.0020519686,0.0003567796,0.0012107926,0.0006363237,0.0017888015,0.0018800497],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071921933,0.0008809606,0.09626967,0.00071265554,0.000691964,0.0007330648,0.0006946948,0.44108316,0.0057014185,0.014496811,0.014724892,0.42329153],"study_design_scores_gemma":[0.000017739672,0.00020404703,0.01710918,0.000048063725,0.000056349207,0.00007957478,0.00014554309,0.9716033,0.0013145156,0.0027948231,0.0065906774,0.000036152058],"about_ca_topic_score_codex":0.015226126,"about_ca_topic_score_gemma":0.010318234,"teacher_disagreement_score":0.015226126,"about_ca_system_score_codex":0.0007844888,"about_ca_system_score_gemma":0.0019659053,"threshold_uncertainty_score":0.030274987},"labels":[],"label_agreement":null},{"id":"W4221015755","doi":"10.3390/mca27020029","title":"Applications of ANFIS-Type Methods in Simulation of Systems in Marine Environments","year":2022,"lang":"en","type":"article","venue":"Mathematical and Computational Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adaptive neuro fuzzy inference system; Particle swarm optimization; Genetic algorithm; Computer science; Evolutionary algorithm; Adaptability; Algorithm; Marine engineering; Simulation; Machine learning; Engineering; Artificial intelligence; Fuzzy logic; Ecology; Fuzzy control system","score_opus":0.025598939121688816,"score_gpt":0.31353720548815495,"score_spread":0.28793826636646613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221015755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01935216,0.0008746055,0.97160983,0.00021179022,0.00009979668,0.000093629315,0.000116205294,0.00063181657,0.007010222],"genre_scores_gemma":[0.75258446,0.0017533908,0.24106292,0.00011686418,0.0000778807,0.0004709649,0.00026074616,0.00009623092,0.0035764754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968064,0.00012916842,0.00003768028,0.00004002951,0.000094379146,0.000018106975],"domain_scores_gemma":[0.9990792,0.0006630762,0.0000861591,0.000036157337,0.00011758541,0.000017868346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008855015,0.00100497,0.00073645596,0.0005648615,0.0004816814,0.0007943549,0.0007146547,0.0011301297,0.0020479592],"category_scores_gemma":[0.0018762132,0.00041049442,0.0008289266,0.0005790496,0.00047602804,0.0006524063,0.0004718515,0.0011045923,0.00023663526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011949952,0.00001234432,0.000356686,0.00006756132,0.00002426941,0.000048348084,0.000044176915,0.98590046,0.0007872803,0.0026085915,0.00014321308,0.009995101],"study_design_scores_gemma":[0.0000026551638,0.000011788821,0.00007026197,0.000013049373,0.0000039484407,0.000008485268,0.0000088524275,0.9979559,0.00029096354,0.0010363167,0.00059429475,0.0000034751347],"about_ca_topic_score_codex":0.0091297,"about_ca_topic_score_gemma":0.0057482845,"teacher_disagreement_score":0.0091297,"about_ca_system_score_codex":0.0004735143,"about_ca_system_score_gemma":0.0006781866,"threshold_uncertainty_score":0.018153131},"labels":[],"label_agreement":null},{"id":"W4224040696","doi":"10.2166/ws.2022.166","title":"Extreme Learning Machine model for assessment of stream health using the Qualitative Habitat Evaluation Index","year":2022,"lang":"en","type":"article","venue":"Water Science & Technology Water Supply","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph; University of Ottawa","funders":"","keywords":"Species richness; Predictability; Extreme learning machine; Mean squared error; Index (typography); Watershed; Habitat; Computer science; Machine learning; Statistics; Artificial intelligence; Ecology; Mathematics; Artificial neural network; Biology","score_opus":0.09873026525774158,"score_gpt":0.3794708483781224,"score_spread":0.2807405831203808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224040696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.701719,0.00025015106,0.29293725,0.0005603454,0.000052297375,0.00012166776,0.0006728616,0.00040772042,0.0032786967],"genre_scores_gemma":[0.99278754,0.000026422911,0.006100296,0.000027261767,0.0000074792974,0.00006482061,0.00015793444,0.000004045343,0.0008243415],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960226,0.000185239,0.000022993761,0.000079998674,0.00004743052,0.00006204333],"domain_scores_gemma":[0.998911,0.0007628972,0.00008773473,0.000034502606,0.00017171007,0.000032059586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001559071,0.0005445635,0.00053727766,0.0007793453,0.00029653357,0.0006244926,0.0008222994,0.0006696475,0.0012912749],"category_scores_gemma":[0.002924932,0.00022618944,0.0006853721,0.0005720349,0.00042338824,0.00036588445,0.00040164698,0.00076667045,0.0001732809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035423982,0.000035960184,0.0057549104,0.000008917396,0.000028162553,0.000028995548,0.000022976159,0.98679453,0.00018496907,0.00052830955,0.00016385759,0.0064129746],"study_design_scores_gemma":[0.0000011282658,0.000006621966,0.00048807877,0.0000010642163,0.0000015201645,0.0000018622654,0.0000029953703,0.9992291,0.000026454996,0.00022355202,0.000016261545,0.0000014537237],"about_ca_topic_score_codex":0.024000686,"about_ca_topic_score_gemma":0.01118508,"teacher_disagreement_score":0.024000686,"about_ca_system_score_codex":0.0011102447,"about_ca_system_score_gemma":0.0006029578,"threshold_uncertainty_score":0.047721922},"labels":[],"label_agreement":null},{"id":"W4224285235","doi":"10.1007/s10661-022-09957-y","title":"Multi-step ahead prediction of hourly influent characteristics for wastewater treatment plants: a case study from North America","year":2022,"lang":"en","type":"article","venue":"Environmental Monitoring and Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hatch (Canada); McMaster University","funders":"","keywords":"Univariate; Multilayer perceptron; Wastewater; Multivariate statistics; Environmental science; Sewage treatment; Random forest; Computer science; Variable (mathematics); Statistics; Environmental engineering; Machine learning; Artificial neural network; Mathematics","score_opus":0.03406643458393255,"score_gpt":0.2757178765819906,"score_spread":0.24165144199805805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224285235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99668807,0.00005856516,0.0020372747,0.00009948598,0.000007386169,0.000011060957,0.00031668032,0.000068874935,0.0007126775],"genre_scores_gemma":[0.9975284,0.000045299676,0.0017752819,0.000008642521,0.0000022236782,0.000005940727,0.0002822557,0.00000404271,0.00034788446],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999037,0.000020246964,0.000005220999,0.000027481827,0.000023471663,0.000019837105],"domain_scores_gemma":[0.9996258,0.00020722265,0.000033106808,0.00002151747,0.00008960244,0.000022754648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003234519,0.0004074364,0.00032195056,0.0003849084,0.0003885627,0.00042261163,0.00034025364,0.00061657303,0.00032999067],"category_scores_gemma":[0.00062109705,0.00021623375,0.00028658673,0.00084507186,0.00015669806,0.0003918983,0.00015732297,0.0003498556,0.00005873767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004816397,0.0007592711,0.15358908,0.00012156368,0.00015768624,0.0016018434,0.00047319254,0.76195985,0.011281824,0.00045482055,0.0032782373,0.06584108],"study_design_scores_gemma":[0.000017269593,0.000097726064,0.095950216,0.0000057321554,0.000033666718,0.00005298868,0.00040647903,0.90050274,0.0019583462,0.00024024807,0.000714108,0.000020469479],"about_ca_topic_score_codex":0.1870118,"about_ca_topic_score_gemma":0.24666236,"teacher_disagreement_score":0.1870118,"about_ca_system_score_codex":0.0009256547,"about_ca_system_score_gemma":0.0008216273,"threshold_uncertainty_score":0.3718465},"labels":[],"label_agreement":null},{"id":"W4224315380","doi":"10.1016/j.envsoft.2022.105402","title":"Machine-learning approach for predicting the occurrence and timing of mid-winter ice breakups on canadian rivers","year":2022,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Resources Canada; Environment and Climate Change Canada","keywords":"Computer science; Robustness (evolution); Probabilistic logic; Machine learning; Preprocessor; Scale (ratio); Model selection; Data mining; Artificial intelligence; Geography; Cartography","score_opus":0.02385358181453426,"score_gpt":0.203775625469272,"score_spread":0.17992204365473774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224315380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97190416,0.00041006424,0.021422775,0.0006425167,0.000042811538,0.000046466077,0.002064979,0.0003497635,0.0031163737],"genre_scores_gemma":[0.9902666,0.00010023455,0.0073323273,0.000032174885,0.000016231434,0.000012801385,0.0011823996,0.000009146495,0.0010479941],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998092,0.00002415752,0.000013256154,0.00005406068,0.00004174889,0.000057667723],"domain_scores_gemma":[0.9991849,0.000341649,0.00008754512,0.000028258199,0.00029022593,0.00006733944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000669347,0.00051154086,0.00039014907,0.001863252,0.0011666395,0.0009938655,0.0012914084,0.0007169935,0.0009468817],"category_scores_gemma":[0.0024403064,0.0002785003,0.00047939754,0.0015880218,0.00040773436,0.00040341174,0.00034991864,0.00080124673,0.0001197193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008912524,0.0001208547,0.112280056,0.00003833763,0.000095361895,0.00008769396,0.00011263973,0.8313142,0.00083202636,0.0013486464,0.0021208283,0.05156026],"study_design_scores_gemma":[0.0000039939387,0.0000055453525,0.017014045,0.000004575263,0.000010690169,0.000005705721,0.000047033656,0.9820473,0.00015886399,0.0004340121,0.00026278888,0.000005543333],"about_ca_topic_score_codex":0.93244594,"about_ca_topic_score_gemma":0.9314805,"teacher_disagreement_score":0.06755406,"about_ca_system_score_codex":0.008167567,"about_ca_system_score_gemma":0.0064787082,"threshold_uncertainty_score":0.13590372},"labels":[],"label_agreement":null},{"id":"W4225677208","doi":"10.3390/mca27020032","title":"On the Prediction of Evaporation in Arid Climate Using Machine Learning Model","year":2022,"lang":"en","type":"article","venue":"Mathematical and Computational Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Adaptive neuro fuzzy inference system; Pan evaporation; Particle swarm optimization; Mean squared error; Inference system; Wind speed; Meteorology; Environmental science; Computer science; Evaporation; Statistics; Mathematics; Fuzzy logic; Machine learning; Artificial intelligence; Geography; Fuzzy control system","score_opus":0.03542537804968154,"score_gpt":0.24788750928022718,"score_spread":0.21246213123054564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225677208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56765664,0.0013631333,0.42165622,0.00042565697,0.000096284464,0.00008931802,0.0003677513,0.0008239697,0.0075210487],"genre_scores_gemma":[0.98329365,0.0003258583,0.014644611,0.000027290103,0.00001640095,0.00004972607,0.00020890303,0.000015700305,0.001417843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980575,0.000063756816,0.000018163568,0.000048651964,0.00003995145,0.000023859286],"domain_scores_gemma":[0.99955314,0.00031874183,0.000037851,0.000013395251,0.00006822094,0.000008502983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005689803,0.0005894096,0.00062794646,0.0005515897,0.00035748997,0.00063563697,0.00045773594,0.0006190151,0.00069975917],"category_scores_gemma":[0.0013079141,0.00023345347,0.00065668224,0.00064092816,0.00017694008,0.0005802786,0.0002638509,0.0005276036,0.00017980224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022293758,0.00003358132,0.0023851325,0.000025815305,0.000030249963,0.000039697843,0.000015749307,0.9848108,0.00043970894,0.00029557242,0.00019091471,0.011710396],"study_design_scores_gemma":[8.9589537e-7,0.0000051981974,0.00032089461,0.0000017104277,0.0000020189566,0.0000025114916,0.0000025808297,0.9994562,0.00009059072,0.000076595075,0.00003925065,0.0000014800952],"about_ca_topic_score_codex":0.021802392,"about_ca_topic_score_gemma":0.012152991,"teacher_disagreement_score":0.021802392,"about_ca_system_score_codex":0.0004493585,"about_ca_system_score_gemma":0.0005845376,"threshold_uncertainty_score":0.043350995},"labels":[],"label_agreement":null},{"id":"W4225913161","doi":"10.1017/eds.2022.2","title":"Evolution of machine learning in environmental science—A perspective","year":2022,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of British Columbia; University of British Columbia","funders":"","keywords":"Parametrization (atmospheric modeling); Perspective (graphical); Computer science; Artificial intelligence; Artificial neural network; Machine learning; Climate science; Data assimilation; Deep learning; Convolutional neural network; General Circulation Model; Climate change; Physics; Meteorology; Ecology","score_opus":0.01709476070128623,"score_gpt":0.2403423857968685,"score_spread":0.22324762509558227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225913161","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010527121,0.47509488,0.057265718,0.30465123,0.0055367807,0.000042951786,0.00027420712,0.00015046906,0.14645672],"genre_scores_gemma":[0.60712326,0.2585326,0.04661373,0.030218283,0.028440619,0.00022174732,0.0002547661,0.00018922897,0.028405795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980136,0.001149622,0.00008077844,0.00030604663,0.00033226243,0.000117625896],"domain_scores_gemma":[0.9935341,0.0047520995,0.00018360022,0.00026851933,0.00090883713,0.0003529854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006208572,0.00071441295,0.0007389565,0.002520393,0.00089938,0.00429577,0.0010003523,0.004148219,0.004269248],"category_scores_gemma":[0.0072581307,0.000389123,0.000532011,0.0015494565,0.009242037,0.0072885975,0.0023508866,0.0060749883,0.0008903866],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025486095,0.0000471029,0.00046545902,0.00017893998,0.000024072633,0.000055497017,0.00019805755,0.0031440742,0.00012320446,0.9501883,0.010000355,0.035549436],"study_design_scores_gemma":[0.000016304559,0.00004620535,0.0008548207,0.00052716763,0.00000875856,0.0000864678,0.00019141396,0.009612717,0.00020004857,0.83336776,0.15505904,0.000029350644],"about_ca_topic_score_codex":0.003443403,"about_ca_topic_score_gemma":0.0020019314,"teacher_disagreement_score":0.006208572,"about_ca_system_score_codex":0.0057611694,"about_ca_system_score_gemma":0.0015610742,"threshold_uncertainty_score":0.04180044},"labels":[],"label_agreement":null},{"id":"W4226023263","doi":"10.14796/jwmm.c486","title":"Water Quality Modeling of the River Ganga in the Northern Region of India Using the Artificial Neural Network Technique","year":2022,"lang":"en","type":"article","venue":"Journal of Water Management Modeling","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Mean squared error; Multilayer perceptron; Radial basis function; Water quality; Uttar pradesh; Perceptron; Computer science; Nonlinear system; Hydrology (agriculture); Environmental science; Data mining; Mathematics; Artificial intelligence; Statistics; Ecology; Geology","score_opus":0.06608359806458866,"score_gpt":0.2611867316580601,"score_spread":0.19510313359347145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226023263","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97053325,0.00011840636,0.025049284,0.00020931092,0.000015296428,0.000032215463,0.00029452896,0.00028094716,0.0034668483],"genre_scores_gemma":[0.997068,0.00006015592,0.0021298039,0.00000623143,0.000002201329,0.000010342381,0.00011529494,0.0000048318684,0.0006030699],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999279,0.00002056607,0.0000057456373,0.000015787151,0.000016888864,0.000013109144],"domain_scores_gemma":[0.9999244,0.00003150028,0.0000130373355,0.000005653466,0.000020692676,0.000004637615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012152311,0.00024984256,0.000194061,0.00035970885,0.00029376018,0.00048088544,0.00033656883,0.00023563427,0.00028399084],"category_scores_gemma":[0.00026636152,0.000121064746,0.00037761562,0.0006797383,0.00017557907,0.0002657867,0.00021753239,0.00020328116,0.00005753889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005024747,0.00009084656,0.045272954,0.000068379384,0.00005955267,0.00027329932,0.00012767935,0.9251203,0.004729086,0.0007918494,0.0004869648,0.022928836],"study_design_scores_gemma":[0.0000051917955,0.000023313904,0.01973704,0.0000034488176,0.000014192557,0.000028211787,0.00008176808,0.9786751,0.0008081733,0.00032757394,0.00028592933,0.000010080081],"about_ca_topic_score_codex":0.06765098,"about_ca_topic_score_gemma":0.06381578,"teacher_disagreement_score":0.06765098,"about_ca_system_score_codex":0.00068041915,"about_ca_system_score_gemma":0.0008118694,"threshold_uncertainty_score":0.13451439},"labels":[],"label_agreement":null},{"id":"W4229447720","doi":"10.1029/2021wr031862","title":"Temporal Hierarchical Reconciliation for Consistent Water Resources Forecasting Across Multiple Timescales: An Application to Precipitation Forecasting","year":2022,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exponential smoothing; Benchmark (surveying); Computer science; Precipitation; Autoregressive integrated moving average; Econometrics; Moving average; Artificial neural network; Scaling; Smoothing; Climatology; Time series; Environmental science; Meteorology; Machine learning; Mathematics; Geography; Geology","score_opus":0.10847613805272727,"score_gpt":0.33838440239893264,"score_spread":0.22990826434620537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229447720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19130866,0.00047813047,0.8036607,0.00036432332,0.00010436126,0.0001100233,0.00033499816,0.0017629027,0.001875847],"genre_scores_gemma":[0.70837426,0.00011972645,0.29011288,0.0000567497,0.000051346484,0.00009370159,0.0005386784,0.00014156711,0.00051109254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986541,0.00066749816,0.00010445263,0.00024661073,0.0002538389,0.00007352707],"domain_scores_gemma":[0.9970132,0.0012788849,0.00039248902,0.0004923113,0.00077033095,0.000052862764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037718248,0.00060104573,0.00062516733,0.0012109072,0.0006516665,0.000734033,0.0007272827,0.00042360643,0.00074796454],"category_scores_gemma":[0.0087782955,0.00027648086,0.0009143937,0.0016880167,0.0003189116,0.0010184457,0.00092036714,0.00077977544,0.00016781349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002090428,0.00011932951,0.020186739,0.00012300606,0.0003486666,0.0001321569,0.00046356747,0.50813425,0.0051606596,0.004967615,0.0024607948,0.4576942],"study_design_scores_gemma":[0.000013572839,0.000034778157,0.006207018,0.00000837846,0.000031659954,0.00001859025,0.00005610339,0.98837566,0.001963108,0.0020164647,0.0012550957,0.000019691777],"about_ca_topic_score_codex":0.015334321,"about_ca_topic_score_gemma":0.015951702,"teacher_disagreement_score":0.015334321,"about_ca_system_score_codex":0.00062538363,"about_ca_system_score_gemma":0.0012322107,"threshold_uncertainty_score":0.0304901},"labels":[],"label_agreement":null},{"id":"W4229643811","doi":"10.36334/modsim.2017.g1.erechtchoukova","title":"Role of a 'combination rule' in hybrid short-term prediction of hydrological events","year":2017,"lang":"en","type":"article","venue":"MODSIM","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Term (time); Computer science; Data mining","score_opus":0.023691731798017604,"score_gpt":0.2542355663541628,"score_spread":0.2305438345561452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229643811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27020305,0.0012184094,0.7137986,0.00042694842,0.00034327345,0.00018692578,0.0005945306,0.0043040435,0.008924175],"genre_scores_gemma":[0.9310867,0.0002864753,0.06651831,0.000085299645,0.00006892153,0.000075969874,0.00046498238,0.000060617003,0.0013526703],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993224,0.00015465086,0.000080679376,0.00019602124,0.00017620549,0.00007009658],"domain_scores_gemma":[0.9975841,0.0012757856,0.00017970936,0.00024043067,0.00061107293,0.00010895423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025093108,0.0007435321,0.0010879391,0.0014906803,0.0003740541,0.0013658096,0.0010227019,0.00069420127,0.0012243027],"category_scores_gemma":[0.0039489577,0.0003249073,0.0006335045,0.0011963795,0.0003595227,0.0013631164,0.00048011987,0.0009318313,0.00070205535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005759303,0.00035583664,0.014808564,0.0001072146,0.00029177198,0.0001847215,0.00010382225,0.40042132,0.007330301,0.0015301965,0.0020048108,0.5722854],"study_design_scores_gemma":[0.000008414938,0.000075467964,0.0017525898,0.000011892557,0.000045879482,0.000032653814,0.000011859655,0.9939767,0.0024561188,0.0009908433,0.00062400586,0.000013446443],"about_ca_topic_score_codex":0.0058680447,"about_ca_topic_score_gemma":0.0043914067,"teacher_disagreement_score":0.0058680447,"about_ca_system_score_codex":0.00044679252,"about_ca_system_score_gemma":0.00066920754,"threshold_uncertainty_score":0.013270676},"labels":[],"label_agreement":null},{"id":"W4230391068","doi":"10.3394/0380-1330-34.4.698","title":"Predicting the Frequency of Water Quality Standard Violations Using Bayesian Calibration of Eutrophication Models","year":2008,"lang":"en","type":"article","venue":"Journal of Great Lakes Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Calibration; Eutrophication; Environmental science; Bayesian probability; Water quality; Quality (philosophy); Statistics; Mathematics; Ecology; Biology; Nutrient; Physics","score_opus":0.15768890062726906,"score_gpt":0.3696145920721922,"score_spread":0.21192569144492315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230391068","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9419928,0.00010221957,0.055922586,0.00032421216,0.000026708783,0.000016969982,0.00027589258,0.00019411986,0.0011444681],"genre_scores_gemma":[0.99625826,0.000026822207,0.003331474,0.000014357249,0.0000070097076,0.000005123186,0.00022249979,0.00000841169,0.0001260013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991204,0.0003243998,0.00007035671,0.00021722005,0.00017303418,0.00009446624],"domain_scores_gemma":[0.98622304,0.009017145,0.0019558908,0.0011054387,0.0014266291,0.0002718837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047958996,0.0005043112,0.0005493603,0.0011363021,0.0003186587,0.00071303896,0.0008870042,0.0010367009,0.0006085093],"category_scores_gemma":[0.021265974,0.00039913986,0.00042596945,0.0010979318,0.0003925049,0.0013655053,0.00061402586,0.001471888,0.00018868066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002697611,0.00014789261,0.085402586,0.000018230901,0.00011700586,0.000046199388,0.0000836938,0.886502,0.0011971771,0.0020472154,0.0006627126,0.023505481],"study_design_scores_gemma":[0.000007661805,0.000011894539,0.0068581644,0.0000021958956,0.0000072157995,0.000009140817,0.000007161722,0.99136645,0.0002457069,0.00143805,0.000039293536,0.0000069702483],"about_ca_topic_score_codex":0.0132143935,"about_ca_topic_score_gemma":0.011351039,"teacher_disagreement_score":0.0132143935,"about_ca_system_score_codex":0.00089147285,"about_ca_system_score_gemma":0.000618121,"threshold_uncertainty_score":0.02627492},"labels":[],"label_agreement":null},{"id":"W4231346947","doi":"10.5194/essd-2021-51-rc2","title":"Comment on essd-2021-51","year":2021,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Eesti Teadusagentuur; H2020 Marie Skłodowska-Curie Actions; Sihtasutus Archimedes","keywords":"Metadata; Flagging; Scale (ratio); Computer science; Outlier; Data quality; Quality (philosophy); Download; Replicate; Data mining; Database; Environmental science; Information retrieval; Cartography; Geography; Statistics; World Wide Web; Mathematics; Metric (unit); Artificial intelligence","score_opus":0.05010223786007216,"score_gpt":0.3015817221813534,"score_spread":0.2514794843212812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231346947","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059103884,0.0016122732,0.001007102,0.4060786,0.26483184,0.00071570015,0.039986096,0.0036494946,0.28152797],"genre_scores_gemma":[0.002614902,0.0007168983,0.0005352334,0.5611008,0.024012322,0.00066241145,0.009043615,0.00083330646,0.40048048],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967188,0.00027294457,0.0003224321,0.00034698093,0.0016717808,0.0006669357],"domain_scores_gemma":[0.9919686,0.0021682105,0.00029400666,0.0006585761,0.0039113173,0.0009993971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004571746,0.00086465233,0.0011951807,0.0014736671,0.0026170376,0.0066980426,0.0032598472,0.027403997,0.2719936],"category_scores_gemma":[0.02308323,0.0005766192,0.002048282,0.0018688687,0.001594193,0.0038746973,0.0032708722,0.011844138,0.22672978],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001557602,0.000004766601,0.00003588936,0.000032760756,9.360035e-7,0.000028553439,0.000006210828,0.000006976825,0.000024213561,0.00055217685,0.9978933,0.0013987357],"study_design_scores_gemma":[0.000019726402,0.000008399382,0.00038360636,0.00009099536,0.0000020640164,0.000013677782,0.000027036178,0.000023545666,0.000062617175,0.00061329536,0.9987446,0.000010396729],"about_ca_topic_score_codex":0.028385429,"about_ca_topic_score_gemma":0.032914404,"teacher_disagreement_score":0.2719936,"about_ca_system_score_codex":0.003990432,"about_ca_system_score_gemma":0.0053746095,"threshold_uncertainty_score":0.90990925},"labels":[],"label_agreement":null},{"id":"W4233935138","doi":"10.21077/ijf.2018.65.4.72559-09","title":"Deep-learning based approach for forecast of water quality in intensive shrimp culture ponds","year":2018,"lang":"en","type":"article","venue":"Indian Journal of Fisheries","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Zhejiang Province Public Welfare Technology Application Research Project; K. C. Wong Magna Fund in Ningbo University; Natural Science Foundation of Zhejiang Province; Ningbo University; National Natural Science Foundation of China","keywords":"Mariculture; Water quality; Environmental science; Aquaculture; Shrimp; Effluent; Quality (philosophy); Deep water; Deep belief network; Environmental quality; Fishery; Environmental engineering; Computer science; Deep learning; Artificial intelligence; Ecology; Engineering; Fish <Actinopterygii>; Marine engineering; Biology","score_opus":0.02915130405129134,"score_gpt":0.26119528560503863,"score_spread":0.23204398155374728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233935138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5886354,0.00055336626,0.40348113,0.00069855957,0.00010758174,0.00004965909,0.0005183126,0.000653771,0.0053022644],"genre_scores_gemma":[0.9908958,0.000104536935,0.0075778654,0.000030660205,0.000014509177,0.000020899133,0.00017922312,0.000008151331,0.0011683378],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999225,0.000011715337,0.000005601868,0.000022352791,0.000016114627,0.000021696373],"domain_scores_gemma":[0.9998548,0.000057703364,0.000020138923,0.00000577753,0.00004305216,0.000018577846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022819142,0.00048578958,0.00043190623,0.00039998983,0.00024894587,0.00050629315,0.00065721665,0.0006164719,0.00090241357],"category_scores_gemma":[0.00056397007,0.00032172474,0.0004428023,0.00041117906,0.00020446615,0.00058129715,0.0004391531,0.0007491787,0.000101070924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003356797,0.00002706559,0.0025866863,0.00001204714,0.000013836888,0.00003362256,0.00001616046,0.98385715,0.00073316984,0.0002827819,0.00021587781,0.0121879345],"study_design_scores_gemma":[0.0000010241972,0.000002506269,0.00016899452,5.4323584e-7,8.81858e-7,6.716017e-7,0.0000023160528,0.9996395,0.000054935164,0.00011284097,0.0000148674535,9.16025e-7],"about_ca_topic_score_codex":0.037614916,"about_ca_topic_score_gemma":0.023203343,"teacher_disagreement_score":0.037614916,"about_ca_system_score_codex":0.00074272975,"about_ca_system_score_gemma":0.0008011547,"threshold_uncertainty_score":0.07479191},"labels":[],"label_agreement":null},{"id":"W4236693359","doi":"10.21203/rs.3.rs-326161/v1","title":"Using regional scaling for temperature forecasts with the Stochastic Seasonal to Interannual Prediction System (StocSIPS).","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Scaling; Climatology; Environmental science; Econometrics; Meteorology; Geography; Economics; Mathematics; Geology","score_opus":0.10250535419293848,"score_gpt":0.3675508145759477,"score_spread":0.2650454603830092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236693359","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16955882,0.00091077515,0.78932136,0.0008330699,0.00092500355,0.00013876501,0.009544823,0.014293075,0.0144743575],"genre_scores_gemma":[0.72428375,0.0003610972,0.26156408,0.00007825116,0.00023205296,0.0001388681,0.009205164,0.0013464649,0.002790238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997353,0.000096990465,0.000021853273,0.00007191646,0.00005940341,0.000014660138],"domain_scores_gemma":[0.9990227,0.00036233113,0.00007762222,0.00024055775,0.00025895183,0.00003786015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009834751,0.0004207948,0.0002935771,0.0005749812,0.00018148021,0.00063485565,0.0004985392,0.00026807794,0.0034289227],"category_scores_gemma":[0.006504282,0.00023643115,0.00033869437,0.0015502137,0.00013414561,0.0013329034,0.00043237588,0.00076403166,0.001227567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020006471,0.000081167935,0.010420744,0.0000957027,0.00020356946,0.000066626606,0.00008765222,0.72117954,0.0036693434,0.011496472,0.024543824,0.22795531],"study_design_scores_gemma":[0.000020744454,0.000008590161,0.0017471439,0.000005053161,0.000015415922,0.000005310035,0.000013999809,0.9906476,0.0008288845,0.0041258773,0.002574716,0.00000664351],"about_ca_topic_score_codex":0.025029156,"about_ca_topic_score_gemma":0.017699733,"teacher_disagreement_score":0.025029156,"about_ca_system_score_codex":0.00039783365,"about_ca_system_score_gemma":0.0006979207,"threshold_uncertainty_score":0.049766958},"labels":[],"label_agreement":null},{"id":"W4240944730","doi":"10.5194/hessd-6-7055-2009","title":"Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology – Part 1: Concepts and methodology","year":2009,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Genetic programming; Computer science; Support vector machine; Data mining; Evapotranspiration; Process (computing); Sampling (signal processing); Regression; Regression analysis; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.18420416337047713,"score_gpt":0.3623999800340776,"score_spread":0.17819581666360046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240944730","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7907253,0.0005021852,0.19922453,0.0006485606,0.00019096199,0.0010891095,0.0021585878,0.0013481883,0.0041124322],"genre_scores_gemma":[0.85513496,0.00026369488,0.14151916,0.00009161561,0.00003615286,0.00087839126,0.0014115593,0.00006420099,0.0006002243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849117,0.0007273004,0.000120756136,0.00025530695,0.00034855944,0.000056910205],"domain_scores_gemma":[0.9908214,0.0061254296,0.0004265006,0.001462171,0.0010326622,0.00013181745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004356432,0.0006890512,0.00039556404,0.0006440615,0.00030971068,0.0011583406,0.0010110707,0.000953713,0.0010734576],"category_scores_gemma":[0.013875531,0.00037532856,0.0006097883,0.001185949,0.0004204766,0.0015633791,0.0006758004,0.0012859643,0.00024887064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027063892,0.0049174256,0.019855157,0.0009885527,0.00042002308,0.00018010693,0.0005794152,0.6865739,0.028283613,0.01709005,0.003731707,0.23467374],"study_design_scores_gemma":[0.0002446308,0.0015629771,0.0035388141,0.00003638235,0.000050983956,0.00005072526,0.00009968056,0.95793885,0.029626243,0.0042807953,0.0025172185,0.000052721232],"about_ca_topic_score_codex":0.0027737143,"about_ca_topic_score_gemma":0.0012582192,"teacher_disagreement_score":0.004356432,"about_ca_system_score_codex":0.0008597825,"about_ca_system_score_gemma":0.00076800486,"threshold_uncertainty_score":0.023039281},"labels":[],"label_agreement":null},{"id":"W4241311550","doi":"10.22541/au.158447031.19938002","title":"Deep Learning for Forecasting Runoffs over China under Climate Changes","year":2020,"lang":"en","type":"dataset","venue":"Authorea","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Beijing Normal University","keywords":"Streamflow; Environmental science; Climate change; Precipitation; Representative Concentration Pathways; Drainage basin; Surface runoff; Global warming; Water resources; Flood forecasting; China; Hydrology (agriculture); Structural basin; Climatology; Climate model; Meteorology; Geography; Geology; Oceanography; Ecology","score_opus":0.042432227416552504,"score_gpt":0.2726666811437049,"score_spread":0.2302344537271524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241311550","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9598808,0.00049797876,0.035492778,0.0006244469,0.000054906304,0.000025825722,0.0009898798,0.0007099701,0.0017233922],"genre_scores_gemma":[0.99662554,0.00011127547,0.002238304,0.00002303623,0.000009941435,0.000010940189,0.00055315194,0.000010130254,0.00041757364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998492,0.000027721624,0.0000121912635,0.00004300272,0.000030435593,0.00003747589],"domain_scores_gemma":[0.99980515,0.00006285301,0.000033752705,0.000013290631,0.000059231003,0.000025741132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047826034,0.0007373179,0.0004406245,0.00071830966,0.0003085992,0.0005086564,0.00056959427,0.00058055494,0.0007108834],"category_scores_gemma":[0.0009978932,0.00033439972,0.0006692701,0.0008592043,0.00026376414,0.0006150136,0.0005623659,0.00064643985,0.00008685209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036309637,0.000032801177,0.011122321,0.000018386461,0.000028370328,0.00006857875,0.000019806283,0.9775587,0.0006544539,0.00028470112,0.000466816,0.009708817],"study_design_scores_gemma":[0.0000020365296,0.0000033131196,0.0014341513,9.749615e-7,0.000002596832,0.0000012251356,0.00000399068,0.9982736,0.00010234175,0.00012842605,0.000045572535,0.0000018154847],"about_ca_topic_score_codex":0.060166087,"about_ca_topic_score_gemma":0.036239527,"teacher_disagreement_score":0.060166087,"about_ca_system_score_codex":0.0012671467,"about_ca_system_score_gemma":0.0012315143,"threshold_uncertainty_score":0.11963177},"labels":[],"label_agreement":null},{"id":"W4242081681","doi":"10.5194/hess-2020-430-rc1","title":"Reviewer comments on manuscript hess-2020-430","year":2020,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Computer science","score_opus":0.07105862390016436,"score_gpt":0.3047308379956221,"score_spread":0.23367221409545774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242081681","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020022863,0.0012238463,0.0062205656,0.46648398,0.4529434,0.0006602537,0.018568698,0.0028402777,0.049056724],"genre_scores_gemma":[0.056749243,0.0039746044,0.014146,0.15840745,0.16242535,0.0012745288,0.018250024,0.00835776,0.57641494],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948665,0.001208301,0.00066416356,0.0005401695,0.002461901,0.0002590616],"domain_scores_gemma":[0.81101334,0.017338019,0.0023629894,0.003030246,0.16294856,0.0033068103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008279539,0.0007857827,0.0007381538,0.0032033678,0.0014530303,0.0033677712,0.0013620938,0.0027853241,0.17981577],"category_scores_gemma":[0.12903592,0.0003298655,0.001064768,0.0027823404,0.00074293965,0.0030639644,0.0018511288,0.0031950425,0.06718515],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022833543,0.0000022694092,0.000095436284,0.00005868119,0.0000039408205,0.000059623933,0.00006315218,0.000052855827,0.00006896737,0.00039291685,0.995877,0.0033022545],"study_design_scores_gemma":[0.000028477089,0.000009025284,0.0008206162,0.00013320449,0.000014793838,0.00006086879,0.00034907434,0.00032097095,0.000410467,0.000831595,0.9969805,0.00004028714],"about_ca_topic_score_codex":0.019149093,"about_ca_topic_score_gemma":0.023161454,"teacher_disagreement_score":0.17981577,"about_ca_system_score_codex":0.0031131802,"about_ca_system_score_gemma":0.0051611923,"threshold_uncertainty_score":0.60154366},"labels":[],"label_agreement":null},{"id":"W4243627243","doi":"10.5194/hessd-12-12311-2015","title":"Dissolved oxygen prediction using a possibility-theory based fuzzy neural network","year":2015,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fuzzy logic; Artificial neural network; Defuzzification; Construct (python library); Computer science; Resource (disambiguation); Data mining; Neuro-fuzzy; Fuzzy set; Artificial intelligence; Machine learning; Fuzzy control system; Fuzzy number","score_opus":0.0522504857865821,"score_gpt":0.27351981811192394,"score_spread":0.22126933232534185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243627243","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26050556,0.00038915026,0.7331791,0.00044937184,0.000090672904,0.000058727805,0.00016107087,0.00035319515,0.004813081],"genre_scores_gemma":[0.93186855,0.00008031967,0.06660213,0.000030023513,0.0000179348,0.000028759721,0.00006957893,0.0000066914,0.0012960193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998486,0.000035233603,0.000009408732,0.00003588544,0.00005654539,0.000014325302],"domain_scores_gemma":[0.9996008,0.00020389752,0.000033540524,0.000013359159,0.00012996496,0.000018469162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047175368,0.00029131063,0.0003004963,0.0005584837,0.00028246274,0.0006346485,0.00057699764,0.0004449055,0.0008832289],"category_scores_gemma":[0.0012664276,0.00017926813,0.00033853634,0.0003957677,0.0003269472,0.00050924846,0.0002910599,0.0004099147,0.00010081729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010386367,0.00004559956,0.0037934135,0.00003995303,0.000047729947,0.000069323054,0.000039116796,0.93937516,0.0030818388,0.0024020346,0.0004833625,0.050518695],"study_design_scores_gemma":[0.0000035340693,0.0000061632268,0.0002509661,0.0000017614714,0.000002708838,0.0000027023,0.000001912741,0.99908876,0.00023134242,0.00034863834,0.000059299866,0.0000021636652],"about_ca_topic_score_codex":0.030516429,"about_ca_topic_score_gemma":0.02476044,"teacher_disagreement_score":0.030516429,"about_ca_system_score_codex":0.0011849186,"about_ca_system_score_gemma":0.00067091204,"threshold_uncertainty_score":0.060677588},"labels":[],"label_agreement":null},{"id":"W4243960837","doi":"10.5194/hessd-7-7957-2010","title":"Generalized versus Non-Generalized Neural Network model for multi-lead inflow forecasting at Aswan High Dam","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generalization; Inflow; Artificial neural network; Computer science; Series (stratigraphy); Machine learning; Artificial intelligence; Mathematics; Meteorology; Geology; Geography","score_opus":0.11594452878738389,"score_gpt":0.30228711096293504,"score_spread":0.18634258217555116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243960837","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8980726,0.00038907793,0.095491596,0.00080957555,0.000155864,0.00004199209,0.00038215079,0.0003542389,0.0043029417],"genre_scores_gemma":[0.99576217,0.00006515095,0.00314286,0.000019799983,0.000009042186,0.000014597783,0.00009844642,0.000007952253,0.00087995775],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980325,0.00007861612,0.000011139146,0.00004894139,0.00003384902,0.000024246445],"domain_scores_gemma":[0.99967754,0.00014041075,0.00003866639,0.0000205988,0.00009658133,0.000026358983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055087067,0.0005691354,0.0005436684,0.00041798383,0.00035531222,0.000684686,0.000853717,0.000808268,0.000916319],"category_scores_gemma":[0.0011051786,0.00020948824,0.00047155312,0.00065290614,0.0003768428,0.00092536415,0.00046324058,0.0007474743,0.0001148351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030648844,0.000016320782,0.0023008664,0.0000179684,0.000013581327,0.000056065124,0.000016502854,0.99229664,0.0004252574,0.00048218895,0.00022437837,0.0041196025],"study_design_scores_gemma":[0.0000013657263,0.000003807708,0.00023690607,7.041309e-7,0.0000013903087,0.0000016543961,0.000002903683,0.9994911,0.000055180815,0.00018333325,0.000019904515,0.000001733893],"about_ca_topic_score_codex":0.032518942,"about_ca_topic_score_gemma":0.03238986,"teacher_disagreement_score":0.032518942,"about_ca_system_score_codex":0.0010686625,"about_ca_system_score_gemma":0.00080951786,"threshold_uncertainty_score":0.06465936},"labels":[],"label_agreement":null},{"id":"W4246229938","doi":"10.22541/au.163251902.21099343/v1","title":"Learning from mistakes - Assessing the performance and uncertainty in process-based models","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; BGC Engineering (Canada)","funders":"","keywords":"Process (computing); Computer science; Basis (linear algebra); Cluster analysis; Variable (mathematics); Errors-in-variables models; Set (abstract data type); Process modeling; Data mining; Principal component analysis; Machine learning; Artificial intelligence; Mathematics; Work in process; Engineering","score_opus":0.04249601030279104,"score_gpt":0.2754217843308965,"score_spread":0.23292577402810544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246229938","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34810317,0.00064901006,0.6469786,0.00065715285,0.00007340244,0.0002570053,0.00038568888,0.0005256014,0.0023703142],"genre_scores_gemma":[0.9299747,0.00017787483,0.06901256,0.000056656118,0.000033355747,0.000117145464,0.00034692197,0.000065893386,0.00021485901],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9807734,0.009704199,0.00207315,0.0024136477,0.0044712615,0.00056427304],"domain_scores_gemma":[0.77242756,0.19368085,0.013346604,0.010342098,0.008767253,0.0014356328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04048054,0.002097537,0.0015024758,0.004216765,0.0009103188,0.0034776242,0.0019109971,0.0020068563,0.0007973991],"category_scores_gemma":[0.14940956,0.0006916331,0.0013207091,0.0022348568,0.002638297,0.005320269,0.0036575363,0.0021155423,0.00017332817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003571102,0.00015628495,0.05709623,0.00031300227,0.0005302842,0.00024918187,0.0009589175,0.8709235,0.0006828772,0.010089129,0.0004307828,0.05821267],"study_design_scores_gemma":[0.00001755822,0.00020040678,0.0076286867,0.00008437452,0.000052801737,0.00007361348,0.00023666082,0.9676431,0.0012051341,0.022496715,0.00031103764,0.00005000818],"about_ca_topic_score_codex":0.005416715,"about_ca_topic_score_gemma":0.0032101367,"teacher_disagreement_score":0.04048054,"about_ca_system_score_codex":0.0020243437,"about_ca_system_score_gemma":0.0020921603,"threshold_uncertainty_score":0.21408409},"labels":[],"label_agreement":null},{"id":"W4248117579","doi":"10.5194/hessd-9-4667-2012","title":"Record extension for short-gauged water quality parameters using a newly proposed robust version of the line of organic correlation technique","year":2012,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Outlier; Monte Carlo method; Ordinary least squares; Skewness; Percentile; Statistics; Econometrics; Robust regression; Variance (accounting); Regression; Mathematics; Computer science; Accounting","score_opus":0.09486942715338843,"score_gpt":0.29639355796101435,"score_spread":0.20152413080762593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248117579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019342598,0.00022598446,0.9787785,0.00006360873,0.00004852638,0.000040127168,0.00020323004,0.0005825604,0.00071483094],"genre_scores_gemma":[0.2782617,0.00047055574,0.7171709,0.00009347926,0.00015399359,0.00014626111,0.0012273979,0.0002603088,0.0022154574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875236,0.0002817509,0.00008508192,0.00026654173,0.0005316632,0.000082576764],"domain_scores_gemma":[0.9960393,0.0011604484,0.0009641387,0.0006072642,0.0011410397,0.00008774804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018210211,0.0006692889,0.0005459842,0.0014634173,0.00031180173,0.00078634865,0.00097629224,0.000541416,0.00155851],"category_scores_gemma":[0.007066906,0.0002323381,0.00097524497,0.002329556,0.00034573555,0.0011975294,0.0010304099,0.00093567505,0.0007160416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037053574,0.00018182998,0.017150475,0.0004026408,0.0004233108,0.00042607827,0.00029077387,0.15193646,0.03416112,0.014533533,0.0043626023,0.77576065],"study_design_scores_gemma":[0.000035106295,0.00027875474,0.011539258,0.00004536896,0.00013933318,0.00044046724,0.00007753728,0.95383966,0.017125547,0.0038243504,0.012523691,0.00013084996],"about_ca_topic_score_codex":0.002844343,"about_ca_topic_score_gemma":0.0030777669,"teacher_disagreement_score":0.002844343,"about_ca_system_score_codex":0.0002870861,"about_ca_system_score_gemma":0.0009248582,"threshold_uncertainty_score":0.0096306205},"labels":[],"label_agreement":null},{"id":"W4256238924","doi":"10.5194/hess-2020-430","title":"Resampling and ensemble techniques for improving ANN-based high streamflow forecast accuracy","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Resampling; Boosting (machine learning); Computer science; AdaBoost; Flood forecasting; Random forest; Streamflow; Machine learning; Artificial neural network; Ensemble learning; Artificial intelligence; Ensemble forecasting; Bootstrap aggregating; Data mining; Undersampling; Flood myth; Support vector machine","score_opus":0.04604312162746976,"score_gpt":0.27971623407730933,"score_spread":0.23367311244983957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256238924","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29534262,0.0011166033,0.6980343,0.00032747278,0.00023460978,0.00009638192,0.00022339394,0.0016805577,0.0029440427],"genre_scores_gemma":[0.8588168,0.0002523355,0.13961111,0.0000853958,0.000090957896,0.000062846026,0.00037083033,0.000060751878,0.00064893404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999411,0.00021246128,0.000045583707,0.000089248744,0.00018841885,0.000053191005],"domain_scores_gemma":[0.99770516,0.0010798962,0.00016253113,0.00024653669,0.0007571703,0.000048650323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027153974,0.00068315945,0.00076883746,0.0011224304,0.00033021727,0.00048685857,0.00052548014,0.00040243284,0.0005962537],"category_scores_gemma":[0.005488212,0.0002433644,0.0006392846,0.00060413615,0.00018807966,0.0007492208,0.00049531093,0.00071470917,0.00022043585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018668326,0.00013933438,0.010500689,0.000056468725,0.00023700176,0.0000612749,0.00007941003,0.711352,0.0062594395,0.001123055,0.0017948712,0.2682098],"study_design_scores_gemma":[0.0000048326056,0.0000324351,0.0014545084,0.000006000588,0.000015582431,0.00000799028,0.000007912924,0.9962192,0.0015823834,0.0003630223,0.0003007492,0.000005426366],"about_ca_topic_score_codex":0.00791508,"about_ca_topic_score_gemma":0.01011284,"teacher_disagreement_score":0.00791508,"about_ca_system_score_codex":0.00046616347,"about_ca_system_score_gemma":0.00056839874,"threshold_uncertainty_score":0.01573801},"labels":[],"label_agreement":null},{"id":"W4280513172","doi":"10.18280/ria.360208","title":"An Adaptive Gradient Boosting Model for the Prediction of Rainfall Using ID3 as a Base Estimator","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Decision tree; Gradient boosting; Boosting (machine learning); Information gain ratio; Incremental decision tree; ID3 algorithm; Data mining; Computer science; Estimator; Decision tree learning; Pruning; Raw data; Artificial intelligence; Decision tree model; Machine learning; Tree (set theory); Regression; Mathematics; Statistics; Random forest","score_opus":0.10490446470943296,"score_gpt":0.29267827987532957,"score_spread":0.1877738151658966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280513172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03992063,0.00069185323,0.95552504,0.00023531265,0.00013381804,0.00011297189,0.00020822589,0.0010298934,0.0021422436],"genre_scores_gemma":[0.7406603,0.0006071806,0.2524431,0.00023592157,0.00013074295,0.00028281714,0.0007095763,0.000104722014,0.0048256684],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993917,0.00019912419,0.00003699424,0.00012606484,0.00016118081,0.000084826235],"domain_scores_gemma":[0.9993693,0.00024248856,0.000048403082,0.00004542689,0.00026327357,0.00003106945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021798592,0.00067870645,0.0015011801,0.00082804996,0.00044138145,0.00085843384,0.0019638182,0.00091258076,0.0013102512],"category_scores_gemma":[0.00212967,0.00040838908,0.0011030334,0.0010290277,0.0003290454,0.0007284415,0.0005495462,0.0011958794,0.0009430926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030641837,0.00021315023,0.004933535,0.000098703546,0.00018372439,0.00012830054,0.00007361963,0.7994844,0.00432295,0.004688275,0.0031289507,0.182438],"study_design_scores_gemma":[0.000005578681,0.00002934961,0.00029410454,0.0000033112474,0.000009526679,0.000011342596,0.0000022577556,0.99818534,0.00038230262,0.0006545462,0.00041760266,0.0000047112158],"about_ca_topic_score_codex":0.00977213,"about_ca_topic_score_gemma":0.006118621,"teacher_disagreement_score":0.00977213,"about_ca_system_score_codex":0.0006255714,"about_ca_system_score_gemma":0.0011638475,"threshold_uncertainty_score":0.019430459},"labels":[],"label_agreement":null},{"id":"W4281999679","doi":"10.3390/su14116624","title":"A Smart Post-Processing System for Forecasting the Climate Precipitation Based on Machine Learning Computations","year":2022,"lang":"en","type":"article","venue":"Sustainability","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Machine learning; Computer science; Random forest; Artificial intelligence; Computation; Support vector machine; Data processing; Set (abstract data type); Flood myth; Software; Data mining; Algorithm; Database","score_opus":0.017617897112529462,"score_gpt":0.25192970401135417,"score_spread":0.23431180689882472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281999679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037473436,0.00017188778,0.8786156,0.00017354976,0.00015805653,0.00028339933,0.0013772487,0.076126315,0.005620576],"genre_scores_gemma":[0.4390845,0.00022617978,0.54770505,0.00017488922,0.00011736157,0.00041520884,0.0034269695,0.0011935512,0.007656301],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968517,0.00004575058,0.00002954618,0.00008794719,0.00012219112,0.000029499666],"domain_scores_gemma":[0.9993563,0.00019544922,0.00004961611,0.00014546247,0.00021563953,0.00003762411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005776178,0.00070489786,0.00048996875,0.001010467,0.00036470097,0.0007375136,0.0009099741,0.0004060115,0.007748011],"category_scores_gemma":[0.0014232356,0.000249224,0.00049947837,0.00071553246,0.00017220632,0.0009687555,0.0004210229,0.0006143513,0.0026378804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010781403,0.0005165831,0.010285161,0.00037049575,0.00018319272,0.0003924043,0.00047046706,0.06281081,0.07328855,0.006718294,0.03404092,0.80984485],"study_design_scores_gemma":[0.00013614233,0.0002742351,0.009044508,0.000040297626,0.00008704504,0.0001511339,0.000079486425,0.8829498,0.06645685,0.0053187753,0.035381246,0.000080417245],"about_ca_topic_score_codex":0.0030698339,"about_ca_topic_score_gemma":0.0021355331,"teacher_disagreement_score":0.007748011,"about_ca_system_score_codex":0.0003067869,"about_ca_system_score_gemma":0.0006818979,"threshold_uncertainty_score":0.025919676},"labels":[],"label_agreement":null},{"id":"W4283809800","doi":"10.3390/su14138065","title":"A Comprehensive Study of Artificial Intelligence Applications for Soil Temperature Prediction in Ordinary Climate Conditions and Extremely Hot Events","year":2022,"lang":"en","type":"article","venue":"Sustainability","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Research Council Canada","keywords":"Random forest; Perceptron; Environmental science; Gradient boosting; Multilayer perceptron; Predictive modelling; Boosting (machine learning); Artificial neural network; Machine learning; Computer science; Meteorology; Artificial intelligence","score_opus":0.026624457119161005,"score_gpt":0.2998606248748633,"score_spread":0.2732361677557023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283809800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5189721,0.06246023,0.37376308,0.0031924509,0.0007587101,0.00017935192,0.0005639088,0.00083164184,0.039278522],"genre_scores_gemma":[0.94679976,0.019634953,0.030591652,0.00017148953,0.00025443148,0.000048048045,0.0002964074,0.00003838418,0.002164865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956626,0.00014372559,0.000034473192,0.00007346156,0.0001521149,0.000029903762],"domain_scores_gemma":[0.9991386,0.00046535226,0.000076713186,0.000053987238,0.00023154002,0.000033794076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008602828,0.00056202564,0.0003624363,0.0007533194,0.00023028944,0.00080898654,0.00037777328,0.00050570763,0.0005937664],"category_scores_gemma":[0.002155772,0.00018432879,0.0006283356,0.0012503564,0.00023531569,0.0009388971,0.00043176732,0.00060630706,0.00015617076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112354566,0.00020969249,0.031591427,0.0008833546,0.00026346216,0.0004178944,0.00019430244,0.46047238,0.010181907,0.00878059,0.0043684524,0.48252422],"study_design_scores_gemma":[0.000006170408,0.00020027513,0.022484107,0.00018663885,0.000083631974,0.00013361305,0.00014323313,0.95922774,0.004419789,0.0038677724,0.009211264,0.00003574615],"about_ca_topic_score_codex":0.0028903477,"about_ca_topic_score_gemma":0.002178502,"teacher_disagreement_score":0.0028903477,"about_ca_system_score_codex":0.00026205886,"about_ca_system_score_gemma":0.00041094667,"threshold_uncertainty_score":0.0057470202},"labels":[],"label_agreement":null},{"id":"W4285200969","doi":"10.1007/978-981-19-2519-1_20","title":"Pre-processing and Input Vector Selection Techniques in Computational Soft Computing Models of Water Engineering","year":2022,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Soft computing; Feature selection; Computer science; Selection (genetic algorithm); Artificial intelligence; Principal component analysis; Data mining; Field (mathematics); Algorithm; Pattern recognition (psychology); Artificial neural network; Mathematics","score_opus":0.053507095596771095,"score_gpt":0.301478676028039,"score_spread":0.24797158043126794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285200969","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037253555,0.0018332296,0.9898252,0.0003076471,0.00019166293,0.00003095263,0.00006900899,0.00031995669,0.0036970763],"genre_scores_gemma":[0.16752459,0.004961543,0.7946404,0.00030949613,0.0007063216,0.00028244057,0.00040524546,0.0003813204,0.030788573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996489,0.0001265365,0.0000289702,0.00005367784,0.000120615725,0.00002130548],"domain_scores_gemma":[0.99874544,0.000878053,0.00003841351,0.00012222212,0.00020225566,0.000013509227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068298046,0.0007991395,0.0008193896,0.00045500154,0.00038435363,0.0011187088,0.001096752,0.0008045699,0.0047690985],"category_scores_gemma":[0.0024318888,0.0005305186,0.00067769166,0.0014675194,0.00061070145,0.0015864046,0.00051103503,0.002418539,0.0012757867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008971594,0.000101987855,0.0003395529,0.0003070763,0.00007075294,0.00009123032,0.00009345179,0.47564837,0.0050435844,0.049269877,0.010092271,0.4588522],"study_design_scores_gemma":[0.0000033283982,0.000036668378,0.00019694022,0.00002477021,0.000011749866,0.000029523273,0.000008398772,0.969415,0.0029136357,0.023307245,0.0040412825,0.000011361283],"about_ca_topic_score_codex":0.0023505746,"about_ca_topic_score_gemma":0.005349136,"teacher_disagreement_score":0.0047690985,"about_ca_system_score_codex":0.0003343519,"about_ca_system_score_gemma":0.0005471238,"threshold_uncertainty_score":0.015954196},"labels":[],"label_agreement":null},{"id":"W4285421078","doi":"10.24191/mij.v2i1.10898","title":"Penambahbaikan Kaedah Peramalan Purata Setempat bagi Peramalan Data Siri Masa Aras Sungai di Kawasan Banjir","year":2021,"lang":"id","type":"article","venue":"Mathematical Sciences and Informatics Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Encana (Canada)","funders":"","keywords":"Physics; Forestry; Geography","score_opus":0.07343643234923002,"score_gpt":0.2974133168911824,"score_spread":0.22397688454195236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285421078","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24918933,0.025465626,0.01685025,0.016758481,0.0027605963,0.001401548,0.010236089,0.0023938841,0.67494416],"genre_scores_gemma":[0.38219947,0.014703373,0.015907187,0.003976997,0.00062038854,0.0005760835,0.006078793,0.00065102614,0.5752867],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976962,0.00037200912,0.00014484172,0.000436758,0.000988969,0.00036119923],"domain_scores_gemma":[0.996894,0.00049825775,0.00033304477,0.00035516388,0.0014263138,0.00049327454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018439798,0.0006754903,0.00058194745,0.0011833238,0.0023453003,0.0040371474,0.001147613,0.0012914304,0.060247164],"category_scores_gemma":[0.0022231722,0.00046099946,0.0006057679,0.0015079323,0.00096401107,0.0022854873,0.0022366736,0.002214723,0.017240733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017673158,0.001189606,0.036450066,0.003805012,0.00022269905,0.0018481946,0.0083492445,0.00061089324,0.12420105,0.017855933,0.13160859,0.67209136],"study_design_scores_gemma":[0.00002744237,0.00041011852,0.023388818,0.00033487697,0.00008539264,0.0007352953,0.003558986,0.0001751268,0.021406611,0.0008787895,0.94894445,0.000054057247],"about_ca_topic_score_codex":0.010994271,"about_ca_topic_score_gemma":0.018951261,"teacher_disagreement_score":0.060247164,"about_ca_system_score_codex":0.002068607,"about_ca_system_score_gemma":0.0043467195,"threshold_uncertainty_score":0.20154685},"labels":[],"label_agreement":null},{"id":"W4286517726","doi":"10.18280/ria.360308","title":"How M5 Model Trees (M5-MT) on Continuous Data Are Used in Rainfall Prediction: An Experimental Evaluation","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pruning; Benchmark (surveying); Decision tree; Tree (set theory); Computer science; Mean squared error; Standard deviation; Machine learning; Data mining; Artificial intelligence; Reduction (mathematics); Test data; Support vector machine; Mathematics; Statistics; Geography","score_opus":0.1637501238476778,"score_gpt":0.32015857104698875,"score_spread":0.15640844719931096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286517726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8490249,0.0029708238,0.11939102,0.0014481691,0.0008336042,0.00108129,0.0046405913,0.0058122515,0.014797352],"genre_scores_gemma":[0.8093192,0.00077803433,0.18065163,0.0003128064,0.00009586844,0.0005713396,0.005132807,0.0005432211,0.0025950472],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99593544,0.0022734082,0.0002996119,0.0005399194,0.0007278719,0.00022365843],"domain_scores_gemma":[0.9757582,0.018415615,0.0006665921,0.002056981,0.002616656,0.00048594867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008952323,0.0016629962,0.0010598984,0.0016805826,0.0009711157,0.0015257288,0.0018004382,0.0020716793,0.0034232975],"category_scores_gemma":[0.033992674,0.00043400226,0.0011863591,0.0021927685,0.00057139224,0.0028573899,0.0011913531,0.0019246974,0.0011995815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047092275,0.002446916,0.019123318,0.0011869643,0.0006856866,0.00035707344,0.0007219503,0.5311987,0.0047670403,0.00419537,0.0151104955,0.41549733],"study_design_scores_gemma":[0.0002022847,0.0010610931,0.004396064,0.00008436882,0.00011762693,0.00007063363,0.00030733363,0.9838688,0.004359704,0.0022766192,0.003208261,0.00004720698],"about_ca_topic_score_codex":0.015554173,"about_ca_topic_score_gemma":0.015010088,"teacher_disagreement_score":0.015554173,"about_ca_system_score_codex":0.0012193472,"about_ca_system_score_gemma":0.0014564276,"threshold_uncertainty_score":0.047344983},"labels":[],"label_agreement":null},{"id":"W4287833909","doi":"10.3390/app12157464","title":"Physics-Informed Data-Driven Model for Predicting Streamflow: A Case Study of the Voshmgir Basin, Iran","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bedford Institute of Oceanography; University of Guelph","funders":"National Research Foundation of Korea","keywords":"Surface runoff; Streamflow; Environmental science; Water resources; Structural basin; Hydrological modelling; Field (mathematics); Hydrology (agriculture); Meteorology; Drainage basin; Runoff model; Climatology; Computer science; Machine learning; Watershed; Geography; Geology; Cartography; Mathematics","score_opus":0.11044113149162565,"score_gpt":0.30495692874665886,"score_spread":0.1945157972550332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287833909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865954,0.0001368741,0.010504119,0.00034926535,0.000029057814,0.000054546414,0.00038865616,0.00019209605,0.0017499663],"genre_scores_gemma":[0.9964445,0.00006133848,0.0027213853,0.000015412572,0.000008106905,0.000031630396,0.0002495561,0.000008111839,0.00045994163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985194,0.000041009655,0.0000099444605,0.00004071614,0.000022184828,0.00003427691],"domain_scores_gemma":[0.9996326,0.00019545216,0.000030927204,0.00002273463,0.00008747407,0.00003075391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063537166,0.000771773,0.0006705959,0.00045745587,0.00070711516,0.0008119189,0.0011628955,0.0013232664,0.0008057242],"category_scores_gemma":[0.0009918441,0.0003885364,0.0008829668,0.000570157,0.00047504218,0.00073911925,0.0005485629,0.00092099875,0.00008444289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045537312,0.00012435699,0.007399194,0.00002192136,0.000034462842,0.00025387894,0.000042971544,0.9864299,0.00058593735,0.00046005618,0.00037483664,0.004226892],"study_design_scores_gemma":[0.000014213152,0.000017619826,0.0016781538,0.0000016466558,0.0000074926484,0.000007596153,0.000032171327,0.9977004,0.00016905463,0.00025436212,0.000111305526,0.0000059106897],"about_ca_topic_score_codex":0.10567207,"about_ca_topic_score_gemma":0.07005202,"teacher_disagreement_score":0.10567207,"about_ca_system_score_codex":0.0015493968,"about_ca_system_score_gemma":0.0022525534,"threshold_uncertainty_score":0.21011394},"labels":[],"label_agreement":null},{"id":"W4290098772","doi":"10.5194/isprs-archives-xlviii-4-w1-2022-187-2022","title":"DEPLOYMENT OF AI-ENHANCED SERVICES IN CLIMATE RESILIENCE INFORMATION SYSTEMS","year":2022,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ouranos","funders":"","keywords":"Interoperability; Software deployment; Resilience (materials science); Climate change; Computer science; Information system; Environmental resource management; Environmental science; Engineering; World Wide Web; Software engineering; Ecology","score_opus":0.011795858563725968,"score_gpt":0.24262072225965314,"score_spread":0.23082486369592717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290098772","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052033957,0.0013938424,0.7514876,0.004130051,0.00050769513,0.0009401682,0.004922156,0.09599424,0.08859037],"genre_scores_gemma":[0.5915263,0.0016702355,0.3715815,0.0014699824,0.0003693064,0.0006434469,0.013023656,0.0033153652,0.016400244],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970926,0.0009313297,0.00033896373,0.00029768675,0.0010681587,0.00027125448],"domain_scores_gemma":[0.9930154,0.0018371826,0.0003509362,0.0024874653,0.0017706285,0.0005382392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049260175,0.0006753036,0.00047193628,0.0023877409,0.00083770714,0.004403728,0.002003016,0.0012941473,0.0071420786],"category_scores_gemma":[0.009902486,0.00031567487,0.00058807945,0.0033425973,0.0007875676,0.004952364,0.0036974875,0.0017849844,0.0044051814],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012351258,0.0006650812,0.012356555,0.0016211094,0.00031621996,0.0014315711,0.004030689,0.026367242,0.035455585,0.20277454,0.11724741,0.5964989],"study_design_scores_gemma":[0.00012949627,0.00018920915,0.006636614,0.00081838394,0.00012432472,0.00053680444,0.0011887661,0.3009282,0.04073464,0.08324376,0.5652615,0.00020827382],"about_ca_topic_score_codex":0.0069783423,"about_ca_topic_score_gemma":0.0022321895,"teacher_disagreement_score":0.0071420786,"about_ca_system_score_codex":0.0018452703,"about_ca_system_score_gemma":0.0018208252,"threshold_uncertainty_score":0.026051521},"labels":[],"label_agreement":null},{"id":"W4294067900","doi":"10.1007/978-981-19-2840-6_3","title":"Forecasting Flash Floods with Optimized Adaptive Neuro-Fuzzy Inference System and Internet of Things","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Adaptive neuro fuzzy inference system; Flash flood; Flood myth; Flooding (psychology); Computer science; Internet of Things; Neuro-fuzzy; Climate change; Fuzzy logic; Data mining; Environmental science; Artificial intelligence; Meteorology; Fuzzy control system; Geography; Computer security; Geology","score_opus":0.022209235605829495,"score_gpt":0.20555096470723835,"score_spread":0.18334172910140886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294067900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11293357,0.0022267934,0.8707963,0.0004082112,0.00052190793,0.00005787436,0.00029771784,0.0008289009,0.011928731],"genre_scores_gemma":[0.9009303,0.00066775735,0.09343292,0.000085369225,0.00010756162,0.000045481516,0.00025607608,0.000027981043,0.004446554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992263,0.0000128447255,0.000007385615,0.000021137685,0.00002445606,0.000011517858],"domain_scores_gemma":[0.9998921,0.000056663805,0.000008833929,0.000007672489,0.00003107634,0.0000035668004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025474228,0.00042331396,0.00047077905,0.00034891264,0.00024678637,0.00049998617,0.0004874648,0.0006039355,0.0010262121],"category_scores_gemma":[0.00063603936,0.0002297331,0.0005919743,0.0004899295,0.00017098915,0.00059676374,0.00029669644,0.00046429402,0.00016087467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010668354,0.00004940796,0.0013077519,0.000072345654,0.000107029315,0.000113289505,0.00003075394,0.8547824,0.0034048704,0.004003937,0.0021802196,0.13384134],"study_design_scores_gemma":[0.000002359097,0.000009808829,0.00037569672,0.0000025935867,0.00001110436,0.000010124713,0.0000059234776,0.9971564,0.0003389505,0.0018245841,0.00025910555,0.000003300816],"about_ca_topic_score_codex":0.0069541833,"about_ca_topic_score_gemma":0.010265279,"teacher_disagreement_score":0.0069541833,"about_ca_system_score_codex":0.0003035256,"about_ca_system_score_gemma":0.00024018328,"threshold_uncertainty_score":0.013827443},"labels":[],"label_agreement":null},{"id":"W4294741338","doi":"10.5194/gmd-2022-174-rc2","title":"Comment on gmd-2022-174","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Uppsala Universitet; Vetenskapsrådet; Svenska Forskningsrådet Formas; Norges Forskningsråd; European Commission; Joint Programming Initiative Water challenges for a changing world","keywords":"Algal bloom; Chlorophyll a; Computer science; Fish <Actinopterygii>; Bathythermograph; Nutrient; Bloom; Workflow; Machine learning; Environmental science; Oceanography; Statistics; Phytoplankton; Ecology; Fishery; Mathematics; Chemistry; Biology; Geology","score_opus":0.04818500599431969,"score_gpt":0.2964158101885684,"score_spread":0.2482308041942487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294741338","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004665036,0.0011697488,0.0010611503,0.4787464,0.36036217,0.00060018006,0.009104636,0.004619725,0.14386946],"genre_scores_gemma":[0.0031536142,0.0009351072,0.0010045762,0.47197044,0.07283597,0.00055694656,0.0026715186,0.0013156524,0.44555622],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973455,0.00022404772,0.00023220087,0.00029384534,0.001518339,0.00038610728],"domain_scores_gemma":[0.98819214,0.003221677,0.0005685757,0.00095571956,0.0056602564,0.0014015662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029190776,0.0010178268,0.0011316652,0.0019753934,0.0028247393,0.0042595733,0.0031375682,0.022823274,0.22232169],"category_scores_gemma":[0.02947567,0.0006007677,0.0013387862,0.0018456753,0.0020938783,0.003200601,0.002425009,0.011628346,0.18072799],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001262652,0.000005335179,0.000030642983,0.000028699387,9.4677137e-7,0.000039118848,0.0000068312206,0.000009958676,0.00003147499,0.00042658707,0.9972283,0.0021795128],"study_design_scores_gemma":[0.000015389225,0.000006639053,0.00032660353,0.00006216656,0.0000012829559,0.00001808741,0.000017792767,0.000045573637,0.00006920626,0.00043714762,0.9989911,0.000009029292],"about_ca_topic_score_codex":0.029458221,"about_ca_topic_score_gemma":0.029945362,"teacher_disagreement_score":0.22232169,"about_ca_system_score_codex":0.0036710456,"about_ca_system_score_gemma":0.003933178,"threshold_uncertainty_score":0.74374014},"labels":[],"label_agreement":null},{"id":"W4296822450","doi":"10.5194/hess-2022-96-ac16","title":"Reply on CC2","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Global Institute for Water Security","funders":"Global Institute for Water Security, University of Saskatchewan","keywords":"Span (engineering); Evapotranspiration; Life span; Mathematics; Precipitation; Mean squared error; Fertilizer; Statistics; Irrigation; Environmental science; Hydrology (agriculture); Meteorology; Physics; Agronomy; Engineering; Ecology","score_opus":0.04760981058257825,"score_gpt":0.29525157184126294,"score_spread":0.2476417612586847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296822450","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032362586,0.0018063668,0.00038426113,0.6010971,0.3209987,0.00017498934,0.0013544346,0.000759212,0.07310132],"genre_scores_gemma":[0.004107472,0.0013949923,0.00030496193,0.6182157,0.100294895,0.00026556518,0.0007143692,0.00047844945,0.27422363],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980567,0.00032156022,0.0001987744,0.00034320075,0.0007155036,0.00036420487],"domain_scores_gemma":[0.99482536,0.0014373221,0.00019142064,0.0003315404,0.0022776218,0.0009368625],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002018967,0.0008147648,0.00094168505,0.0010848064,0.0024185623,0.0036627392,0.0024437262,0.017138023,0.27932844],"category_scores_gemma":[0.023500167,0.0004298081,0.0012262202,0.0008057208,0.0015974591,0.0027761792,0.0022484323,0.013742896,0.17158248],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011945117,0.0000032040637,0.000035612353,0.000013834817,0.0000012787411,0.000054059194,0.0000058257065,0.000004671832,0.00001688823,0.00029836435,0.99698526,0.002569084],"study_design_scores_gemma":[0.000012091311,0.0000071618833,0.00016584135,0.000049445378,0.0000021554713,0.00007411709,0.000035744353,0.00003054902,0.000056762816,0.00048720805,0.999071,0.000008039768],"about_ca_topic_score_codex":0.0062063984,"about_ca_topic_score_gemma":0.007427465,"teacher_disagreement_score":0.72067153,"about_ca_system_score_codex":0.0026785603,"about_ca_system_score_gemma":0.0026862833,"threshold_uncertainty_score":0.9344467},"labels":[],"label_agreement":null},{"id":"W4297007333","doi":"10.5194/iahs2022-732","title":"Seasonal Precipitation forecasting with large scale climate predictors: A hybrid &amp;#160;wavelet multiresolution -NARX scheme","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Nonlinear autoregressive exogenous model; Autoregressive model; Precipitation; Environmental science; Climatology; Wavelet; Scale (ratio); Teleconnection; Meteorology; Econometrics; Computer science; Mathematics; Geography; Geology","score_opus":0.03157456197785843,"score_gpt":0.2533495429241356,"score_spread":0.22177498094627715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297007333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22271034,0.00064886955,0.77250564,0.0003258781,0.0001169381,0.000063129235,0.00022626019,0.0005353442,0.0028675848],"genre_scores_gemma":[0.85523486,0.00036547982,0.14035375,0.00006530402,0.000051870826,0.00008002528,0.0003571993,0.000031464788,0.0034600836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998658,0.000046263547,0.000010946655,0.00002681858,0.00003555589,0.000014640115],"domain_scores_gemma":[0.9998448,0.000058147143,0.000018766807,0.000021410038,0.000046514077,0.000010399708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067383656,0.00030211356,0.00043854004,0.00019240353,0.00018039143,0.0005097351,0.0006356112,0.00044777192,0.0009881817],"category_scores_gemma":[0.0008528027,0.00019220458,0.00038307993,0.00029970234,0.0001292535,0.0005872353,0.0004322716,0.00060510024,0.00025267265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001528512,0.00008831933,0.0022564954,0.000050112354,0.00007555181,0.0001158117,0.00007055951,0.82280225,0.009004453,0.002884906,0.0009269199,0.16157185],"study_design_scores_gemma":[0.0000019222853,0.000008357827,0.00017743904,0.0000010520647,0.000002188304,0.0000023442353,0.0000019556135,0.99938536,0.00020159257,0.00010819892,0.00010811641,0.0000014290499],"about_ca_topic_score_codex":0.0047167884,"about_ca_topic_score_gemma":0.0044075684,"teacher_disagreement_score":0.0047167884,"about_ca_system_score_codex":0.00022475728,"about_ca_system_score_gemma":0.0003807663,"threshold_uncertainty_score":0.009378672},"labels":[],"label_agreement":null},{"id":"W4297023514","doi":"10.5194/hess-2022-96-ac15","title":"Reply on CC2","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Global Institute for Water Security","funders":"Global Institute for Water Security, University of Saskatchewan","keywords":"Span (engineering); Life span; Evapotranspiration; Mathematics; Precipitation; Mean squared error; Fertilizer; Statistics; Irrigation; Environmental science; Hydrology (agriculture); Meteorology; Physics; Agronomy; Engineering; Ecology","score_opus":0.04760981058257825,"score_gpt":0.29525157184126294,"score_spread":0.2476417612586847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297023514","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032362586,0.0018063668,0.00038426113,0.6010971,0.3209987,0.00017498934,0.0013544346,0.000759212,0.07310132],"genre_scores_gemma":[0.004107472,0.0013949923,0.00030496193,0.6182157,0.100294895,0.00026556518,0.0007143692,0.00047844945,0.27422363],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980567,0.00032156022,0.0001987744,0.00034320075,0.0007155036,0.00036420487],"domain_scores_gemma":[0.99482536,0.0014373221,0.00019142064,0.0003315404,0.0022776218,0.0009368625],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002018967,0.0008147648,0.00094168505,0.0010848064,0.0024185623,0.0036627392,0.0024437262,0.017138023,0.27932844],"category_scores_gemma":[0.023500167,0.0004298081,0.0012262202,0.0008057208,0.0015974591,0.0027761792,0.0022484323,0.013742896,0.17158248],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011945117,0.0000032040637,0.000035612353,0.000013834817,0.0000012787411,0.000054059194,0.0000058257065,0.000004671832,0.00001688823,0.00029836435,0.99698526,0.002569084],"study_design_scores_gemma":[0.000012091311,0.0000071618833,0.00016584135,0.000049445378,0.0000021554713,0.00007411709,0.000035744353,0.00003054902,0.000056762816,0.00048720805,0.999071,0.000008039768],"about_ca_topic_score_codex":0.0062063984,"about_ca_topic_score_gemma":0.007427465,"teacher_disagreement_score":0.72067153,"about_ca_system_score_codex":0.0026785603,"about_ca_system_score_gemma":0.0026862833,"threshold_uncertainty_score":0.9344467},"labels":[],"label_agreement":null},{"id":"W4297038138","doi":"10.5194/hess-2022-96-ac14","title":"Reply on CC1","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Global Institute for Water Security","funders":"Global Institute for Water Security, University of Saskatchewan","keywords":"Span (engineering); Evapotranspiration; Life span; Mathematics; Precipitation; Fertilizer; Mean squared error; Statistics; Irrigation; Moisture; Environmental science; Hydrology (agriculture); Meteorology; Physics; Agronomy; Geology; Ecology; Engineering","score_opus":0.047926259433055576,"score_gpt":0.2954688617724277,"score_spread":0.24754260233937214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297038138","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029176768,0.0019347713,0.00031848694,0.68177396,0.25219747,0.00017359186,0.0012443692,0.00062769593,0.06143799],"genre_scores_gemma":[0.0038099596,0.0014362993,0.0002725877,0.68855184,0.08043302,0.00025080855,0.00066266424,0.00034265415,0.22424015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99802554,0.00036677523,0.00021393197,0.00034084372,0.0006820626,0.0003709147],"domain_scores_gemma":[0.9940201,0.00172378,0.0002226961,0.0003357565,0.0027159655,0.0009817663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002013061,0.00081953255,0.0009863329,0.0011005831,0.002485923,0.0034569898,0.0025227582,0.018423839,0.27238864],"category_scores_gemma":[0.02578705,0.00044856762,0.0011850089,0.00082754705,0.0016156797,0.0027384693,0.0023268235,0.014615252,0.1606445],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011493385,0.000002922151,0.000035074194,0.00001406992,0.0000011724446,0.000051750845,0.000006308266,0.0000038719704,0.000013760319,0.00024770878,0.997326,0.0022858982],"study_design_scores_gemma":[0.00001353454,0.000008711389,0.00019464726,0.00006356892,0.0000024575138,0.000087754735,0.000046520705,0.00002799401,0.000054920536,0.00050827744,0.9989826,0.000009094714],"about_ca_topic_score_codex":0.006465073,"about_ca_topic_score_gemma":0.007726485,"teacher_disagreement_score":0.27238864,"about_ca_system_score_codex":0.002956795,"about_ca_system_score_gemma":0.0027019111,"threshold_uncertainty_score":0.9112308},"labels":[],"label_agreement":null},{"id":"W4297121113","doi":"10.1061/(asce)ir.1943-4774.0001722","title":"Discussion of “Comprehensive Evaluation of Machine Learning Techniques for Hydrological Drought Forecasting” by Muhammad Jehanzaib, Muhammad Bilal Idrees, Dongkyun Kim, and Tae-Woong Kim","year":2022,"lang":"en","type":"article","venue":"Journal of Irrigation and Drainage Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Artificial intelligence; Computer science","score_opus":0.022797095781152615,"score_gpt":0.24254935109068276,"score_spread":0.21975225530953016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297121113","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021175176,0.059503026,0.12778851,0.7279739,0.025720969,0.0003498093,0.0011489748,0.00048438506,0.03585525],"genre_scores_gemma":[0.46494713,0.045609355,0.13808341,0.24571949,0.069061406,0.0007200928,0.0017096895,0.00051650143,0.033632874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.983997,0.009028626,0.0011640599,0.00089436764,0.0045583504,0.00035752828],"domain_scores_gemma":[0.9305352,0.046575245,0.0011436457,0.001616904,0.019391838,0.00073720905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030721135,0.001064162,0.0010725504,0.003166867,0.0015381448,0.0063080424,0.0022736662,0.004900143,0.005043653],"category_scores_gemma":[0.091916576,0.00031814087,0.001816485,0.0035306718,0.0019148143,0.006091918,0.0019402159,0.0041797166,0.0010110008],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010352068,0.00038337134,0.008400468,0.0015982944,0.0014021959,0.0007604727,0.0009268567,0.038297776,0.0036821205,0.18645535,0.38545302,0.37160486],"study_design_scores_gemma":[0.00045583906,0.001189863,0.017004892,0.00478267,0.0012521804,0.0008199988,0.0036628502,0.13495487,0.014243908,0.24571094,0.5754524,0.00046960035],"about_ca_topic_score_codex":0.0061947014,"about_ca_topic_score_gemma":0.008570145,"teacher_disagreement_score":0.030721135,"about_ca_system_score_codex":0.002123055,"about_ca_system_score_gemma":0.0026676178,"threshold_uncertainty_score":0.16247088},"labels":[],"label_agreement":null},{"id":"W4304469632","doi":"10.5194/gmd-2022-174-ac2","title":"Reply on RC1","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Uppsala Universitet; Vetenskapsrådet; Svenska Forskningsrådet Formas; Norges Forskningsråd; European Commission; Joint Programming Initiative Water challenges for a changing world","keywords":"Algal bloom; Computer science; Fish <Actinopterygii>; Bathythermograph; Chlorophyll a; Nutrient; Workflow; Bloom; Training set; Machine learning; Environmental science; Artificial intelligence; Oceanography; Phytoplankton; Ecology; Fishery; Chemistry; Geology; Biology","score_opus":0.048234306815310685,"score_gpt":0.2956930229855484,"score_spread":0.2474587161702377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304469632","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017637188,0.0009296756,0.00023782437,0.8588109,0.12629838,0.00007353831,0.0006926634,0.0003528684,0.01242774],"genre_scores_gemma":[0.0024869137,0.0008458385,0.0002407598,0.8705335,0.062730886,0.00016484913,0.00036680317,0.0002353486,0.062395092],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736845,0.00048073652,0.00032436816,0.00043670365,0.000978738,0.0004109519],"domain_scores_gemma":[0.9875058,0.004031813,0.0005018895,0.00063498924,0.0056900857,0.0016354909],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030090099,0.0008201989,0.0010493661,0.0013413191,0.0027139399,0.0036311704,0.0031203183,0.023985503,0.116094634],"category_scores_gemma":[0.043537673,0.0005666331,0.001187725,0.0009613841,0.0018433557,0.0037338748,0.0024174775,0.020056058,0.08437412],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008452447,0.0000021868902,0.00003943987,0.000013092729,0.0000014079675,0.00004925783,0.000007871855,0.0000037858106,0.000015551856,0.00018333139,0.99818546,0.0014901219],"study_design_scores_gemma":[0.0000144062105,0.0000085888805,0.00030767723,0.00007004257,0.000004218628,0.00011323401,0.00006780244,0.00004323535,0.000095771364,0.0006572637,0.99860185,0.000015766502],"about_ca_topic_score_codex":0.009786634,"about_ca_topic_score_gemma":0.011185291,"teacher_disagreement_score":0.88390535,"about_ca_system_score_codex":0.0037233566,"about_ca_system_score_gemma":0.0035705988,"threshold_uncertainty_score":0.38837522},"labels":[],"label_agreement":null},{"id":"W4304588604","doi":"10.5194/gmd-2022-174-ac1","title":"Reply on CEC1","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Uppsala Universitet; Vetenskapsrådet; Svenska Forskningsrådet Formas; Norges Forskningsråd; European Commission; Joint Programming Initiative Water challenges for a changing world","keywords":"Algal bloom; Computer science; Chlorophyll a; Fish <Actinopterygii>; Nutrient; Bloom; Bathythermograph; Workflow; Training set; Machine learning; Environmental science; Oceanography; Phytoplankton; Artificial intelligence; Ecology; Fishery; Chemistry; Biology; Geology","score_opus":0.04792323377388096,"score_gpt":0.2945439741124979,"score_spread":0.24662074033861692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304588604","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018715052,0.00082290027,0.00022304003,0.8653519,0.12236288,0.00005798737,0.0006533725,0.00031343193,0.010027401],"genre_scores_gemma":[0.0026934617,0.00083308434,0.0002349531,0.87755567,0.06395726,0.00013789885,0.00039723597,0.00020112268,0.05398924],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99795806,0.0003997565,0.00023897224,0.00031664263,0.0007636729,0.00032291835],"domain_scores_gemma":[0.9886092,0.0037017479,0.00046861486,0.00043390327,0.005183034,0.0016036144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002778152,0.00085510017,0.0010053143,0.0013392415,0.0024836515,0.003307587,0.0024690737,0.021641215,0.10100388],"category_scores_gemma":[0.03554381,0.0005296743,0.0010306691,0.0008516001,0.0017076251,0.003503209,0.0022242968,0.016951634,0.06273323],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010394934,0.0000024828407,0.000048148457,0.000011648604,0.0000012882576,0.000050066086,0.0000062900963,0.0000038146013,0.000016643278,0.00014730645,0.9983399,0.0013619469],"study_design_scores_gemma":[0.000019394802,0.000011413647,0.00042958744,0.00007067326,0.000004264554,0.00012650025,0.00006621307,0.00005904589,0.00010410442,0.0006573245,0.99843377,0.00001776501],"about_ca_topic_score_codex":0.006673263,"about_ca_topic_score_gemma":0.008997641,"teacher_disagreement_score":0.10100388,"about_ca_system_score_codex":0.002896,"about_ca_system_score_gemma":0.0028035853,"threshold_uncertainty_score":0.33789164},"labels":[],"label_agreement":null},{"id":"W4304607364","doi":"10.5194/gmd-2022-174-ac3","title":"Reply on RC2","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Uppsala Universitet; Vetenskapsrådet; Svenska Forskningsrådet Formas; Norges Forskningsråd; European Commission; Joint Programming Initiative Water challenges for a changing world","keywords":"Algal bloom; Computer science; Bathythermograph; Chlorophyll a; Nutrient; Workflow; Bloom; Fish <Actinopterygii>; Environmental science; Machine learning; Oceanography; Phytoplankton; Ecology; Fishery; Chemistry; Biology; Geology","score_opus":0.048234306815310685,"score_gpt":0.2956930229855484,"score_spread":0.2474587161702377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304607364","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021853899,0.000996389,0.00029469933,0.819924,0.16220438,0.000077466866,0.0007131422,0.000408385,0.015162981],"genre_scores_gemma":[0.0031830827,0.00096533465,0.00028465886,0.8304289,0.07772943,0.00016885147,0.0004029538,0.0002992129,0.086537555],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978344,0.00038302472,0.00025243819,0.0003722207,0.0008256085,0.00033236566],"domain_scores_gemma":[0.9906048,0.0029275713,0.00036419462,0.0005021083,0.004287089,0.001314152],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024962313,0.0007843,0.00090857066,0.0012009735,0.0023735587,0.003368722,0.0027568555,0.019977188,0.11666449],"category_scores_gemma":[0.035912223,0.00047864206,0.0011065075,0.0008128161,0.0016427243,0.003444316,0.0021655313,0.017254079,0.083188795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009231345,0.0000023551415,0.00004076216,0.000011929307,0.0000014581531,0.00005804764,0.000007295251,0.0000043258274,0.000017765531,0.00019446334,0.99795675,0.0016956518],"study_design_scores_gemma":[0.000012496997,0.0000074650175,0.0002578535,0.000053546188,0.0000037070504,0.000116571675,0.000059224065,0.000045679695,0.0000993098,0.0006025297,0.99872845,0.00001323151],"about_ca_topic_score_codex":0.0084218765,"about_ca_topic_score_gemma":0.009749514,"teacher_disagreement_score":0.88333553,"about_ca_system_score_codex":0.0030691363,"about_ca_system_score_gemma":0.0028663639,"threshold_uncertainty_score":0.39028162},"labels":[],"label_agreement":null},{"id":"W4310478181","doi":"10.3390/hydrology9120216","title":"Forecasting High-Flow Discharges in a Flashy Catchment Using Multiple Precipitation Estimates as Predictors in Machine Learning Models","year":2022,"lang":"en","type":"article","venue":"Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Environment and Climate Change Canada","keywords":"Quantitative precipitation estimation; Precipitation; Flow (mathematics); Machine learning; Computer science; Novelty; Meteorology; Radar; Artificial intelligence; Environmental science; Mathematics; Geography","score_opus":0.0365505414412861,"score_gpt":0.2420428748720379,"score_spread":0.2054923334307518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310478181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91591996,0.0001225185,0.083163284,0.00011838117,0.000012985872,0.000012934726,0.000090104404,0.00017360611,0.00038619994],"genre_scores_gemma":[0.99337983,0.000033811,0.0063919025,0.0000053435683,0.0000055878904,0.000005064634,0.00006187949,0.000003268259,0.00011336305],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976224,0.00009439874,0.000016974498,0.000057671394,0.000043049327,0.000025759917],"domain_scores_gemma":[0.9987722,0.0009190516,0.00011276209,0.00006000052,0.00009751694,0.000038439022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011812504,0.00037161438,0.00043431183,0.0007016744,0.00015343579,0.0005361974,0.00030107098,0.00033770854,0.00020785395],"category_scores_gemma":[0.0028746636,0.00018184795,0.00026667485,0.0006623802,0.0002726104,0.0008016778,0.000418409,0.0004965686,0.00005053019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000600907,0.00005337676,0.01892414,0.000015223214,0.00004417718,0.00004917415,0.000028140239,0.9523954,0.0016327051,0.00037831385,0.000084072555,0.026335277],"study_design_scores_gemma":[0.0000015051828,0.000014698772,0.002166391,9.469434e-7,0.0000025632562,0.000003238622,0.0000050221734,0.9971308,0.00041802682,0.00023251692,0.000022346043,0.0000018491991],"about_ca_topic_score_codex":0.006411596,"about_ca_topic_score_gemma":0.0059768613,"teacher_disagreement_score":0.006411596,"about_ca_system_score_codex":0.00044587185,"about_ca_system_score_gemma":0.0003731761,"threshold_uncertainty_score":0.012748539},"labels":[],"label_agreement":null},{"id":"W4311838393","doi":"","title":"ANN output updating of lumped conceptual rainfall-runoff forecasting models","year":2003,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Surface runoff; Environmental science; Meteorology; Hydrology (agriculture); Runoff model; Computer science; Geology; Geography; Geotechnical engineering","score_opus":0.09499551402833611,"score_gpt":0.25639347417035063,"score_spread":0.16139796014201452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311838393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.689966,0.00039862323,0.30086774,0.00020500392,0.00014708172,0.00010617019,0.00036028924,0.0018626334,0.0060864487],"genre_scores_gemma":[0.97900087,0.000072976,0.020090941,0.000016692979,0.000009202619,0.00003098051,0.00014371918,0.000024772946,0.00060993276],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995976,0.00014397579,0.000042049254,0.00009338524,0.0000924487,0.000030510604],"domain_scores_gemma":[0.99846715,0.0008163675,0.00016929544,0.00019680386,0.0003213377,0.000029003555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015861002,0.0006807398,0.00046193643,0.00036303402,0.00014990785,0.00056273537,0.0008377878,0.00041188695,0.0008221709],"category_scores_gemma":[0.0059081726,0.00021998839,0.00028618673,0.0004356378,0.00026503287,0.0008569068,0.0004678299,0.00055409,0.00013602259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019708785,0.00005311705,0.0024620222,0.00008005885,0.000052222233,0.000044699278,0.00004449496,0.9357055,0.0029539238,0.0011164194,0.00028668783,0.057003748],"study_design_scores_gemma":[0.000007686859,0.000027310927,0.0004940145,0.000003861033,0.000010010269,0.0000065032605,0.000003253068,0.99762243,0.0012851743,0.00042994157,0.00010500647,0.0000046944174],"about_ca_topic_score_codex":0.0042295866,"about_ca_topic_score_gemma":0.004048387,"teacher_disagreement_score":0.0042295866,"about_ca_system_score_codex":0.00049841614,"about_ca_system_score_gemma":0.00026686687,"threshold_uncertainty_score":0.008409917},"labels":[],"label_agreement":null},{"id":"W4312242043","doi":"10.2139/ssrn.4293414","title":"Assessing the Uncertainties in Modeling Water Temperatures During River Cooling and Freeze-Up Periods","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Environmental science; Hydrology (agriculture); Geology; Geotechnical engineering","score_opus":0.011827002441363784,"score_gpt":0.24180082408715978,"score_spread":0.229973821645796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312242043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98184514,0.000171139,0.015561519,0.00025302888,0.00003476787,0.000018047245,0.0004755693,0.000094825125,0.0015460022],"genre_scores_gemma":[0.9984005,0.000038323928,0.0012415419,0.000011098934,0.00000849151,0.000006538811,0.00016004132,0.000010077986,0.00012344435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995974,0.00015108704,0.00003057637,0.0000894376,0.000065865,0.00006558914],"domain_scores_gemma":[0.9921515,0.0065307645,0.00046131114,0.00021621857,0.00044423027,0.00019607593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028358502,0.0007654524,0.00061510823,0.0006760139,0.0004784078,0.001389086,0.0007524613,0.0012889347,0.00047513092],"category_scores_gemma":[0.009341701,0.0006101642,0.0007091062,0.00075252086,0.000522187,0.0016511126,0.00066077174,0.0013569419,0.000067471046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059435057,0.000015205559,0.006472732,0.000008621189,0.000033252534,0.000019145815,0.000012784916,0.9916408,0.00023004434,0.00018917014,0.00004498973,0.0012737486],"study_design_scores_gemma":[0.000007564989,0.000027229793,0.0034786246,0.0000035738535,0.00001606803,0.0000042849165,0.00001942599,0.9955537,0.0004903132,0.0003390372,0.000052753872,0.0000074072454],"about_ca_topic_score_codex":0.04420414,"about_ca_topic_score_gemma":0.022249803,"teacher_disagreement_score":0.04420414,"about_ca_system_score_codex":0.0013642912,"about_ca_system_score_gemma":0.0009459674,"threshold_uncertainty_score":0.087893724},"labels":[],"label_agreement":null},{"id":"W4312385468","doi":"10.2139/ssrn.4261893","title":"Screening of Waterflooding Using Smart Proxy Model Coupled with Deep Convolutional Neural Network","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Proxy (statistics); Convolutional neural network; Computer science; Artificial intelligence; Petroleum engineering; Geology; Machine learning","score_opus":0.017260142974075826,"score_gpt":0.21939433202447775,"score_spread":0.20213418905040192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312385468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9169539,0.00041018234,0.07603446,0.00038129423,0.00011303392,0.000036475292,0.0017739135,0.0013801076,0.0029167351],"genre_scores_gemma":[0.98965585,0.000091297254,0.008334393,0.000034514993,0.000014666089,0.0000075290714,0.0010119774,0.000033674354,0.0008160557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998635,0.000016559636,0.0000068033896,0.000046939764,0.000027259246,0.000038892766],"domain_scores_gemma":[0.9995907,0.00014589912,0.00004314481,0.000047511185,0.00011165178,0.00006117476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032651235,0.0006503657,0.0007086425,0.00093037676,0.00031088217,0.00070664694,0.0008011211,0.0011192317,0.0017709344],"category_scores_gemma":[0.0015503914,0.00036943093,0.0006326136,0.00087807,0.00021361628,0.00111688,0.00052072026,0.0005050171,0.00037901258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004909671,0.0002624443,0.07334852,0.00017828152,0.00018240008,0.000781748,0.00006249288,0.8298868,0.017621424,0.0013860383,0.003818314,0.071980506],"study_design_scores_gemma":[0.000006592639,0.0000096395615,0.002003654,0.000002644393,0.000009167658,0.000008226617,0.000010373389,0.9964844,0.0011677222,0.00020914442,0.0000830714,0.000005307853],"about_ca_topic_score_codex":0.021299321,"about_ca_topic_score_gemma":0.020363279,"teacher_disagreement_score":0.021299321,"about_ca_system_score_codex":0.00043737236,"about_ca_system_score_gemma":0.0009618683,"threshold_uncertainty_score":0.04235071},"labels":[],"label_agreement":null},{"id":"W4313532989","doi":"10.5194/gmd-16-35-2023","title":"Prediction of algal blooms via data-driven machine learning models: an evaluation using data from a well-monitored mesotrophic lake","year":2023,"lang":"en","type":"article","venue":"Geoscientific model development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Uppsala Universitet; Vetenskapsrådet; Svenska Forskningsrådet Formas; Norges Forskningsråd; European Commission; Joint Programming Initiative Water challenges for a changing world","keywords":"Algal bloom; Chlorophyll a; Computer science; Bloom; Nutrient; Environmental science; Bathythermograph; Test data; Machine learning; Phytoplankton; Oceanography; Ecology; Chemistry; Biology","score_opus":0.28688024410384416,"score_gpt":0.30663351084318236,"score_spread":0.019753266739338193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313532989","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9769786,0.0002018274,0.020563673,0.00025200006,0.000039576098,0.00006451751,0.00043113792,0.0007634617,0.0007052266],"genre_scores_gemma":[0.98642725,0.00006715503,0.012547181,0.00003844792,0.00000953115,0.000052312957,0.0005536695,0.000016111702,0.00028838607],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997801,0.000087159286,0.000021002303,0.0000555809,0.000035365705,0.00002073716],"domain_scores_gemma":[0.9982326,0.0011149376,0.000085401574,0.000092016744,0.00039886555,0.00007607417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017426958,0.0010340569,0.0005407239,0.0005626901,0.0003201209,0.0005426353,0.0006615313,0.00088487193,0.0005247469],"category_scores_gemma":[0.0031356898,0.00035818983,0.00063571514,0.0004975394,0.00032488775,0.0008338022,0.00039500504,0.00091864774,0.00016208537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020746025,0.00029580118,0.0113400845,0.00005147357,0.00009516974,0.00007838273,0.0000410844,0.96757746,0.0021468657,0.00013846176,0.00030647044,0.017721392],"study_design_scores_gemma":[0.000008441635,0.00003008516,0.000968735,0.0000014189251,0.0000049229766,0.000002280056,0.00000443622,0.9983511,0.0005573842,0.00004324886,0.000024948873,0.0000031623094],"about_ca_topic_score_codex":0.035692688,"about_ca_topic_score_gemma":0.030326413,"teacher_disagreement_score":0.035692688,"about_ca_system_score_codex":0.0012138659,"about_ca_system_score_gemma":0.0010493536,"threshold_uncertainty_score":0.07096988},"labels":[],"label_agreement":null},{"id":"W4313897362","doi":"10.1007/s10661-022-10870-7","title":"Prediction of water quality extremes with composite quantile regression neural network","year":2023,"lang":"en","type":"article","venue":"Environmental Monitoring and Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"WSP (Canada)","funders":"Water Research Foundation","keywords":"Quantile regression; Quantile; Statistics; Turbidity; Regression; Linear regression; Water quality; Predictability; Regression analysis; Artificial neural network; Environmental science; Econometrics; Mathematics; Computer science; Machine learning; Geology","score_opus":0.04599524938881236,"score_gpt":0.2913978143730039,"score_spread":0.24540256498419152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313897362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63075185,0.00042731722,0.36552855,0.00018563485,0.00010618219,0.00003434797,0.000382181,0.00072129216,0.0018626308],"genre_scores_gemma":[0.99001896,0.00004617928,0.009338178,0.000013760492,0.000015509777,0.000012507391,0.00014253198,0.000007511985,0.0004048115],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998184,0.00004042197,0.000009871992,0.000055788114,0.000040785304,0.00003482193],"domain_scores_gemma":[0.9993247,0.00038143154,0.00007317108,0.00003432198,0.0001583981,0.000028040424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006968417,0.00040312437,0.00049082906,0.00056972675,0.00016642855,0.0003834784,0.0004637533,0.00040693063,0.00072124484],"category_scores_gemma":[0.0018018151,0.0001979925,0.00038115543,0.0006980338,0.00018448476,0.00046302046,0.0004054383,0.0006885083,0.000109047796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026106325,0.00010199563,0.010207825,0.000021142483,0.00006992957,0.000041034815,0.000015515789,0.9362272,0.0015073108,0.00065472786,0.00053921225,0.05035305],"study_design_scores_gemma":[0.0000016138125,0.000005054607,0.00056886766,3.1144646e-7,0.0000016314082,0.0000010479719,6.9561224e-7,0.99920887,0.00008371335,0.000118010845,0.000009349508,9.242588e-7],"about_ca_topic_score_codex":0.009991048,"about_ca_topic_score_gemma":0.007227578,"teacher_disagreement_score":0.009991048,"about_ca_system_score_codex":0.0004385421,"about_ca_system_score_gemma":0.00028370478,"threshold_uncertainty_score":0.01986581},"labels":[],"label_agreement":null},{"id":"W4321481323","doi":"10.5194/egusphere-egu23-5736","title":"A Novel Workflow for Streamflow Prediction in the Presence of Missing Gauge Observations","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Streamflow; Missing data; Imputation (statistics); Categorical variable; Computer science; Flood myth; Flood forecasting; Leverage (statistics); Environmental science; Climatology; Data mining; Artificial intelligence; Machine learning; Cartography; Drainage basin; Geography","score_opus":0.1495463023783649,"score_gpt":0.2983499661939493,"score_spread":0.14880366381558444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321481323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012828313,0.00006537359,0.917355,0.0002011188,0.00010534469,0.00022747184,0.0038449098,0.06323972,0.0021327462],"genre_scores_gemma":[0.21984342,0.00020266588,0.7574141,0.00020605008,0.000071061724,0.00036337652,0.014747626,0.0019012432,0.005250468],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991792,0.00007188667,0.000100429475,0.00033802772,0.0002510748,0.000059402024],"domain_scores_gemma":[0.99837106,0.00041377495,0.000120365774,0.0005485026,0.000413133,0.00013330636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020494333,0.00094832806,0.0006733869,0.00092089165,0.0008049997,0.0016374704,0.0018652581,0.0006745601,0.004772621],"category_scores_gemma":[0.0043068943,0.0004846545,0.0011162445,0.000937207,0.00044071485,0.0018306213,0.0017676969,0.0011608807,0.0028527335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010173018,0.0004255207,0.025196524,0.00034424016,0.000237265,0.0013796054,0.0011298164,0.14202715,0.034123465,0.020316793,0.05021442,0.7235879],"study_design_scores_gemma":[0.00006547535,0.0000481537,0.0026320806,0.000026259453,0.000026525622,0.0001595411,0.00012256483,0.9442219,0.014984555,0.014996442,0.02266362,0.00005290596],"about_ca_topic_score_codex":0.014155793,"about_ca_topic_score_gemma":0.013137601,"teacher_disagreement_score":0.014155793,"about_ca_system_score_codex":0.0006580721,"about_ca_system_score_gemma":0.0034281798,"threshold_uncertainty_score":0.028146803},"labels":[],"label_agreement":null},{"id":"W4321493748","doi":"10.5194/egusphere-egu23-39","title":"Deep Convolutional Architectures for Uncertainty Quantification and Forecast in Inundation Problems","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Uncertainty quantification; Solver; Convolutional neural network; Nonlinear system; Benchmark (surveying); Context (archaeology); Artificial neural network; Perceptron; Algorithm; Propagation of uncertainty; Mathematical optimization; Surrogate model; Machine learning; Artificial intelligence; Data mining; Mathematics","score_opus":0.0725238480437835,"score_gpt":0.2887131021988196,"score_spread":0.21618925415503612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321493748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032195356,0.0010149828,0.9621967,0.000531289,0.000069146365,0.000017691284,0.00020970056,0.0009813842,0.0027836943],"genre_scores_gemma":[0.84144866,0.0017922078,0.14992122,0.00019962447,0.00011343658,0.00007456669,0.000761205,0.00014873121,0.005540388],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998411,0.00003703326,0.000011670917,0.000038654864,0.00005067024,0.000020884978],"domain_scores_gemma":[0.99964917,0.00017792836,0.000041534135,0.000041349052,0.000073906296,0.000016055636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005166826,0.0007533736,0.0004730377,0.00039916817,0.00021993408,0.00076646765,0.000783135,0.0008282729,0.0014787313],"category_scores_gemma":[0.0016658859,0.00042923176,0.00055047806,0.00046294942,0.0004582148,0.0010204628,0.0007775541,0.0017423865,0.00029932428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026069134,0.000014372873,0.00032800602,0.000039144034,0.00002658211,0.000024855848,0.000026043539,0.95144933,0.00220079,0.010120824,0.0007304652,0.035013486],"study_design_scores_gemma":[4.296339e-7,0.000002546901,0.00004273133,0.0000020834557,0.0000017031806,0.0000015773974,0.0000012358578,0.99789774,0.00026489497,0.0016432188,0.00014052133,0.0000012617542],"about_ca_topic_score_codex":0.01109881,"about_ca_topic_score_gemma":0.008770867,"teacher_disagreement_score":0.01109881,"about_ca_system_score_codex":0.001012862,"about_ca_system_score_gemma":0.0007189,"threshold_uncertainty_score":0.022068381},"labels":[],"label_agreement":null},{"id":"W4321996236","doi":"10.5194/egusphere-egu23-10575","title":"Machine learning and hydrological sciences: A systematic overview  of review papers","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Context (archaeology); Computer science; Artificial intelligence; Systematic review; Scope (computer science); Data science; Management science; Machine learning; Geography; Engineering; Political science","score_opus":0.11894929350185371,"score_gpt":0.32694262508799926,"score_spread":0.20799333158614555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321996236","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002549647,0.99820495,0.00024688634,0.00045700293,0.00015970995,0.00014156844,0.00022328564,0.000007840946,0.00030378805],"genre_scores_gemma":[0.0017463424,0.9963483,0.00082987174,0.00038152043,0.00011346469,0.0002823801,0.00016452465,0.0000046123505,0.00012906855],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99299824,0.0020105182,0.0026127256,0.0005590402,0.0015410497,0.00027836705],"domain_scores_gemma":[0.9726924,0.016690724,0.005413318,0.00034197484,0.004472208,0.00038935358],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010842448,0.0020364968,0.004833429,0.031450015,0.0008476744,0.0035146102,0.0017767146,0.001904621,0.004821203],"category_scores_gemma":[0.035094135,0.0010917848,0.005261803,0.029237669,0.0007395257,0.004566857,0.0020956425,0.001423885,0.0008545475],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017260229,0.000029917304,0.00091875065,0.7877863,0.002531883,0.00033585884,0.00053367176,0.00028138421,0.0005098765,0.001536422,0.011690401,0.19367296],"study_design_scores_gemma":[0.00005710164,0.00016719285,0.0027498526,0.8379315,0.010712881,0.00072411424,0.0005339278,0.00013120213,0.00029050757,0.0012742612,0.1453764,0.000051036623],"about_ca_topic_score_codex":0.0055159195,"about_ca_topic_score_gemma":0.016311657,"teacher_disagreement_score":0.98915756,"about_ca_system_score_codex":0.004493311,"about_ca_system_score_gemma":0.01564885,"threshold_uncertainty_score":0.05734098},"labels":[],"label_agreement":null},{"id":"W4322208747","doi":"10.5194/egusphere-egu23-15968","title":"Differentiable modeling to unify machine learning and physical models and advance Geosciences","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Interpretability; Machine learning; Artificial intelligence; Computer science; Differentiable function; Leverage (statistics); Consistency (knowledge bases); Deep learning; Data science; Artificial neural network; Mathematics","score_opus":0.0497047783015673,"score_gpt":0.2844941740250474,"score_spread":0.2347893957234801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322208747","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032927662,0.002490992,0.9782857,0.0039639217,0.00026752808,0.000023592966,0.00029905885,0.0005499832,0.010826455],"genre_scores_gemma":[0.3712278,0.014160897,0.58530885,0.0026238835,0.0013368877,0.0003261232,0.0010032033,0.0011606008,0.022851657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992478,0.00027696983,0.00004166898,0.00017274376,0.00021685113,0.0000440359],"domain_scores_gemma":[0.9978296,0.0013161028,0.00019641317,0.00035786437,0.00021978359,0.00008017822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018740114,0.0015196747,0.001035624,0.0013406422,0.000507842,0.0031233486,0.001728013,0.0019126175,0.0046752635],"category_scores_gemma":[0.0053239795,0.00074462796,0.0016004752,0.0014049588,0.0030353204,0.004700433,0.0028385269,0.005260588,0.0015271214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021268788,0.00002554707,0.0007864254,0.00019201222,0.000055803815,0.00007852694,0.00012059638,0.21072558,0.0010405008,0.7383935,0.0049827937,0.04357754],"study_design_scores_gemma":[0.000006715132,0.00002254421,0.00024160692,0.00008772038,0.00002067787,0.00004287141,0.000023969185,0.5136501,0.0007745495,0.45890394,0.026198817,0.000026517102],"about_ca_topic_score_codex":0.005197572,"about_ca_topic_score_gemma":0.003506103,"teacher_disagreement_score":0.005197572,"about_ca_system_score_codex":0.0020331172,"about_ca_system_score_gemma":0.0016767014,"threshold_uncertainty_score":0.015640318},"labels":[],"label_agreement":null},{"id":"W4323047633","doi":"10.5194/egusphere-2022-852-ac2","title":"Reply on RC2","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Ministry of Science and Technology, Taiwan; Academia Sinica; Global Lake Ecological Observatory Network","keywords":"Typhoon; Environmental science; Dissolved organic carbon; Stratification (seeds); Subtropics; Ecosystem; Hydrology (agriculture); Monsoon; Lake ecosystem; Oceanography; Inflow; Ecology; Geology","score_opus":0.06951189450486074,"score_gpt":0.3139567726992264,"score_spread":0.24444487819436567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323047633","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022280139,0.0018833386,0.0002528996,0.6846813,0.27885225,0.0000815173,0.00046408392,0.0004271331,0.033134654],"genre_scores_gemma":[0.0029163342,0.0012866157,0.00026518488,0.7428073,0.094890244,0.00015195116,0.00024099657,0.00027883376,0.15716244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981577,0.0003240458,0.00018496846,0.00037058152,0.00067952037,0.00028320384],"domain_scores_gemma":[0.9950014,0.0013838512,0.00021307555,0.0003862526,0.0020904718,0.0009250475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019868237,0.00096501136,0.00096645544,0.0010449692,0.0024956593,0.003989888,0.0030309858,0.020703575,0.15593797],"category_scores_gemma":[0.01928807,0.0005536666,0.0012687118,0.000753327,0.002117881,0.004007314,0.0026775862,0.020414623,0.12056381],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008761685,0.0000035958467,0.00003217459,0.0000141216615,0.000001555855,0.00006792278,0.000008910999,0.0000047480703,0.000021860838,0.00029353818,0.9970692,0.0024736093],"study_design_scores_gemma":[0.000008616398,0.000005392333,0.00014857753,0.000040561503,0.00000206096,0.00007614602,0.000047931848,0.000021453137,0.00005425494,0.00044045586,0.9991468,0.000007831029],"about_ca_topic_score_codex":0.005724984,"about_ca_topic_score_gemma":0.0067900666,"teacher_disagreement_score":0.15593797,"about_ca_system_score_codex":0.0027734928,"about_ca_system_score_gemma":0.0024411783,"threshold_uncertainty_score":0.5216645},"labels":[],"label_agreement":null},{"id":"W4324361274","doi":"10.1016/j.envsoft.2023.105682","title":"Regional frequency analysis of stream temperature at ungauged sites using non-linear canonical correlation analysis and generalized additive models","year":2023,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pacific Institute for Climate Solutions; University of Victoria; University of New Brunswick; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Bundesamt für Umwelt; Natural Sciences and Engineering Research Council of Canada","keywords":"Canonical correlation; Generalized additive model; Generalized linear model; Linearity; Mathematics; Linear correlation; Nonlinear system; Econometrics; Statistics; Environmental science; Engineering; Physics","score_opus":0.03392986769235722,"score_gpt":0.24586149877508112,"score_spread":0.2119316310827239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324361274","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98367935,0.000045817847,0.014766999,0.000025966381,0.000010073306,0.000012191398,0.0006615825,0.00018424593,0.0006137533],"genre_scores_gemma":[0.9935088,0.000017837567,0.0055996897,0.0000023892087,0.0000049329856,0.000009140955,0.00066804973,0.000031053776,0.00015807933],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994319,0.00025124536,0.000029437679,0.00015053898,0.00007287639,0.00006394667],"domain_scores_gemma":[0.99808973,0.0009303617,0.00021086275,0.00024726498,0.00045031737,0.00007138571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011531787,0.00025864088,0.0003223102,0.0016932631,0.00023168842,0.0004432563,0.00035435508,0.00021573312,0.00074501947],"category_scores_gemma":[0.0031167013,0.00016358725,0.00069175777,0.0019055116,0.00017183302,0.00038750845,0.00036701775,0.00026271679,0.00023366259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047254458,0.00015751117,0.7596686,0.000096988464,0.00055175606,0.000194251,0.00063056225,0.14965802,0.00807827,0.0017565961,0.0014675182,0.07726731],"study_design_scores_gemma":[0.000015305404,0.000056057175,0.59910804,0.000008931378,0.00009679357,0.0000852245,0.00018889696,0.3984937,0.0009400761,0.0004101135,0.00056032994,0.000036513156],"about_ca_topic_score_codex":0.027654007,"about_ca_topic_score_gemma":0.040561285,"teacher_disagreement_score":0.027654007,"about_ca_system_score_codex":0.0003879396,"about_ca_system_score_gemma":0.00046788206,"threshold_uncertainty_score":0.05498606},"labels":[],"label_agreement":null},{"id":"W4327519687","doi":"10.2139/ssrn.4379752","title":"Copula-Based Joint Modelling of Extreme River Temperature and Low Flow Characteristics in the Risk Assessment of Aquatic Life","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institut National de la Recherche Scientifique","funders":"","keywords":"Copula (linguistics); Environmental science; Joint (building); Risk assessment; Econometrics; Computer science; Engineering; Mathematics; Civil engineering","score_opus":0.037803139460983536,"score_gpt":0.23797656206581888,"score_spread":0.20017342260483534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327519687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41220975,0.0006639048,0.581922,0.00028910013,0.00008236663,0.00004801838,0.00037846973,0.0004161145,0.0039902744],"genre_scores_gemma":[0.987432,0.00018626825,0.010140765,0.000024073164,0.000023538822,0.000026169726,0.000153958,0.000047487054,0.0019656697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978167,0.000092755065,0.000011449926,0.000049184295,0.00003141128,0.000033483502],"domain_scores_gemma":[0.9990627,0.0006027934,0.0001076855,0.000037759044,0.00012988098,0.000059087586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008674502,0.0004869653,0.00080149947,0.00043486297,0.00024250991,0.0010090802,0.000856953,0.0006533048,0.0011224486],"category_scores_gemma":[0.002940821,0.00040242248,0.00060678634,0.0006504321,0.00034586035,0.0009341478,0.00060659176,0.00078572624,0.00024762755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015944712,0.000010896602,0.00065905397,0.000006868784,0.000026899404,0.000017611877,0.000010220569,0.99568695,0.00022531317,0.0008250909,0.00010565565,0.0024094104],"study_design_scores_gemma":[5.0840913e-7,0.0000026167932,0.00014770225,5.1719223e-7,0.0000023208675,0.0000019461343,0.0000011960093,0.9996209,0.00002200802,0.00018383996,0.00001515487,0.0000012743296],"about_ca_topic_score_codex":0.025310457,"about_ca_topic_score_gemma":0.014527883,"teacher_disagreement_score":0.025310457,"about_ca_system_score_codex":0.00045011216,"about_ca_system_score_gemma":0.0007352308,"threshold_uncertainty_score":0.050326288},"labels":[],"label_agreement":null},{"id":"W4327967133","doi":"10.1007/s00180-023-01340-w","title":"Unsupervised learning on U.S. weather forecast performance","year":2023,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Principal component analysis; Computer science; Cluster (spacecraft); Similarity (geometry); Variance (accounting); Data mining; Machine learning; Artificial intelligence","score_opus":0.025820202626612537,"score_gpt":0.24529413944102244,"score_spread":0.2194739368144099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327967133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95749885,0.0007749385,0.026994077,0.0019821734,0.00012743968,0.00001773757,0.0039328937,0.00054985913,0.008122014],"genre_scores_gemma":[0.9953969,0.00014615277,0.0018666636,0.000048190963,0.000051470135,0.000005209113,0.001970082,0.000037679238,0.00047757747],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946624,0.00022622554,0.000033186676,0.00013087662,0.000093369235,0.000050059993],"domain_scores_gemma":[0.98776895,0.008706785,0.00075050123,0.0009661307,0.0015990396,0.00020851819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022144977,0.00032696963,0.00026825638,0.0010428827,0.00023257372,0.0008412084,0.0003385725,0.00042613634,0.0014023067],"category_scores_gemma":[0.02127082,0.00016611797,0.0002890341,0.001134838,0.0003998362,0.0009970403,0.00053506787,0.00087526045,0.0005842786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044295038,0.00016919832,0.2588557,0.000072109884,0.00029451612,0.00007610426,0.00013977972,0.586849,0.0016767659,0.008801952,0.019951405,0.12267061],"study_design_scores_gemma":[0.000012743487,0.00003623136,0.123398036,0.000026221529,0.000025035724,0.000025099409,0.00004806563,0.8674014,0.001298669,0.0061907102,0.0015174975,0.000020342606],"about_ca_topic_score_codex":0.023129154,"about_ca_topic_score_gemma":0.034578655,"teacher_disagreement_score":0.023129154,"about_ca_system_score_codex":0.0009660439,"about_ca_system_score_gemma":0.0008178377,"threshold_uncertainty_score":0.045989096},"labels":[],"label_agreement":null},{"id":"W4353031169","doi":"10.1017/9781107588493","title":"Introduction to Environmental Data Science","year":2023,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Random forest; Data science; Artificial neural network; Cluster analysis; Boosting (machine learning)","score_opus":0.03312832911835908,"score_gpt":0.21497140058614117,"score_spread":0.18184307146778209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353031169","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093321106,0.06630077,0.085981645,0.020849505,0.010895131,0.00033989374,0.018775802,0.0051024947,0.7908215],"genre_scores_gemma":[0.008050271,0.07640176,0.06275138,0.010480566,0.007065987,0.00039728446,0.015985964,0.0030121831,0.81585467],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989504,0.00013759965,0.0000750841,0.0001786174,0.0006173744,0.00004094061],"domain_scores_gemma":[0.9976178,0.0012821555,0.00006723093,0.00029744583,0.00061621453,0.00011908033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097243366,0.00096829556,0.0009868112,0.0026733493,0.0008496447,0.0046083187,0.0011263931,0.0012076308,0.107383125],"category_scores_gemma":[0.0039011196,0.0006268552,0.0007288074,0.005674195,0.0009514387,0.004101608,0.0018909591,0.0035571423,0.061137836],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008577567,0.000021451804,0.0001731574,0.00035837156,0.000013291406,0.00009030419,0.00017361394,0.0010447808,0.00025107904,0.059146993,0.7765771,0.16214134],"study_design_scores_gemma":[8.8842467e-7,0.0000020219923,0.00008654005,0.000082559534,0.0000010257342,0.000048271544,0.000015407179,0.00015665598,0.000024088851,0.012545321,0.98703384,0.0000034622558],"about_ca_topic_score_codex":0.0025943678,"about_ca_topic_score_gemma":0.004292117,"teacher_disagreement_score":0.107383125,"about_ca_system_score_codex":0.0011789134,"about_ca_system_score_gemma":0.0019416033,"threshold_uncertainty_score":0.35923237},"labels":[],"label_agreement":null},{"id":"W4353047559","doi":"10.1016/j.ecoinf.2023.102079","title":"Development of a sensitivity analysis framework for aquatic biogeochemical models using machine learning","year":2023,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Clean Air Regulatory Agenda; China Scholarship Council; Department of the Environment, Australian Government; Mitacs; Government of Canada","keywords":"Machine learning; Equifinality; Computer science; Sensitivity (control systems); Biogeochemical cycle; Ecology; Artificial intelligence; Biology","score_opus":0.07157095124181152,"score_gpt":0.2920708098434655,"score_spread":0.220499858601654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353047559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037645488,0.00004266319,0.9947267,0.00010175255,0.000010248154,0.00003592779,0.000047879217,0.00023533536,0.0010349439],"genre_scores_gemma":[0.43049666,0.00020939624,0.56584495,0.00011888004,0.0000701787,0.00035526566,0.0002833507,0.00021221803,0.0024090593],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992211,0.00035051827,0.000051236322,0.000095737756,0.0002270321,0.00005441848],"domain_scores_gemma":[0.99798536,0.001362724,0.00011753914,0.00013396547,0.00033758086,0.00006274208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002895521,0.0008450288,0.00074789074,0.0010841354,0.000551845,0.0011093689,0.0012272613,0.00079294934,0.0023176144],"category_scores_gemma":[0.0054759136,0.0006534228,0.0014236917,0.0005591393,0.0006007565,0.0011276777,0.0016268154,0.0019765133,0.00027823835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000797846,0.0000287803,0.00028576178,0.000025384383,0.000041273754,0.000038330552,0.000023865441,0.9677986,0.0007614139,0.017618466,0.00027758698,0.0130925635],"study_design_scores_gemma":[0.0000010932449,0.0000036442646,0.00002988264,0.0000025369618,0.0000028719562,0.0000027291364,0.0000019764661,0.99281436,0.00018664756,0.0067104683,0.0002416286,0.0000021988953],"about_ca_topic_score_codex":0.009823926,"about_ca_topic_score_gemma":0.0070951385,"teacher_disagreement_score":0.009823926,"about_ca_system_score_codex":0.001059794,"about_ca_system_score_gemma":0.00184699,"threshold_uncertainty_score":0.019533455},"labels":[],"label_agreement":null},{"id":"W4361292991","doi":"10.1016/j.psep.2023.03.062","title":"Surface water electrical conductivity and bicarbonate ion determination using a smart hybridization of optimal Boruta package with Elman recurrent neural network","year":2023,"lang":"en","type":"article","venue":"Process Safety and Environmental Protection","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Artificial neural network; BET theory; Artificial intelligence; Computer science; Data mining; Chemistry; Adsorption","score_opus":0.019638533642043262,"score_gpt":0.2258822585811569,"score_spread":0.20624372493911364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361292991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112968154,0.00012504851,0.87714034,0.00016276645,0.00010054428,0.000097210825,0.0003351294,0.0059653465,0.0031054749],"genre_scores_gemma":[0.5835268,0.00009207738,0.41042113,0.0001035802,0.000019939791,0.00020029722,0.00039062454,0.00024402767,0.0050015966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978215,0.000031655516,0.00001537476,0.00007989175,0.00006653641,0.00002440086],"domain_scores_gemma":[0.9998223,0.000047051308,0.000012714307,0.000029664558,0.00007730412,0.000010869347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046375193,0.0005305012,0.00052372454,0.00029567958,0.00031295608,0.00041752844,0.001006942,0.0005790821,0.0031537123],"category_scores_gemma":[0.0006308979,0.00049682736,0.00040242786,0.0003359389,0.00019730745,0.00057731953,0.00041230023,0.000575873,0.00080770603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008741468,0.0003953107,0.00875672,0.0003942276,0.00023281178,0.0001709463,0.00033495558,0.14011922,0.41705564,0.0036233657,0.004618851,0.4234238],"study_design_scores_gemma":[0.000022479755,0.000102674,0.0017751919,0.0000054563175,0.000031059746,0.0000310556,0.000020859508,0.92056507,0.07503444,0.00056530844,0.0018223197,0.000024092178],"about_ca_topic_score_codex":0.0046423394,"about_ca_topic_score_gemma":0.008772203,"teacher_disagreement_score":0.0046423394,"about_ca_system_score_codex":0.00040310746,"about_ca_system_score_gemma":0.00054566737,"threshold_uncertainty_score":0.010550201},"labels":[],"label_agreement":null},{"id":"W4366263125","doi":"10.1016/j.ecoinf.2023.102107","title":"Non-parametric, semi-parametric, and machine learning models for river temperature frequency analysis at ungauged basins","year":2023,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Bundesamt für Umwelt; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Multivariate adaptive regression splines; Mars Exploration Program; Canonical correlation; Generalized additive model; Random forest; Gradient boosting; Feature selection; Extreme learning machine; Parametric statistics; Computer science; Artificial neural network; Artificial intelligence; Lasso (programming language); Multivariate statistics; Boosting (machine learning); Mean squared error; Machine learning; Mathematics; Regression analysis; Statistics; Nonparametric regression","score_opus":0.03512882131692962,"score_gpt":0.24479435844566388,"score_spread":0.20966553712873426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366263125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49929568,0.00046670646,0.49675962,0.0005672769,0.00005686961,0.00004671685,0.00039186273,0.0006722042,0.0017430494],"genre_scores_gemma":[0.98917586,0.00006468849,0.009575974,0.000016509499,0.000020569558,0.000035476533,0.00014274169,0.000022851043,0.00094538473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930227,0.0003825733,0.000044639288,0.00012675322,0.00007012787,0.00007356791],"domain_scores_gemma":[0.9935243,0.0053778733,0.00038417632,0.00023134387,0.0003909593,0.00009123265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022792318,0.00057076546,0.000937902,0.0006680443,0.0004891558,0.001214856,0.0014098899,0.0010259412,0.0010495376],"category_scores_gemma":[0.009559706,0.0005153686,0.00084824,0.00077296566,0.0007234108,0.0017294341,0.0009165325,0.0015474446,0.00017572613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028849481,0.00002468173,0.0010895113,0.000009580597,0.00001539646,0.000009929133,0.000022624468,0.9931545,0.00010528606,0.0005753473,0.00008589364,0.0048784195],"study_design_scores_gemma":[7.2530605e-7,0.0000031975005,0.00019036351,5.301819e-7,0.0000011499579,0.0000015804326,0.0000026764649,0.99945945,0.000024117446,0.0003026539,0.000011876542,0.0000017287579],"about_ca_topic_score_codex":0.020363891,"about_ca_topic_score_gemma":0.017510984,"teacher_disagreement_score":0.020363891,"about_ca_system_score_codex":0.00091771607,"about_ca_system_score_gemma":0.00087465346,"threshold_uncertainty_score":0.040490746},"labels":[],"label_agreement":null},{"id":"W4366492351","doi":"10.11159/icgre23.153","title":"Forecast Rainfall Density by Utilizing Machine Learning Models","year":2023,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Civil, Structural, and Environmental Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Meteorology; Artificial intelligence; Machine learning; Geography","score_opus":0.012725212130050567,"score_gpt":0.19072056705021376,"score_spread":0.1779953549201632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366492351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28013194,0.0011734422,0.70235,0.0011162861,0.00018983822,0.00013578827,0.002398143,0.004931875,0.0075726146],"genre_scores_gemma":[0.92519635,0.0005839902,0.07140212,0.0000776703,0.00008790092,0.00005732994,0.0014067816,0.00004376281,0.0011441079],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997451,0.000066653025,0.000026207108,0.000063999294,0.0000687009,0.00002942658],"domain_scores_gemma":[0.99901724,0.0005495317,0.00014638639,0.0000745155,0.00018823813,0.000024110339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072899286,0.00058346364,0.000409725,0.0018518321,0.00018242573,0.0008516123,0.0005683941,0.00045128205,0.0007492422],"category_scores_gemma":[0.0032208674,0.0002336254,0.00046611944,0.0015803581,0.00013605099,0.0012250894,0.00028465822,0.0005126382,0.00045440643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041969586,0.00008275481,0.02426262,0.000060910268,0.000072176175,0.00006182063,0.000048699923,0.85675716,0.0011223452,0.0013632784,0.0020326586,0.11409353],"study_design_scores_gemma":[0.0000023147422,0.000006902831,0.0015571348,0.0000074114573,0.000005301096,0.0000067137826,0.000011713712,0.99683064,0.00034162827,0.0009303274,0.0002950431,0.000004848607],"about_ca_topic_score_codex":0.0141364755,"about_ca_topic_score_gemma":0.010448561,"teacher_disagreement_score":0.0141364755,"about_ca_system_score_codex":0.00047031284,"about_ca_system_score_gemma":0.00044949428,"threshold_uncertainty_score":0.028108358},"labels":[],"label_agreement":null},{"id":"W4366502793","doi":"10.11159/iceptp23.132","title":"Improvement of the Low Resolution of the Dataset and Prediction of the Water Quality Using the SWAT-LSTM Hybrid Model","year":2023,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Civil, Structural, and Environmental Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; SWAT model; Quality (philosophy); Low resolution; Artificial intelligence; Water quality; Resolution (logic); Data mining; Machine learning; High resolution; Remote sensing; Geology; Watershed","score_opus":0.015077866883106904,"score_gpt":0.21260511205251797,"score_spread":0.19752724516941106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366502793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28538537,0.001934985,0.64462644,0.0040819673,0.0019756414,0.00038663344,0.033160836,0.018164098,0.010284133],"genre_scores_gemma":[0.6807617,0.0008591615,0.25962946,0.0007478982,0.00034083682,0.00050800043,0.05251796,0.00043713886,0.004197784],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994549,0.000079654295,0.000054149656,0.00018740169,0.00015750658,0.00006638086],"domain_scores_gemma":[0.9992518,0.00014498137,0.000040763938,0.00014620392,0.0003834858,0.000032853794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011642205,0.0012334648,0.00075481157,0.00095299864,0.00046673705,0.0010806313,0.0016142981,0.0011317201,0.0029949285],"category_scores_gemma":[0.00287704,0.00034983025,0.0010373895,0.0013564581,0.00026178468,0.002507112,0.00089106645,0.0016153005,0.0013958332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003346064,0.0006493843,0.023813557,0.00043528053,0.0003176886,0.00031884288,0.00016061528,0.46930525,0.029704176,0.0028091897,0.048694164,0.42345724],"study_design_scores_gemma":[0.0000316628,0.000019079942,0.004426453,0.000015745689,0.00002892192,0.000017539924,0.00003664115,0.98762405,0.0033127381,0.00064354995,0.0038190794,0.000024473396],"about_ca_topic_score_codex":0.038334414,"about_ca_topic_score_gemma":0.030014513,"teacher_disagreement_score":0.038334414,"about_ca_system_score_codex":0.0006850068,"about_ca_system_score_gemma":0.0014640362,"threshold_uncertainty_score":0.0762226},"labels":[],"label_agreement":null},{"id":"W4366751894","doi":"10.1016/j.envsoft.2023.105709","title":"Regional thermal index model for river temperature frequency analysis in ungauged basins","year":2023,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Index (typography); Environmental science; Drainage basin; Thermal; Hydrology (agriculture); Meteorology; Geology; Geography; Geotechnical engineering; Computer science; Cartography","score_opus":0.028455278669464814,"score_gpt":0.2304190309993476,"score_spread":0.20196375232988278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366751894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6790306,0.0003617902,0.288897,0.00028332492,0.00014141983,0.000105314415,0.009271192,0.008220231,0.013689141],"genre_scores_gemma":[0.9579665,0.00010648004,0.03569734,0.000030455181,0.000014264966,0.00008834563,0.0029211282,0.00024244789,0.0029329779],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999298,0.000016041422,0.0000052467262,0.000023929588,0.000013035441,0.000011994034],"domain_scores_gemma":[0.9998153,0.000059886384,0.00001530419,0.00002683805,0.0000642696,0.000018522926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024618028,0.0004308751,0.0005155683,0.00039904093,0.00023020252,0.00049492985,0.0011430276,0.00042378678,0.0035081329],"category_scores_gemma":[0.0007207896,0.0002864261,0.00048154345,0.0005852551,0.00014217458,0.0005964982,0.00028721232,0.00047039756,0.00063200947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003935866,0.000027731734,0.0016482992,0.000014367729,0.000026564361,0.000017017055,0.000012310178,0.98884577,0.00096576073,0.0006094059,0.00091750984,0.006875873],"study_design_scores_gemma":[0.0000044656454,0.000003559318,0.00035141438,8.1035193e-7,0.000004213666,0.0000017168458,0.0000022068612,0.99912375,0.00020057705,0.0001224001,0.00018270274,0.0000022066147],"about_ca_topic_score_codex":0.06351706,"about_ca_topic_score_gemma":0.048684783,"teacher_disagreement_score":0.06351706,"about_ca_system_score_codex":0.00086650427,"about_ca_system_score_gemma":0.00089413975,"threshold_uncertainty_score":0.12629473},"labels":[],"label_agreement":null},{"id":"W4367182224","doi":"10.18280/mmep.100216","title":"Forecasting of Rainfall Using Seasonal Autoregreressive Integrated Moving Average (SARIMA) Aceh, Indonesia","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Climatology; Environmental science; Meteorology; Geography; Geology","score_opus":0.0491247879023279,"score_gpt":0.22593708307070262,"score_spread":0.1768122951683747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367182224","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82467437,0.0009289299,0.1625212,0.00044132138,0.00012016987,0.00005153882,0.001235405,0.00084016315,0.009187],"genre_scores_gemma":[0.9842126,0.00032943996,0.013531941,0.000010953259,0.00001606603,0.000014508745,0.00044534748,0.000013223194,0.001425903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986637,0.0000360119,0.000012549811,0.00003276189,0.000040887586,0.000011417691],"domain_scores_gemma":[0.9998332,0.00006747689,0.000039347586,0.000010452944,0.000041499094,0.000007997111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034250447,0.00020979067,0.0002650981,0.0003396803,0.00009482479,0.00049676886,0.00028647063,0.00015386037,0.0004252787],"category_scores_gemma":[0.00078733836,0.00010415055,0.00025207206,0.00048719606,0.00009004576,0.0003431068,0.00013327062,0.00027748226,0.00013131648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016829629,0.00021878563,0.07285458,0.00018014433,0.00014853654,0.00034597586,0.00013785141,0.7461391,0.007709723,0.0030664674,0.0034413,0.16558921],"study_design_scores_gemma":[0.000002724517,0.000028130687,0.009002876,0.000006191378,0.000012071853,0.00001996462,0.00001930308,0.9890933,0.0008819975,0.0003299116,0.00059806247,0.000005423927],"about_ca_topic_score_codex":0.011550351,"about_ca_topic_score_gemma":0.012398945,"teacher_disagreement_score":0.011550351,"about_ca_system_score_codex":0.00023305851,"about_ca_system_score_gemma":0.00041909362,"threshold_uncertainty_score":0.022966206},"labels":[],"label_agreement":null},{"id":"W4367609892","doi":"10.1016/j.chemosphere.2023.138831","title":"Quantifying uncertainty of marine water quality forecasts for environmental management using a dynamic multi-factor analysis and multi-resolution ensemble approach","year":2023,"lang":"en","type":"article","venue":"Chemosphere","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Education and Child Care","funders":"","keywords":"Water quality; Interpretability; Computer science; Environmental science; Data mining; Uncertainty analysis; Sampling (signal processing); Machine learning; Ecology","score_opus":0.08836164055998447,"score_gpt":0.31645236762361184,"score_spread":0.22809072706362737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367609892","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6136778,0.000499995,0.38270158,0.00049019424,0.0000894087,0.000029809391,0.0005036153,0.00029118877,0.0017164359],"genre_scores_gemma":[0.9801586,0.0001115846,0.01933345,0.00002239696,0.000029481913,0.000011864278,0.00019312442,0.000017380567,0.00012212842],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995931,0.00014395619,0.00003717501,0.0000783308,0.000107829524,0.000039582785],"domain_scores_gemma":[0.9976979,0.0016134251,0.00021792427,0.0001756989,0.00024082804,0.000054260698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020551386,0.0004572854,0.00048397432,0.0008952163,0.00033587645,0.0008847037,0.00041060188,0.00053813,0.00027946875],"category_scores_gemma":[0.0072808014,0.00035702626,0.00065075606,0.0008200927,0.00025730336,0.0018485554,0.000561718,0.00079228764,0.00003765303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003612505,0.000028807006,0.004947273,0.000013367124,0.000117605734,0.00001985871,0.000020513162,0.976948,0.0011645061,0.0013693817,0.00017579846,0.015158736],"study_design_scores_gemma":[0.000001304348,0.0000037462705,0.00082357426,0.00000118842,0.0000059515146,0.0000015932372,0.000003040142,0.9982938,0.00014802403,0.0006800753,0.000034137338,0.0000034518944],"about_ca_topic_score_codex":0.018182276,"about_ca_topic_score_gemma":0.011562907,"teacher_disagreement_score":0.018182276,"about_ca_system_score_codex":0.0006631428,"about_ca_system_score_gemma":0.00065208436,"threshold_uncertainty_score":0.0361529},"labels":[],"label_agreement":null},{"id":"W4378472646","doi":"10.1007/s11269-023-03528-7","title":"Improving Hybrid Models for Precipitation Forecasting by Combining Nonlinear Machine Learning Methods","year":2023,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Gene expression programming; Genetic programming; Computer science; Support vector machine; Nonlinear system; Mean squared error; Machine learning; Data pre-processing; Artificial intelligence; Data mining; Statistics; Mathematics","score_opus":0.03711088554043078,"score_gpt":0.27218122880898227,"score_spread":0.23507034326855147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378472646","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2370364,0.0008246665,0.7560739,0.0003882213,0.00012036918,0.00007004145,0.00013756112,0.0008263012,0.004522488],"genre_scores_gemma":[0.9580421,0.00022865924,0.03990031,0.000043454904,0.000033574965,0.00005626304,0.000118717726,0.000030666153,0.0015462292],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962294,0.00014987135,0.000026146441,0.00007784082,0.000091078415,0.000032133936],"domain_scores_gemma":[0.9993931,0.0003391812,0.00008054768,0.00003715439,0.00013104476,0.000018907167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010640301,0.0007721941,0.0007445832,0.00076052314,0.00029711312,0.0009112495,0.00077277236,0.00053361326,0.0007884323],"category_scores_gemma":[0.0015294622,0.00036594516,0.00090481614,0.0007439825,0.00028348982,0.00090584345,0.000786834,0.0007551062,0.00020459156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031572414,0.000038631646,0.001338206,0.000022417766,0.00006241647,0.0000248187,0.00002269223,0.9757338,0.00082838506,0.0006419717,0.00017492681,0.021080105],"study_design_scores_gemma":[0.0000011498556,0.000007841412,0.00009899594,0.0000010908375,0.0000042514985,0.0000014919141,0.000002037376,0.99955624,0.000101611426,0.00017070073,0.000052803112,0.0000017331977],"about_ca_topic_score_codex":0.009386346,"about_ca_topic_score_gemma":0.006742827,"teacher_disagreement_score":0.009386346,"about_ca_system_score_codex":0.00052790897,"about_ca_system_score_gemma":0.00045050407,"threshold_uncertainty_score":0.018663466},"labels":[],"label_agreement":null},{"id":"W4378807928","doi":"10.1007/s00477-023-02471-8","title":"Multilayer perceptron-based predictive model using wavelet transform for the reconstruction of missing rainfall data","year":2023,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Korea Meteorological Administration; Chung-Ang University","keywords":"Missing data; Wavelet transform; Multilayer perceptron; Wavelet; Artificial neural network; Mean squared error; Computer science; Statistics; Data mining; Pattern recognition (psychology); Mathematics; Artificial intelligence","score_opus":0.1306623977355057,"score_gpt":0.38947007614608486,"score_spread":0.25880767841057917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378807928","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036114193,0.00045847756,0.9617099,0.00016620308,0.00007574528,0.000015397027,0.0001302082,0.0005223783,0.00080741895],"genre_scores_gemma":[0.90293515,0.0005938901,0.0920485,0.000096575415,0.00007377149,0.000085882035,0.00044754936,0.000074015734,0.0036447411],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962354,0.000111265974,0.000033272467,0.00008595443,0.00008363843,0.00006234078],"domain_scores_gemma":[0.999188,0.00050743547,0.000060613453,0.00005164016,0.00016744644,0.000024754498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001618243,0.0004894289,0.0011288057,0.00052713614,0.00031572636,0.00077581225,0.0014158249,0.0009386945,0.0017572866],"category_scores_gemma":[0.0031114817,0.0004683843,0.0008667215,0.0010159764,0.00036749354,0.0013592144,0.00055983604,0.0017633019,0.00041568174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012421832,0.00006637683,0.0007918114,0.000054383483,0.00008288483,0.000047162794,0.000023141805,0.93728364,0.0013378457,0.003640096,0.00076406065,0.055784337],"study_design_scores_gemma":[0.000001121635,0.0000031262102,0.000042936084,9.3788003e-7,0.0000028900945,0.0000017330871,5.8758917e-7,0.9995888,0.0000666447,0.000269945,0.000020160696,0.0000011779413],"about_ca_topic_score_codex":0.012059504,"about_ca_topic_score_gemma":0.0070815026,"teacher_disagreement_score":0.012059504,"about_ca_system_score_codex":0.00048973574,"about_ca_system_score_gemma":0.0010003896,"threshold_uncertainty_score":0.02397865},"labels":[],"label_agreement":null},{"id":"W4379468994","doi":"10.14796/jwmm.c499","title":"Investigating the Accuracy of Hybrid Models with Wavelet Transform in the Forecast of Watershed Runoff","year":2023,"lang":"en","type":"article","venue":"Journal of Water Management Modeling","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Wavelet; Wavelet transform; Watershed; Discrete wavelet transform; Computer science; Surface runoff; Complex wavelet transform; Scale (ratio); Artificial intelligence; Environmental science; Machine learning; Geography","score_opus":0.044262217843647256,"score_gpt":0.23768600605312876,"score_spread":0.1934237882094815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379468994","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9625426,0.00015425585,0.035278454,0.00013455524,0.00002005922,0.000013634268,0.00008607742,0.00011690363,0.0016533313],"genre_scores_gemma":[0.99558496,0.00005214986,0.0041028922,0.000006777185,0.000004276894,0.0000061067385,0.000056426125,0.0000056958806,0.0001806313],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996786,0.0001266162,0.000025640293,0.000059212492,0.00006636818,0.000043596974],"domain_scores_gemma":[0.99894804,0.00071147614,0.000100861056,0.00006177259,0.00014671475,0.000031202682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016433015,0.00044351368,0.00036154545,0.0006368564,0.00017617946,0.00089794834,0.0005440035,0.0004968286,0.00043126897],"category_scores_gemma":[0.0032063825,0.00023367663,0.00048171007,0.0005650788,0.00021045862,0.0011282467,0.00050348265,0.00045182608,0.000080672384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023829754,0.000087159846,0.019089416,0.000029004044,0.00011082003,0.00004471291,0.000054464173,0.9519136,0.002280181,0.0007933406,0.00014613339,0.025212927],"study_design_scores_gemma":[0.0000033030797,0.000026664253,0.00089003076,0.0000015502942,0.000006529797,0.000002722315,0.000010238188,0.9985971,0.00034061878,0.00008739429,0.000031192347,0.000002646085],"about_ca_topic_score_codex":0.013000425,"about_ca_topic_score_gemma":0.007243369,"teacher_disagreement_score":0.013000425,"about_ca_system_score_codex":0.0005926289,"about_ca_system_score_gemma":0.00043214468,"threshold_uncertainty_score":0.025849521},"labels":[],"label_agreement":null},{"id":"W4379471795","doi":"10.1016/b978-0-443-18953-1.00005-2","title":"Artificial neural modeling for precision agricultural water management practices","year":2023,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Prince Edward Island","funders":"","keywords":"Scope (computer science); Computer science; Artificial intelligence; Machine learning; Domain (mathematical analysis); Management science; Data science; Engineering; Mathematics","score_opus":0.06682625082808405,"score_gpt":0.2760283276522457,"score_spread":0.20920207682416167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379471795","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011829446,0.011805644,0.89629036,0.0014182128,0.0008367679,0.000036110796,0.0005384341,0.00116284,0.076082185],"genre_scores_gemma":[0.41205958,0.020463143,0.3383263,0.0003992089,0.00094217254,0.00019144134,0.0012738121,0.0004628533,0.22588153],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992764,0.000016054426,0.000005204187,0.000012252248,0.000034709923,0.000004150588],"domain_scores_gemma":[0.9998386,0.00009583128,0.000008835057,0.000016069109,0.000037329286,0.0000033749825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025008706,0.0004897565,0.0003385636,0.00026595348,0.0001295762,0.00078695774,0.0005343357,0.00068584486,0.0084071],"category_scores_gemma":[0.0007073497,0.00022621038,0.0002937305,0.0007774089,0.00020320248,0.0008630925,0.0003386427,0.00083208224,0.0014404826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025031757,0.000031246193,0.00028929798,0.00018315014,0.000038517905,0.000043354823,0.000033663906,0.5824779,0.0018383026,0.028237846,0.014613205,0.3721885],"study_design_scores_gemma":[0.0000028400466,0.000011587328,0.0002699125,0.000050221435,0.00001102148,0.00001425195,0.000013305097,0.95563674,0.00065646216,0.02438578,0.01893875,0.000009135717],"about_ca_topic_score_codex":0.010027657,"about_ca_topic_score_gemma":0.01082797,"teacher_disagreement_score":0.010027657,"about_ca_system_score_codex":0.00053154334,"about_ca_system_score_gemma":0.00037883015,"threshold_uncertainty_score":0.028124511},"labels":[],"label_agreement":null},{"id":"W4382560633","doi":"10.3390/hydrology10070139","title":"Predictive MPC-Based Operation of Urban Drainage Systems Using Input Data-Clustered Artificial Neural Networks Rainfall Forecasting Models","year":2023,"lang":"en","type":"article","venue":"Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Model predictive control; Computer science; Artificial neural network; Predictive modelling; Drainage; Control theory (sociology); Environmental science; Control (management); Machine learning; Artificial intelligence","score_opus":0.12872581540697395,"score_gpt":0.2800719510880925,"score_spread":0.15134613568111857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382560633","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50026226,0.00031375742,0.48419094,0.00024000678,0.00007174856,0.000096375006,0.00030287317,0.0013696534,0.013152405],"genre_scores_gemma":[0.99353915,0.000041046183,0.0056454283,0.00000728433,0.000003794459,0.000022620583,0.000058782152,0.0000076141932,0.0006742213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998889,0.000024528084,0.000006571124,0.00003162142,0.000029881796,0.000018415767],"domain_scores_gemma":[0.99981695,0.000069428344,0.000034015688,0.000013902125,0.00005764013,0.0000080822165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021130472,0.00043585425,0.00040766114,0.00021726087,0.00024480562,0.00054587336,0.0005952442,0.00031618177,0.00065230933],"category_scores_gemma":[0.00052890973,0.00020839629,0.000322589,0.00034195586,0.00022386029,0.00036313976,0.0003111342,0.0004572122,0.00007967369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009924262,0.000007669825,0.00030606057,0.000006157004,0.000006276147,0.000010180744,0.000005689396,0.9958609,0.00032032534,0.00019427677,0.00005765265,0.003214969],"study_design_scores_gemma":[9.917395e-7,0.0000029672717,0.00010253454,4.6319803e-7,0.0000013458105,7.4882416e-7,0.0000013874284,0.99966013,0.00012387279,0.00007760912,0.000027281216,7.603981e-7],"about_ca_topic_score_codex":0.027532207,"about_ca_topic_score_gemma":0.017268507,"teacher_disagreement_score":0.027532207,"about_ca_system_score_codex":0.0006346004,"about_ca_system_score_gemma":0.0007556947,"threshold_uncertainty_score":0.054743946},"labels":[],"label_agreement":null},{"id":"W4383215559","doi":"10.1016/j.envsoft.2023.105776","title":"Exploding the myths: An introduction to artificial neural networks for prediction and forecasting","year":2023,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":124,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"Australian Research Council","keywords":"Artificial neural network; Artificial intelligence; Computer science; Mythology; Machine learning; History","score_opus":0.055063829364244005,"score_gpt":0.23392302483125188,"score_spread":0.17885919546700788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383215559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029281587,0.36701643,0.4844779,0.07360726,0.012913835,0.000108977474,0.00047139704,0.00058360177,0.05789245],"genre_scores_gemma":[0.081746995,0.40054312,0.40251958,0.022081684,0.033733472,0.0005428453,0.0004314325,0.0005093567,0.057891496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99933165,0.00026487312,0.000068986395,0.00009314527,0.00021386758,0.000027493543],"domain_scores_gemma":[0.9969838,0.002524531,0.000082275044,0.00009563533,0.00026244557,0.00005135655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001767305,0.0008683301,0.00049946696,0.0013665752,0.0005516502,0.0033512753,0.0014927988,0.0023909723,0.0058056195],"category_scores_gemma":[0.006153129,0.0005163897,0.0006951924,0.0017139332,0.002578974,0.006578715,0.0013732852,0.0054237116,0.0016587819],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056340767,0.000104728824,0.00079061266,0.0013962152,0.00012101519,0.00014334799,0.00057284004,0.024850417,0.0008093916,0.5090897,0.106837146,0.35522828],"study_design_scores_gemma":[0.0000121385665,0.000034062516,0.0003470459,0.0008101127,0.000021068465,0.00011487123,0.000141825,0.040223684,0.00040025884,0.68148667,0.27634448,0.00006380664],"about_ca_topic_score_codex":0.0024549784,"about_ca_topic_score_gemma":0.0030454292,"teacher_disagreement_score":0.0058056195,"about_ca_system_score_codex":0.00096535846,"about_ca_system_score_gemma":0.00075693073,"threshold_uncertainty_score":0.019421697},"labels":[],"label_agreement":null},{"id":"W4383566442","doi":"10.1016/b978-0-443-15284-9.00006-9","title":"Postprocessing approaches","year":2023,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Ottawa","funders":"","keywords":"Plot (graphics); Computer science; Scatter plot; Histogram; Software; Artificial intelligence; Process (computing); MATLAB; Variety (cybernetics); Machine learning; Data mining; Mathematics; Statistics; Image (mathematics)","score_opus":0.06531304208877843,"score_gpt":0.23436785465750087,"score_spread":0.16905481256872246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383566442","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033082694,0.00076953025,0.9232045,0.00027223155,0.000642053,0.00018603711,0.0011837169,0.015697347,0.054736298],"genre_scores_gemma":[0.026932552,0.0010977924,0.80167884,0.000459287,0.00053473766,0.0003154721,0.0059541394,0.005119326,0.1579078],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999196,0.00006965798,0.00006619647,0.0002803271,0.00030901746,0.00007876657],"domain_scores_gemma":[0.99869496,0.00025540093,0.000050564588,0.0005184291,0.00044923503,0.00003140121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083888054,0.0025188986,0.0009855236,0.002123153,0.0012147947,0.00473866,0.0017313765,0.0013214212,0.10632615],"category_scores_gemma":[0.0026321847,0.00087789266,0.0013322332,0.0024641799,0.0006274891,0.0028909661,0.0019591574,0.0018269261,0.06846085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011557881,0.00006358209,0.00028146346,0.00027599235,0.00004578349,0.00013288725,0.00013758022,0.004487026,0.021363944,0.028146805,0.04562954,0.8993198],"study_design_scores_gemma":[0.0000522333,0.00011909083,0.0016289736,0.00018179751,0.00015537202,0.00067922764,0.00025570483,0.11258951,0.09361977,0.09404296,0.6965879,0.00008745963],"about_ca_topic_score_codex":0.0032859987,"about_ca_topic_score_gemma":0.0038260228,"teacher_disagreement_score":0.10632615,"about_ca_system_score_codex":0.00052751915,"about_ca_system_score_gemma":0.001316633,"threshold_uncertainty_score":0.35569638},"labels":[],"label_agreement":null},{"id":"W4383566577","doi":"10.1016/b978-0-443-15284-9.00002-1","title":"Dataset preparation","year":2023,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Ottawa","funders":"","keywords":"Process (computing); Computer science; Sample (material); Management science; Data science; Engineering; Chemistry; Programming language","score_opus":0.03364178429534586,"score_gpt":0.2676409802213966,"score_spread":0.23399919592605073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383566577","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067434844,0.00023851842,0.0029642328,0.00026921692,0.0003662341,0.0005936426,0.97958755,0.009390686,0.0059155044],"genre_scores_gemma":[0.0012867743,0.00012554914,0.009083525,0.0002589422,0.000051445524,0.0015297876,0.98249453,0.00084602623,0.0043233093],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856454,0.0002839996,0.00018794408,0.0005641265,0.0002210701,0.00017838978],"domain_scores_gemma":[0.995096,0.0016302661,0.00020622129,0.0016284776,0.0011083288,0.00033067304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024512177,0.0025285773,0.0011170555,0.005166922,0.0010499551,0.0020637037,0.0021047846,0.0017239648,0.2508793],"category_scores_gemma":[0.017881636,0.0006854178,0.002188518,0.0036821247,0.0005592353,0.001452885,0.0020149567,0.002066525,0.23440991],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104879444,0.00004340233,0.00057558686,0.0005998579,0.000033613294,0.00004119644,0.00002602078,0.00032203176,0.0004295741,0.000420013,0.98034763,0.017056148],"study_design_scores_gemma":[0.0004220125,0.00011372315,0.002985583,0.0005908267,0.000086737586,0.0001593653,0.00016953768,0.0024960614,0.0018294563,0.005359222,0.9857298,0.000057679325],"about_ca_topic_score_codex":0.008540195,"about_ca_topic_score_gemma":0.024481867,"teacher_disagreement_score":0.2508793,"about_ca_system_score_codex":0.0008997743,"about_ca_system_score_gemma":0.0034477566,"threshold_uncertainty_score":0.8392748},"labels":[],"label_agreement":null},{"id":"W4383566738","doi":"10.1016/b978-0-443-15284-9.00003-3","title":"Preprocessing approaches","year":2023,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Ottawa","funders":"","keywords":"Preprocessor; Normalization (sociology); Computer science; Standardization; Data pre-processing; Artificial intelligence; Machine learning; Data mining; Coding (social sciences); Dimension (graph theory); Mathematics","score_opus":0.07269545722146624,"score_gpt":0.23846395126924144,"score_spread":0.16576849404777522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383566738","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023015437,0.0016723812,0.8266392,0.00077310356,0.0010062172,0.00038820572,0.004589541,0.0257949,0.13683489],"genre_scores_gemma":[0.029551791,0.0030380671,0.68859845,0.0011147509,0.0007118794,0.0007597787,0.027104327,0.007874892,0.24124607],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99874556,0.00013368948,0.00009200294,0.00045610155,0.0004640845,0.00010853092],"domain_scores_gemma":[0.9986332,0.00026042465,0.00004730011,0.0006154882,0.00040596313,0.000037683687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092357694,0.0024239165,0.0010224407,0.002821534,0.0012837829,0.004414852,0.0022162064,0.001398683,0.13266021],"category_scores_gemma":[0.0035755052,0.0009508994,0.0015990607,0.0036244672,0.00056520966,0.0031769352,0.0023785161,0.0022744625,0.11288324],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118218726,0.00008528441,0.00028710486,0.00040298476,0.000052996227,0.00012168117,0.00013836348,0.0038899782,0.011210907,0.03587562,0.12056988,0.827247],"study_design_scores_gemma":[0.000047340243,0.00006505579,0.0008888778,0.00025745307,0.00009320073,0.00046942622,0.00024084892,0.046467602,0.030797144,0.11116687,0.80944264,0.00006348105],"about_ca_topic_score_codex":0.0036172625,"about_ca_topic_score_gemma":0.003860676,"teacher_disagreement_score":0.13266021,"about_ca_system_score_codex":0.0006623249,"about_ca_system_score_gemma":0.0016935904,"threshold_uncertainty_score":0.44379264},"labels":[],"label_agreement":null},{"id":"W4383648114","doi":"10.2139/ssrn.4504411","title":"How Reliable are Hybrid Ai-Based Models Compared to Numerical Model for Predicting Long-Term Horizon Groundwater Level Under Changing Climate?","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Term (time); Horizon; Groundwater; Environmental science; Econometrics; Computer science; Economics; Mathematics; Geology; Geotechnical engineering; Physics","score_opus":0.07655254906301043,"score_gpt":0.282172961496871,"score_spread":0.20562041243386056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383648114","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69565296,0.004935261,0.27394176,0.00604334,0.0012830927,0.00007847279,0.002659085,0.002931405,0.012474617],"genre_scores_gemma":[0.9836715,0.0006552348,0.013984263,0.00013493517,0.00017601212,0.000023463404,0.00053006766,0.000102051774,0.00072243705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916184,0.00029070373,0.00007174667,0.00019684523,0.00021086211,0.00006813736],"domain_scores_gemma":[0.9925103,0.0044182,0.0006225199,0.00084044714,0.0013998564,0.00020876397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027096793,0.0007710864,0.0012780488,0.0011071438,0.0003872937,0.003206178,0.0016147039,0.0014908477,0.002743568],"category_scores_gemma":[0.022548882,0.0004849621,0.0005624257,0.0013244617,0.0006554795,0.0055206036,0.00080312905,0.0012000987,0.00084425975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010239669,0.00014878938,0.038381077,0.00024306356,0.00067721953,0.00007917865,0.00008492773,0.8503984,0.003732878,0.006622548,0.00310197,0.09550593],"study_design_scores_gemma":[0.00002094008,0.000040969953,0.002227907,0.00001996305,0.000047788042,0.000016913862,0.000038588783,0.9928116,0.0008575445,0.0036107586,0.00028920098,0.000017796461],"about_ca_topic_score_codex":0.01225115,"about_ca_topic_score_gemma":0.006553074,"teacher_disagreement_score":0.01225115,"about_ca_system_score_codex":0.00070780556,"about_ca_system_score_gemma":0.00074648164,"threshold_uncertainty_score":0.024359643},"labels":[],"label_agreement":null},{"id":"W4384499117","doi":"10.32920/23696937","title":"Application of Artificial Neural Network and Information Entropy Theory to Assess Rainfall Station Distribution: A Case Study from Colombia","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Universidad de La Sabana; Pontificia Universidad Javeriana; Universidad Tecnológica de Bolívar","keywords":"Artificial neural network; Entropy (arrow of time); Acronym; Probabilistic logic; Computer science; Artificial intelligence; Meteorology; Data mining; Geography","score_opus":0.032612251847514366,"score_gpt":0.28229734958076036,"score_spread":0.249685097733246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384499117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98650265,0.00036828977,0.0069200825,0.00026009127,0.000016816368,0.00006944838,0.0006577063,0.00007631421,0.0051285783],"genre_scores_gemma":[0.9963684,0.00010018775,0.0028502943,0.000007079969,0.000004308814,0.000010622677,0.00017909553,0.0000042947054,0.00047564338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996592,0.00013334693,0.000027350954,0.000045517434,0.00008807139,0.00004650367],"domain_scores_gemma":[0.9990934,0.0005146662,0.00007805308,0.000043649983,0.00021816854,0.000052036976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056092645,0.0004160461,0.00029265127,0.0016962924,0.00033762195,0.0009511268,0.00047924992,0.00044674336,0.0006539695],"category_scores_gemma":[0.002281687,0.000111547946,0.00028279203,0.0016179595,0.00034031173,0.00042529023,0.00039181256,0.00024064264,0.000055393397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067157554,0.00034671056,0.2856423,0.0006905162,0.00025836733,0.005417803,0.0017561415,0.52707374,0.005802379,0.005087511,0.002780255,0.16447273],"study_design_scores_gemma":[0.000039474548,0.00017085405,0.19430059,0.00008070812,0.00009626511,0.00036159388,0.0032904323,0.7929935,0.0040555107,0.0015840065,0.0029455298,0.00008147987],"about_ca_topic_score_codex":0.13326465,"about_ca_topic_score_gemma":0.13338326,"teacher_disagreement_score":0.13326465,"about_ca_system_score_codex":0.0023961437,"about_ca_system_score_gemma":0.00046772466,"threshold_uncertainty_score":0.26497793},"labels":[],"label_agreement":null},{"id":"W4384499423","doi":"10.32920/23696937.v1","title":"Application of Artificial Neural Network and Information Entropy Theory to Assess Rainfall Station Distribution: A Case Study from Colombia","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Universidad de La Sabana; Pontificia Universidad Javeriana; Universidad Tecnológica de Bolívar","keywords":"Artificial neural network; Entropy (arrow of time); Computer science; Probabilistic logic; Acronym; Meteorology; Environmental science; Artificial intelligence; Data mining; Geography","score_opus":0.032612251847514366,"score_gpt":0.28229734958076036,"score_spread":0.249685097733246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384499423","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98650265,0.00036828977,0.0069200825,0.00026009127,0.000016816368,0.00006944838,0.0006577063,0.00007631421,0.0051285783],"genre_scores_gemma":[0.9963684,0.00010018775,0.0028502943,0.000007079969,0.000004308814,0.000010622677,0.00017909553,0.0000042947054,0.00047564338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996592,0.00013334693,0.000027350954,0.000045517434,0.00008807139,0.00004650367],"domain_scores_gemma":[0.9990934,0.0005146662,0.00007805308,0.000043649983,0.00021816854,0.000052036976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056092645,0.0004160461,0.00029265127,0.0016962924,0.00033762195,0.0009511268,0.00047924992,0.00044674336,0.0006539695],"category_scores_gemma":[0.002281687,0.000111547946,0.00028279203,0.0016179595,0.00034031173,0.00042529023,0.00039181256,0.00024064264,0.000055393397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067157554,0.00034671056,0.2856423,0.0006905162,0.00025836733,0.005417803,0.0017561415,0.52707374,0.005802379,0.005087511,0.002780255,0.16447273],"study_design_scores_gemma":[0.000039474548,0.00017085405,0.19430059,0.00008070812,0.00009626511,0.00036159388,0.0032904323,0.7929935,0.0040555107,0.0015840065,0.0029455298,0.00008147987],"about_ca_topic_score_codex":0.13326465,"about_ca_topic_score_gemma":0.13338326,"teacher_disagreement_score":0.13326465,"about_ca_system_score_codex":0.0023961437,"about_ca_system_score_gemma":0.00046772466,"threshold_uncertainty_score":0.26497793},"labels":[],"label_agreement":null},{"id":"W4385407065","doi":"10.1007/s11356-023-29030-6","title":"Comparison of multi-DLM approaches for predicting daily runoff: evidence from the data-driven model in one of China’s largest wheat production-bases","year":2023,"lang":"en","type":"article","venue":"Environmental Science and Pollution Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Hebei Province","keywords":"Surface runoff; Watershed; Environmental science; Residual; Hydrology (agriculture); Precipitation; Water resources; Runoff curve number; Agriculture; Water year; Artificial neural network; Meteorology; Computer science; Machine learning; Geography; Engineering; Ecology","score_opus":0.42346989050350636,"score_gpt":0.40766174752440365,"score_spread":0.015808142979102713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385407065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9768083,0.0011354522,0.015535548,0.001275326,0.00010938521,0.000049728875,0.0011886664,0.00051196606,0.0033856228],"genre_scores_gemma":[0.99337363,0.00020875715,0.0052650007,0.00008278585,0.000023182809,0.000019222523,0.0006581869,0.000024804487,0.00034430958],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915636,0.00035109304,0.00008584054,0.00020535773,0.00012624881,0.000075014825],"domain_scores_gemma":[0.99495256,0.003496374,0.00024482934,0.00038947814,0.000665691,0.00025105296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042637866,0.0012187127,0.0009710458,0.0016092851,0.0006802068,0.0014997484,0.0018113202,0.0015090663,0.00093747623],"category_scores_gemma":[0.00667769,0.0005748341,0.0010221438,0.0013272731,0.0004442573,0.002320315,0.0009291937,0.0011424343,0.00026379005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012398021,0.0007641514,0.054340277,0.00018450619,0.0006820551,0.00007975024,0.0001409238,0.87325627,0.0014610396,0.0015897625,0.0012226417,0.06503882],"study_design_scores_gemma":[0.00007396651,0.000086150794,0.008470885,0.0000100788175,0.000067051,0.0000060697985,0.000056448927,0.9896597,0.0005262319,0.0006953002,0.0003253133,0.000022788905],"about_ca_topic_score_codex":0.064920805,"about_ca_topic_score_gemma":0.041328132,"teacher_disagreement_score":0.064920805,"about_ca_system_score_codex":0.0023066215,"about_ca_system_score_gemma":0.0014210431,"threshold_uncertainty_score":0.12908584},"labels":[],"label_agreement":null},{"id":"W4385739340","doi":"10.2478/johh-2023-0019","title":"Output updating of a physically based model for gauged and ungauged sites of the Upper Thames River watershed","year":2023,"lang":"en","type":"article","venue":"Journal of Hydrology and Hydromechanics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"Universiti Teknologi Malaysia","keywords":"Streamflow; Watershed; Hydrology (agriculture); Calibration; Precipitation; Environmental science; Process (computing); Hydrological modelling; Flood forecasting; Computer science; Meteorology; Geology; Mathematics; Geography; Statistics; Climatology; Machine learning; Cartography; Geotechnical engineering; Drainage basin","score_opus":0.023775176936061262,"score_gpt":0.23744976477513846,"score_spread":0.2136745878390772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385739340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9660711,0.000049219507,0.030661685,0.00010354499,0.000026937932,0.00002887313,0.00025770123,0.00025933754,0.0025416086],"genre_scores_gemma":[0.9966343,0.000010514047,0.002825406,0.000007386319,0.0000028491547,0.0000105919635,0.00009502606,0.0000037230966,0.00041019774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998902,0.000026284504,0.000009063961,0.000030618452,0.00002600153,0.000017786699],"domain_scores_gemma":[0.9997646,0.00008648495,0.00002685871,0.000020992004,0.000087214314,0.00001389795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036110537,0.00028568812,0.00024513798,0.00024112611,0.00030277963,0.00053510355,0.0006270437,0.00039226795,0.00082311034],"category_scores_gemma":[0.0009755247,0.0001749127,0.00028016182,0.00022257144,0.000251762,0.0003211027,0.00022230759,0.0003853036,0.000078746816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023068695,0.000024096256,0.005007077,0.0000072926987,0.000013609634,0.000036700167,0.000012755498,0.98904395,0.00071300747,0.000109371555,0.00009234987,0.004916738],"study_design_scores_gemma":[0.0000022676606,0.0000055476603,0.0018994523,8.249927e-7,0.0000027601227,0.0000024367084,0.000002952086,0.997818,0.00020126182,0.000027141754,0.00003551178,0.0000019455408],"about_ca_topic_score_codex":0.12944818,"about_ca_topic_score_gemma":0.094484456,"teacher_disagreement_score":0.8705518,"about_ca_system_score_codex":0.0011996255,"about_ca_system_score_gemma":0.0009472896,"threshold_uncertainty_score":0.25738943},"labels":[],"label_agreement":null},{"id":"W4385843387","doi":"10.35516/hum.v50i3.5404","title":"Assessment of Regression Model for Rainfall in Saudi Arabia (1979-2011) Using Dummy Variables","year":2023,"lang":"en","type":"article","venue":"Dirasat Human and Social Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linear regression; Regression analysis; Statistics; Variables; Quarter (Canadian coin); Regression; Mathematics; Geography","score_opus":0.13718158280694542,"score_gpt":0.37744186677247854,"score_spread":0.24026028396553312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385843387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90708345,0.00071684207,0.08548457,0.0007753395,0.00010160304,0.00016597769,0.002779472,0.0006212937,0.0022713877],"genre_scores_gemma":[0.98090047,0.00031583413,0.014633524,0.00004733256,0.000035184232,0.00012515983,0.0024661946,0.0000648414,0.001411323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997247,0.0017548949,0.00011335581,0.0004965168,0.00017717828,0.00021112156],"domain_scores_gemma":[0.9821743,0.014652212,0.0014650418,0.00040973478,0.0011132626,0.00018549335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008595492,0.0013139803,0.0008306919,0.0015800248,0.00034463202,0.0016961221,0.0014694863,0.0007717336,0.002627117],"category_scores_gemma":[0.016003221,0.00054627203,0.0021196695,0.0014808979,0.00029998706,0.0010797406,0.000783132,0.0014575704,0.0007650677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033901582,0.00018362275,0.2781143,0.00025463244,0.0010453219,0.00034786042,0.0004464585,0.6840777,0.0008773867,0.0043441,0.0025856474,0.027384],"study_design_scores_gemma":[0.00001808443,0.00013786694,0.03004713,0.000036725356,0.00012155732,0.000054049277,0.0002557,0.96722645,0.0003201186,0.00078265765,0.0009788508,0.000020822954],"about_ca_topic_score_codex":0.03659391,"about_ca_topic_score_gemma":0.016841922,"teacher_disagreement_score":0.03659391,"about_ca_system_score_codex":0.0015705694,"about_ca_system_score_gemma":0.0013610875,"threshold_uncertainty_score":0.07276183},"labels":[],"label_agreement":null},{"id":"W4385859762","doi":"10.1007/978-3-031-34593-7_69","title":"Artificial Neural Networks and Extended Kalman Filter for Easy-to-Implement Runoff Estimation Models","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in civil engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"","keywords":"Extended Kalman filter; Artificial neural network; Computer science; Kalman filter; Multilayer perceptron; Scalability; Machine learning; Artificial intelligence; Data mining","score_opus":0.031192814095516195,"score_gpt":0.24139353749675246,"score_spread":0.21020072340123627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385859762","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00217517,0.0022442236,0.99015373,0.00012205176,0.00022281046,0.00001490582,0.000097560805,0.000684556,0.0042849793],"genre_scores_gemma":[0.15932132,0.0053794174,0.7863999,0.0001674258,0.0005611033,0.00015743339,0.0007494435,0.00046079123,0.046803206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998091,0.000041744108,0.00001657686,0.000049560538,0.000068278714,0.000014725201],"domain_scores_gemma":[0.99970955,0.00016078663,0.000019385352,0.000041267795,0.00006224503,0.000006777994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044561885,0.00078909186,0.00056886754,0.00034472518,0.00020523064,0.00071413623,0.0007968674,0.0010301586,0.006003436],"category_scores_gemma":[0.0016072867,0.00051094196,0.0005506129,0.0007820864,0.0003455173,0.0012655979,0.0006222658,0.001451122,0.0020303088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007722504,0.00005997327,0.00037830023,0.00022445654,0.00006857169,0.00011507441,0.00005498357,0.5043903,0.005481321,0.058079798,0.009835935,0.42123404],"study_design_scores_gemma":[0.0000038318576,0.00001194822,0.00016464104,0.000013417166,0.0000095167725,0.000017968146,0.0000035198527,0.97968745,0.0011355791,0.013386601,0.005555745,0.000009796176],"about_ca_topic_score_codex":0.0061809984,"about_ca_topic_score_gemma":0.009247628,"teacher_disagreement_score":0.0061809984,"about_ca_system_score_codex":0.00048975763,"about_ca_system_score_gemma":0.0003739282,"threshold_uncertainty_score":0.020083487},"labels":[],"label_agreement":null},{"id":"W4386027236","doi":"10.1080/19942060.2023.2242445","title":"Machine learning models coupled with empirical mode decomposition for simulating monthly and yearly streamflows: a case study of three watersheds in Ontario, Canada","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Computational Fluid Mechanics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Korea Environmental Industry and Technology Institute; National Research Foundation of Korea; Ministry of Science and ICT, South Korea; Ministry of Education, India; Ministry of Environment; Chung-Ang University; National Research Foundation","keywords":"Mean squared error; Hilbert–Huang transform; Support vector machine; Streamflow; Backpropagation; Artificial neural network; Computer science; Convolutional neural network; Artificial intelligence; Correlation coefficient; Machine learning; Environmental science; Statistics; Mathematics; Geography","score_opus":0.022020380957885465,"score_gpt":0.2648871094874852,"score_spread":0.2428667285295997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386027236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903195,0.00013763888,0.0055188453,0.0002542617,0.000011314293,0.00006942998,0.0007457667,0.00023043538,0.0027127815],"genre_scores_gemma":[0.9944072,0.00008059837,0.004010408,0.000019418687,0.000003836587,0.000021204598,0.00048113675,0.000015700693,0.0009605553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997181,0.000043508364,0.000017092314,0.00006438261,0.000072717776,0.000084171676],"domain_scores_gemma":[0.9995252,0.0001588379,0.0000432044,0.000029962852,0.00018847344,0.00005425944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005721609,0.0010087226,0.0005214275,0.0006324406,0.0014981956,0.0010884197,0.0016119819,0.001254196,0.00077049213],"category_scores_gemma":[0.0013505991,0.00037672085,0.0007157203,0.001353586,0.0007613015,0.00054796506,0.00049255334,0.0007641328,0.00009061962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008564057,0.00019862244,0.05095082,0.000074089025,0.00006658534,0.000707775,0.0002094165,0.9306257,0.0016400297,0.0008514194,0.0010030976,0.0135867],"study_design_scores_gemma":[0.000021558426,0.000017249487,0.012890491,0.0000060245193,0.000017786151,0.000018569022,0.00018017112,0.9857305,0.000547029,0.00012499897,0.00042827343,0.000017207984],"about_ca_topic_score_codex":0.96326417,"about_ca_topic_score_gemma":0.95434374,"teacher_disagreement_score":0.036735833,"about_ca_system_score_codex":0.012258237,"about_ca_system_score_gemma":0.011148676,"threshold_uncertainty_score":0.088940084},"labels":[],"label_agreement":null},{"id":"W4386575378","doi":"10.1016/j.jhydrol.2023.130138","title":"Bayesian extreme learning machines for hydrological prediction uncertainty","year":2023,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Colleges and Universities; University of Waterloo","keywords":"Computer science; Extreme learning machine; Probabilistic logic; Streamflow; Monte Carlo method; Multilayer perceptron; Perceptron; Machine learning; Dropout (neural networks); Artificial intelligence; Artificial neural network; Evapotranspiration; Statistics; Mathematics","score_opus":0.03409063600264407,"score_gpt":0.2652666191260667,"score_spread":0.23117598312342263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386575378","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012376509,0.0008824222,0.9847114,0.0006758143,0.00007590906,0.000020063017,0.000106150874,0.00023172902,0.0009200037],"genre_scores_gemma":[0.80510384,0.0015941594,0.18452297,0.00034184568,0.0007207074,0.0003062396,0.0007587603,0.00019273267,0.006458757],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978992,0.0011489412,0.00014005101,0.00032578112,0.0003531865,0.00013287636],"domain_scores_gemma":[0.967334,0.029603463,0.0009090419,0.0007910753,0.0010974931,0.00026496593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061577237,0.0008428303,0.0022521291,0.0015791286,0.0007072523,0.0018599983,0.0020302073,0.0027042648,0.0030252247],"category_scores_gemma":[0.034327243,0.0009402291,0.001020515,0.001778864,0.0019992867,0.003510846,0.0020109345,0.004296631,0.00045175484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006584665,0.000040115137,0.00049073587,0.00005243569,0.000053715015,0.00003192221,0.00003917548,0.9270703,0.00012228449,0.045560353,0.001049236,0.025423948],"study_design_scores_gemma":[0.0000036348,0.000003013726,0.000050766834,0.000003869649,0.0000021076992,0.000002499377,0.0000015817585,0.96417224,0.000023228125,0.035655342,0.00007857254,0.000003164994],"about_ca_topic_score_codex":0.005450565,"about_ca_topic_score_gemma":0.0030148532,"teacher_disagreement_score":0.0061577237,"about_ca_system_score_codex":0.0015025459,"about_ca_system_score_gemma":0.0009930729,"threshold_uncertainty_score":0.032565534},"labels":[],"label_agreement":null},{"id":"W4386697003","doi":"10.1016/j.eswa.2023.121512","title":"Monthly sodium adsorption ratio forecasting in rivers using a dual interpretable glass-box complementary intelligent system: Hybridization of ensemble TVF-EMD-VMD, Boruta-SHAP, and eXplainable GPR","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Hilbert–Huang transform; Artificial intelligence; Computer science; Wavelet; Perceptron; Artificial neural network; Feature (linguistics); Pattern recognition (psychology); Data mining; Mathematics; Energy (signal processing); Statistics","score_opus":0.03588246122780619,"score_gpt":0.2607271769611985,"score_spread":0.22484471573339232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386697003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8260505,0.00018999583,0.17001623,0.00024449587,0.000079024896,0.000027036667,0.0002730914,0.0012974897,0.0018221588],"genre_scores_gemma":[0.97522914,0.000038735918,0.024112077,0.000028444781,0.000013383291,0.000011698512,0.00014498727,0.000017805773,0.00040378215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986625,0.000031166594,0.000009277878,0.000048968188,0.000024591682,0.00001977396],"domain_scores_gemma":[0.9997861,0.00009467678,0.000015329873,0.000017602995,0.000070019785,0.00001637881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049140205,0.00043470776,0.0006650711,0.00045845186,0.00024366642,0.00044540668,0.0004624314,0.0006987013,0.0005107114],"category_scores_gemma":[0.0008096675,0.00022261706,0.00054976204,0.00040372336,0.00012445205,0.0004949244,0.00030319157,0.00042257272,0.00012311967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069704896,0.00039047148,0.026968652,0.000102407386,0.0002316263,0.00017646332,0.0001319843,0.6558876,0.038835764,0.00075020443,0.0014197913,0.27440795],"study_design_scores_gemma":[0.0000051681836,0.000015523334,0.0014551454,8.30278e-7,0.000012567247,0.0000046345685,0.0000044361313,0.9973406,0.001055352,0.000055929453,0.000045354474,0.0000043864775],"about_ca_topic_score_codex":0.008595321,"about_ca_topic_score_gemma":0.009936752,"teacher_disagreement_score":0.008595321,"about_ca_system_score_codex":0.00033709354,"about_ca_system_score_gemma":0.0003616695,"threshold_uncertainty_score":0.017090559},"labels":[],"label_agreement":null},{"id":"W4386760161","doi":"10.1007/s11269-023-03613-x","title":"Hybrid Iterative and Tree-Based Machine Learning Algorithms for Lake Water Level Forecasting","year":2023,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Random forest; Algorithm; Computer science; Decision tree; Autoregressive model; Machine learning; Ensemble learning; Artificial intelligence; Tree (set theory); Time series; Ensemble forecasting; Data mining; Mathematics; Statistics","score_opus":0.052421606748173304,"score_gpt":0.2409556969541197,"score_spread":0.1885340902059464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386760161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03428748,0.0003565585,0.96246356,0.0000956553,0.00005311518,0.000042782594,0.00006421068,0.0007134303,0.0019232369],"genre_scores_gemma":[0.5040082,0.00032716335,0.49159646,0.00012138969,0.00009386926,0.00027076053,0.0002674182,0.00013683371,0.003177942],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994523,0.00019750821,0.000047650257,0.00007626073,0.00017257656,0.000053777432],"domain_scores_gemma":[0.9969194,0.0020342951,0.00012733536,0.00011188052,0.00074082165,0.0000663519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019442239,0.00051512447,0.0010684966,0.0011258218,0.00045742386,0.0008665138,0.0015625309,0.0010130174,0.0018505388],"category_scores_gemma":[0.005747,0.00037997725,0.000631124,0.0016287992,0.0004214614,0.0014407234,0.0007464603,0.0010368455,0.00043476373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000111881745,0.000090484056,0.0011332284,0.000053526506,0.00007944787,0.000021061329,0.000071560695,0.7907591,0.0015327764,0.0030323558,0.0009557213,0.20215894],"study_design_scores_gemma":[0.000005154705,0.000011091908,0.00009302263,0.0000017952071,0.000003965993,0.0000029949995,0.0000022834242,0.99894243,0.00018205654,0.00065340084,0.000099086974,0.0000027110361],"about_ca_topic_score_codex":0.014635633,"about_ca_topic_score_gemma":0.013403097,"teacher_disagreement_score":0.014635633,"about_ca_system_score_codex":0.00085879833,"about_ca_system_score_gemma":0.0013952106,"threshold_uncertainty_score":0.029100895},"labels":[],"label_agreement":null},{"id":"W4386868814","doi":"10.2139/ssrn.4572361","title":"Predicting and Analyzing the Algal Population Dynamics of a Grass-Type Lake with Explainable Machine Learning","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Dynamics (music); Type (biology); Population; Algal bloom; Computer science; Ecology; Biology; Phytoplankton; Demography; Psychology; Sociology","score_opus":0.011500848386015774,"score_gpt":0.22812634932069428,"score_spread":0.2166255009346785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386868814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98646784,0.000031308507,0.01289579,0.00013210559,0.000005191222,0.000004409554,0.000074088406,0.000038956565,0.00035028908],"genre_scores_gemma":[0.99741614,0.000013930647,0.0023205117,0.0000051459847,0.0000043917867,0.0000028611062,0.00006541675,0.0000031496552,0.00016843558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999602,0.000008180257,0.0000018625443,0.000013429888,0.0000062792983,0.000009972147],"domain_scores_gemma":[0.9997186,0.0001702524,0.000038451195,0.0000150617125,0.00003217406,0.000025369767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024622463,0.00024199531,0.00019243693,0.00024975298,0.00027135582,0.00032983342,0.00034343373,0.00047960435,0.00048518728],"category_scores_gemma":[0.0011724443,0.0001838268,0.00027238304,0.0003289441,0.00028544935,0.00048386565,0.0002653656,0.00035113053,0.000045705943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005268212,0.000042685704,0.038770862,0.000018055573,0.00003613638,0.000089573776,0.00006489982,0.9471495,0.003766548,0.0010510256,0.00024357524,0.008714472],"study_design_scores_gemma":[0.0000018121389,0.000004526985,0.003556355,3.009188e-7,0.0000021368978,0.0000025957195,0.000005437373,0.9959151,0.00014163325,0.00035327615,0.00001522271,0.00000162296],"about_ca_topic_score_codex":0.02896566,"about_ca_topic_score_gemma":0.025583329,"teacher_disagreement_score":0.02896566,"about_ca_system_score_codex":0.0005925256,"about_ca_system_score_gemma":0.0005796349,"threshold_uncertainty_score":0.05759412},"labels":[],"label_agreement":null},{"id":"W4387233192","doi":"10.20944/preprints202309.2161.v1","title":"New Graph-Based and Transformers Deep Learning Models for River Dissolved Oxygen Forecasting","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Mean squared error; Watershed; Benchmarking; Water quality; Transformer; Graph; Computer science; Environmental science; Eutrophication; Machine learning; Data mining; Hydrology (agriculture); Statistics; Mathematics; Engineering; Ecology; Nutrient","score_opus":0.20630315393489773,"score_gpt":0.3128636964566238,"score_spread":0.10656054252172609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387233192","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1514832,0.00078565686,0.8397934,0.0005133237,0.00013521421,0.0000448462,0.00058763125,0.0011589068,0.005497743],"genre_scores_gemma":[0.94595075,0.00034093135,0.048286747,0.00013171542,0.000035694604,0.000052655752,0.00073366135,0.000048319678,0.0044194562],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998989,0.000021319262,0.0000070113047,0.000030945477,0.000023153034,0.000018673005],"domain_scores_gemma":[0.99966264,0.00016757105,0.000032041757,0.000019358798,0.0000982462,0.00002014602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040590082,0.0005785344,0.00047145944,0.00048661148,0.0001728418,0.0006404415,0.0009639734,0.0006495849,0.0015669694],"category_scores_gemma":[0.0012319613,0.00025281773,0.0005413077,0.0005719515,0.00032802307,0.0008183312,0.00062163745,0.0009659344,0.00021275181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022384707,0.000019405967,0.0007374686,0.000012127694,0.000016810183,0.000016365217,0.000012211406,0.9794861,0.00041790502,0.0019383893,0.00043220306,0.016888594],"study_design_scores_gemma":[7.626873e-7,0.0000027871777,0.000047873218,7.563834e-7,0.000001548649,0.000001080618,9.57546e-7,0.9992207,0.00005302874,0.00061989523,0.000049731207,7.84538e-7],"about_ca_topic_score_codex":0.015977014,"about_ca_topic_score_gemma":0.016756924,"teacher_disagreement_score":0.015977014,"about_ca_system_score_codex":0.0007980608,"about_ca_system_score_gemma":0.00060978136,"threshold_uncertainty_score":0.031768084},"labels":[],"label_agreement":null},{"id":"W4387451098","doi":"10.1002/rvr2.63","title":"Water level prediction using deep learning models: A case study of the Kien Giang River, Quang Binh Province","year":2023,"lang":"en","type":"article","venue":"River","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Typhoon; Water level; Mean squared error; Flood myth; Wind speed; Computer science; Long short term memory; Meteorology; Environmental science; Artificial intelligence; Recurrent neural network; Statistics; Geography; Artificial neural network; Cartography; Mathematics","score_opus":0.10893924002684521,"score_gpt":0.2621455300029658,"score_spread":0.1532062899761206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387451098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961218,0.000055845503,0.0020136742,0.00017833141,0.000009528524,0.00001560577,0.00047346242,0.00007990989,0.0010519094],"genre_scores_gemma":[0.9983553,0.000025537263,0.00093700335,0.0000068008603,0.0000017505427,0.0000062669315,0.00027047002,0.0000034411944,0.00039328056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999876,0.000027766131,0.000008423104,0.00002967365,0.000025782514,0.000032328186],"domain_scores_gemma":[0.99971753,0.00010843181,0.00003054076,0.000025953692,0.00008066048,0.00003687356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003227225,0.00041797647,0.0002750202,0.0005178094,0.00049958145,0.0005524344,0.000655383,0.00050125696,0.0007360865],"category_scores_gemma":[0.0007188367,0.00020582795,0.00031700972,0.0012680074,0.00035707804,0.00047999743,0.00034374653,0.000460092,0.000068645204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016874548,0.00027045546,0.122633435,0.000103284845,0.00010740783,0.0020461157,0.0002909906,0.83523935,0.0025233456,0.0016759053,0.0018545168,0.033086374],"study_design_scores_gemma":[0.000012106636,0.000020183548,0.016742704,0.0000050748963,0.000014168285,0.000018846538,0.00022839473,0.9817246,0.00064072176,0.00024708433,0.00033529583,0.000010891925],"about_ca_topic_score_codex":0.41450778,"about_ca_topic_score_gemma":0.4274944,"teacher_disagreement_score":0.41450778,"about_ca_system_score_codex":0.0033585601,"about_ca_system_score_gemma":0.001816658,"threshold_uncertainty_score":0.82419014},"labels":[],"label_agreement":null},{"id":"W4387735350","doi":"10.1109/ic3ina60834.2023.10285812","title":"Harmful Algal Blooms Prediction Model: Dealing With Limited Datasets","year":2023,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Transfer of learning; Computer science; Buoy; Process (computing); Artificial intelligence; Machine learning; Data modeling; Algal bloom; Artificial neural network; Water quality; Deep learning; Data mining; Ecology; Engineering","score_opus":0.027945054231561364,"score_gpt":0.240157906524908,"score_spread":0.21221285229334663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387735350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5773839,0.0026583285,0.39584497,0.003786348,0.00047049025,0.0002991387,0.0066380203,0.004242806,0.008675901],"genre_scores_gemma":[0.9403974,0.0004963832,0.04787558,0.00040280476,0.00012748424,0.00027763474,0.005576818,0.000064966254,0.00478104],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975497,0.00004634267,0.00002306697,0.00009706686,0.000036737976,0.000041787258],"domain_scores_gemma":[0.99922705,0.00043141883,0.00006333133,0.00006771341,0.00017474139,0.000035735582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010677426,0.0009806345,0.00084307964,0.0006021945,0.0003370688,0.00076475355,0.0014232668,0.0013017048,0.0016160941],"category_scores_gemma":[0.0028036667,0.00035793945,0.0007545016,0.0006952132,0.00029280197,0.0011075806,0.0006935704,0.0019054555,0.0004356428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018438963,0.00015396769,0.008946397,0.00008457952,0.00010084244,0.00016605572,0.00004131715,0.9281639,0.001103349,0.00079790555,0.0037974424,0.056459773],"study_design_scores_gemma":[0.000003911772,0.00000850535,0.00038941833,0.0000026814137,0.0000046379696,0.000006820411,0.0000040552864,0.99890864,0.00015167668,0.0003813962,0.00013597195,0.000002231566],"about_ca_topic_score_codex":0.029085483,"about_ca_topic_score_gemma":0.017526217,"teacher_disagreement_score":0.029085483,"about_ca_system_score_codex":0.00070322846,"about_ca_system_score_gemma":0.00096143916,"threshold_uncertainty_score":0.05783236},"labels":[],"label_agreement":null},{"id":"W4387806820","doi":"10.1016/j.jhydrol.2023.130363","title":"A2DWQPE: Adaptive and automated data-driven water quality parameter estimation","year":2023,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Environment and Climate Change Canada; National Aeronautics and Space Administration","keywords":"Computer science; Hyperparameter; Data mining; Artificial neural network; Cluster analysis; Estimation; Estimation theory; Remote sensing; Machine learning; Spectroradiometer; Bayesian probability; Water quality; Artificial intelligence; Algorithm; Reflectivity","score_opus":0.07892590568940143,"score_gpt":0.335780201259912,"score_spread":0.25685429557051054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387806820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01309085,0.00010882548,0.93854886,0.00013952736,0.00014707934,0.0001509249,0.0021188748,0.04435835,0.0013367649],"genre_scores_gemma":[0.23634827,0.00012372115,0.7522024,0.0002409647,0.000089884925,0.00044981332,0.0051412936,0.001482371,0.003921236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973005,0.000043197186,0.000016723612,0.00006670989,0.00011628898,0.000027078368],"domain_scores_gemma":[0.99923754,0.0002871464,0.00004390093,0.00011721304,0.000267333,0.0000468898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069935183,0.000854449,0.0006977807,0.0008884993,0.00026887527,0.0006869108,0.0017343558,0.00067477516,0.007246266],"category_scores_gemma":[0.0034294038,0.0004928434,0.00045695773,0.0007711249,0.00020144969,0.0009732182,0.0012479466,0.0011589532,0.0022200772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005314884,0.0004024717,0.003913169,0.00021087757,0.0002157654,0.00016949483,0.00008330683,0.17621906,0.019146295,0.0030451878,0.057292562,0.7387704],"study_design_scores_gemma":[0.00003156384,0.000013230609,0.00038261482,0.0000021265246,0.000003902321,0.00001227973,0.000004106355,0.9947025,0.0023131084,0.00070787023,0.0018169672,0.000009659985],"about_ca_topic_score_codex":0.011603698,"about_ca_topic_score_gemma":0.015043866,"teacher_disagreement_score":0.011603698,"about_ca_system_score_codex":0.00031667048,"about_ca_system_score_gemma":0.0010059394,"threshold_uncertainty_score":0.02424115},"labels":[],"label_agreement":null},{"id":"W4388141454","doi":"10.2166/hydro.2023.122","title":"A methodology for integrating time-lagged rainfall and river flow data into machine learning models to improve prediction of quality parameters of raw water supplying a treatment plant","year":2023,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Turbidity; Water quality; Environmental science; Watershed; Hydrology (agriculture); Rank correlation; Environmental engineering; Statistics; Machine learning; Computer science; Mathematics; Engineering; Ecology","score_opus":0.16924282485585376,"score_gpt":0.32118804426913616,"score_spread":0.1519452194132824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388141454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06469207,0.00010362212,0.93421096,0.000079738435,0.000024505283,0.00004575968,0.00007935609,0.0003788121,0.0003851667],"genre_scores_gemma":[0.77309096,0.00011453197,0.22566874,0.00003140622,0.000024918705,0.00017294289,0.00017434004,0.000020671734,0.0007016382],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962425,0.00017961636,0.000035286084,0.00008041785,0.00005861,0.000021847949],"domain_scores_gemma":[0.99880075,0.00071345735,0.00015861337,0.000064685984,0.00023569132,0.00002690015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019344084,0.00067358615,0.00043648874,0.00067755894,0.00016817871,0.00049819506,0.0006408265,0.00057922956,0.00062877533],"category_scores_gemma":[0.0032130643,0.00034063307,0.00059735955,0.00049045373,0.000191685,0.00064522325,0.00037713442,0.0007591379,0.00012008768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044218457,0.00010667717,0.002837865,0.000032384873,0.00011609841,0.000035418077,0.000025632176,0.94233733,0.003190982,0.0012211775,0.00011321869,0.04993895],"study_design_scores_gemma":[0.0000020376872,0.000026365267,0.0002768301,0.0000018367792,0.0000046632176,0.0000025040279,0.0000018491985,0.99900466,0.00038899158,0.00023049055,0.000057118952,0.0000026755786],"about_ca_topic_score_codex":0.0054888134,"about_ca_topic_score_gemma":0.0044208877,"teacher_disagreement_score":0.0054888134,"about_ca_system_score_codex":0.00038094327,"about_ca_system_score_gemma":0.0007260719,"threshold_uncertainty_score":0.01091373},"labels":[],"label_agreement":null},{"id":"W4388197891","doi":"10.18280/mmep.100532","title":"Analysis of Salinity Indices Using SVM Based Approach of Ballari Town, India","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Salinity; Statistics; Environmental science; Pattern recognition (psychology); Geography; Data mining; Computer science; Artificial intelligence; Mathematics; Geology; Oceanography","score_opus":0.05032193127242552,"score_gpt":0.23355042204906323,"score_spread":0.18322849077663772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388197891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98403984,0.00012971163,0.0117039345,0.00011640223,0.000034198343,0.00003309746,0.00052756455,0.00028755836,0.0031276504],"genre_scores_gemma":[0.99514186,0.00007073354,0.0029892966,0.000014566585,0.000006631782,0.000012808928,0.0007226207,0.0000101129735,0.0010313147],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985397,0.00001958062,0.000012158347,0.000038300448,0.000038322334,0.0000375885],"domain_scores_gemma":[0.9997874,0.00004607878,0.000026168407,0.0000155621,0.00010163396,0.000023053468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016993623,0.0003392222,0.00031891614,0.0013823629,0.0002138794,0.0007885375,0.0003495657,0.0002461305,0.00096282974],"category_scores_gemma":[0.0005369858,0.00012645926,0.000438277,0.000835808,0.00019613944,0.00029465638,0.00032145155,0.000231238,0.00038910462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012062965,0.00045379766,0.39957651,0.00035966304,0.00032177265,0.0029838462,0.0010904878,0.16022529,0.07474938,0.0014443876,0.00779767,0.34979096],"study_design_scores_gemma":[0.000019493255,0.00021095858,0.3736932,0.000025449663,0.000108963184,0.0003867426,0.0016812893,0.6103952,0.01074129,0.0005079429,0.0021697285,0.000059741753],"about_ca_topic_score_codex":0.018659545,"about_ca_topic_score_gemma":0.012777707,"teacher_disagreement_score":0.018659545,"about_ca_system_score_codex":0.00035846807,"about_ca_system_score_gemma":0.00026213733,"threshold_uncertainty_score":0.037101865},"labels":[],"label_agreement":null},{"id":"W4388201889","doi":"10.18280/mmep.100521","title":"Hybrid Algorithm of Backpropagation and Relevance Vector Machine with Radial Basis Function Kernel for Hydro-Climatological Data Prediction","year":2023,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Backpropagation; Radial basis function; Computer science; Artificial neural network; Relevance vector machine; Machine learning; Algorithm; Artificial intelligence; Evapotranspiration; Mean squared error; Support vector machine; Kernel (algebra); Wind speed; Data mining; Mathematics; Statistics; Meteorology","score_opus":0.03385867687077909,"score_gpt":0.21144840176034133,"score_spread":0.17758972488956223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388201889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038675603,0.0010099049,0.95583296,0.000167811,0.0001125265,0.00010311723,0.000053598647,0.0024636362,0.0015809657],"genre_scores_gemma":[0.58474314,0.00071750366,0.4073988,0.00014708866,0.000088994544,0.00032423713,0.00028610005,0.00015220592,0.0061419527],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998936,0.00024959454,0.00009480599,0.00022968216,0.00037608447,0.00011389659],"domain_scores_gemma":[0.9990183,0.00031330672,0.00007938779,0.00009391962,0.00046824085,0.000026702533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001855662,0.0012532049,0.0011878302,0.0010162992,0.00044003522,0.0008129625,0.001548941,0.001313326,0.0010884503],"category_scores_gemma":[0.0035433334,0.00045793754,0.00083553325,0.0010356486,0.00038306677,0.0012868242,0.000720483,0.0011656298,0.00073134614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002370983,0.00018851591,0.001823266,0.00015657101,0.00016855275,0.00014231747,0.00011297538,0.4028167,0.00978862,0.0022637644,0.0023380509,0.57996356],"study_design_scores_gemma":[0.000008421028,0.000048968413,0.00034954405,0.0000045650613,0.000011081537,0.000028299772,0.0000058923797,0.996615,0.0019903749,0.00040598487,0.00052267755,0.000009065082],"about_ca_topic_score_codex":0.009571628,"about_ca_topic_score_gemma":0.005215371,"teacher_disagreement_score":0.009571628,"about_ca_system_score_codex":0.0005825729,"about_ca_system_score_gemma":0.0012954368,"threshold_uncertainty_score":0.019031882},"labels":[],"label_agreement":null},{"id":"W4388569146","doi":"10.2166/aqua.2023.005","title":"Exploring the rise of AI-based smart water management systems","year":2023,"lang":"en","type":"article","venue":"AQUA - Water Infrastructure Ecosystems and Society","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data science","score_opus":0.023969727878381947,"score_gpt":0.2110546604703008,"score_spread":0.18708493259191886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388569146","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087571084,0.046949405,0.5480448,0.11368833,0.005626535,0.00022185472,0.00049395126,0.0019957875,0.19540821],"genre_scores_gemma":[0.69232136,0.052662548,0.21302618,0.0057338057,0.0028626176,0.00017078128,0.00074107497,0.00035784513,0.032123763],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985588,0.00046918585,0.0000770979,0.00017709151,0.00057257776,0.00014520796],"domain_scores_gemma":[0.9961488,0.002309411,0.00017386019,0.00027529345,0.0008169972,0.00027560367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031906627,0.00037675677,0.0003101412,0.00077848276,0.00063392695,0.003959469,0.0011871917,0.0018218325,0.004587549],"category_scores_gemma":[0.0063882605,0.00028915505,0.00043153856,0.0014490188,0.0012354262,0.009473736,0.002291265,0.0022592926,0.0008344702],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008219453,0.00015373925,0.00393629,0.00069455,0.000092544855,0.0003308948,0.0010560094,0.042485323,0.005473802,0.44223055,0.045106474,0.4583576],"study_design_scores_gemma":[0.000026625063,0.00013789347,0.0020251705,0.0003637811,0.000042114374,0.00015646314,0.001138722,0.28056863,0.0063871304,0.21062604,0.49845222,0.00007523066],"about_ca_topic_score_codex":0.0021533945,"about_ca_topic_score_gemma":0.0017467254,"teacher_disagreement_score":0.004587549,"about_ca_system_score_codex":0.0016225097,"about_ca_system_score_gemma":0.0012502522,"threshold_uncertainty_score":0.016874075},"labels":[],"label_agreement":null},{"id":"W4388733469","doi":"10.1007/s12517-023-11779-2","title":"Predicting rainfall in Nineveh Governorate in northern Iraq using machine learning time-series forecasting algorithm","year":2023,"lang":"en","type":"article","venue":"Arabian Journal of Geosciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Environmental science; Water resources; Series (stratigraphy); Climatology; Climate change; Time series; Meteorology; Scarcity; Hydrology (agriculture); Geography; Mathematics; Statistics; Geology; Oceanography","score_opus":0.025954004855918037,"score_gpt":0.23466467094748425,"score_spread":0.20871066609156622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388733469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99805,0.000059590933,0.00040450497,0.000121243735,0.000019515677,0.0000070211486,0.00059272937,0.000039282764,0.0007061555],"genre_scores_gemma":[0.99816304,0.00005234767,0.0004797457,0.0000107341475,0.000013945587,0.0000073775554,0.0007256275,0.000002883356,0.0005443767],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999025,0.00001566397,0.000011039872,0.000020441226,0.000020589547,0.000029674973],"domain_scores_gemma":[0.9997458,0.000053566135,0.000044595556,0.00001625156,0.000104006875,0.000035779925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019594672,0.0002501381,0.00026733827,0.0005763612,0.00045138228,0.00044392693,0.0003915482,0.0004516291,0.0008623834],"category_scores_gemma":[0.0005302992,0.0001265962,0.00023904144,0.000839306,0.00022711286,0.0002544636,0.00024625118,0.00029703352,0.00015311732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029725084,0.00038976496,0.7568763,0.00011488931,0.0001967712,0.0018044976,0.00063263404,0.19302338,0.004540848,0.0008649545,0.0061252974,0.03513342],"study_design_scores_gemma":[0.000035249024,0.000058874157,0.51493865,0.000018627903,0.000046428322,0.00010154978,0.0012288397,0.48009667,0.0011025916,0.00017787122,0.0021744897,0.000020156862],"about_ca_topic_score_codex":0.18694237,"about_ca_topic_score_gemma":0.18848707,"teacher_disagreement_score":0.18694237,"about_ca_system_score_codex":0.00095770584,"about_ca_system_score_gemma":0.0008549609,"threshold_uncertainty_score":0.3717085},"labels":[],"label_agreement":null},{"id":"W4388976461","doi":"10.1007/s11356-023-30774-4","title":"Forecasting water quality variable using deep learning and weighted averaging ensemble models","year":2023,"lang":"en","type":"article","venue":"Environmental Science and Pollution Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Convolutional neural network; Ensemble forecasting; Water quality; Artificial neural network; Genetic algorithm; Deep learning; Machine learning; Predictive modelling; Ecology; Biology","score_opus":0.11669739880054253,"score_gpt":0.34415482428884164,"score_spread":0.22745742548829911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388976461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39799458,0.0008322057,0.5967554,0.00047644065,0.00030579796,0.00002809262,0.0004482422,0.00071729015,0.0024420458],"genre_scores_gemma":[0.963003,0.00024087436,0.03484153,0.00006471242,0.00009310912,0.000024299947,0.00043621706,0.000024567544,0.0012717712],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976414,0.000044770193,0.000019228317,0.00006330364,0.00006466088,0.000043901287],"domain_scores_gemma":[0.99932635,0.00027739,0.00007346453,0.00007061255,0.00021810539,0.000034099397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089074695,0.0006323758,0.0010257888,0.00072313333,0.00029137117,0.0005944638,0.00073748274,0.00064142497,0.0006405642],"category_scores_gemma":[0.0018826462,0.0003483101,0.00077715114,0.0010961279,0.000228268,0.0013209871,0.00055810425,0.0012488592,0.00013482348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063118096,0.000081252416,0.003547897,0.000016420352,0.00012219051,0.00002189239,0.000015363477,0.9425968,0.0011989317,0.0009593483,0.00078961154,0.050587155],"study_design_scores_gemma":[7.9650283e-7,0.000002426477,0.00015017825,3.8379005e-7,0.0000032727917,8.0403095e-7,6.184841e-7,0.9995447,0.000072406445,0.00020645236,0.000016965658,9.665408e-7],"about_ca_topic_score_codex":0.01968653,"about_ca_topic_score_gemma":0.02017613,"teacher_disagreement_score":0.01968653,"about_ca_system_score_codex":0.0005300572,"about_ca_system_score_gemma":0.0006623729,"threshold_uncertainty_score":0.03914386},"labels":[],"label_agreement":null},{"id":"W4389357892","doi":"10.1130/abs/2023am-395190","title":"DETERMINING AQUIFER VULNERABILITY AND RECHARGE RATES IN ALBERTA, CANADA USING HYDROGRAPH DATA ANALYSIS","year":2023,"lang":"en","type":"article","venue":"Abstracts with programs - Geological Society of America","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; University of Waterloo","funders":"","keywords":"Groundwater recharge; Hydrograph; Aquifer; Vulnerability (computing); Hydrology (agriculture); Environmental science; Water resource management; Vulnerability assessment; Geology; Groundwater; Computer science; Geography; Geotechnical engineering; Cartography","score_opus":0.04884322825657938,"score_gpt":0.2869288872863927,"score_spread":0.23808565902981332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389357892","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922733,0.00022449551,0.00036533567,0.00018233263,0.000005870986,0.000032459746,0.0042651156,0.000050179504,0.0026007474],"genre_scores_gemma":[0.99477273,0.00024408111,0.000662468,0.000036264544,0.0000024961041,0.000012055308,0.0021356705,0.000007725659,0.002126532],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996525,0.000027739123,0.00002284177,0.000046653364,0.00015116528,0.0000990404],"domain_scores_gemma":[0.99852103,0.0002044756,0.00016010215,0.000033475808,0.0008137477,0.0002672736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057296443,0.00028801602,0.00022625674,0.0023660802,0.0015469791,0.0010592787,0.00086263695,0.00036031703,0.0011893547],"category_scores_gemma":[0.00163443,0.00025109077,0.00031539783,0.004137458,0.00058188173,0.0003542521,0.0005312301,0.00030882968,0.00017280836],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012614897,0.000055740464,0.97347915,0.000040956686,0.00008627227,0.00025191673,0.00063732936,0.005160246,0.0004524547,0.00033401296,0.0024365506,0.016939307],"study_design_scores_gemma":[0.000013488676,0.000010387298,0.98770636,0.000023926483,0.000039370978,0.000049506096,0.0019439538,0.008451136,0.00024951712,0.000114918,0.001379435,0.00001793286],"about_ca_topic_score_codex":0.99790835,"about_ca_topic_score_gemma":0.9990657,"teacher_disagreement_score":0.02368418,"about_ca_system_score_codex":0.02368418,"about_ca_system_score_gemma":0.0233747,"threshold_uncertainty_score":0.17184156},"labels":[],"label_agreement":null},{"id":"W4389559997","doi":"10.3390/environments10120217","title":"New Graph-Based and Transformer Deep Learning Models for River Dissolved Oxygen Forecasting","year":2023,"lang":"en","type":"article","venue":"Environments","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakes Environmental (Canada); University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Benchmarking; Mean squared error; Water quality; Watershed; Computer science; Transformer; Environmental science; Artificial neural network; STREAMS; Data mining; Machine learning; Hydrology (agriculture); Statistics; Mathematics; Engineering; Ecology","score_opus":0.04237375490471945,"score_gpt":0.22818375069933974,"score_spread":0.1858099957946203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389559997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16893137,0.0006066728,0.8236957,0.00044521043,0.000109148474,0.00004612056,0.0004234542,0.0009810457,0.004761189],"genre_scores_gemma":[0.9569145,0.00023488166,0.039064486,0.00010762468,0.000022086173,0.000043223292,0.0004771808,0.00002922306,0.0031067585],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998851,0.00002362659,0.000007739885,0.000033974302,0.00002797874,0.00002157204],"domain_scores_gemma":[0.9996332,0.00017481142,0.00003806886,0.000019767163,0.00011267894,0.000021420332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048052619,0.00055303134,0.00046970596,0.0005340714,0.00018614784,0.0005765296,0.0010436649,0.00056007836,0.0011841141],"category_scores_gemma":[0.0012294147,0.00023938266,0.00053488987,0.00058206083,0.0003355441,0.00084589364,0.0005933772,0.0008969423,0.00016007166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020772479,0.000023063576,0.00087930885,0.000010499367,0.00001695368,0.000015007185,0.000011539638,0.9788603,0.00037895193,0.0017239575,0.0003676655,0.017691972],"study_design_scores_gemma":[6.988008e-7,0.0000029571502,0.000051083694,5.380689e-7,0.0000014516447,9.982139e-7,9.1329713e-7,0.99940956,0.000050337203,0.00044763988,0.000033175966,7.4874646e-7],"about_ca_topic_score_codex":0.021553418,"about_ca_topic_score_gemma":0.022882072,"teacher_disagreement_score":0.021553418,"about_ca_system_score_codex":0.0010055107,"about_ca_system_score_gemma":0.0007055041,"threshold_uncertainty_score":0.04285592},"labels":[],"label_agreement":null},{"id":"W4389637730","doi":"10.1016/j.compag.2023.108479","title":"Accurate monitoring of micronutrients in tilled potato soils of eastern Canada: Application of an eXplainable inspired-adaptive boosting framework coupled with SelectKbest","year":2023,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; University of Prince Edward Island","funders":"","keywords":"AdaBoost; Boosting (machine learning); Machine learning; Categorical variable; Kriging; Micronutrient; Artificial intelligence; Computer science; Feature selection; Soil water; Regression; Multivariate adaptive regression splines; Agricultural engineering; Environmental science; Mathematics; Regression analysis; Engineering; Soil science; Statistics; Support vector machine; Nonparametric regression; Chemistry","score_opus":0.008686663299929124,"score_gpt":0.21306959138702095,"score_spread":0.20438292808709183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389637730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93843085,0.00061032915,0.056427922,0.00024678468,0.000031839096,0.00004637048,0.0011847347,0.0006636063,0.002357521],"genre_scores_gemma":[0.98624694,0.00008630209,0.012661335,0.000019121999,0.000005224808,0.000007199118,0.00028339768,0.0000144409,0.00067598827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99992454,0.000007748418,0.0000028419554,0.00002526703,0.000022692937,0.000016959259],"domain_scores_gemma":[0.9998124,0.000032897064,0.000015040991,0.00001202569,0.000110619636,0.000017045626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003010661,0.00033906073,0.00033712952,0.00046552822,0.0005029543,0.00050525856,0.0007996053,0.00040914095,0.00046719954],"category_scores_gemma":[0.0005630404,0.00014077485,0.00029047002,0.00056376914,0.00019187096,0.00025742434,0.00034023257,0.00031655066,0.00010787609],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039186855,0.00017855021,0.15360133,0.00021452771,0.00022250696,0.00020532808,0.00024625403,0.64380854,0.0389926,0.0009837637,0.0020633102,0.15909146],"study_design_scores_gemma":[0.000009634075,0.000014886766,0.03191584,0.0000044360063,0.00002599655,0.00001127967,0.00005166621,0.9640138,0.0031750924,0.0002660608,0.00050029473,0.000010927658],"about_ca_topic_score_codex":0.62638867,"about_ca_topic_score_gemma":0.75189257,"teacher_disagreement_score":0.37361133,"about_ca_system_score_codex":0.0017975946,"about_ca_system_score_gemma":0.0025435742,"threshold_uncertainty_score":0.7516232},"labels":[],"label_agreement":null},{"id":"W4389650839","doi":"10.48550/arxiv.2312.05961","title":"TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University; Canada Excellence Research Chairs, Government of Canada","keywords":"Computer science; Benchmark (surveying); Graph; Flood forecasting; Data mining; Artificial neural network; Encoder; Streamflow; Machine learning; Artificial intelligence; Flood myth; Theoretical computer science","score_opus":0.11504164975307654,"score_gpt":0.19401028737582066,"score_spread":0.07896863762274411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389650839","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06696547,0.001598922,0.92105126,0.00091656524,0.0002570932,0.000059084596,0.00078535965,0.004080592,0.004285618],"genre_scores_gemma":[0.91107535,0.00072191743,0.07963446,0.00033771468,0.00009718288,0.00010698153,0.0011796493,0.00014691694,0.0066998815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985623,0.000029163644,0.0000069400917,0.000057074816,0.000025243677,0.000025295052],"domain_scores_gemma":[0.9997359,0.0001413836,0.0000258534,0.000022925975,0.000058205333,0.000015798247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039663832,0.000836105,0.0005566963,0.0005369088,0.0002646019,0.00047907067,0.0011928692,0.0007315135,0.002359233],"category_scores_gemma":[0.001276536,0.00027528647,0.00057991454,0.0006350545,0.0003507026,0.0011517439,0.00070443517,0.0013717734,0.00040373125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090033165,0.000069518916,0.00082597573,0.000048647686,0.000058175367,0.00007666424,0.0000409117,0.88612163,0.0027368201,0.0062790015,0.0031277994,0.10052479],"study_design_scores_gemma":[0.0000015730678,0.000005816786,0.000044288823,0.0000011564458,0.0000035084909,0.0000026116143,9.116894e-7,0.9982175,0.00015559127,0.0014423799,0.0001232909,0.0000013968781],"about_ca_topic_score_codex":0.024333868,"about_ca_topic_score_gemma":0.024859684,"teacher_disagreement_score":0.024333868,"about_ca_system_score_codex":0.0008628935,"about_ca_system_score_gemma":0.0007989583,"threshold_uncertainty_score":0.048384428},"labels":[],"label_agreement":null},{"id":"W4389867379","doi":"10.15485/2229439","title":"Improving the Estimation of the Atmospheric Water Vapor Pressure Using Interpretable Long Short-Term Memory Networks: Dataset, Python code, and trained models","year":2023,"lang":"en","type":"dataset","venue":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Python (programming language); Long short term memory; Computer science; Estimation; Term (time); Code (set theory); Artificial intelligence; Artificial neural network; Data mining; Programming language; Engineering; Recurrent neural network; Physics","score_opus":0.017036202308738615,"score_gpt":0.23139825104550335,"score_spread":0.21436204873676473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389867379","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20953274,0.0010911013,0.061242476,0.0019392048,0.0014755308,0.00090501463,0.6074206,0.10289021,0.013503114],"genre_scores_gemma":[0.118655816,0.00034153624,0.08291243,0.000653028,0.000111105735,0.0012682788,0.7866213,0.002934543,0.006502095],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995291,0.000072826304,0.000034379525,0.00016624812,0.00011605203,0.0000813333],"domain_scores_gemma":[0.99910116,0.00023865278,0.000045058954,0.00022367502,0.00033399358,0.000057502268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011709131,0.0025221596,0.0006056998,0.0011853803,0.00072348595,0.0010119278,0.002900077,0.0011036799,0.0076717967],"category_scores_gemma":[0.004598015,0.0005943629,0.0012408391,0.001572165,0.00055082317,0.0015954988,0.0013502243,0.0028529074,0.006555806],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005538371,0.0009051422,0.020553863,0.0010008186,0.00038204866,0.00044219545,0.0002190064,0.16965006,0.0073730247,0.002372591,0.65071565,0.14583178],"study_design_scores_gemma":[0.0005612778,0.00026781598,0.031897355,0.00029497404,0.00016864287,0.00020586772,0.00025646636,0.82253665,0.024434596,0.0076305284,0.11151654,0.00022934095],"about_ca_topic_score_codex":0.09070868,"about_ca_topic_score_gemma":0.11623388,"teacher_disagreement_score":0.09070868,"about_ca_system_score_codex":0.0016420966,"about_ca_system_score_gemma":0.001987622,"threshold_uncertainty_score":0.18036139},"labels":[],"label_agreement":null},{"id":"W4390125374","doi":"10.1007/s10040-023-02740-4","title":"Groundwater level monitoring using exploited domestic wells: outlier removal and imputation of missing values","year":2023,"lang":"en","type":"article","venue":"Hydrogeology Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Outlier; Imputation (statistics); Missing data; Hydrogeology; Groundwater; Interpolation (computer graphics); Kalman filter; Data mining; Computer science; Geology; Statistics; Mathematics; Artificial intelligence; Geotechnical engineering","score_opus":0.07544844101826664,"score_gpt":0.3085105044475969,"score_spread":0.23306206342933028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390125374","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64903927,0.00018469701,0.34457028,0.00024533502,0.000056576308,0.000058984424,0.0033130997,0.0010372214,0.0014944951],"genre_scores_gemma":[0.9281303,0.000050296097,0.06814089,0.000021848304,0.000016462784,0.000043141277,0.0029323997,0.000035555815,0.00062914897],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806756,0.0007070655,0.00027846225,0.00045050262,0.00028521693,0.00021131222],"domain_scores_gemma":[0.9926339,0.0017400733,0.0011005034,0.0030101344,0.0013991325,0.00011624868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037719144,0.00041221513,0.0009172278,0.0008875576,0.0004929916,0.0010422186,0.0014286885,0.0008095372,0.00090962864],"category_scores_gemma":[0.011003323,0.00033732195,0.0007951107,0.003297938,0.00036834937,0.0009676255,0.00068562204,0.00071768835,0.00028366098],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012262651,0.0006431861,0.47881603,0.00022481226,0.0008372057,0.00044473793,0.0006376266,0.18786909,0.010200805,0.005814269,0.0053536138,0.3079323],"study_design_scores_gemma":[0.00006762438,0.00022093202,0.10733906,0.000041035823,0.00020979696,0.00020468465,0.00036593794,0.8680213,0.01250561,0.007154427,0.0038089866,0.000060627928],"about_ca_topic_score_codex":0.007521782,"about_ca_topic_score_gemma":0.008791146,"teacher_disagreement_score":0.007521782,"about_ca_system_score_codex":0.00035420462,"about_ca_system_score_gemma":0.0011197878,"threshold_uncertainty_score":0.019948065},"labels":[],"label_agreement":null},{"id":"W4390298135","doi":"10.21203/rs.3.rs-3703387/v1","title":"A new data-driven model to predict monthly runoff at watershed scale: insights from deep learning method applied in data-driven model","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Hebei Province","keywords":"Surface runoff; Watershed; Hydrography; Hydrology (agriculture); Environmental science; Runoff curve number; Runoff model; Scale (ratio); Water year; SMA*; Water resources; Meteorology; Computer science; Geography; Cartography; Machine learning; Engineering; Ecology","score_opus":0.17933406734909585,"score_gpt":0.3903640026449373,"score_spread":0.21102993529584146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390298135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11628186,0.0005741191,0.87734914,0.0010692622,0.00016283563,0.000069692265,0.0004495279,0.0008424916,0.0032010206],"genre_scores_gemma":[0.92729753,0.00029958057,0.06833522,0.00019542438,0.00005817418,0.00012205659,0.00059198507,0.000046120087,0.003053978],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984086,0.00003256916,0.000014303295,0.00004949976,0.000037890073,0.000024862855],"domain_scores_gemma":[0.999718,0.0001096276,0.000025653437,0.000020458283,0.000103678074,0.000022583055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006266847,0.0005694531,0.00052075123,0.00047793362,0.00027519988,0.00074140483,0.0010335885,0.00086222484,0.00089394976],"category_scores_gemma":[0.0012713386,0.00033921818,0.0007243303,0.0005222689,0.00030877403,0.00090515794,0.0006333342,0.0011169895,0.00015600525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001923789,0.000038559,0.002229501,0.000023304483,0.000046932226,0.00003600475,0.000018877316,0.9689288,0.0011023686,0.0019874189,0.00059500034,0.024973888],"study_design_scores_gemma":[9.122671e-7,0.0000028699258,0.00008088223,7.833858e-7,0.0000017971736,0.0000016482735,7.6126366e-7,0.9994837,0.00008907428,0.00027152643,0.00006473979,0.0000012188893],"about_ca_topic_score_codex":0.017603243,"about_ca_topic_score_gemma":0.015241271,"teacher_disagreement_score":0.017603243,"about_ca_system_score_codex":0.00071513565,"about_ca_system_score_gemma":0.0010768464,"threshold_uncertainty_score":0.035001576},"labels":[],"label_agreement":null},{"id":"W4390392193","doi":"10.31223/x5nt2b","title":"A Systematic Review of Machine Learning Algorithms in Groundwater Level Simulations and Forecasting","year":2023,"lang":"en","type":"review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"West African Science Service Centre on Climate Change and Adapted Land Use; International Development Research Centre","keywords":"Machine learning; Artificial intelligence; Computer science; Context (archaeology); Artificial neural network; Groundwater; Water resources; Resource (disambiguation); Engineering; Geography","score_opus":0.16531699169233954,"score_gpt":0.33812641305877567,"score_spread":0.17280942136643612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390392193","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014170223,0.99677545,0.0018030782,0.00035218807,0.00017772133,0.000024008037,0.00010792912,0.000019681276,0.00059818494],"genre_scores_gemma":[0.0013805772,0.9956039,0.0023774314,0.00016499811,0.00013270583,0.000035140278,0.00013610677,0.000009384312,0.00015983354],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99815184,0.00061178056,0.0004819228,0.00019819422,0.00050403597,0.000052247182],"domain_scores_gemma":[0.98818165,0.009601141,0.00069921394,0.00021672188,0.001204351,0.00009679303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038815935,0.0013091611,0.002110986,0.004498051,0.0003553502,0.0014221694,0.0014799006,0.0013514496,0.0041163107],"category_scores_gemma":[0.014928975,0.0006590924,0.001971312,0.008574967,0.00051267067,0.0018752329,0.00074371387,0.0013580616,0.0012579532],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007501007,0.00006061585,0.00045129532,0.12553996,0.00068626227,0.000071749804,0.00009744061,0.0038424048,0.0003753875,0.0050869887,0.022287857,0.84142506],"study_design_scores_gemma":[0.000068955866,0.00031414602,0.0026891418,0.13140306,0.00284599,0.00045218715,0.0001550006,0.004383695,0.0009961443,0.009943751,0.84662825,0.00011961411],"about_ca_topic_score_codex":0.0048745917,"about_ca_topic_score_gemma":0.00712385,"teacher_disagreement_score":0.0048745917,"about_ca_system_score_codex":0.00091167464,"about_ca_system_score_gemma":0.004863098,"threshold_uncertainty_score":0.020528018},"labels":[],"label_agreement":null},{"id":"W4390572757","doi":"10.5194/hess-2023-237-ac1","title":"Reply on RC1","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Streamflow; Routing (electronic design automation); Structural basin; Drainage basin; Feature (linguistics); Computer science; Adaptive routing; Flow routing; Hydrology (agriculture); Artificial intelligence; Environmental science; Climatology; Geology; Geography; Cartography; Geomorphology","score_opus":0.04657684144921223,"score_gpt":0.30578056109909907,"score_spread":0.25920371964988687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390572757","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023614803,0.0017556857,0.00033551862,0.8071035,0.16144855,0.00011360185,0.00092683494,0.00051767466,0.027562529],"genre_scores_gemma":[0.0029184432,0.0011353266,0.00025493192,0.8483809,0.054053865,0.00020951536,0.00037790823,0.0002848916,0.09238412],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99715745,0.0005668634,0.0003168935,0.00054588617,0.0009375313,0.00047537786],"domain_scores_gemma":[0.9925493,0.0026411067,0.00033657462,0.0004945491,0.002916406,0.0010619959],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002789608,0.0009937959,0.0012000924,0.0012348514,0.0033141437,0.0044441284,0.0033653858,0.026108226,0.16404599],"category_scores_gemma":[0.034325305,0.00059161166,0.0015692405,0.0009318512,0.0020713718,0.0039846064,0.0028538813,0.023107287,0.11527333],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010726934,0.000002839507,0.00003369859,0.000014777273,0.0000019278168,0.00006156393,0.000011326368,0.000004217487,0.000017386046,0.0003241947,0.9973363,0.0021810837],"study_design_scores_gemma":[0.0000136316185,0.000008762709,0.00017481884,0.000068947644,0.0000042918386,0.00010690517,0.00008023293,0.00003385907,0.00009206096,0.0006754821,0.99872845,0.000012596021],"about_ca_topic_score_codex":0.006673358,"about_ca_topic_score_gemma":0.0072168224,"teacher_disagreement_score":0.835954,"about_ca_system_score_codex":0.0037583192,"about_ca_system_score_gemma":0.003531259,"threshold_uncertainty_score":0.54878855},"labels":[],"label_agreement":null},{"id":"W4390646422","doi":"10.37934/arfmts.111.1.96108","title":"Mathematical Modeling of Groundwater Surface Water Interaction Represented using Boussinesq Equation – A Bibliometric Study","year":2023,"lang":"en","type":"article","venue":"Journal of Advanced Research in Fluid Mechanics and Thermal Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Ministry of Science and Technology of the People's Republic of China; Japan Society for the Promotion of Science; Ministry of Education of the People's Republic of China; Natural Sciences and Engineering Research Council of Canada; European Commission; Office of Naval Research; National Natural Science Foundation of China; National Science Foundation; Government of Canada; U.S. Department of Defense","keywords":"Groundwater; Resource (disambiguation); Natural resource; Natural (archaeology); Agriculture; Water resources; Hydrology (agriculture); Computer science; Geography; Engineering; Geotechnical engineering; Political science; Ecology","score_opus":0.24907590735537297,"score_gpt":0.419885811422653,"score_spread":0.17080990406728006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390646422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37360197,0.01493244,0.5068878,0.0070943055,0.00033333982,0.00046192828,0.0038744342,0.00063322275,0.092180446],"genre_scores_gemma":[0.94838256,0.008803598,0.031607922,0.00014995338,0.00016641994,0.0003670883,0.0013627479,0.000073256866,0.009086464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9989104,0.00038159918,0.00009782471,0.00013587548,0.0003617525,0.00011243684],"domain_scores_gemma":[0.99733186,0.0018344367,0.00031035446,0.00006228168,0.00041841748,0.00004279778],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0018682816,0.00056480634,0.00088508904,0.007112251,0.0006853457,0.0023642653,0.0011150653,0.0011244027,0.0039646854],"category_scores_gemma":[0.0074285627,0.00024827247,0.0012943508,0.0085223,0.0005771778,0.0020086085,0.0008593336,0.00046191065,0.0007162825],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006816855,0.00015532551,0.03657247,0.0014931919,0.00023351172,0.00082595454,0.0010622035,0.7110949,0.0019237142,0.12626497,0.010826105,0.1094795],"study_design_scores_gemma":[0.000005260365,0.000030086854,0.0056440625,0.000102335456,0.000043849945,0.00015576609,0.00023414254,0.96402997,0.00037514343,0.022268672,0.0070816237,0.000029125576],"about_ca_topic_score_codex":0.014739793,"about_ca_topic_score_gemma":0.0050015557,"teacher_disagreement_score":0.99288774,"about_ca_system_score_codex":0.001987098,"about_ca_system_score_gemma":0.0011123657,"threshold_uncertainty_score":0.029307961},"labels":[],"label_agreement":null},{"id":"W4390672688","doi":"10.31223/x53x3s","title":"A Review of Geological and Climatic Variables in Groundwater Availability Prediction in Africa: Machine Learning Approaches","year":2024,"lang":"en","type":"review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"West African Science Service Centre on Climate Change and Adapted Land Use; International Development Research Centre","keywords":"Machine learning; Groundwater; Agriculture; Decision tree; Artificial intelligence; Computer science; Population; Water supply; Resource (disambiguation); Scarcity; Water resources; Climate change; Geography; Engineering; Geology; Environmental engineering; Ecology","score_opus":0.12211785250784568,"score_gpt":0.283959564417849,"score_spread":0.1618417119100033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390672688","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014843476,0.9984218,0.0003776067,0.00029985787,0.00012863697,0.000006413362,0.00003759771,0.0000069524963,0.0005727338],"genre_scores_gemma":[0.00092369993,0.9982685,0.00044938573,0.00009316986,0.00010474659,0.0000063678417,0.000032946373,0.0000014736545,0.000119726974],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995883,0.00010177481,0.00009216975,0.00007670366,0.0001192896,0.000021812188],"domain_scores_gemma":[0.99663585,0.0025578775,0.00028265393,0.000045512745,0.00041535182,0.00006282873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014788109,0.0010919544,0.0015757761,0.004389516,0.00030672402,0.0012452287,0.0011063305,0.0011418251,0.0027891754],"category_scores_gemma":[0.0035731818,0.0004718162,0.0011808077,0.0071458127,0.00041769407,0.0017942282,0.0005435668,0.0012346044,0.001002991],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047299327,0.00007024209,0.0006994052,0.05946193,0.00031516032,0.00012379567,0.00010748622,0.001982079,0.000607041,0.004210044,0.017068371,0.91530704],"study_design_scores_gemma":[0.0000204096,0.00022000387,0.004197008,0.046769008,0.0011486149,0.0007439605,0.00022077859,0.0015023034,0.0008133835,0.0053280005,0.9389546,0.00008195542],"about_ca_topic_score_codex":0.0034704218,"about_ca_topic_score_gemma":0.004850655,"teacher_disagreement_score":0.004389516,"about_ca_system_score_codex":0.00078630744,"about_ca_system_score_gemma":0.0022418918,"threshold_uncertainty_score":0.00933069},"labels":[],"label_agreement":null},{"id":"W4390911415","doi":"10.1007/s00477-023-02574-2","title":"Correction to: Multilayer perceptron-based predictive model using wavelet transform for the reconstruction of missing rainfall data","year":2024,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computational intelligence; Missing data; Computer science; Wavelet transform; Multilayer perceptron; Pattern recognition (psychology); Wavelet; Artificial intelligence; Business intelligence; Data mining; Artificial neural network; Machine learning","score_opus":0.08525669706561556,"score_gpt":0.3822466554068866,"score_spread":0.29698995834127107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390911415","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00731918,0.0026086576,0.19913584,0.032075547,0.72021174,0.00024577347,0.015348368,0.01807277,0.0049821893],"genre_scores_gemma":[0.3452997,0.0050302623,0.2839376,0.017650079,0.06269388,0.00096289086,0.032760687,0.01998495,0.23167998],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948742,0.0007841105,0.00095531263,0.0011464955,0.0017291022,0.00051089353],"domain_scores_gemma":[0.968036,0.0064723184,0.0019012663,0.006501578,0.015771857,0.0013168858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048119305,0.0030547464,0.0031947466,0.003809507,0.002239671,0.003616728,0.0054455805,0.006417698,0.2069666],"category_scores_gemma":[0.074548535,0.0016892031,0.002116092,0.006188422,0.0012748028,0.00424232,0.0040920633,0.0073220925,0.06446139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005609202,0.0000710584,0.0012814412,0.0007387929,0.00019736393,0.000976699,0.00016644804,0.0065657077,0.0024369126,0.008937096,0.9115349,0.06653248],"study_design_scores_gemma":[0.00049946265,0.00019910268,0.00755567,0.000671002,0.000248515,0.00320599,0.00041978105,0.20438713,0.018136077,0.04074944,0.7234125,0.00051531655],"about_ca_topic_score_codex":0.009618923,"about_ca_topic_score_gemma":0.010651947,"teacher_disagreement_score":0.2069666,"about_ca_system_score_codex":0.0025267955,"about_ca_system_score_gemma":0.0046878587,"threshold_uncertainty_score":0.6923722},"labels":[],"label_agreement":null},{"id":"W4391127583","doi":"10.61091/jcmcc117-20","title":"Research on the Application Effect of Metalearning Method Based on Prototype Network in Corrective Measures for Member State Audit","year":2023,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Audit; Computer science; Generalization; Artificial intelligence; Machine learning; Accounting; Mathematics","score_opus":0.047152702311887,"score_gpt":0.3517737079399025,"score_spread":0.3046210056280155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391127583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32569224,0.0025505233,0.66073704,0.0013029281,0.00025502627,0.0004682959,0.00033390542,0.0016674243,0.006992563],"genre_scores_gemma":[0.91866624,0.00056947704,0.07917252,0.00011303277,0.000049997525,0.00012261474,0.00020931596,0.000046393776,0.0010503819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957969,0.0020577274,0.000266982,0.00093269005,0.000695522,0.00025015805],"domain_scores_gemma":[0.98474586,0.010231771,0.0013724611,0.0011729378,0.0021464983,0.00033049117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069638747,0.00132065,0.0011131439,0.0029995448,0.0007584026,0.0020617524,0.002233765,0.0013742868,0.0015612273],"category_scores_gemma":[0.027819384,0.00043504874,0.0009259815,0.0018403752,0.0007949235,0.0046880012,0.0011777388,0.0015226578,0.00029333285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005069382,0.0005961093,0.050354872,0.0005538439,0.00043323456,0.00018230804,0.00078026485,0.3837133,0.0033476162,0.007926259,0.0029523794,0.5486529],"study_design_scores_gemma":[0.00001932521,0.00026616434,0.0052758856,0.000073976335,0.000107476764,0.000088250956,0.000305398,0.98494464,0.002757189,0.0049102195,0.0012161131,0.000035280405],"about_ca_topic_score_codex":0.008549462,"about_ca_topic_score_gemma":0.007949624,"teacher_disagreement_score":0.008549462,"about_ca_system_score_codex":0.0016647871,"about_ca_system_score_gemma":0.001660627,"threshold_uncertainty_score":0.036828935},"labels":[],"label_agreement":null},{"id":"W4391454103","doi":"10.1007/978-3-031-49088-0_1","title":"Introduction","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Computer science","score_opus":0.014621894570678322,"score_gpt":0.207732634576425,"score_spread":0.19311074000574666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391454103","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023506653,0.0019251418,0.008017864,0.0013119663,0.002443874,0.00009702415,0.0013856745,0.0008514358,0.983732],"genre_scores_gemma":[0.00074988045,0.0011341694,0.0020815427,0.00047057625,0.00032864144,0.000040763778,0.00092974294,0.00023789902,0.9940269],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996044,0.000032765587,0.000013291968,0.00008247297,0.00023133538,0.000035720997],"domain_scores_gemma":[0.9995204,0.000077979435,0.00001492055,0.00007244082,0.0002493976,0.00006493899],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00043920294,0.0008841425,0.0005203382,0.001662655,0.0010337442,0.0032328286,0.0012762418,0.0013323005,0.5096216],"category_scores_gemma":[0.001631597,0.0003786406,0.00050939387,0.0016500643,0.0004480913,0.002837002,0.0016523697,0.0016852202,0.41517407],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001437612,0.000034731318,0.00007578447,0.00013039078,0.0000022768677,0.00004478022,0.00009088579,0.0003176997,0.0005034108,0.033623714,0.7416433,0.2235187],"study_design_scores_gemma":[0.0000010408359,0.0000036230028,0.000054209715,0.0000444256,8.0578195e-7,0.000032868098,0.000021845692,0.00007333812,0.00009847738,0.0045021824,0.99516475,0.0000023495627],"about_ca_topic_score_codex":0.0033934808,"about_ca_topic_score_gemma":0.0067679747,"teacher_disagreement_score":0.49037838,"about_ca_system_score_codex":0.0011866213,"about_ca_system_score_gemma":0.0012453223,"threshold_uncertainty_score":0.6994653},"labels":[],"label_agreement":null},{"id":"W4391661497","doi":"10.1109/jstars.2024.3364020","title":"Fuzzy Similarity Analysis of Effective Training Samples to Improve Machine Learning Estimations of Water Quality Parameters Using Sentinel-2 Remote Sensing Data","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; University of Waterloo","funders":"","keywords":"Computer science; Mean absolute percentage error; Support vector machine; Mean squared error; Water quality; Artificial intelligence; Regression; Similarity (geometry); Data mining; Machine learning; Remote sensing; Statistics; Artificial neural network; Mathematics","score_opus":0.09748984460820852,"score_gpt":0.3131189630593307,"score_spread":0.21562911845112215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391661497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29129547,0.0002612266,0.7065706,0.00011086757,0.00004728712,0.000056173056,0.00008285135,0.00052896095,0.0010465455],"genre_scores_gemma":[0.84991163,0.000100564,0.14917615,0.000051916893,0.000035535395,0.000047972717,0.00019676035,0.000028295022,0.0004511223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923277,0.00018175393,0.000064389846,0.0001522538,0.00031880866,0.00005006377],"domain_scores_gemma":[0.9984118,0.00069756055,0.00019563056,0.00011571266,0.0005458266,0.00003338588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016259761,0.0004650838,0.0006049241,0.0013095664,0.00031549737,0.0005119187,0.00063296885,0.00052474765,0.00044200587],"category_scores_gemma":[0.0051481295,0.00021248481,0.000717285,0.0007707194,0.0002809236,0.0009864931,0.00051188644,0.00044306132,0.00015185874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047065064,0.0003351225,0.015512714,0.00016409653,0.00016210543,0.00017344466,0.00026315506,0.36128956,0.048558623,0.002531208,0.001191716,0.5693476],"study_design_scores_gemma":[0.000006696446,0.00003842482,0.0020927405,0.0000033271372,0.000014304593,0.000018206058,0.0000200782,0.9910512,0.0060563483,0.00046510602,0.00022558465,0.0000080247455],"about_ca_topic_score_codex":0.0037989914,"about_ca_topic_score_gemma":0.0029717968,"teacher_disagreement_score":0.0037989914,"about_ca_system_score_codex":0.000369897,"about_ca_system_score_gemma":0.0005019282,"threshold_uncertainty_score":0.008599043},"labels":[],"label_agreement":null},{"id":"W4391867658","doi":"10.1016/j.jenvman.2024.120324","title":"Tackling data challenges in forecasting effluent characteristics of wastewater treatment plants","year":2024,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Effluent; Missing data; Sewage treatment; Wastewater; Computer science; Environmental science; Engineering; Environmental engineering; Machine learning","score_opus":0.07833034344813825,"score_gpt":0.2599497111288624,"score_spread":0.18161936768072415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391867658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62064207,0.0023845711,0.35539964,0.009205285,0.00068052404,0.000118684016,0.0055336263,0.00099712,0.005038494],"genre_scores_gemma":[0.9488698,0.00042553095,0.047791563,0.00018902442,0.00015938202,0.000038054837,0.0019101124,0.00004649947,0.00056999],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990088,0.0003900984,0.00013336225,0.00019006802,0.00020097425,0.00007665343],"domain_scores_gemma":[0.98423785,0.012663662,0.0008783708,0.0007739436,0.001236977,0.00020925005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036614237,0.0005349419,0.00078646967,0.0013362456,0.0005036687,0.0019767738,0.00089762075,0.0013118602,0.0005694417],"category_scores_gemma":[0.02249465,0.0004478705,0.00040544407,0.0020391527,0.00041208218,0.0033190553,0.0007520689,0.00184249,0.0001903017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021665389,0.00022781373,0.05008654,0.00026251923,0.00015072366,0.00026311024,0.00016611176,0.7936931,0.0025706373,0.0043390743,0.0057124128,0.1423113],"study_design_scores_gemma":[0.0000058798687,0.000017093837,0.002176334,0.0000102826125,0.000009805059,0.000019764968,0.00010885017,0.99221486,0.0006569287,0.003987899,0.000785492,0.0000069237926],"about_ca_topic_score_codex":0.017663218,"about_ca_topic_score_gemma":0.014598826,"teacher_disagreement_score":0.017663218,"about_ca_system_score_codex":0.00056886073,"about_ca_system_score_gemma":0.0010752344,"threshold_uncertainty_score":0.035120785},"labels":[],"label_agreement":null},{"id":"W4392023204","doi":"10.1139/er-2023-0098","title":"Responses of multimetric indices to disturbance are affected by index construction features","year":2024,"lang":"en","type":"article","venue":"Environmental Reviews","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Disturbance (geology); Index (typography); Environmental science; Geography; Ecology; Computer science; Biology","score_opus":0.011982996959876287,"score_gpt":0.25464656643912237,"score_spread":0.24266356947924608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392023204","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.255184,0.6990493,0.020749489,0.0045302925,0.0010464863,0.0007580126,0.011927907,0.00021002228,0.006544508],"genre_scores_gemma":[0.90910447,0.070176415,0.012766864,0.00155662,0.0006628385,0.0008603345,0.0041161426,0.00014448758,0.0006118806],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95651054,0.018993223,0.012798127,0.005547707,0.0054367944,0.00071350933],"domain_scores_gemma":[0.7104532,0.24228552,0.02996597,0.009716096,0.006723844,0.00085542066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04209386,0.0012685015,0.002855938,0.009131866,0.00038509266,0.0034497592,0.001578362,0.0011863874,0.0019587202],"category_scores_gemma":[0.1572161,0.0006421179,0.009559368,0.013398452,0.0017252176,0.002518114,0.0016342704,0.0012121178,0.00028311278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021441786,0.0000929973,0.5339847,0.11723802,0.18668364,0.0005383242,0.0019021333,0.0025331695,0.0024223882,0.0014507616,0.0039629424,0.1470468],"study_design_scores_gemma":[0.00035878096,0.0006544193,0.77774835,0.022581201,0.15295158,0.0013773944,0.00202427,0.0022358298,0.0029199596,0.0079926625,0.028953595,0.0002019096],"about_ca_topic_score_codex":0.0023410653,"about_ca_topic_score_gemma":0.0039485283,"teacher_disagreement_score":0.04209386,"about_ca_system_score_codex":0.00080548966,"about_ca_system_score_gemma":0.0011340269,"threshold_uncertainty_score":0.22261626},"labels":[],"label_agreement":null},{"id":"W4392151222","doi":"10.1016/j.jenvman.2024.120394","title":"Predicting and analyzing the algal population dynamics of a grass-type lake with explainable machine learning","year":2024,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Saint Mary's University","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Algal bloom; Water quality; Eutrophication; Environmental science; Generalization; Computer science; Machine learning; Ecology; Mathematics; Biology; Phytoplankton","score_opus":0.005304934060739995,"score_gpt":0.19545715821843854,"score_spread":0.19015222415769853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392151222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99339974,0.00001575639,0.0062265806,0.00007838661,0.000003403482,0.0000036080646,0.00004300778,0.00002661071,0.00020291342],"genre_scores_gemma":[0.9982565,0.0000069260673,0.0015792954,0.000003830428,0.0000022612287,0.000002438486,0.000044457836,0.0000015472166,0.00010269127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99995685,0.000008869366,0.0000026208997,0.000012611057,0.000006987786,0.000012039157],"domain_scores_gemma":[0.9996941,0.00017696447,0.000040395138,0.000016340142,0.000043650656,0.000028647884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026000143,0.00022437528,0.0001759649,0.000279113,0.00030440892,0.00027256412,0.00035157765,0.00037419173,0.00037396437],"category_scores_gemma":[0.001026191,0.00016643807,0.00028187063,0.00027310828,0.00023972984,0.00043544333,0.00021962207,0.00033095,0.000036687125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064925385,0.00007377553,0.054597985,0.0000125376855,0.000045833403,0.00007847488,0.0000553119,0.9308218,0.003275402,0.0005605324,0.00020027878,0.0102130575],"study_design_scores_gemma":[0.0000017381435,0.0000051082925,0.0038991224,2.269349e-7,0.0000022268198,0.0000020138605,0.0000058110436,0.9958112,0.00011346648,0.0001464676,0.000011203547,0.0000014559315],"about_ca_topic_score_codex":0.037160415,"about_ca_topic_score_gemma":0.04021687,"teacher_disagreement_score":0.037160415,"about_ca_system_score_codex":0.0007113883,"about_ca_system_score_gemma":0.00063940865,"threshold_uncertainty_score":0.07388824},"labels":[],"label_agreement":null},{"id":"W4392239955","doi":"10.3390/w16050707","title":"Dissolved Oxygen Forecasting for Lake Erie’s Central Basin Using Hybrid Long Short-Term Memory and Gated Recurrent Unit Networks","year":2024,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakes Environmental (Canada); University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Environmental science; Water quality; Surface runoff; Freshwater ecosystem; Pollution; Stormwater; Hydrology (agriculture); Drainage basin; Ecosystem; Ecology; Cartography; Geography; Engineering","score_opus":0.04635528877780506,"score_gpt":0.25898843386281967,"score_spread":0.2126331450850146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392239955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95817965,0.00064823497,0.03652841,0.00043353662,0.00007369485,0.000021122973,0.00084706466,0.0007524298,0.0025159356],"genre_scores_gemma":[0.99502474,0.00010136418,0.0036300481,0.000034674613,0.000011269789,0.0000126794,0.0005155642,0.0000097095335,0.0006598514],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999176,0.000006990898,0.000006647265,0.000033832013,0.000015450401,0.000019426609],"domain_scores_gemma":[0.9998839,0.000027346823,0.000021976786,0.000005724186,0.000050248258,0.000010847503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018962771,0.000672192,0.00040657932,0.00039320806,0.0002456991,0.0004243111,0.0005815221,0.0005252896,0.0004884236],"category_scores_gemma":[0.00045318788,0.00024690732,0.0005266261,0.0004910935,0.000145127,0.00049859245,0.00047731647,0.00040198083,0.00008912885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016855448,0.0001320559,0.035561524,0.000093669965,0.00016548077,0.00028695472,0.00009427974,0.8984406,0.009350146,0.0004204449,0.0020722386,0.05321396],"study_design_scores_gemma":[0.0000032934163,0.000006180771,0.0017158848,0.0000017233383,0.00000802768,0.0000029051355,0.000008271267,0.997684,0.00042368413,0.00006605465,0.0000763981,0.0000035382027],"about_ca_topic_score_codex":0.07621927,"about_ca_topic_score_gemma":0.085960366,"teacher_disagreement_score":0.92378074,"about_ca_system_score_codex":0.00075381715,"about_ca_system_score_gemma":0.0007501978,"threshold_uncertainty_score":0.15155125},"labels":[],"label_agreement":null},{"id":"W4392273918","doi":"","title":"Statistical contributions to hydrometeorological forecasting from ensemble methods","year":2017,"lang":"fr","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hydrometeorology; Computer science; Statistics; Meteorology; Geography; Mathematics; Precipitation","score_opus":0.08975355993030498,"score_gpt":0.3850740644005028,"score_spread":0.2953205044701978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392273918","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05089256,0.00324177,0.93998337,0.0011365779,0.00040394816,0.00002934012,0.00025055607,0.0006005637,0.0034612482],"genre_scores_gemma":[0.7446003,0.005082906,0.24270244,0.0003845734,0.0015324813,0.00010295257,0.00080075127,0.0003181707,0.0044753174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989525,0.00039972118,0.000071081166,0.00014952337,0.00036167324,0.00006550315],"domain_scores_gemma":[0.99291986,0.005085436,0.0002935769,0.0005252825,0.0010365566,0.00013940083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036762515,0.0009341171,0.00085267145,0.0013487578,0.00045813643,0.0016474214,0.00069620047,0.00068765355,0.001152963],"category_scores_gemma":[0.01374391,0.0004392572,0.0008250787,0.0013816034,0.00043175125,0.0015907465,0.0011644735,0.0014280056,0.0003249277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000111676745,0.000040914358,0.00815055,0.00010102807,0.00024502512,0.00007261804,0.00012855888,0.7554065,0.002502142,0.013630376,0.0017742488,0.21783634],"study_design_scores_gemma":[0.0000033552978,0.0000141656565,0.0009699839,0.000014627984,0.000020646892,0.000013575796,0.000007898449,0.9921669,0.00050874974,0.0051346417,0.0011361771,0.000009354208],"about_ca_topic_score_codex":0.009388133,"about_ca_topic_score_gemma":0.010053749,"teacher_disagreement_score":0.009388133,"about_ca_system_score_codex":0.00058556505,"about_ca_system_score_gemma":0.0010344977,"threshold_uncertainty_score":0.019442081},"labels":[],"label_agreement":null},{"id":"W4392577972","doi":"10.5194/egusphere-egu24-11277","title":"Accurate monthly forecasting of Rainfall pattern in Atlantic climates: an Empirical Fourier Decomposition-based Deep ensemble learning paradigm","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Climatology; Ensemble learning; Decomposition; Econometrics; Ensemble forecasting; Environmental science; Computer science; Artificial intelligence; Meteorology; Geography; Geology; Mathematics; Ecology","score_opus":0.04929531911331204,"score_gpt":0.3176215995205704,"score_spread":0.26832628040725837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392577972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18600939,0.00040817665,0.8106582,0.00028130796,0.000040256517,0.000018855186,0.00010655065,0.00031435804,0.0021627995],"genre_scores_gemma":[0.9374927,0.00026472524,0.060862027,0.000042463456,0.000026464282,0.000020252608,0.00018782538,0.000016297021,0.0010871309],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999285,0.000015399273,0.000005634483,0.000016059063,0.000019545174,0.00001491722],"domain_scores_gemma":[0.9998598,0.00005406321,0.000018654511,0.000013991212,0.000045993693,0.000007413207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004508054,0.00032278497,0.0002763383,0.00028770973,0.00012922159,0.00032144206,0.0004689819,0.00033697786,0.00039359808],"category_scores_gemma":[0.0007517826,0.00013413104,0.00035526993,0.00028779177,0.00013701034,0.0005115921,0.00032932186,0.0005600058,0.000085087275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042608008,0.0000487497,0.0037815587,0.000019267894,0.00005151598,0.00005833207,0.000039565744,0.87185514,0.004361373,0.002968982,0.00054504425,0.11622784],"study_design_scores_gemma":[4.81229e-7,0.0000028984098,0.00018746176,7.411409e-7,0.0000020578025,0.0000021324138,0.0000016080821,0.9993767,0.00016616714,0.0002173852,0.000041434996,9.567734e-7],"about_ca_topic_score_codex":0.0104576815,"about_ca_topic_score_gemma":0.011150379,"teacher_disagreement_score":0.0104576815,"about_ca_system_score_codex":0.00028604898,"about_ca_system_score_gemma":0.00042753038,"threshold_uncertainty_score":0.020793676},"labels":[],"label_agreement":null},{"id":"W4392586168","doi":"10.5194/egusphere-egu24-4000","title":"The impact of our warming climate on global groundwater temperatures","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Global warming; Environmental science; Groundwater; Climate change; Climatology; Water resource management; Natural resource economics; Geology; Economics; Oceanography","score_opus":0.02144387113600832,"score_gpt":0.3148584526405005,"score_spread":0.2934145815044922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392586168","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9467321,0.002087592,0.01958856,0.0036517177,0.00017596663,0.000019033016,0.005131792,0.00036268256,0.022250548],"genre_scores_gemma":[0.99447733,0.0010810952,0.0026326217,0.00021409044,0.000030370737,0.0000116916,0.00072056067,0.000070017064,0.0007622438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99990153,0.000029194043,0.0000046732657,0.000025513547,0.000018497372,0.000020626161],"domain_scores_gemma":[0.99989414,0.00003057891,0.00002526978,0.000015039136,0.000020964473,0.000013991264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020672461,0.00036168122,0.00018362273,0.00024267183,0.00027780732,0.0009696032,0.00024134829,0.0006093987,0.0018749848],"category_scores_gemma":[0.00072575617,0.00014845846,0.00052465213,0.00060261856,0.00033167555,0.0010588287,0.00059437036,0.0004190103,0.00024303093],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021348204,0.0000730988,0.25029692,0.00036417608,0.00036458333,0.0006423246,0.0006651163,0.61543995,0.022130556,0.02739398,0.008005199,0.07441055],"study_design_scores_gemma":[0.000044628883,0.00027346486,0.42148334,0.00021889586,0.0003751739,0.00061946746,0.0014467726,0.45656273,0.01203847,0.037244532,0.0695128,0.00017963552],"about_ca_topic_score_codex":0.015396561,"about_ca_topic_score_gemma":0.013330974,"teacher_disagreement_score":0.015396561,"about_ca_system_score_codex":0.0008440543,"about_ca_system_score_gemma":0.00047806415,"threshold_uncertainty_score":0.0306139},"labels":[],"label_agreement":null},{"id":"W4392587707","doi":"10.5194/egusphere-egu24-2896","title":"Seasonal Precipitation Forecast Using an Ensemble of Artificial Neural Networks and Climate Oscillation Indices. A Case Study of Cear&amp;#225;, northeastern Brazil.","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Precipitation; Climatology; Environmental science; Artificial neural network; Meteorology; Oscillation (cell signaling); El Niño Southern Oscillation; Geography; Computer science; Artificial intelligence; Geology; Biology","score_opus":0.06575865200371933,"score_gpt":0.3162712856760991,"score_spread":0.25051263367237975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392587707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627704,0.0006428144,0.029582635,0.0005901115,0.00005198235,0.00003436266,0.001025749,0.00024362766,0.005058193],"genre_scores_gemma":[0.9939704,0.00015628236,0.0050256415,0.000009472611,0.000007407648,0.0000075486882,0.00037221384,0.000009777667,0.00044126264],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998621,0.000043600532,0.000010991387,0.00003319716,0.000036760208,0.000013380414],"domain_scores_gemma":[0.9997397,0.000101921265,0.000039316714,0.000023889905,0.000080189195,0.000014897772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005375927,0.00036770542,0.00024657045,0.0004460538,0.0002077224,0.00036188713,0.00032587143,0.00027264206,0.00026505283],"category_scores_gemma":[0.0015664846,0.00015091224,0.00033080237,0.00059601513,0.00010434906,0.0004556906,0.00023704398,0.0002138429,0.00008153363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010001869,0.00012623404,0.15838556,0.000106485095,0.00025274788,0.00076300686,0.00020742152,0.7354928,0.0042364136,0.001517767,0.0020035587,0.096808],"study_design_scores_gemma":[0.0000053586164,0.000019237788,0.023750855,0.00000899592,0.000035435372,0.00003446628,0.000069259506,0.9743294,0.0006452249,0.00043182832,0.0006636407,0.000006368098],"about_ca_topic_score_codex":0.09652956,"about_ca_topic_score_gemma":0.123644546,"teacher_disagreement_score":0.09652956,"about_ca_system_score_codex":0.00082890724,"about_ca_system_score_gemma":0.00045287822,"threshold_uncertainty_score":0.19193536},"labels":[],"label_agreement":null},{"id":"W4392631055","doi":"10.5194/egusphere-egu24-16210","title":"rechaRge &amp;#8211; a package for integrated groundwater recharge modelling in R","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Groundwater recharge; Depression-focused recharge; Groundwater; Hydrology (agriculture); Environmental science; Water resource management; Geology; Aquifer; Geotechnical engineering","score_opus":0.08232699984979554,"score_gpt":0.2923725166310966,"score_spread":0.21004551678130107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392631055","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011140191,0.0011164838,0.4952299,0.0016798886,0.0008310605,0.00027709745,0.12531242,0.35611752,0.01832158],"genre_scores_gemma":[0.028975073,0.0017919651,0.44501364,0.0022634564,0.00044621815,0.003319725,0.12489109,0.36194122,0.031357594],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979983,0.00073687313,0.00016753217,0.00048033666,0.00049566175,0.00012138832],"domain_scores_gemma":[0.9948885,0.0030661395,0.00039267773,0.00075062667,0.0007322702,0.00016986276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003190068,0.0024741536,0.0019475057,0.001646378,0.00058861525,0.0026628876,0.0034909258,0.0011905268,0.19652927],"category_scores_gemma":[0.019595196,0.0019389829,0.0025149956,0.0016188502,0.00075993885,0.002083185,0.0027782077,0.003246235,0.15679839],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007657623,0.000015259873,0.0007150638,0.0010099598,0.00025590393,0.00015647792,0.00011856887,0.005962046,0.0015250432,0.011995464,0.93460697,0.043562774],"study_design_scores_gemma":[0.00026645281,0.000048751113,0.0015567578,0.0003314385,0.00017214402,0.00032567047,0.00003416918,0.024184322,0.004208946,0.04078377,0.9279419,0.00014566266],"about_ca_topic_score_codex":0.0037363307,"about_ca_topic_score_gemma":0.0043883095,"teacher_disagreement_score":0.19652927,"about_ca_system_score_codex":0.0006765308,"about_ca_system_score_gemma":0.0019292324,"threshold_uncertainty_score":0.6574559},"labels":[],"label_agreement":null},{"id":"W4392642783","doi":"10.5194/egusphere-egu24-22255","title":"Enhancing Runoff Generation Mechanisms for Flood Simulation through Integrating Machine Learning and Process-Based Modeling","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Global Institute for Water Security; University of Saskatchewan","funders":"","keywords":"Process (computing); Flood myth; Computer science; Surface runoff; Artificial intelligence; Machine learning; Environmental science; Geography; Programming language; Archaeology; Ecology","score_opus":0.0436595003195642,"score_gpt":0.3136736349709162,"score_spread":0.27001413465135204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392642783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095897265,0.00022720093,0.8874582,0.0012307847,0.00012201035,0.00013503693,0.00019466283,0.0022262987,0.012508584],"genre_scores_gemma":[0.909624,0.0001851353,0.0873313,0.00017612576,0.00005731982,0.0001129722,0.00014786098,0.00018115666,0.00218413],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977916,0.00007775527,0.000015314248,0.00004603707,0.000056774235,0.00002504489],"domain_scores_gemma":[0.99896264,0.0006475706,0.00010295216,0.00009227305,0.00013359159,0.00006085008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091382576,0.0005173482,0.0006373826,0.00063717726,0.0006117116,0.0015736267,0.0015075591,0.0012487349,0.0032602823],"category_scores_gemma":[0.003410099,0.00037391324,0.0008162265,0.00046679509,0.0007926796,0.0017795567,0.0013020817,0.0011362041,0.00044118354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017230479,0.000037988902,0.00076286483,0.000021520833,0.000012924381,0.00003040686,0.000042648735,0.98476356,0.0011656842,0.0060240626,0.000209902,0.006911214],"study_design_scores_gemma":[0.0000028071756,0.0000040491577,0.000032191256,0.0000017185796,0.0000015898628,0.0000025550655,0.0000032955923,0.99810517,0.00019822994,0.0014259611,0.00022024194,0.0000022145973],"about_ca_topic_score_codex":0.007670552,"about_ca_topic_score_gemma":0.006263233,"teacher_disagreement_score":0.007670552,"about_ca_system_score_codex":0.0013806426,"about_ca_system_score_gemma":0.0012790492,"threshold_uncertainty_score":0.015251815},"labels":[],"label_agreement":null},{"id":"W4392643135","doi":"10.5194/egusphere-egu24-21666","title":"Simulating Nature&amp;#8217;s randomness with CoSMoS - A Versatile Stochastic Modeling Framework for Hydrometeorological Phenomena","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hydrometeorology; Randomness; Computer science; Cosmos (plant); Physics; Meteorology; Mathematics; Statistics; Biology","score_opus":0.04022419129582331,"score_gpt":0.2990660244724311,"score_spread":0.25884183317660775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392643135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022600139,0.0008266268,0.9465993,0.0022130606,0.00031110572,0.00008588999,0.002154358,0.0020768496,0.023132632],"genre_scores_gemma":[0.4667701,0.0024891282,0.51064396,0.0006670225,0.0003783193,0.000520336,0.002521257,0.0014020815,0.014607778],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999686,0.00014087305,0.000016102444,0.00004044307,0.000091520225,0.000025039715],"domain_scores_gemma":[0.99936146,0.00030013866,0.00005837723,0.00012704199,0.000085194886,0.00006777524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011593142,0.00041504783,0.0004025188,0.0003882478,0.0005240758,0.0010955652,0.0010180193,0.00082066644,0.0041260254],"category_scores_gemma":[0.0024307,0.00035842965,0.0010263611,0.0005317448,0.00084123877,0.001473656,0.0014065605,0.0015129197,0.00078778603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040568713,0.00002113858,0.0028017159,0.00007243738,0.00005096067,0.00017644108,0.00014343683,0.6470646,0.0015379217,0.31364748,0.012663303,0.021780005],"study_design_scores_gemma":[0.00002188072,0.000014430434,0.00038834027,0.00002415348,0.0000078442245,0.00006373561,0.000017929908,0.9068089,0.0006898144,0.06507076,0.026872156,0.000020049161],"about_ca_topic_score_codex":0.009324886,"about_ca_topic_score_gemma":0.007401427,"teacher_disagreement_score":0.009324886,"about_ca_system_score_codex":0.0007157834,"about_ca_system_score_gemma":0.0011827005,"threshold_uncertainty_score":0.018541217},"labels":[],"label_agreement":null},{"id":"W4392645987","doi":"10.5194/egusphere-egu24-19352","title":"Learning phytoplankton bloom patterns - A long and rocky road from data to equations&amp;#160;","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University","funders":"","keywords":"Phytoplankton; Bloom; Algal bloom; Environmental science; Oceanography; Ecology; Biology; Geology; Nutrient","score_opus":0.08689004309385785,"score_gpt":0.30639449774107197,"score_spread":0.21950445464721413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392645987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106619865,0.0067161117,0.8582661,0.017083485,0.00062716106,0.00009251075,0.0024454559,0.0021473025,0.0060019274],"genre_scores_gemma":[0.60036147,0.00480021,0.3820156,0.0026238943,0.0006783151,0.00023757007,0.0030329523,0.00028136157,0.0059686163],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956304,0.0001503924,0.00004077656,0.00012263823,0.00010359302,0.00001959089],"domain_scores_gemma":[0.9963399,0.0025744862,0.00024280805,0.00051965297,0.00026905866,0.00005418974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015348867,0.00076804106,0.0005797871,0.00069240376,0.0003320606,0.0017721157,0.00091126957,0.0014554836,0.0030294217],"category_scores_gemma":[0.011115292,0.0004946572,0.0007890734,0.000880926,0.0012338315,0.0024035447,0.0014559348,0.0023637502,0.00086772343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096445656,0.0001896592,0.03231006,0.0007030353,0.00028084076,0.00035936525,0.00074792304,0.41390395,0.004347479,0.050378673,0.016002635,0.48067993],"study_design_scores_gemma":[0.000029224051,0.000046213,0.0070128767,0.00016238596,0.00002092588,0.000059796308,0.00025401646,0.8615566,0.001627503,0.11387911,0.015312032,0.00003937104],"about_ca_topic_score_codex":0.010247141,"about_ca_topic_score_gemma":0.0117813125,"teacher_disagreement_score":0.010247141,"about_ca_system_score_codex":0.00075473636,"about_ca_system_score_gemma":0.0009889568,"threshold_uncertainty_score":0.020375013},"labels":[],"label_agreement":null},{"id":"W4392945234","doi":"10.1109/icmla58977.2023.00092","title":"TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting","year":2023,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Transduction (biophysics); Artificial neural network; Graph; Flow (mathematics); Artificial intelligence; Theoretical computer science; Mathematics; Chemistry","score_opus":0.04083434605214447,"score_gpt":0.23927112333792097,"score_spread":0.1984367772857765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392945234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08173936,0.0016442622,0.9062585,0.0008303258,0.00025747754,0.00006622018,0.00075376325,0.004151714,0.004298311],"genre_scores_gemma":[0.9247327,0.000626587,0.06765586,0.0002825472,0.000075739954,0.00009577606,0.0009700697,0.00011204277,0.005448817],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999864,0.000025694548,0.000006964173,0.0000535644,0.000023686283,0.000026107045],"domain_scores_gemma":[0.99975353,0.00012763136,0.000025274565,0.000020309786,0.00005810132,0.000015059682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000390257,0.00083832606,0.00057012954,0.000532277,0.0002765017,0.000461285,0.0012000472,0.0006820334,0.0021757],"category_scores_gemma":[0.001153931,0.0002712252,0.0005855974,0.00060670654,0.00033409634,0.0010840545,0.0006336216,0.001311187,0.0003536759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008542706,0.000065570326,0.0008326722,0.000042103544,0.00005353603,0.00007237279,0.000035835466,0.897489,0.0026173422,0.0045387326,0.0023750921,0.09179229],"study_design_scores_gemma":[0.0000014446744,0.0000060977263,0.000046294015,9.893241e-7,0.0000034478744,0.0000024849958,8.618108e-7,0.9987625,0.0001430043,0.00093804277,0.00009341247,0.0000013601339],"about_ca_topic_score_codex":0.02921571,"about_ca_topic_score_gemma":0.029632678,"teacher_disagreement_score":0.02921571,"about_ca_system_score_codex":0.00089431397,"about_ca_system_score_gemma":0.0008414593,"threshold_uncertainty_score":0.058091342},"labels":[],"label_agreement":null},{"id":"W4392964600","doi":"10.1007/978-3-031-47079-0_18","title":"Potential of Support Vector Machine Fed by ERA5 for Predicting Daily Discharge in the High Atlas of Morocco","year":2024,"lang":"en","type":"book-chapter","venue":"Advances in Science, Technology & Innovation/Advances in science, technology & innovation","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Atlas (anatomy); Support vector machine; Vector (molecular biology); Environmental science; Computer science; Artificial intelligence; Medicine; Biology; Anatomy","score_opus":0.008260577392733353,"score_gpt":0.27467351509422583,"score_spread":0.2664129377014925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392964600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8853671,0.0066827848,0.07862384,0.0017212667,0.0008482036,0.000053857104,0.00687021,0.0064427974,0.013390073],"genre_scores_gemma":[0.9705523,0.0006542271,0.021415265,0.00011816661,0.0001453011,0.00002559205,0.0033276747,0.00009145892,0.0036699674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998553,0.00004741728,0.000010478735,0.000035841633,0.00002224002,0.00002865764],"domain_scores_gemma":[0.999655,0.00015848628,0.000016539156,0.00003142597,0.00012187542,0.0000166417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006950774,0.00081722427,0.0003815339,0.00061325915,0.00025431733,0.00077720155,0.00065006333,0.00051868276,0.002190761],"category_scores_gemma":[0.0015310307,0.00014297097,0.00047178808,0.0005865216,0.000103898994,0.0006197861,0.00034403306,0.00048262905,0.0008043825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071209494,0.00017042516,0.028487202,0.00022763308,0.00038432173,0.0003013321,0.00012981136,0.47781593,0.0043869116,0.0022508772,0.014375272,0.47075823],"study_design_scores_gemma":[0.000015987905,0.000058136837,0.009714086,0.000022217615,0.000056507874,0.000016932989,0.00004547946,0.9847099,0.0019042077,0.0010300108,0.0024111934,0.000015330013],"about_ca_topic_score_codex":0.04366898,"about_ca_topic_score_gemma":0.02753208,"teacher_disagreement_score":0.04366898,"about_ca_system_score_codex":0.00057508977,"about_ca_system_score_gemma":0.0005731622,"threshold_uncertainty_score":0.0868296},"labels":[],"label_agreement":null},{"id":"W4393203148","doi":"10.1016/j.xinn.2024.100617","title":"Deep learning for cross-region streamflow and flood forecasting at a global scale","year":2024,"lang":"en","type":"article","venue":"The Innovation","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"Institute of Mountain Hazards and Environment; Sichuan Province Science and Technology Support Program; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Streamflow; Flood forecasting; Scale (ratio); Flood myth; Climatology; Meteorology; Environmental science; Geology; Geography; Cartography; Archaeology; Drainage basin","score_opus":0.032889754385044406,"score_gpt":0.278877492304427,"score_spread":0.24598773791938258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393203148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21343979,0.0012107549,0.7768829,0.0008093057,0.000116714036,0.000033995144,0.00080566906,0.0022096564,0.0044912556],"genre_scores_gemma":[0.9350905,0.00035000485,0.061768956,0.00009910384,0.00004128372,0.000028951368,0.0007280685,0.00005156195,0.0018415857],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998894,0.000020718195,0.000007189116,0.000038387305,0.00002335259,0.000020945987],"domain_scores_gemma":[0.9997452,0.00010617019,0.00003569514,0.0000380931,0.0000552168,0.000019656092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006144998,0.0005479431,0.00034202565,0.0006089723,0.0002223502,0.0005462533,0.0006385497,0.00044298806,0.0012822144],"category_scores_gemma":[0.0012689293,0.00018550518,0.00033224045,0.0009058599,0.00027746824,0.0012810181,0.0008856518,0.00094901095,0.0003264778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006724099,0.00007904291,0.0075030527,0.000058700447,0.00009193954,0.00007147882,0.00006573317,0.7309258,0.0062101725,0.005587847,0.0024563721,0.24688262],"study_design_scores_gemma":[0.0000017844807,0.000009451135,0.0006168027,0.0000035242058,0.000005042004,0.0000046910895,0.000008627066,0.995194,0.0009729137,0.0028233633,0.00035726652,0.0000023838966],"about_ca_topic_score_codex":0.009721881,"about_ca_topic_score_gemma":0.013713972,"teacher_disagreement_score":0.009721881,"about_ca_system_score_codex":0.0006527117,"about_ca_system_score_gemma":0.0008746881,"threshold_uncertainty_score":0.019330561},"labels":[],"label_agreement":null},{"id":"W4393360369","doi":"10.1007/978-981-97-1316-5_9","title":"Machine Learning (ML) in Water Resources","year":2024,"lang":"en","type":"book-chapter","venue":"Water science and technology library","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.007508778024634585,"score_gpt":0.17826870407448095,"score_spread":0.17075992604984636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393360369","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018154628,0.15016027,0.5047765,0.01126041,0.004216266,0.000048113165,0.0006419042,0.0024502685,0.32463083],"genre_scores_gemma":[0.061144743,0.15926458,0.19311793,0.00474263,0.010004654,0.00025957765,0.0010714434,0.0014086047,0.56898594],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996685,0.000086872235,0.000018814137,0.00005729181,0.00015415155,0.00001438344],"domain_scores_gemma":[0.99906677,0.00074532884,0.000027549238,0.000081502796,0.00006298919,0.000015897844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050918583,0.0007354383,0.00085474784,0.0010863666,0.00032547183,0.0018641585,0.00075163215,0.0011463026,0.02060051],"category_scores_gemma":[0.0018956655,0.0004409754,0.00037191226,0.0031134954,0.0011899661,0.003655978,0.0010615188,0.0023099466,0.010321111],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013154563,0.000044125532,0.00012228255,0.00058342743,0.00001772488,0.000035310662,0.00008604087,0.009149674,0.0005917827,0.245046,0.17056288,0.5737476],"study_design_scores_gemma":[0.0000069212165,0.000027253653,0.00032657987,0.00030789152,0.000013727933,0.00010894019,0.00004091648,0.039873775,0.0011725284,0.48354053,0.47455943,0.000021501632],"about_ca_topic_score_codex":0.0014808509,"about_ca_topic_score_gemma":0.0021063725,"teacher_disagreement_score":0.02060051,"about_ca_system_score_codex":0.00073830993,"about_ca_system_score_gemma":0.00069177087,"threshold_uncertainty_score":0.068915546},"labels":[],"label_agreement":null},{"id":"W4393484683","doi":"10.5281/zenodo.10223596","title":"Generative deep learning for hydrological forecasting: CVAE-75 basins from CANOPEX_v1","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generative grammar; Artificial intelligence; Climatology; Computer science; Econometrics; Environmental science; Geography; Machine learning; Meteorology; Geology; Mathematics","score_opus":0.06913441974173826,"score_gpt":0.2564358105716017,"score_spread":0.18730139082986344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393484683","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0098183,0.00040066353,0.0033093921,0.0005531483,0.00023407323,0.000108525375,0.9585447,0.02170413,0.0053270757],"genre_scores_gemma":[0.011554277,0.000110027206,0.0045048622,0.00012511214,0.000021240694,0.00013171045,0.9805792,0.00082808663,0.0021455747],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99963975,0.000065049644,0.000020326115,0.00010753612,0.000099241945,0.000068034344],"domain_scores_gemma":[0.99940836,0.0001506595,0.000024546289,0.00022235561,0.00012442948,0.000069760485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079892785,0.0025641797,0.00088655466,0.0013526337,0.00056389085,0.0012143082,0.0032459528,0.0020770787,0.037909415],"category_scores_gemma":[0.0026119282,0.0008800702,0.0016748218,0.0019288952,0.0005450602,0.0008707992,0.0014785862,0.0023920336,0.030048732],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001343056,0.0001457123,0.00173267,0.0002978129,0.00010524028,0.00007144954,0.00003244825,0.026354384,0.00048471184,0.0011038384,0.95794976,0.0115877045],"study_design_scores_gemma":[0.0014391509,0.00019757767,0.011742816,0.00037941663,0.0001085143,0.00021104809,0.00012239363,0.23904195,0.005604781,0.01593077,0.72502565,0.00019594685],"about_ca_topic_score_codex":0.042953063,"about_ca_topic_score_gemma":0.07910916,"teacher_disagreement_score":0.9570469,"about_ca_system_score_codex":0.0011805013,"about_ca_system_score_gemma":0.0017001226,"threshold_uncertainty_score":0.12681961},"labels":[],"label_agreement":null},{"id":"W4393540625","doi":"10.5281/zenodo.4071885","title":"Models and Predictions for \"Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network\"","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Term (time); Surface runoff; Environmental science; Computer science; Climatology; Geology; Physics; Ecology","score_opus":0.04872614810696903,"score_gpt":0.2259776562196659,"score_spread":0.17725150811269685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393540625","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006921525,0.0007825442,0.089710735,0.0039182957,0.0017253454,0.0002642587,0.7471467,0.09855157,0.05097897],"genre_scores_gemma":[0.0383893,0.0009444957,0.07494796,0.0008962186,0.00041940555,0.00076813734,0.79744154,0.028693616,0.05749935],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99947613,0.000078885794,0.000039264312,0.00011159299,0.000245851,0.00004829611],"domain_scores_gemma":[0.999091,0.00019801137,0.00005141388,0.00022183733,0.00036469774,0.00007304307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010949731,0.0012047057,0.0007861587,0.00082486053,0.00046903998,0.0015966494,0.0028667008,0.0016043657,0.10434966],"category_scores_gemma":[0.0037730539,0.000853872,0.0022522318,0.0017286942,0.00021823333,0.003095334,0.00136966,0.0017585133,0.0673367],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014494518,0.00005859141,0.0016530802,0.00034751312,0.00012435853,0.000060676794,0.00004483303,0.032390844,0.00097589934,0.0056319064,0.9251693,0.03339806],"study_design_scores_gemma":[0.00042967062,0.00006690785,0.004791464,0.00026915665,0.00014570961,0.00009335202,0.000065072025,0.20498963,0.008030979,0.02328987,0.75769776,0.00013044283],"about_ca_topic_score_codex":0.021985617,"about_ca_topic_score_gemma":0.015864534,"teacher_disagreement_score":0.10434966,"about_ca_system_score_codex":0.0010793826,"about_ca_system_score_gemma":0.0016292956,"threshold_uncertainty_score":0.34908438},"labels":[],"label_agreement":null},{"id":"W4393596802","doi":"10.5281/zenodo.4404600","title":"Trained convolutional neural network for the identification of long-duration mixed precipitation in Montréal (Canada)","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Duration (music); Precipitation; Convolutional neural network; Identification (biology); Artificial neural network; Environmental science; Geography; Artificial intelligence; Computer science; Meteorology; Art; Biology; Ecology","score_opus":0.02988293253470871,"score_gpt":0.22476213380014343,"score_spread":0.19487920126543473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393596802","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014897698,0.00029116217,0.0007559173,0.00027080174,0.000116636096,0.00006312366,0.97782785,0.0022664526,0.0035103671],"genre_scores_gemma":[0.014633822,0.00010889809,0.001365614,0.000059218164,0.000015430533,0.000037869704,0.9803341,0.00016879597,0.0032763127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99956876,0.000020342706,0.000013157406,0.000109511144,0.00013367519,0.00015462174],"domain_scores_gemma":[0.9992275,0.000043916072,0.000037033133,0.000116276875,0.0004070732,0.00016825025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034833746,0.0023849993,0.0007239342,0.0019352408,0.001192898,0.0010841535,0.0028138906,0.0011780082,0.016122567],"category_scores_gemma":[0.0014160601,0.00046890767,0.001139687,0.00350149,0.0006507982,0.0005538925,0.0009890712,0.0015203195,0.009438096],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029728754,0.00010986786,0.00827565,0.00031479128,0.00017427797,0.00015674664,0.00005764187,0.011608299,0.001155715,0.0007621466,0.96184266,0.015244909],"study_design_scores_gemma":[0.0009173462,0.00013216904,0.15741244,0.00046377713,0.00028898893,0.00032853152,0.000655503,0.08467979,0.009805315,0.002912148,0.7420683,0.0003356998],"about_ca_topic_score_codex":0.9384553,"about_ca_topic_score_gemma":0.969801,"teacher_disagreement_score":0.061544716,"about_ca_system_score_codex":0.00865419,"about_ca_system_score_gemma":0.012192955,"threshold_uncertainty_score":0.123814285},"labels":[],"label_agreement":null},{"id":"W4393600581","doi":"10.5281/zenodo.4072701","title":"Data for \"Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network\"","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Surface runoff; Term (time); Environmental science; Computer science; Hydrology (agriculture); Geology; Geotechnical engineering; Ecology; Physics","score_opus":0.07277879475274603,"score_gpt":0.24715543883663185,"score_spread":0.1743766440838858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393600581","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041782192,0.00006621111,0.00022026109,0.00016044812,0.00008782471,0.000023060711,0.9958216,0.0019375613,0.0012652911],"genre_scores_gemma":[0.0007124324,0.000030321244,0.00048536042,0.000057133333,0.0000087537455,0.000042881336,0.99787915,0.00012324887,0.00066070416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999366,0.000098180804,0.000056937366,0.00016408622,0.00019598006,0.00011879403],"domain_scores_gemma":[0.9989619,0.0001602526,0.00007388169,0.00031029418,0.00033549775,0.00015817006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095958094,0.003027911,0.0013376112,0.0013143859,0.00080947735,0.0015394108,0.003985235,0.0024631792,0.05402625],"category_scores_gemma":[0.0026302189,0.0007145291,0.0016435707,0.0026293758,0.000592808,0.001561924,0.0018369316,0.00271637,0.089748055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004724148,0.00003246079,0.00033282355,0.00020075895,0.000021567446,0.000014368236,0.000010267223,0.00084542466,0.00013132222,0.00023660125,0.9963211,0.0018061992],"study_design_scores_gemma":[0.00068306684,0.000052417596,0.006202582,0.00022664355,0.000049350187,0.000101471625,0.000101703656,0.0078412285,0.0018840539,0.0031589405,0.9796243,0.00007428503],"about_ca_topic_score_codex":0.03163006,"about_ca_topic_score_gemma":0.0684737,"teacher_disagreement_score":0.05402625,"about_ca_system_score_codex":0.0015593502,"about_ca_system_score_gemma":0.0017285239,"threshold_uncertainty_score":0.18073583},"labels":[],"label_agreement":null},{"id":"W4393704578","doi":"10.5281/zenodo.4404599","title":"Trained convolutional neural network for the identification of long-duration mixed precipitation in Montréal (Canada)","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Duration (music); Precipitation; Convolutional neural network; Identification (biology); Artificial neural network; Environmental science; Geography; Artificial intelligence; Computer science; Meteorology; Art; Biology; Ecology","score_opus":0.02988293253470871,"score_gpt":0.22476213380014343,"score_spread":0.19487920126543473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393704578","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014897698,0.00029116217,0.0007559173,0.00027080174,0.000116636096,0.00006312366,0.97782785,0.0022664526,0.0035103671],"genre_scores_gemma":[0.014633822,0.00010889809,0.001365614,0.000059218164,0.000015430533,0.000037869704,0.9803341,0.00016879597,0.0032763127],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99956876,0.000020342706,0.000013157406,0.000109511144,0.00013367519,0.00015462174],"domain_scores_gemma":[0.9992275,0.000043916072,0.000037033133,0.000116276875,0.0004070732,0.00016825025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034833746,0.0023849993,0.0007239342,0.0019352408,0.001192898,0.0010841535,0.0028138906,0.0011780082,0.016122567],"category_scores_gemma":[0.0014160601,0.00046890767,0.001139687,0.00350149,0.0006507982,0.0005538925,0.0009890712,0.0015203195,0.009438096],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029728754,0.00010986786,0.00827565,0.00031479128,0.00017427797,0.00015674664,0.00005764187,0.011608299,0.001155715,0.0007621466,0.96184266,0.015244909],"study_design_scores_gemma":[0.0009173462,0.00013216904,0.15741244,0.00046377713,0.00028898893,0.00032853152,0.000655503,0.08467979,0.009805315,0.002912148,0.7420683,0.0003356998],"about_ca_topic_score_codex":0.9384553,"about_ca_topic_score_gemma":0.969801,"teacher_disagreement_score":0.061544716,"about_ca_system_score_codex":0.00865419,"about_ca_system_score_gemma":0.012192955,"threshold_uncertainty_score":0.123814285},"labels":[],"label_agreement":null},{"id":"W4393763406","doi":"10.5281/zenodo.4071886","title":"Models and Predictions for \"Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network\"","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Term (time); Surface runoff; Environmental science; Computer science; Physics; Ecology","score_opus":0.04872614810696903,"score_gpt":0.2259776562196659,"score_spread":0.17725150811269685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393763406","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008628219,0.0009373434,0.1211943,0.0055316426,0.0020569821,0.00046689704,0.70087993,0.08479429,0.07551045],"genre_scores_gemma":[0.04846598,0.001184886,0.0861923,0.0014670889,0.00052406115,0.0010273572,0.7700891,0.019685127,0.0713641],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994005,0.000094124065,0.000045196077,0.00012696616,0.00027685743,0.000056325367],"domain_scores_gemma":[0.9989195,0.0002853099,0.000057015255,0.00024322713,0.00041699372,0.000077995006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012707562,0.0013288005,0.0006338324,0.00074673386,0.0004761685,0.0014798859,0.003001121,0.0016502441,0.10916952],"category_scores_gemma":[0.004130836,0.00079148664,0.0021401523,0.001431231,0.0002103182,0.0028628064,0.0014813923,0.0016257261,0.059502628],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013965419,0.000070616275,0.0016471511,0.00041474722,0.00014768777,0.000060932474,0.0000411828,0.040107958,0.0010971392,0.007078248,0.9130743,0.036120355],"study_design_scores_gemma":[0.0004808624,0.00008677528,0.0046345987,0.0002516543,0.00015395661,0.00008862807,0.00007018356,0.26332408,0.00983996,0.024695527,0.6962452,0.00012855389],"about_ca_topic_score_codex":0.019816611,"about_ca_topic_score_gemma":0.016834304,"teacher_disagreement_score":0.10916952,"about_ca_system_score_codex":0.0011380928,"about_ca_system_score_gemma":0.0016931753,"threshold_uncertainty_score":0.3652084},"labels":[],"label_agreement":null},{"id":"W4393836913","doi":"10.5281/zenodo.4072700","title":"Data for \"Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network\"","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Surface runoff; Term (time); Environmental science; Computer science; Hydrology (agriculture); Geology; Geotechnical engineering; Ecology; Physics","score_opus":0.07277879475274603,"score_gpt":0.24715543883663185,"score_spread":0.1743766440838858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393836913","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041782192,0.00006621111,0.00022026109,0.00016044812,0.00008782471,0.000023060711,0.9958216,0.0019375613,0.0012652911],"genre_scores_gemma":[0.0007124324,0.000030321244,0.00048536042,0.000057133333,0.0000087537455,0.000042881336,0.99787915,0.00012324887,0.00066070416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999366,0.000098180804,0.000056937366,0.00016408622,0.00019598006,0.00011879403],"domain_scores_gemma":[0.9989619,0.0001602526,0.00007388169,0.00031029418,0.00033549775,0.00015817006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095958094,0.003027911,0.0013376112,0.0013143859,0.00080947735,0.0015394108,0.003985235,0.0024631792,0.05402625],"category_scores_gemma":[0.0026302189,0.0007145291,0.0016435707,0.0026293758,0.000592808,0.001561924,0.0018369316,0.00271637,0.089748055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004724148,0.00003246079,0.00033282355,0.00020075895,0.000021567446,0.000014368236,0.000010267223,0.00084542466,0.00013132222,0.00023660125,0.9963211,0.0018061992],"study_design_scores_gemma":[0.00068306684,0.000052417596,0.006202582,0.00022664355,0.000049350187,0.000101471625,0.000101703656,0.0078412285,0.0018840539,0.0031589405,0.9796243,0.00007428503],"about_ca_topic_score_codex":0.03163006,"about_ca_topic_score_gemma":0.0684737,"teacher_disagreement_score":0.05402625,"about_ca_system_score_codex":0.0015593502,"about_ca_system_score_gemma":0.0017285239,"threshold_uncertainty_score":0.18073583},"labels":[],"label_agreement":null},{"id":"W4393837409","doi":"10.5281/zenodo.2601978","title":"Supporting model output for 'Empirical stream thermal sensitivities may underestimate stream temperature response to climate warming'.","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canadian Forest Service","funders":"","keywords":"Environmental science; Climate change; Climatology; Global warming; Atmospheric sciences; Geology; Oceanography","score_opus":0.06339535862157676,"score_gpt":0.31334283840879096,"score_spread":0.2499474797872142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393837409","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015989531,0.000022768128,0.00010847594,0.00007618637,0.00003843685,0.0000069867715,0.99851006,0.0006323054,0.00044486375],"genre_scores_gemma":[0.00068066624,0.000024635916,0.00039393172,0.00005217394,0.000006549962,0.000045488345,0.9982089,0.00011815377,0.00046955157],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993474,0.0001056777,0.0000843434,0.00019047163,0.00016347824,0.00010865132],"domain_scores_gemma":[0.9980038,0.00068476785,0.00017831611,0.00042622356,0.00053625624,0.0001706355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010892884,0.0021965946,0.0009840656,0.0015852132,0.00052607455,0.0017550798,0.0030184316,0.0026863727,0.08173033],"category_scores_gemma":[0.0050921743,0.0007217437,0.0015996728,0.0029975732,0.000433182,0.0012889298,0.0014340838,0.0021500138,0.07508803],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049222686,0.00002230289,0.00075857015,0.00038177692,0.0000396851,0.000018546625,0.000011802722,0.0015363089,0.000099422025,0.0003397656,0.9954035,0.0013390465],"study_design_scores_gemma":[0.0010905481,0.00002684454,0.0073860907,0.0004484693,0.000068628426,0.00007260824,0.00007439471,0.008703166,0.00095084566,0.0037550179,0.9773539,0.00006939185],"about_ca_topic_score_codex":0.03861793,"about_ca_topic_score_gemma":0.07124056,"teacher_disagreement_score":0.08173033,"about_ca_system_score_codex":0.0015949544,"about_ca_system_score_gemma":0.002157696,"threshold_uncertainty_score":0.2734152},"labels":[],"label_agreement":null},{"id":"W4393923141","doi":"10.5281/zenodo.4387067","title":"Data for \"Gaining Hydrological Insights Through Wilk's Feature Importance: A Test-Statistic Interpretation method for Reliable and Robust Inference\"","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Inference; Statistic; Interpretation (philosophy); Computer science; Feature (linguistics); Test statistic; Test (biology); Data mining; Artificial intelligence; Machine learning; Econometrics; Statistics; Statistical hypothesis testing; Mathematics; Geology; Programming language","score_opus":0.08481732111876146,"score_gpt":0.31183038248981904,"score_spread":0.2270130613710576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393923141","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003092487,0.000022786948,0.00033842138,0.00007317962,0.000032490694,0.000013910597,0.9982191,0.0005759883,0.00041483098],"genre_scores_gemma":[0.0009045066,0.00001879386,0.0008585747,0.000041446317,0.00000501143,0.000078301695,0.99769634,0.00007645051,0.00032055142],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991703,0.00014929262,0.00010236123,0.00018973633,0.00026740553,0.000120977784],"domain_scores_gemma":[0.9974208,0.0005701662,0.00026620974,0.000767927,0.0007319037,0.00024289534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017245337,0.0019195216,0.0008677139,0.001508272,0.0005314451,0.0011603008,0.002749303,0.002004138,0.025589207],"category_scores_gemma":[0.006534304,0.0006629192,0.0011193014,0.00289502,0.0005475842,0.00083882344,0.0014956262,0.0018838313,0.031800576],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101902035,0.000040951712,0.0013766722,0.00041248227,0.00004736169,0.000027803682,0.00002285575,0.0015823707,0.0003043187,0.0008077555,0.99228996,0.0029857145],"study_design_scores_gemma":[0.0007625236,0.000060053248,0.012417586,0.00030368313,0.000061776926,0.00010099027,0.00009618389,0.0048520053,0.0017732993,0.0045793,0.9749205,0.000071978044],"about_ca_topic_score_codex":0.03139208,"about_ca_topic_score_gemma":0.060691774,"teacher_disagreement_score":0.03139208,"about_ca_system_score_codex":0.0012447567,"about_ca_system_score_gemma":0.0022954894,"threshold_uncertainty_score":0.08560437},"labels":[],"label_agreement":null},{"id":"W4393932440","doi":"10.3390/w16071042","title":"Applying Recurrent Neural Networks and Blocked Cross-Validation to Model Conventional Drinking Water Treatment Processes","year":2024,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Recurrent neural network; Computer science; Test set; Artificial intelligence; Artificial neural network; Process (computing); Perceptron; Multilayer perceptron; Machine learning","score_opus":0.030686349013756782,"score_gpt":0.27969540218243266,"score_spread":0.2490090531686759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393932440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47936413,0.00091031514,0.5150082,0.00018711873,0.000091191956,0.00015940194,0.00037368917,0.0021100815,0.0017958749],"genre_scores_gemma":[0.93745655,0.000100554535,0.060673267,0.000057105502,0.000013375036,0.000137654,0.00051082997,0.00007528745,0.00097536284],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990232,0.00043282166,0.00009298244,0.00022285957,0.00014119486,0.00008689253],"domain_scores_gemma":[0.9967204,0.0022761894,0.00023345152,0.00019766949,0.00051350595,0.00005871134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004621393,0.0013148773,0.0006656722,0.0007051737,0.00031194265,0.0006524567,0.0013321248,0.0009851402,0.0007999875],"category_scores_gemma":[0.00712266,0.00052599906,0.00083644013,0.00044121675,0.00044735335,0.0008687948,0.0006169275,0.0013038669,0.00024486796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007434658,0.00007151368,0.0021430487,0.00004208493,0.000096391435,0.000025874295,0.000023163217,0.97615904,0.0020934336,0.0003722102,0.00018937378,0.018709514],"study_design_scores_gemma":[0.0000021737044,0.000023418606,0.00025746532,0.0000016067437,0.0000036220167,0.0000020265463,0.0000015348684,0.99893254,0.0006298983,0.000101641424,0.00004118137,0.0000029483626],"about_ca_topic_score_codex":0.025258468,"about_ca_topic_score_gemma":0.019611962,"teacher_disagreement_score":0.025258468,"about_ca_system_score_codex":0.0010930988,"about_ca_system_score_gemma":0.0011940286,"threshold_uncertainty_score":0.050222933},"labels":[],"label_agreement":null},{"id":"W4394023488","doi":"10.5281/zenodo.3703190","title":"Data and code for \"Predicting evaporation in stream temperature models – Penman, Dalton or something else?\"","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Forest Service; University of British Columbia","funders":"","keywords":"Code (set theory); Evaporation; Environmental science; Computer science; Meteorology; Geography; Programming language","score_opus":0.10273561310367055,"score_gpt":0.29334831791199234,"score_spread":0.1906127048083218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394023488","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011168333,0.000020293242,0.0001562011,0.000037292462,0.000027556544,0.000012641042,0.9984534,0.00087218493,0.00030872185],"genre_scores_gemma":[0.00035102526,0.000024185392,0.0006601737,0.000043776337,0.000005456865,0.00009292506,0.998223,0.0002086774,0.0003907287],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992156,0.00012545165,0.00010366294,0.00024094517,0.00020316396,0.00011108669],"domain_scores_gemma":[0.9984768,0.00038199453,0.00013218359,0.000474237,0.0003921288,0.00014262799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012052745,0.0025914896,0.0012321731,0.0017945844,0.00055671384,0.0013563341,0.0028470533,0.0017429828,0.08210161],"category_scores_gemma":[0.0039819144,0.0008534384,0.001792121,0.0034475685,0.00044338516,0.0013704252,0.0013635376,0.0021985958,0.12392813],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051232648,0.000024496274,0.0006338623,0.00034066988,0.000025799205,0.00001368976,0.000011822669,0.00096543843,0.00013436114,0.0002802362,0.9958332,0.001685194],"study_design_scores_gemma":[0.0005820971,0.000035721216,0.0058382675,0.00025885273,0.000040337593,0.000081119215,0.00006306447,0.00308165,0.0011861285,0.0027883379,0.9859767,0.00006776097],"about_ca_topic_score_codex":0.018137293,"about_ca_topic_score_gemma":0.030780336,"teacher_disagreement_score":0.08210161,"about_ca_system_score_codex":0.0011697536,"about_ca_system_score_gemma":0.0013688698,"threshold_uncertainty_score":0.27465725},"labels":[],"label_agreement":null},{"id":"W4394039249","doi":"10.5281/zenodo.4568482","title":"Data for \"Gaining Hydrological Insights Through Wilk's Feature Importance: A Test-Statistic Interpretation method for Reliable and Robust Inference\"","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Inference; Statistic; Interpretation (philosophy); Computer science; Feature (linguistics); Test statistic; Data mining; Artificial intelligence; Statistics; Machine learning; Data science; Natural language processing; Statistical hypothesis testing; Mathematics; Programming language","score_opus":0.08481732111876146,"score_gpt":0.31183038248981904,"score_spread":0.2270130613710576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394039249","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003092487,0.000022786948,0.00033842138,0.00007317962,0.000032490694,0.000013910597,0.9982191,0.0005759883,0.00041483098],"genre_scores_gemma":[0.0009045066,0.00001879386,0.0008585747,0.000041446317,0.00000501143,0.000078301695,0.99769634,0.00007645051,0.00032055142],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991703,0.00014929262,0.00010236123,0.00018973633,0.00026740553,0.000120977784],"domain_scores_gemma":[0.9974208,0.0005701662,0.00026620974,0.000767927,0.0007319037,0.00024289534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017245337,0.0019195216,0.0008677139,0.001508272,0.0005314451,0.0011603008,0.002749303,0.002004138,0.025589207],"category_scores_gemma":[0.006534304,0.0006629192,0.0011193014,0.00289502,0.0005475842,0.00083882344,0.0014956262,0.0018838313,0.031800576],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101902035,0.000040951712,0.0013766722,0.00041248227,0.00004736169,0.000027803682,0.00002285575,0.0015823707,0.0003043187,0.0008077555,0.99228996,0.0029857145],"study_design_scores_gemma":[0.0007625236,0.000060053248,0.012417586,0.00030368313,0.000061776926,0.00010099027,0.00009618389,0.0048520053,0.0017732993,0.0045793,0.9749205,0.000071978044],"about_ca_topic_score_codex":0.03139208,"about_ca_topic_score_gemma":0.060691774,"teacher_disagreement_score":0.03139208,"about_ca_system_score_codex":0.0012447567,"about_ca_system_score_gemma":0.0022954894,"threshold_uncertainty_score":0.08560437},"labels":[],"label_agreement":null},{"id":"W4394192127","doi":"10.6084/m9.figshare.11358350","title":"Dataset for: Simulating a spill of diluted bitumen: Environmental weathering and submergence in a model freshwater system","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Weathering; Asphalt; Environmental science; Oil spill; Geology; Geochemistry; Geography; Environmental engineering; Cartography","score_opus":0.04817013760610227,"score_gpt":0.2581716163113408,"score_spread":0.2100014787052385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394192127","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041992657,0.00040396673,0.0054589133,0.0018553296,0.00039168063,0.00024032792,0.93523633,0.00998769,0.004433057],"genre_scores_gemma":[0.088945314,0.0001835612,0.01401087,0.00041845543,0.000055156495,0.00047884163,0.8933817,0.00053511234,0.0019909604],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99978334,0.000045332727,0.000023808292,0.000064630185,0.000047452504,0.00003540152],"domain_scores_gemma":[0.999265,0.000336602,0.000042233725,0.000115749055,0.00014680554,0.00009361637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006597064,0.0014832916,0.00084058894,0.00069417973,0.00058146036,0.001084027,0.0027316099,0.0027936965,0.017391775],"category_scores_gemma":[0.002472436,0.00040692944,0.0016077507,0.000928112,0.000490299,0.0007635229,0.0008382813,0.0016021576,0.0044657122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004895298,0.00052998733,0.016457088,0.001438295,0.00048753296,0.00051362347,0.00012659212,0.371033,0.0015494452,0.0029361313,0.58710796,0.017330766],"study_design_scores_gemma":[0.0021867724,0.00022445004,0.016391592,0.00020438746,0.0001274192,0.00018452319,0.0002285565,0.78671736,0.0019414929,0.007306819,0.18433699,0.00014967931],"about_ca_topic_score_codex":0.04982599,"about_ca_topic_score_gemma":0.08382438,"teacher_disagreement_score":0.04982599,"about_ca_system_score_codex":0.0011518735,"about_ca_system_score_gemma":0.0010981372,"threshold_uncertainty_score":0.09907198},"labels":[],"label_agreement":null},{"id":"W4394685310","doi":"10.1016/j.gsd.2024.101174","title":"Unraveling aquifer dynamics: Time series evaluation for informed groundwater management","year":2024,"lang":"en","type":"article","venue":"Groundwater for Sustainable Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Aquifer; Groundwater; Series (stratigraphy); Environmental science; Geology; Hydrology (agriculture); Geotechnical engineering","score_opus":0.014633114812600517,"score_gpt":0.25292342658062517,"score_spread":0.23829031176802465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394685310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34162974,0.00085019163,0.6474423,0.0015852329,0.00014315911,0.00009047818,0.0018167604,0.00087342696,0.0055686943],"genre_scores_gemma":[0.96417445,0.0003841932,0.033724073,0.00006624569,0.000053640226,0.000029604986,0.00059757987,0.000040304694,0.00092981727],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972624,0.00010599114,0.000022832259,0.00004924117,0.00007382472,0.000021886153],"domain_scores_gemma":[0.99850816,0.00093925075,0.00019081363,0.00014609707,0.00016681373,0.000048936017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017777628,0.000532585,0.00057619065,0.0012604732,0.00019166617,0.0011194017,0.000516433,0.00087075605,0.0016500007],"category_scores_gemma":[0.005695123,0.00018378491,0.00035141397,0.0012670942,0.00031587807,0.0019151288,0.0004329366,0.0007421906,0.00018276404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014101205,0.00013394444,0.015069936,0.00009019728,0.000084807856,0.00005923841,0.000041285202,0.8574768,0.003291379,0.007037047,0.001340959,0.11523336],"study_design_scores_gemma":[0.0000016281838,0.000012359743,0.0008497429,0.0000031148472,0.000004782355,0.0000035271619,0.00001217597,0.9959974,0.00037221817,0.0025858188,0.00015392066,0.0000033100193],"about_ca_topic_score_codex":0.006440134,"about_ca_topic_score_gemma":0.005486885,"teacher_disagreement_score":0.006440134,"about_ca_system_score_codex":0.00053164724,"about_ca_system_score_gemma":0.0006257655,"threshold_uncertainty_score":0.012805283},"labels":[],"label_agreement":null},{"id":"W4394892254","doi":"10.2166/wst.2024.096","title":"Estimation of instantaneous peak flows in Canadian rivers: an evaluation of conventional, nonlinear regression, and machine learning methods","year":2024,"lang":"en","type":"article","venue":"Water Science & Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada","funders":"Infrastructure Canada; National Research Council Canada","keywords":"Nonlinear regression; Nonlinear system; Regression; Estimation; Statistics; Regression analysis; Computer science; Mathematics; Machine learning; Environmental science; Artificial intelligence; Econometrics; Engineering; Physics","score_opus":0.03336880853771761,"score_gpt":0.3332604282619923,"score_spread":0.2998916197242747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394892254","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66958684,0.002942962,0.31986457,0.00075842167,0.000075695236,0.00016533818,0.00087232684,0.0013814034,0.0043525156],"genre_scores_gemma":[0.8792552,0.0008923755,0.117673285,0.00005177764,0.000039736336,0.00004732796,0.00080039294,0.000058289887,0.0011816474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99876773,0.0003535563,0.00007175148,0.00027807275,0.00042591145,0.00010293364],"domain_scores_gemma":[0.99617505,0.0022059246,0.00027335295,0.000144558,0.0011077966,0.00009327208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047106543,0.0010403557,0.0006341789,0.0016224092,0.0006863124,0.0010882319,0.0013054998,0.00049722486,0.0003508195],"category_scores_gemma":[0.010796976,0.00026271906,0.0004318208,0.0016709347,0.00045017287,0.0009941539,0.0006028242,0.00067105173,0.00008586307],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000271821,0.00012596278,0.05424778,0.00020396909,0.00020463116,0.00006794242,0.00016734257,0.6412656,0.0020606567,0.0019659877,0.0008865631,0.2985318],"study_design_scores_gemma":[0.000009257063,0.000025702739,0.014525807,0.0000090267695,0.000023947123,0.000011407522,0.000050773135,0.9841308,0.00071524514,0.00019097856,0.0002898336,0.00001727782],"about_ca_topic_score_codex":0.70107293,"about_ca_topic_score_gemma":0.61379826,"teacher_disagreement_score":0.29892707,"about_ca_system_score_codex":0.0038765802,"about_ca_system_score_gemma":0.0065598725,"threshold_uncertainty_score":0.601375},"labels":[],"label_agreement":null},{"id":"W4395010606","doi":"10.3390/su16083461","title":"Advancing Spatial Drought Forecasts by Integrating an Improved Outlier Robust Extreme Learning Machine with Gridded Data: A Case Study of the Lower Mainland Basin, British Columbia, Canada","year":2024,"lang":"en","type":"article","venue":"Sustainability","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Université Laval","funders":"","keywords":"Outlier; Extreme learning machine; Mainland; Structural basin; Climatology; Data mining; Computer science; Meteorology; Artificial intelligence; Geography; Machine learning; Cartography; Geology; Geomorphology; Archaeology; Artificial neural network","score_opus":0.010240357416497111,"score_gpt":0.2226530991125721,"score_spread":0.212412741696075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395010606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932672,0.00023808247,0.0033500663,0.00035396457,0.000012143103,0.000046663543,0.0010384902,0.00016675006,0.0015267888],"genre_scores_gemma":[0.99458176,0.00013769565,0.0035691103,0.000025760299,0.000005134568,0.000014126615,0.00085856894,0.000011351195,0.00079645216],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978095,0.000048979284,0.000014107876,0.000051972267,0.000046703342,0.00005737317],"domain_scores_gemma":[0.9995702,0.00014106566,0.000029605422,0.000032272408,0.00018623703,0.00004064353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005706215,0.00065040385,0.0003795121,0.0006415286,0.0008292292,0.0010505584,0.0009939934,0.00043769542,0.00050459633],"category_scores_gemma":[0.0017467446,0.0001841273,0.00031283766,0.0016668901,0.00038174164,0.0003240445,0.00046949068,0.0004475901,0.000069086185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022810693,0.00021810479,0.12361061,0.00013494141,0.00014689902,0.0011499828,0.00026122376,0.8221427,0.0016180645,0.0008454923,0.0029419,0.046702],"study_design_scores_gemma":[0.0000224401,0.000023277888,0.035167288,0.000014890662,0.000035004352,0.000028364833,0.0004439167,0.96229464,0.00067846524,0.0002457525,0.0010253194,0.000020715079],"about_ca_topic_score_codex":0.9511548,"about_ca_topic_score_gemma":0.95480484,"teacher_disagreement_score":0.048845172,"about_ca_system_score_codex":0.00729984,"about_ca_system_score_gemma":0.0055102804,"threshold_uncertainty_score":0.09826559},"labels":[],"label_agreement":null},{"id":"W4395465422","doi":"10.18280/ijdne.190226","title":"Applying Remote Sensing and Artificial Neural Networks for Water Quality Index Modeling in the Euphrates River","year":2024,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Anbar","keywords":"Artificial neural network; Index (typography); Environmental science; Water quality; Remote sensing; Computer science; Artificial intelligence; Water resource management; Hydrology (agriculture); Geography; Engineering; Geotechnical engineering; Ecology","score_opus":0.037979952638246495,"score_gpt":0.29228487530336905,"score_spread":0.25430492266512256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395465422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87575096,0.00026301216,0.11886922,0.00018245738,0.00003597479,0.00006525354,0.00017037419,0.00045037313,0.0042123743],"genre_scores_gemma":[0.9818287,0.00010139036,0.016807273,0.000017953404,0.0000068700224,0.000040377174,0.00009906621,0.000012611923,0.0010858127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998541,0.000043148353,0.000011538474,0.000042810207,0.000029830699,0.000018529281],"domain_scores_gemma":[0.9998592,0.000071008544,0.000023473865,0.0000064413416,0.00003395551,0.0000058944133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047462215,0.00039215075,0.00028394914,0.00043520762,0.00023533207,0.0005532338,0.0004963155,0.00048934424,0.0004892372],"category_scores_gemma":[0.0007384986,0.0002709099,0.00047684324,0.00047814366,0.00018545089,0.0004813661,0.00027469813,0.00031399043,0.00009171553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023498249,0.000040916344,0.0029439728,0.00001391815,0.000017716631,0.00004677064,0.000020348398,0.98482704,0.0010309642,0.0002629443,0.00008202728,0.010689879],"study_design_scores_gemma":[0.0000011742404,0.000004409842,0.00039215165,5.8954043e-7,0.0000018359674,0.0000014212648,0.0000033116128,0.99938333,0.00014055213,0.000040294864,0.00002923964,0.0000016155188],"about_ca_topic_score_codex":0.048556175,"about_ca_topic_score_gemma":0.02565954,"teacher_disagreement_score":0.048556175,"about_ca_system_score_codex":0.00085437327,"about_ca_system_score_gemma":0.00072046067,"threshold_uncertainty_score":0.09654713},"labels":[],"label_agreement":null},{"id":"W4396518616","doi":"10.3390/w16091284","title":"Daily Streamflow Forecasting Using Networks of Real-Time Monitoring Stations and Hybrid Machine Learning Methods","year":2024,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakes Environmental (Canada); University of Guelph","funders":"","keywords":"Streamflow; Environmental science; Computer science; Meteorology; Geography; Cartography","score_opus":0.03715052268210813,"score_gpt":0.29813385978391843,"score_spread":0.2609833371018103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396518616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40196568,0.0033046263,0.58378965,0.00075307826,0.00038866873,0.00008769956,0.0015109279,0.0020348632,0.006164771],"genre_scores_gemma":[0.9632574,0.00057882495,0.034171015,0.00006606311,0.000097939155,0.00005473723,0.0007693827,0.000023198962,0.0009813923],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961394,0.00008468213,0.000036587702,0.00012928143,0.000096413314,0.000039095965],"domain_scores_gemma":[0.99947315,0.0002310193,0.00009873569,0.000053671884,0.000120119905,0.000023312436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000912266,0.00092758425,0.0006998929,0.001064342,0.00021561571,0.0008800929,0.001032325,0.00073462294,0.0008571191],"category_scores_gemma":[0.002124401,0.0003854234,0.0007491555,0.0013665024,0.00023699742,0.0015243944,0.00057863194,0.0006992706,0.00023673566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010503978,0.000073516196,0.0065078596,0.000068477006,0.00014588295,0.00006557749,0.000027407119,0.9042424,0.001049421,0.0012404764,0.0008275725,0.08564641],"study_design_scores_gemma":[0.0000014988799,0.0000065362074,0.00048614727,0.0000031913496,0.0000049641503,0.0000027580927,0.0000026364828,0.9990038,0.00012649056,0.00026952167,0.00008966008,0.0000028059487],"about_ca_topic_score_codex":0.015586991,"about_ca_topic_score_gemma":0.0129271345,"teacher_disagreement_score":0.015586991,"about_ca_system_score_codex":0.00078599766,"about_ca_system_score_gemma":0.0006651839,"threshold_uncertainty_score":0.030992568},"labels":[],"label_agreement":null},{"id":"W4396572906","doi":"10.2139/ssrn.4815563","title":"Short-Term Predictions of Transient Shallow Groundwater Levels at a Local Scale Using Data-Driven Models","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Term (time); Transient (computer programming); Groundwater; Scale (ratio); Environmental science; Hydrology (agriculture); Soil science; Geology; Computer science; Geotechnical engineering; Physics; Geography; Cartography","score_opus":0.06651965385611745,"score_gpt":0.2865024021895783,"score_spread":0.21998274833346082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396572906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.951329,0.0001309796,0.04479936,0.00031085606,0.00006440525,0.000014724081,0.00120783,0.00039324604,0.0017496655],"genre_scores_gemma":[0.996995,0.000040230672,0.0020741876,0.000008814964,0.000008325751,0.0000081885155,0.0004362363,0.00001568519,0.0004134222],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99994063,0.00000963772,0.0000043117843,0.000022999133,0.0000102549375,0.000012170284],"domain_scores_gemma":[0.9995111,0.00023297373,0.00005049643,0.000043234828,0.00009844937,0.00006374635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029656469,0.0003509533,0.00042843077,0.0003161619,0.00023727531,0.00074489345,0.00054605055,0.0006838757,0.000890236],"category_scores_gemma":[0.001366803,0.0003172888,0.00035571624,0.0006588161,0.00031875353,0.0009024772,0.0003519561,0.0006636164,0.00019294476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046044788,0.000028750548,0.0040592067,0.000011628331,0.000014181582,0.000024984054,0.000011836121,0.990607,0.00092329737,0.00041347838,0.00027813113,0.00358144],"study_design_scores_gemma":[0.000003384383,0.000004466001,0.000691444,6.9722836e-7,0.0000022867168,0.000001019907,0.000004373527,0.9987956,0.00020025016,0.00026624463,0.000028293345,0.000001931527],"about_ca_topic_score_codex":0.027703762,"about_ca_topic_score_gemma":0.024464473,"teacher_disagreement_score":0.027703762,"about_ca_system_score_codex":0.00089577184,"about_ca_system_score_gemma":0.00076804805,"threshold_uncertainty_score":0.055085003},"labels":[],"label_agreement":null},{"id":"W4396602603","doi":"10.24124/2024/59485","title":"Advancing water quality prediction through integrating machine learning with data augmentation: A case study for First Nations communities in British Columbia","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Machine learning; Resource (disambiguation); Artificial intelligence; Indigenous; Predictive modelling; Manganese; Computer science; Water quality; Test data; Data mining; Materials science; Ecology","score_opus":0.046810675857067975,"score_gpt":0.3287688082064347,"score_spread":0.28195813234936673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396602603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930981,0.00004955817,0.0019648736,0.00048093128,0.00000834484,0.0000862899,0.00023830179,0.00010024123,0.003973422],"genre_scores_gemma":[0.9922083,0.00007385717,0.004174029,0.000059550854,0.0000033450601,0.000030443223,0.00021844209,0.000016369724,0.0032157204],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997552,0.000071178045,0.000008865674,0.000043989912,0.00006683849,0.0000539458],"domain_scores_gemma":[0.9993383,0.0002379698,0.00002913403,0.00004657443,0.0002738911,0.00007399049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004523316,0.0004319268,0.0002756702,0.0003388945,0.0014656411,0.00087615656,0.00078207406,0.00069913757,0.0010552594],"category_scores_gemma":[0.0015623746,0.00017487167,0.00022107971,0.0009138471,0.0005913461,0.00036991056,0.00044599065,0.0008638819,0.00016051001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006850582,0.0023101673,0.2743542,0.0004187094,0.00018642611,0.008201851,0.004418416,0.47610465,0.012128735,0.0031082192,0.013221675,0.20486188],"study_design_scores_gemma":[0.000082998704,0.00030271258,0.12341295,0.000051556355,0.00005510529,0.0002475862,0.009596421,0.84908825,0.007607468,0.0017304812,0.007742284,0.00008220992],"about_ca_topic_score_codex":0.83268195,"about_ca_topic_score_gemma":0.9171092,"teacher_disagreement_score":0.16731805,"about_ca_system_score_codex":0.006173899,"about_ca_system_score_gemma":0.0045729005,"threshold_uncertainty_score":0.3366068},"labels":[],"label_agreement":null},{"id":"W4396900897","doi":"10.5194/hess-2024-111","title":"Data-driven modeling of hydraulic head time series: results and lessons learned from the 2022 groundwater modeling challenge","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Horizon 2020; Canada First Research Excellence Fund","keywords":"Groundwater; Series (stratigraphy); Head (geology); Hydraulic head; Groundwater model; Computer science; Hydrology (agriculture); Environmental science; Engineering; Geology; Groundwater flow; Geotechnical engineering; Aquifer; Geomorphology","score_opus":0.1703569354296154,"score_gpt":0.31721070739415336,"score_spread":0.14685377196453794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396900897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81772405,0.004312712,0.11249354,0.031054541,0.0022283457,0.0002896499,0.016241273,0.007069904,0.008586034],"genre_scores_gemma":[0.91538036,0.00076166686,0.060724694,0.0017688305,0.00030317003,0.00015148954,0.018051708,0.00069282035,0.0021652877],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99700934,0.0016103777,0.000160649,0.0005264183,0.00052143406,0.00017183129],"domain_scores_gemma":[0.9837891,0.0108147245,0.00036700888,0.0013060259,0.0027963293,0.00092691067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00978797,0.0016570962,0.0014419957,0.00057405303,0.0004831534,0.0018188901,0.0021192923,0.0025499358,0.0015381712],"category_scores_gemma":[0.019936021,0.0006043594,0.0019390214,0.000759113,0.00078376953,0.0022383428,0.0015460845,0.0029065015,0.0004880476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030402764,0.00037474438,0.011689112,0.0003073865,0.00028276563,0.00017416915,0.00016442328,0.94381565,0.0010982553,0.0030709028,0.017042829,0.021675711],"study_design_scores_gemma":[0.000042422587,0.00007460506,0.0012927366,0.000020289459,0.000018310953,0.000014166703,0.00007567145,0.9926831,0.0008232154,0.0023077587,0.0026255862,0.000022133849],"about_ca_topic_score_codex":0.0431265,"about_ca_topic_score_gemma":0.030923681,"teacher_disagreement_score":0.0431265,"about_ca_system_score_codex":0.0022481498,"about_ca_system_score_gemma":0.0024851286,"threshold_uncertainty_score":0.08575094},"labels":[],"label_agreement":null},{"id":"W4396966114","doi":"10.1016/j.wroa.2024.100228","title":"Spatiotemporal estimation of groundwater and surface water conditions by integrating deep learning and physics-based watershed models","year":2024,"lang":"en","type":"article","venue":"Water Research X","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Korea Environmental Industry and Technology Institute; National Research Foundation of Korea; Ministry of Science and ICT, South Korea; Ministry of Education, India; Ministry of Environment; Korea Institute of Geoscience and Mineral Resources; National Research Foundation","keywords":"Watershed; Groundwater; Surface water; Environmental science; Hydrology (agriculture); Remote sensing; Computer science; Geology; Machine learning; Environmental engineering; Geotechnical engineering","score_opus":0.047078486757311896,"score_gpt":0.3273579896901047,"score_spread":0.2802795029327928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396966114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40475646,0.00050370203,0.5897977,0.0005579032,0.00006184398,0.00004008973,0.0006385466,0.0013845124,0.0022592428],"genre_scores_gemma":[0.9675067,0.00018100845,0.031414565,0.000053726584,0.000021648311,0.00002406411,0.00034761924,0.000026862022,0.00042373515],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99991083,0.000013523881,0.000007298217,0.0000341972,0.000017930863,0.00001633555],"domain_scores_gemma":[0.99985826,0.000036665395,0.000033071585,0.000020452568,0.000035073557,0.000016497475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002803331,0.00051936106,0.00032533315,0.00058517786,0.0001624403,0.00043960652,0.00082821096,0.00041820502,0.0004157295],"category_scores_gemma":[0.0007568207,0.0003760893,0.0005263908,0.00071411586,0.00030467342,0.0011732649,0.000724842,0.00055651175,0.00007826082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001515251,0.00003407413,0.0056720697,0.000018780305,0.000046424284,0.000035356625,0.000014795193,0.9679032,0.0027725399,0.0009836307,0.00019439858,0.022309547],"study_design_scores_gemma":[0.0000012124732,0.0000017023117,0.00036707884,8.05814e-7,0.0000029030875,0.0000016385654,0.0000019111915,0.99902034,0.00019680665,0.00035311544,0.00005096285,0.0000016099204],"about_ca_topic_score_codex":0.028547501,"about_ca_topic_score_gemma":0.028276622,"teacher_disagreement_score":0.028547501,"about_ca_system_score_codex":0.00089479506,"about_ca_system_score_gemma":0.0010566778,"threshold_uncertainty_score":0.056762636},"labels":[],"label_agreement":null},{"id":"W4398171713","doi":"10.20944/preprints202405.1259.v1","title":"Enhancing Turbidity Modeling in the Mississippi River Using Machine Learning and Sentinel‐2 Remote Sensing Data: A Generalizability Analysis","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Generalizability theory; Turbidity; Environmental science; Remote sensing; Computer science; Geography; Geology; Oceanography; Statistics; Mathematics","score_opus":0.2218239208339587,"score_gpt":0.36560016871114553,"score_spread":0.14377624787718685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398171713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9569517,0.00028890846,0.04002859,0.00035933935,0.000023336119,0.00004816234,0.00023259988,0.00041091396,0.0016563988],"genre_scores_gemma":[0.9840868,0.00014528607,0.014779288,0.000051049894,0.000016276257,0.00001837698,0.0004979718,0.000031751486,0.00037315773],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992261,0.00033614127,0.000033222525,0.00019756994,0.00015064281,0.000056317847],"domain_scores_gemma":[0.9979488,0.0010795991,0.00016856492,0.00024633014,0.00051358185,0.000043154036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004391344,0.00060073927,0.00037856319,0.00081396516,0.0003732643,0.00086385844,0.00042430277,0.0005173886,0.00050949294],"category_scores_gemma":[0.005808659,0.00020974866,0.00093755795,0.000707901,0.0003477608,0.00094001816,0.00075562345,0.0005423532,0.00016359662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036562965,0.0003858421,0.20909928,0.0002241096,0.00059527694,0.0002267536,0.00045683223,0.61340255,0.019427095,0.0010737162,0.0012412572,0.15350161],"study_design_scores_gemma":[0.000011519443,0.00017702422,0.0447267,0.000018471854,0.00010158144,0.000036940695,0.0001875252,0.94770885,0.005638801,0.0005625126,0.0008075907,0.000022404938],"about_ca_topic_score_codex":0.031688288,"about_ca_topic_score_gemma":0.025831614,"teacher_disagreement_score":0.031688288,"about_ca_system_score_codex":0.00062494393,"about_ca_system_score_gemma":0.0007692691,"threshold_uncertainty_score":0.06300765},"labels":[],"label_agreement":null},{"id":"W4398204086","doi":"10.3389/frwa.2024.1378598","title":"Improving monthly precipitation prediction accuracy using machine learning models: a multi-view stacking learning technique","year":2024,"lang":"en","type":"article","venue":"Frontiers in Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Stacking; Machine learning; Artificial intelligence; Computer science; Precipitation; Meteorology; Chemistry; Geography","score_opus":0.03209203658974742,"score_gpt":0.2488303090734869,"score_spread":0.2167382724837395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398204086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095573455,0.0006723297,0.8996102,0.00026056834,0.000114758106,0.00003502736,0.00012208507,0.0018848924,0.0017266525],"genre_scores_gemma":[0.7639644,0.00031764645,0.23383673,0.00011532887,0.00012220484,0.000051249357,0.0004191488,0.00011106406,0.0010622552],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952376,0.00012831419,0.00003177647,0.00010950767,0.00014146554,0.00006521751],"domain_scores_gemma":[0.99925095,0.00024223127,0.0001068883,0.000115279676,0.00024538385,0.00003925165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012829577,0.0011670636,0.0011200886,0.001103035,0.0004334957,0.00086469844,0.0011798145,0.00085743977,0.000927838],"category_scores_gemma":[0.0026216854,0.0004544383,0.0012702014,0.00089856505,0.00024598552,0.001344302,0.00101581,0.0012044184,0.00049760466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001492552,0.00016716555,0.006350973,0.00006574526,0.00022428027,0.00010493106,0.000115139424,0.5876072,0.009212876,0.0017791142,0.0020272261,0.39219612],"study_design_scores_gemma":[0.0000021233734,0.000024159119,0.00039622164,0.0000036326273,0.000014064058,0.000010410556,0.000007250356,0.9978217,0.0011086377,0.00043745452,0.00016921974,0.0000051272687],"about_ca_topic_score_codex":0.0055239364,"about_ca_topic_score_gemma":0.0052516526,"teacher_disagreement_score":0.0055239364,"about_ca_system_score_codex":0.000385466,"about_ca_system_score_gemma":0.00076494925,"threshold_uncertainty_score":0.010983586},"labels":[],"label_agreement":null},{"id":"W4398668721","doi":"10.7910/dvn/gwuike/prypnx","title":"2016_PR_data.tab","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.021082204781995153,"score_gpt":0.23093634990755002,"score_spread":0.20985414512555486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398668721","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005962186,0.000016632926,0.00003535751,0.000029128762,0.00001797423,0.000004638785,0.9988042,0.0003587496,0.00067373895],"genre_scores_gemma":[0.00028821602,0.0000272435,0.00012738178,0.000033902983,0.0000067189553,0.000024004617,0.9986505,0.00013241895,0.0007095627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917823,0.00008818691,0.00011159719,0.00026477667,0.00018867881,0.00016848632],"domain_scores_gemma":[0.998288,0.00034897507,0.00018093144,0.00043772368,0.0005497447,0.00019459745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000856435,0.0023718015,0.0011785973,0.0027356304,0.0006197075,0.0026594023,0.0018780768,0.0014198405,0.20636795],"category_scores_gemma":[0.0040488387,0.00093472074,0.0011815571,0.005325379,0.00037778934,0.0020026793,0.0019709612,0.0015606121,0.26742345],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004582214,0.000015079832,0.00059189193,0.00033403325,0.000018631517,0.000010481879,0.000016524502,0.00023140786,0.000095352385,0.00035478408,0.9964469,0.0018391421],"study_design_scores_gemma":[0.00019981494,0.000016651791,0.003436082,0.00016817842,0.000019019428,0.000030306215,0.000047499103,0.00049121946,0.00038863978,0.0010056476,0.99417007,0.00002681407],"about_ca_topic_score_codex":0.021637566,"about_ca_topic_score_gemma":0.028980127,"teacher_disagreement_score":0.79363203,"about_ca_system_score_codex":0.0013214998,"about_ca_system_score_gemma":0.0017596093,"threshold_uncertainty_score":0.6903696},"labels":[],"label_agreement":null},{"id":"W4399285245","doi":"10.1007/s42452-024-05994-z","title":"Evaluation of the support vector regression (SVR) and the random forest (RF) models accuracy for streamflow prediction under a data-scarce basin in Morocco","year":2024,"lang":"en","type":"article","venue":"Discover Applied Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Fondation OCP; Université Mohammed VI Polytechnique","keywords":"Random forest; Support vector machine; Streamflow; Regression; Decision tree; Predictive modelling; Structural basin; Artificial intelligence; Computer science; Data mining; Drainage basin; Machine learning; Geography; Statistics; Geology; Mathematics; Cartography; Geomorphology","score_opus":0.08851451697431165,"score_gpt":0.3240920655958109,"score_spread":0.23557754862149924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399285245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907997,0.00070679747,0.0063302955,0.000332863,0.000054613403,0.000015630358,0.0005433218,0.00029178706,0.0009250265],"genre_scores_gemma":[0.9973646,0.000081045255,0.0019139346,0.000014918357,0.000010206905,0.000008248864,0.0003737813,0.00000810589,0.0002251749],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946636,0.00021697243,0.00004714305,0.00011291507,0.000074784635,0.00008170228],"domain_scores_gemma":[0.99816656,0.0011686448,0.00014138855,0.00008308634,0.0003526241,0.00008780121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023392797,0.00070681394,0.00064869743,0.0008397968,0.000352059,0.00076347013,0.00059374265,0.0006704301,0.00069156033],"category_scores_gemma":[0.003668169,0.00013664842,0.0006143446,0.0005324833,0.0001952064,0.00048787665,0.00036738074,0.00046799358,0.00019689757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005767991,0.00023220752,0.09014415,0.00020342972,0.00023192423,0.0004142576,0.00013512305,0.82614595,0.0043007815,0.0006562557,0.0024939594,0.074465215],"study_design_scores_gemma":[0.000008984688,0.00006244918,0.013833199,0.00001796923,0.000022701115,0.000014142206,0.00006121922,0.98468864,0.0009188903,0.00008963681,0.00027343485,0.000008651373],"about_ca_topic_score_codex":0.05843809,"about_ca_topic_score_gemma":0.034031436,"teacher_disagreement_score":0.05843809,"about_ca_system_score_codex":0.00093950966,"about_ca_system_score_gemma":0.0008577045,"threshold_uncertainty_score":0.11619592},"labels":[],"label_agreement":null},{"id":"W4399293874","doi":"10.1016/j.jenvman.2024.121259","title":"Robust clustering-based hybrid technique enabling reliable reservoir water quality prediction with uncertainty quantification and spatial analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Sultan Qaboos University","keywords":"Computer science; Cluster analysis; Support vector machine; Data mining; Artificial neural network; Multilayer perceptron; Algorithm; Artificial intelligence; Machine learning","score_opus":0.0231329884382452,"score_gpt":0.23664755619106329,"score_spread":0.21351456775281807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399293874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025937919,0.00016732307,0.97209203,0.000061361,0.000034504672,0.000021234106,0.00009535972,0.00063040765,0.00095976895],"genre_scores_gemma":[0.6560439,0.00017304803,0.3405243,0.000057656194,0.000057834844,0.000077199176,0.0004770624,0.000109021224,0.0024800308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995716,0.00007224252,0.000025400512,0.000104030805,0.00018377675,0.00004293293],"domain_scores_gemma":[0.99937576,0.00018892465,0.00006435001,0.00007552472,0.00027494744,0.000020516074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005248119,0.00056926947,0.0006167276,0.0011272485,0.00038340015,0.000655428,0.0009825967,0.0006233553,0.0008987213],"category_scores_gemma":[0.0014012761,0.00032928016,0.0007466161,0.0013552958,0.00023315253,0.0007603354,0.0007285328,0.00053167716,0.00034796327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028906655,0.00013696768,0.002474479,0.00014327586,0.00024241142,0.00013200751,0.00011636741,0.55513334,0.057646483,0.0048164944,0.0031736642,0.37569553],"study_design_scores_gemma":[0.0000023145728,0.000012032154,0.0005118208,0.0000019200838,0.000008871286,0.000014194103,0.000005882734,0.99632144,0.0024324125,0.0004472558,0.000233296,0.000008534362],"about_ca_topic_score_codex":0.007137107,"about_ca_topic_score_gemma":0.008034377,"teacher_disagreement_score":0.007137107,"about_ca_system_score_codex":0.00037038553,"about_ca_system_score_gemma":0.0007086806,"threshold_uncertainty_score":0.014191151},"labels":[],"label_agreement":null},{"id":"W4399316221","doi":"10.1016/j.engappai.2024.108744","title":"Hybrid machine learning system based on multivariate data decomposition and feature selection for improved multitemporal evapotranspiration forecasting","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"Natural Resources Conservation Service; U.S. Department of Agriculture","keywords":"Computer science; Feature selection; Evapotranspiration; Multivariate statistics; Artificial intelligence; Machine learning; Selection (genetic algorithm); Decomposition; Data mining; Feature (linguistics); Pattern recognition (psychology)","score_opus":0.03889269337246543,"score_gpt":0.2869871289383238,"score_spread":0.24809443556585836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399316221","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10315441,0.0005284341,0.89195657,0.00018309054,0.00015209458,0.00006358047,0.00018606392,0.0020625421,0.0017132685],"genre_scores_gemma":[0.8348427,0.00023412085,0.1618549,0.00008805241,0.000083972685,0.0001435507,0.0003932245,0.00006321645,0.0022961993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969816,0.00005226733,0.000031641994,0.00008461774,0.00008783065,0.0000454206],"domain_scores_gemma":[0.99974376,0.000076004566,0.000025131381,0.000023129005,0.00011796474,0.000013933572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055279315,0.0005237889,0.0010421631,0.00068972824,0.00042876252,0.00061387516,0.0005587182,0.00050461316,0.0015579618],"category_scores_gemma":[0.00078430044,0.00029637106,0.00068528333,0.00088166416,0.00012951742,0.00073139113,0.00037492946,0.0005180632,0.0003486453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049920176,0.00042942454,0.0038804142,0.00013826948,0.00026349572,0.000174837,0.00007698365,0.31085056,0.047735214,0.0016806256,0.0039007056,0.63037026],"study_design_scores_gemma":[0.000008639801,0.00003549904,0.0009703024,0.0000024928993,0.000020616593,0.000018967863,0.0000034654206,0.9965244,0.001947301,0.00018852868,0.00027160713,0.000008039568],"about_ca_topic_score_codex":0.005401523,"about_ca_topic_score_gemma":0.005112209,"teacher_disagreement_score":0.005401523,"about_ca_system_score_codex":0.00033589537,"about_ca_system_score_gemma":0.0006251489,"threshold_uncertainty_score":0.010740161},"labels":[],"label_agreement":null},{"id":"W4399361088","doi":"10.37798/2024732502","title":"Regression Learner Application Model-Based Short-Term Load Forecasting for Mascouche (Quebec, Canada)","year":2024,"lang":"en","type":"article","venue":"Journal of Energy - Energija","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Term (time); Computer science; Regression analysis; Econometrics; Regression; Statistics; Artificial intelligence; Machine learning; Mathematics","score_opus":0.02444436779833319,"score_gpt":0.249596026242515,"score_spread":0.2251516584441818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399361088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7275754,0.0037338743,0.11034532,0.0060322313,0.0005454848,0.0005496519,0.07897462,0.022288878,0.0499546],"genre_scores_gemma":[0.894006,0.0010120878,0.03715409,0.00021361293,0.000058268346,0.000120974204,0.0398016,0.0003342536,0.027299125],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976677,0.000026642025,0.000011608731,0.000060170973,0.00007915248,0.00005573153],"domain_scores_gemma":[0.9988135,0.00018595484,0.00003884399,0.000062438485,0.0008157104,0.00008354332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065287994,0.00067545776,0.0003925382,0.0008847627,0.0008617271,0.0011157984,0.0011483693,0.00047931503,0.0062288316],"category_scores_gemma":[0.0023629789,0.00019558123,0.00034624335,0.0013663332,0.0001798072,0.000522748,0.00033880805,0.00069846195,0.0014791321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004988488,0.00043134028,0.07259524,0.00026411447,0.00019774128,0.00040056038,0.0002194784,0.4541605,0.0043099015,0.0025470601,0.15163636,0.31273898],"study_design_scores_gemma":[0.000028523818,0.000023678082,0.021744965,0.000019906074,0.000020504105,0.000017329881,0.00013842667,0.96386325,0.0013580895,0.00028892723,0.012469391,0.000027076623],"about_ca_topic_score_codex":0.98539793,"about_ca_topic_score_gemma":0.9842009,"teacher_disagreement_score":0.014602065,"about_ca_system_score_codex":0.009363331,"about_ca_system_score_gemma":0.011870492,"threshold_uncertainty_score":0.06793612},"labels":[],"label_agreement":null},{"id":"W4399369766","doi":"10.1016/j.jenvman.2024.121378","title":"Ensemble machine learning using hydrometeorological information to improve modeling of quality parameter of raw water supplying treatment plants","year":2024,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Water quality; Raw water; Turbidity; Environmental science; Decision tree; Boosting (machine learning); Computer science; Machine learning; Environmental engineering; Ecology","score_opus":0.029654397412055104,"score_gpt":0.26268527639567324,"score_spread":0.23303087898361813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399369766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5063623,0.00065316726,0.48985183,0.00035388183,0.000077955636,0.000046668032,0.00023600525,0.00072311785,0.0016950839],"genre_scores_gemma":[0.9792427,0.00012442567,0.019739415,0.000044782304,0.00002433834,0.00003114435,0.00017682415,0.000017292206,0.00059919944],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973744,0.0000980008,0.000015279009,0.0000615781,0.000046536417,0.000041238847],"domain_scores_gemma":[0.9990633,0.0005522275,0.0000868165,0.0000537338,0.00020189233,0.00004200134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014312166,0.00065236096,0.0010586894,0.00067185034,0.00029022558,0.00061753165,0.00067765877,0.0007534674,0.0005078304],"category_scores_gemma":[0.0021974777,0.000398576,0.0009716816,0.0005202559,0.00020921536,0.0006002523,0.00044809366,0.0009121855,0.00011419074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002154168,0.000029567684,0.002030506,0.0000067663836,0.000035276757,0.000015239659,0.000009640541,0.9869413,0.00049765996,0.00016648478,0.00012497885,0.010120976],"study_design_scores_gemma":[4.7208118e-7,0.0000027828776,0.0001399204,4.4176628e-7,0.0000012174942,5.194815e-7,4.5875134e-7,0.99974984,0.000038983697,0.000053862284,0.000010533777,8.590488e-7],"about_ca_topic_score_codex":0.014274424,"about_ca_topic_score_gemma":0.008888675,"teacher_disagreement_score":0.014274424,"about_ca_system_score_codex":0.00061445695,"about_ca_system_score_gemma":0.0007687924,"threshold_uncertainty_score":0.028382659},"labels":[],"label_agreement":null},{"id":"W4399388696","doi":"10.1016/j.gsd.2024.101213","title":"Enhancing groundwater level prediction accuracy using interpolation techniques in deep learning models","year":2024,"lang":"en","type":"article","venue":"Groundwater for Sustainable Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Prince Edward Island","funders":"","keywords":"Groundwater; Interpolation (computer graphics); Computer science; Environmental science; Artificial intelligence; Machine learning; Geology; Geotechnical engineering","score_opus":0.03886062812670319,"score_gpt":0.2637255772579898,"score_spread":0.2248649491312866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399388696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18923245,0.00034290183,0.8049938,0.0004007824,0.00011572424,0.000017534008,0.00026216157,0.0015274464,0.0031071608],"genre_scores_gemma":[0.9300505,0.00016025263,0.06820698,0.000054807017,0.000028313527,0.000013965269,0.0001918699,0.00005383673,0.0012395267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998785,0.000026841693,0.000008564014,0.000027361444,0.000040396306,0.00001825337],"domain_scores_gemma":[0.9992322,0.00039760253,0.00006487645,0.000105867344,0.00017878112,0.000020652593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065143616,0.00035539203,0.00032315325,0.00039285774,0.00018076022,0.00053868396,0.00066537503,0.0005525719,0.0014144387],"category_scores_gemma":[0.002877159,0.00022956931,0.00029479826,0.0006124452,0.00021913886,0.0009615137,0.0005229376,0.00095111685,0.00028534516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011744363,0.000093549155,0.0034772588,0.00004563102,0.000031764153,0.000027608916,0.000033863107,0.83855027,0.0070055197,0.0025367003,0.0008237727,0.14725658],"study_design_scores_gemma":[0.0000015446328,0.0000067014516,0.00015962066,0.0000018971425,0.000002221952,0.000002136922,0.0000015621177,0.998058,0.0011260461,0.0005432122,0.00009530439,0.0000016200262],"about_ca_topic_score_codex":0.0090491,"about_ca_topic_score_gemma":0.010120944,"teacher_disagreement_score":0.0090491,"about_ca_system_score_codex":0.0004287484,"about_ca_system_score_gemma":0.0005868191,"threshold_uncertainty_score":0.017992854},"labels":[],"label_agreement":null},{"id":"W4399505898","doi":"10.1007/s11269-024-03907-8","title":"A New Data-Driven Model to Predict Monthly Runoff at Watershed Scale: Insights from Deep Learning Method Applied in Data-Driven Model","year":2024,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Hebei Province","keywords":"Watershed; Scale (ratio); Hydrogeology; Surface runoff; Hydrological modelling; Hydrology (agriculture); Environmental science; Data mining; Computer science; Machine learning; Geology; Climatology; Cartography; Geography; Geotechnical engineering; Ecology","score_opus":0.035478637529650775,"score_gpt":0.259951244124569,"score_spread":0.22447260659491822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399505898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05724865,0.00017311005,0.9380433,0.0007738642,0.0001350491,0.000042549018,0.00043932442,0.0006416343,0.0025024682],"genre_scores_gemma":[0.8599347,0.00020265908,0.13211507,0.00030866388,0.0000842899,0.00015109904,0.0007578658,0.00012864903,0.0063170455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99989593,0.00001722927,0.0000068051345,0.00003480916,0.000030119416,0.00001510524],"domain_scores_gemma":[0.999665,0.00013142452,0.000028866885,0.000027207663,0.0001204441,0.000027036844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052109855,0.00041424978,0.0005152576,0.00028678516,0.00025559182,0.0007562022,0.0011669708,0.000995039,0.0011959797],"category_scores_gemma":[0.0012537612,0.00037193834,0.0004155498,0.0004119643,0.00035480162,0.001007011,0.0006350235,0.0013562901,0.0002411245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013329357,0.00002693467,0.00061184407,0.000010322037,0.000018869752,0.000016470109,0.0000100006655,0.9826078,0.00096071337,0.002400392,0.00056162296,0.012761773],"study_design_scores_gemma":[6.62699e-7,0.0000011751723,0.000023077817,3.5467386e-7,7.0904923e-7,7.545543e-7,2.5570893e-7,0.999589,0.00006478954,0.0002682058,0.000050271017,6.619504e-7],"about_ca_topic_score_codex":0.015573152,"about_ca_topic_score_gemma":0.019509304,"teacher_disagreement_score":0.015573152,"about_ca_system_score_codex":0.0007519567,"about_ca_system_score_gemma":0.0014024149,"threshold_uncertainty_score":0.03096497},"labels":[],"label_agreement":null},{"id":"W4399620115","doi":"10.1016/j.psep.2024.06.050","title":"Development of forecasting of monthly SAR time series in river systems: A multivariate data decomposition-based hybrid approach","year":2024,"lang":"en","type":"article","venue":"Process Safety and Environmental Protection","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Multivariate statistics; Series (stratigraphy); Time series; Decomposition; Computer science; Data mining; Climatology; Machine learning; Geology","score_opus":0.02933578752791406,"score_gpt":0.23381737777033906,"score_spread":0.20448159024242502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399620115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03292657,0.00009427513,0.9656054,0.000052355746,0.000016066475,0.000019523915,0.00010431017,0.0003948619,0.0007866634],"genre_scores_gemma":[0.57453907,0.0002473037,0.42253014,0.000036142806,0.000040743547,0.00013413119,0.0005622645,0.00011448922,0.0017957357],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987185,0.000033309814,0.000010343895,0.00003304284,0.0000331059,0.000018306539],"domain_scores_gemma":[0.99962676,0.00015887283,0.000033507156,0.000026003605,0.00013174626,0.000023037039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004914133,0.00055113324,0.00048326552,0.0007802321,0.00017713217,0.0004860791,0.00043088064,0.00041018988,0.0011892448],"category_scores_gemma":[0.0011614602,0.00035311765,0.0007300176,0.00067431,0.00012460594,0.0005517185,0.00034000463,0.00057920004,0.0003147703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004971759,0.00005308718,0.0017288864,0.000054992903,0.00007326135,0.00004619302,0.0000389602,0.81363297,0.00916157,0.0020046197,0.00068267813,0.17247313],"study_design_scores_gemma":[8.890981e-7,0.000003839305,0.00016510599,9.27659e-7,0.000002956507,0.000002122246,0.0000022204963,0.99934083,0.0002598696,0.0001473764,0.00007234847,0.0000014170371],"about_ca_topic_score_codex":0.008616505,"about_ca_topic_score_gemma":0.0063586216,"teacher_disagreement_score":0.008616505,"about_ca_system_score_codex":0.00026498488,"about_ca_system_score_gemma":0.0006199512,"threshold_uncertainty_score":0.0171327},"labels":[],"label_agreement":null},{"id":"W4399654926","doi":"10.54097/j4mg8b52","title":"Big data climate prediction model based on linear regression","year":2024,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Climate change; Longitude; Climatology; Linear regression; Latitude; Sea surface temperature; Environmental science; Trend analysis; Dimension (graph theory); Time series; Government (linguistics); Global temperature; Meteorology; Global warming; Geography; Statistics; Geology; Mathematics; Oceanography; Geodesy","score_opus":0.025944135110001494,"score_gpt":0.2497408759502438,"score_spread":0.22379674084024231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399654926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19517596,0.0016930791,0.7688637,0.005071986,0.0005448233,0.0001354609,0.004641796,0.0048245755,0.019048702],"genre_scores_gemma":[0.9556054,0.00085647235,0.030071834,0.00019925546,0.00018407672,0.0001683848,0.001846641,0.00010916404,0.01095867],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999445,0.0001417704,0.000028329216,0.0001913456,0.00009480058,0.000098694494],"domain_scores_gemma":[0.99903584,0.0004582697,0.00009609116,0.000044162138,0.00031572138,0.000049878112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010646862,0.0007020968,0.0007072826,0.00067427463,0.0006482781,0.001374597,0.0016174103,0.00073597394,0.0031574788],"category_scores_gemma":[0.002732627,0.00041191347,0.0006641181,0.0013474784,0.00046694308,0.0012730446,0.0006927553,0.0015517827,0.00082380755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056714183,0.000037194248,0.005370664,0.00004105211,0.00006045991,0.00008145312,0.00005345164,0.96263176,0.00028593867,0.006121532,0.0032928672,0.02196694],"study_design_scores_gemma":[0.0000019826239,0.0000031340467,0.00026288204,0.0000018387038,0.0000036639635,0.0000028754446,0.000004086028,0.9985171,0.000029846577,0.0009196861,0.0002502147,0.0000027003568],"about_ca_topic_score_codex":0.17261656,"about_ca_topic_score_gemma":0.08353277,"teacher_disagreement_score":0.17261656,"about_ca_system_score_codex":0.0015748282,"about_ca_system_score_gemma":0.0019380482,"threshold_uncertainty_score":0.34322363},"labels":[],"label_agreement":null},{"id":"W4399772806","doi":"10.1016/j.envpol.2024.124395","title":"Exploring spatiotemporal patterns of algal cell density in lake Dianchi with explainable machine learning","year":2024,"lang":"en","type":"article","venue":"Environmental Pollution","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Henan Provincial Science and Technology Research Project; Science and Technology Department, Henan Province; Natural Science Foundation of Henan Province; National Natural Science Foundation of China","keywords":"Water quality; Environmental science; Algal bloom; Computer science; Ecology; Phytoplankton; Biology; Nutrient","score_opus":0.022706812258821894,"score_gpt":0.18818684506542294,"score_spread":0.16548003280660104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399772806","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99532855,0.00004577517,0.0038660574,0.00017900112,0.0000036034774,0.0000038478147,0.00020571727,0.000040951436,0.0003264873],"genre_scores_gemma":[0.99843794,0.000013750617,0.0012683511,0.0000038253374,0.0000024904673,0.0000039500915,0.00013946334,0.0000022069219,0.00012806263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9999602,0.0000092423825,0.0000021474013,0.00001385201,0.000004365634,0.000010176582],"domain_scores_gemma":[0.9998004,0.000111913156,0.00003180995,0.00001410846,0.000023227534,0.000018600094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021851753,0.00018429119,0.0002314228,0.00047943773,0.0002866064,0.00039837896,0.00053878815,0.0003950587,0.0008633881],"category_scores_gemma":[0.00086619845,0.0002051117,0.0003337328,0.0005384445,0.0001932434,0.00043494714,0.00031556864,0.0003219966,0.00006114066],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022506692,0.00013796403,0.22836727,0.000067750865,0.00017422585,0.0001480127,0.00020771602,0.7367275,0.0060122567,0.002073124,0.00071351096,0.02514565],"study_design_scores_gemma":[0.0000039139063,0.0000053337767,0.026839502,0.0000013286268,0.000005811096,0.000003967353,0.00003044811,0.97247654,0.000170914,0.00038553408,0.000072499,0.0000042489023],"about_ca_topic_score_codex":0.10652682,"about_ca_topic_score_gemma":0.09751941,"teacher_disagreement_score":0.10652682,"about_ca_system_score_codex":0.0012537003,"about_ca_system_score_gemma":0.0006666321,"threshold_uncertainty_score":0.21181351},"labels":[],"label_agreement":null},{"id":"W4400174213","doi":"10.2172/2377932","title":"Using Knowledge-Guided Machine Learning To Assess Patterns of Areal Change in Waterbodies across the Contiguous United States","year":2024,"lang":"en","type":"report","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Los Alamos National Laboratory; Laboratory Directed Research and Development; Natural Sciences and Engineering Research Council of Canada; McGill University; National Science Foundation","keywords":"Proxy (statistics); Physical geography; Machine learning; Geography; Cartography; Environmental science; Computer science","score_opus":0.24125374423143262,"score_gpt":0.4060361502592818,"score_spread":0.1647824060278492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400174213","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99393976,0.000067514855,0.0036429632,0.0001704038,0.000004361114,0.000027596545,0.0010231985,0.000099712386,0.0010245849],"genre_scores_gemma":[0.99458545,0.00003229937,0.0038093352,0.00002349072,0.0000049915184,0.000016021251,0.0013837958,0.0000048724223,0.00013982282],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996408,0.00013997362,0.000031332303,0.00009035032,0.000060533857,0.0000369276],"domain_scores_gemma":[0.998102,0.0010552523,0.00034426976,0.00017515913,0.0002441997,0.000079216785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011200833,0.00025508934,0.00019615458,0.0016097655,0.00025832467,0.00047466555,0.00030932797,0.00031138113,0.0004721862],"category_scores_gemma":[0.0054254537,0.0001068949,0.00030719023,0.0012040794,0.00029173528,0.0005996687,0.0005321778,0.00027581427,0.00011637953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065845285,0.00015926332,0.89287037,0.000023203249,0.00013658548,0.00004751717,0.00016678672,0.06285995,0.00047454788,0.00023997528,0.0011692947,0.0417867],"study_design_scores_gemma":[0.000013962554,0.00008459173,0.4859699,0.000020127065,0.00004447781,0.000026400323,0.00041281068,0.5107408,0.000714389,0.0012129826,0.0007427489,0.0000169172],"about_ca_topic_score_codex":0.10328576,"about_ca_topic_score_gemma":0.18425871,"teacher_disagreement_score":0.10328576,"about_ca_system_score_codex":0.0010081197,"about_ca_system_score_gemma":0.00067249604,"threshold_uncertainty_score":0.20536911},"labels":[],"label_agreement":null},{"id":"W4400212361","doi":"10.1080/02626667.2024.2374868","title":"Ensemble learning of decomposition-based machine learning models for multistep-ahead daily streamflow forecasting in northwest China","year":2024,"lang":"en","type":"article","venue":"Hydrological Sciences Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; United Nations University Institute for Water, Environment, and Health; Université du Québec en Abitibi-Témiscamingue; Université du Québec à Montréal","funders":"National Natural Science Foundation of China","keywords":"Streamflow; Decomposition; Ensemble learning; China; Artificial intelligence; Computer science; Machine learning; Ensemble forecasting; Geography; Chemistry; Cartography","score_opus":0.04738448630195611,"score_gpt":0.285077824144489,"score_spread":0.2376933378425329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400212361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71817935,0.0005597323,0.2787034,0.0003348734,0.000056207125,0.000026602402,0.00022640933,0.00028369858,0.0016295969],"genre_scores_gemma":[0.98901564,0.00012852397,0.010210586,0.000012195618,0.000009412636,0.000017143262,0.00016691253,0.000008409253,0.00043112217],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980813,0.000067763256,0.000013072519,0.00004135488,0.000037658676,0.000031943808],"domain_scores_gemma":[0.9995846,0.00020749927,0.00004262608,0.000029761857,0.000105311374,0.000030138626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012662702,0.0005413143,0.000641805,0.00053455046,0.00030284026,0.000454007,0.00048511746,0.0003500411,0.00027127098],"category_scores_gemma":[0.0016791152,0.00025303185,0.0005696616,0.00046183163,0.0001663037,0.00057613273,0.00043897398,0.0006091708,0.00004881959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002067549,0.000017596478,0.003153991,0.000008506749,0.00003928611,0.000016672268,0.000017543129,0.97583085,0.0004462962,0.00046687215,0.0001936476,0.01978813],"study_design_scores_gemma":[4.521437e-7,0.0000021424619,0.00025100837,3.8339576e-7,0.0000018522073,4.6202183e-7,0.0000013913358,0.99956006,0.000043784632,0.000119626064,0.000017902536,8.973567e-7],"about_ca_topic_score_codex":0.044564936,"about_ca_topic_score_gemma":0.033796195,"teacher_disagreement_score":0.044564936,"about_ca_system_score_codex":0.0007968928,"about_ca_system_score_gemma":0.0010114753,"threshold_uncertainty_score":0.08861107},"labels":[],"label_agreement":null},{"id":"W4400262525","doi":"10.1038/s41598-024-65837-0","title":"Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Mean squared error; Artificial intelligence; Convolutional neural network; Computer science; Feature selection; Perceptron; Artificial neural network; Feature (linguistics); Multilayer perceptron; Pattern recognition (psychology); Machine learning; Algorithm; Mathematics; Statistics","score_opus":0.0336701325315195,"score_gpt":0.26820072681493534,"score_spread":0.23453059428341583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400262525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68527496,0.0012731047,0.307216,0.0004031915,0.00020960093,0.000047216072,0.00046786512,0.0018159284,0.0032920933],"genre_scores_gemma":[0.98204076,0.00016904743,0.016246177,0.00004165914,0.000016736014,0.000028156548,0.0002696426,0.00001797726,0.0011699109],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990296,0.000011734721,0.000008257234,0.000037850023,0.000020950087,0.000018218996],"domain_scores_gemma":[0.9998864,0.000041487212,0.000019274808,0.0000058551864,0.000039382376,0.0000076014494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027485035,0.0005862405,0.0005604786,0.00035697946,0.00022599306,0.00042882733,0.00053977926,0.0005396797,0.00043093815],"category_scores_gemma":[0.00046070557,0.0003454514,0.0007121307,0.00043650935,0.00016375331,0.00046543044,0.00025754166,0.0005467432,0.00012832436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001153933,0.000087967106,0.005415792,0.00006020534,0.000082221435,0.00014785302,0.000038618015,0.930056,0.00820746,0.00033849588,0.0007979393,0.05465207],"study_design_scores_gemma":[0.0000021250323,0.000009722712,0.00060917635,0.0000016149673,0.0000043490572,0.000004093365,0.0000020662385,0.99875355,0.00049191195,0.00006179061,0.000056795507,0.000002809069],"about_ca_topic_score_codex":0.024661781,"about_ca_topic_score_gemma":0.022256577,"teacher_disagreement_score":0.024661781,"about_ca_system_score_codex":0.00052300416,"about_ca_system_score_gemma":0.00056344544,"threshold_uncertainty_score":0.049036443},"labels":[],"label_agreement":null},{"id":"W4400270618","doi":"10.1016/j.jwpe.2024.105696","title":"Global research landscape on coagulation-flocculation for wastewater treatment: A 2000–2023 bibliometric analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Water Process Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Teknologi Malaysia; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Jiangsu Province; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; National Natural Science Foundation of China; Conselho Nacional de Desenvolvimento Científico e Tecnológico; China Postdoctoral Science Foundation; Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"China; Flocculation; Web of science; Publishing; Sewage treatment; Citation; Bibliometrics; Wastewater; Environmental science; Engineering; Environmental resource management; Library science; Political science; Environmental engineering; Computer science","score_opus":0.04645153116612354,"score_gpt":0.3343852425333033,"score_spread":0.28793371136717977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400270618","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40676335,0.454963,0.0029552758,0.020741906,0.0006188472,0.00012266883,0.07452933,0.0004230277,0.038882677],"genre_scores_gemma":[0.76123524,0.18552177,0.0039872616,0.001481217,0.0007831521,0.000112820206,0.043535057,0.000087192006,0.0032563382],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99572855,0.0007578758,0.0010216562,0.000564083,0.0015940133,0.0003337848],"domain_scores_gemma":[0.97173506,0.011420685,0.0066206176,0.0010859768,0.0081017,0.0010359553],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.005621596,0.0006424087,0.001152043,0.0770045,0.0007271147,0.0048778285,0.0005159028,0.0009406467,0.0030314154],"category_scores_gemma":[0.017926728,0.0002667898,0.0016264266,0.17979275,0.0009551352,0.0036468357,0.0017876024,0.0006062066,0.00062558154],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061723404,0.00014874249,0.276228,0.019255383,0.0027109212,0.0006249159,0.0024144417,0.004551444,0.003543409,0.020714577,0.049021125,0.62016994],"study_design_scores_gemma":[0.000025552541,0.000109289576,0.80839187,0.004529785,0.0014629423,0.000547382,0.0017862443,0.0020000602,0.0010820702,0.002754885,0.1772397,0.000070188085],"about_ca_topic_score_codex":0.02014712,"about_ca_topic_score_gemma":0.025951734,"teacher_disagreement_score":0.9229955,"about_ca_system_score_codex":0.0033029076,"about_ca_system_score_gemma":0.0056541283,"threshold_uncertainty_score":0.040059686},"labels":[],"label_agreement":null},{"id":"W4400475696","doi":"10.3389/faquc.2024.1365123","title":"Forecasting ocean hypoxia in salmonid fish farms","year":2024,"lang":"en","type":"article","venue":"Frontiers in Aquaculture","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Vector Institute; Dalhousie University","funders":"Fisheries Research and Development Corporation; Australian Government","keywords":"Hypoxia (environmental); Fishery; Environmental science; Fish kill; Leverage (statistics); Probabilistic logic; Environmental resource management; Computer science; Ecology; Machine learning; Biology; Oxygen; Artificial intelligence","score_opus":0.016111440545853478,"score_gpt":0.22575447727248965,"score_spread":0.20964303672663617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400475696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9687293,0.00010116897,0.028941093,0.00025764722,0.000016261969,0.000032594005,0.0004065644,0.00021545758,0.0012998142],"genre_scores_gemma":[0.9956215,0.00002931974,0.0038662588,0.000012900568,0.0000055487567,0.000007957388,0.00015227667,0.0000030209437,0.00030118623],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998927,0.000022842314,0.000007360601,0.000039752347,0.000014995291,0.00002225286],"domain_scores_gemma":[0.9992649,0.00041026092,0.00011058542,0.000023021279,0.00013753511,0.000053709235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005991554,0.00035810977,0.00028938675,0.00046204365,0.00023896398,0.00040748666,0.00051278254,0.00036706636,0.0008991864],"category_scores_gemma":[0.0015374633,0.00016820774,0.00024165981,0.00032638694,0.00020919002,0.00038803468,0.00029385093,0.0002704681,0.000097568016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039728864,0.000029618064,0.052442268,0.000011211044,0.000018057599,0.000041601277,0.000017419368,0.93627006,0.0005630991,0.0001476392,0.0002423169,0.010176973],"study_design_scores_gemma":[0.0000028412583,0.000013116537,0.008104261,0.0000024566139,0.0000037628854,0.0000037106538,0.000018015575,0.9914533,0.00013227918,0.00020743386,0.000056604433,0.0000022589966],"about_ca_topic_score_codex":0.10742516,"about_ca_topic_score_gemma":0.08060394,"teacher_disagreement_score":0.10742516,"about_ca_system_score_codex":0.0009748766,"about_ca_system_score_gemma":0.000749844,"threshold_uncertainty_score":0.21359974},"labels":[],"label_agreement":null},{"id":"W4400575142","doi":"10.3390/limnolrev24030013","title":"Design and Implementation of a Deep Learning Model and Stochastic Model for the Forecasting of the Monthly Lake Water Level","year":2024,"lang":"en","type":"article","venue":"Limnological Review","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Econometrics; Environmental science; Meteorology; Mathematics; Geography","score_opus":0.12562478371006305,"score_gpt":0.31146654592636097,"score_spread":0.18584176221629792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400575142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05752688,0.00013275798,0.9367758,0.00029136718,0.000070349524,0.00018411064,0.0002262031,0.0011699521,0.0036225647],"genre_scores_gemma":[0.8500102,0.00014014484,0.14529642,0.0000923318,0.000022870467,0.0004986771,0.00045079185,0.00004604022,0.0034424718],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998042,0.000022820977,0.0000146323455,0.00005755733,0.000058583217,0.00004219816],"domain_scores_gemma":[0.9997228,0.0000594801,0.000038506732,0.000017910676,0.00013614289,0.00002521959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005633987,0.00067772204,0.00045730092,0.00036396342,0.00038636825,0.000625974,0.0011588257,0.0009239132,0.001649421],"category_scores_gemma":[0.0007259886,0.00043774335,0.0006398448,0.00027154165,0.0003209815,0.0006420234,0.0006227885,0.0011693899,0.00032805715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003953888,0.000054370274,0.0015331558,0.00003313148,0.000021346601,0.000046188008,0.000018651073,0.9738341,0.0034122283,0.0016744038,0.00040658726,0.01892629],"study_design_scores_gemma":[0.0000031769503,0.000010967834,0.00009761354,0.0000013876738,0.0000032469063,0.0000020387508,0.000001772296,0.9989172,0.00068148,0.00014369091,0.00013527996,0.0000021847525],"about_ca_topic_score_codex":0.03130754,"about_ca_topic_score_gemma":0.019108653,"teacher_disagreement_score":0.03130754,"about_ca_system_score_codex":0.0010595961,"about_ca_system_score_gemma":0.0029460646,"threshold_uncertainty_score":0.062250614},"labels":[],"label_agreement":null},{"id":"W4400685436","doi":"10.5194/hess-2024-169-rc2","title":"Comment on hess-2024-169","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"","keywords":"Computer science","score_opus":0.054781337794397866,"score_gpt":0.31305444993981,"score_spread":0.25827311214541215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400685436","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011397519,0.0021701502,0.0016795645,0.3686407,0.25865754,0.000565993,0.06299156,0.004908098,0.2992467],"genre_scores_gemma":[0.014424005,0.0024592585,0.0018181184,0.16736394,0.049724482,0.00069311087,0.019621972,0.0023397226,0.74155545],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979138,0.00017733479,0.0001392088,0.00018112149,0.0013443943,0.00024417718],"domain_scores_gemma":[0.993032,0.0014345833,0.0002926456,0.00061925844,0.0042414833,0.00038007868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018288568,0.0008105399,0.00091783184,0.0017038843,0.001608272,0.0042751567,0.0018896951,0.009013449,0.19209597],"category_scores_gemma":[0.015481116,0.00040600065,0.0010287993,0.0025898076,0.0009756865,0.0028984204,0.0015544913,0.005636582,0.11015091],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012688582,0.000002113949,0.000033254786,0.000036536374,0.0000012786361,0.00002456991,0.000004856028,0.00003340061,0.000038206224,0.0008476854,0.99717253,0.0017928812],"study_design_scores_gemma":[0.00001004639,0.000003422849,0.00042186407,0.000040299583,0.0000016935575,0.000009466683,0.00001976725,0.00007067646,0.00012633264,0.000621384,0.9986657,0.000009339899],"about_ca_topic_score_codex":0.042045254,"about_ca_topic_score_gemma":0.036663942,"teacher_disagreement_score":0.19209597,"about_ca_system_score_codex":0.002658091,"about_ca_system_score_gemma":0.004258603,"threshold_uncertainty_score":0.64262503},"labels":[],"label_agreement":null},{"id":"W4400782410","doi":"10.1029/2023ea003473","title":"Multi‐Model Machine Learning Approach Accurately Predicts Lake Dissolved Oxygen With Multiple Environmental Inputs","year":2024,"lang":"en","type":"article","venue":"Earth and Space Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"Svenska Forskningsrådet Formas","keywords":"Computer science; Artificial intelligence; Environmental science; Oxygen; Machine learning; Chemistry","score_opus":0.022600931353399852,"score_gpt":0.22507823946584854,"score_spread":0.20247730811244868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400782410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8512074,0.00028154056,0.14389242,0.00030061853,0.00006732974,0.0000548056,0.00031017052,0.0014474539,0.0024381448],"genre_scores_gemma":[0.9865203,0.000030730127,0.012412856,0.000033226046,0.000008501541,0.000048118505,0.00016053076,0.000018610841,0.00076728413],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998565,0.000032278203,0.000009810499,0.000055025648,0.000020105566,0.000026279758],"domain_scores_gemma":[0.99964285,0.00018585577,0.00003380085,0.00002180768,0.000089834815,0.000025776082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005700285,0.0010238977,0.00055394345,0.000459733,0.0003866352,0.00076364545,0.00078018155,0.0010911993,0.0008961936],"category_scores_gemma":[0.0009163892,0.00056747306,0.0009616695,0.00023791142,0.00024205806,0.00085087446,0.0005191376,0.00091168203,0.00023979224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006065171,0.00006032555,0.0029171866,0.000015880203,0.000053094434,0.000023184139,0.00001768054,0.98452157,0.0022069465,0.0001338299,0.00012389301,0.009865732],"study_design_scores_gemma":[0.0000017278505,0.000008583703,0.00016423098,5.269244e-7,0.000002391785,8.57604e-7,0.0000010492444,0.9995677,0.000205042,0.000032848264,0.000013527558,0.0000014824683],"about_ca_topic_score_codex":0.023501687,"about_ca_topic_score_gemma":0.018809173,"teacher_disagreement_score":0.023501687,"about_ca_system_score_codex":0.0011242668,"about_ca_system_score_gemma":0.00133222,"threshold_uncertainty_score":0.046729803},"labels":[],"label_agreement":null},{"id":"W4400997048","doi":"10.2139/ssrn.4905294","title":"Advancing Machine Learning-Based Streamflow Prediction Through Event Greedy Sampling, Asymmetric Loss Function, and Rainfall Forecasting Uncertainty","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Streamflow; Event (particle physics); Computer science; Sampling (signal processing); Function (biology); Artificial intelligence; Machine learning; Econometrics; Mathematics; Geography; Cartography","score_opus":0.01554636131830269,"score_gpt":0.2487518274038975,"score_spread":0.2332054660855948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400997048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16988696,0.00025369076,0.82725424,0.00070097484,0.00007155329,0.000033299304,0.000099381876,0.0002597715,0.0014401022],"genre_scores_gemma":[0.92963994,0.00016243523,0.068886146,0.0001225389,0.00012823658,0.00004928125,0.00017161849,0.0000432528,0.00079659186],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909306,0.00039203474,0.000050861003,0.00014905576,0.00020625952,0.00010875428],"domain_scores_gemma":[0.99178326,0.0065578,0.0005149301,0.00036929175,0.0005417371,0.00023304358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004553024,0.00062341953,0.0012947225,0.0006388717,0.00046994784,0.0010415636,0.0013909632,0.001129516,0.0008384654],"category_scores_gemma":[0.016824892,0.0005884256,0.0005318332,0.0007173236,0.0010281355,0.0021367935,0.0015980729,0.0016097043,0.00011928344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015568074,0.00006136865,0.0015301411,0.000022519842,0.000030573432,0.000030998406,0.000019635187,0.97554374,0.00068967976,0.008325139,0.00034382846,0.0132466955],"study_design_scores_gemma":[0.0000029676892,0.0000046872515,0.000050485203,7.637562e-7,0.0000012634638,0.0000013813099,7.8256187e-7,0.9981964,0.0001035652,0.001623075,0.000013695942,9.2234535e-7],"about_ca_topic_score_codex":0.005174909,"about_ca_topic_score_gemma":0.0040473086,"teacher_disagreement_score":0.005174909,"about_ca_system_score_codex":0.001061074,"about_ca_system_score_gemma":0.0015584462,"threshold_uncertainty_score":0.024078965},"labels":[],"label_agreement":null},{"id":"W4401043857","doi":"10.1016/j.gsd.2024.101296","title":"A meta-ensemble machine learning strategy to assess groundwater holistic vulnerability in coastal aquifers","year":2024,"lang":"en","type":"article","venue":"Groundwater for Sustainable Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Aquifer; Groundwater; Vulnerability (computing); Environmental science; Water resource management; Hydrology (agriculture); Petroleum engineering; Geology; Computer science; Geotechnical engineering","score_opus":0.09444486748809207,"score_gpt":0.3014054524312475,"score_spread":0.20696058494315545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401043857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31216958,0.0005137178,0.68155456,0.0007319885,0.00009800036,0.00006905986,0.00040511272,0.00054342014,0.0039145565],"genre_scores_gemma":[0.9530564,0.00008128524,0.045399938,0.00008983463,0.00004760246,0.000058883586,0.0002685468,0.00002509366,0.000972415],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957937,0.00017694467,0.000029806806,0.000083179344,0.00006943528,0.00006119688],"domain_scores_gemma":[0.998458,0.00081693364,0.00010870122,0.00015336026,0.000393919,0.00006908494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021568462,0.000751697,0.0010353216,0.0013571093,0.0005500168,0.0008835248,0.0011811267,0.0010054973,0.0012864916],"category_scores_gemma":[0.0039688284,0.00033819134,0.000987463,0.0010053809,0.0003459512,0.0013927534,0.0009539688,0.0007769724,0.00017559718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072087496,0.00007104044,0.005228771,0.00001834358,0.0002555475,0.000037271813,0.000032560965,0.93776804,0.0007510314,0.0024305785,0.0007955549,0.052539125],"study_design_scores_gemma":[0.0000017109273,0.0000114799805,0.00026560947,0.0000017238564,0.000012562253,0.0000032864295,0.0000053970657,0.9986494,0.00010331264,0.00090515433,0.00003823031,0.000002259637],"about_ca_topic_score_codex":0.007913855,"about_ca_topic_score_gemma":0.007996028,"teacher_disagreement_score":0.007913855,"about_ca_system_score_codex":0.0006448298,"about_ca_system_score_gemma":0.0008666822,"threshold_uncertainty_score":0.015735567},"labels":[],"label_agreement":null},{"id":"W4401111564","doi":"10.31223/x5vx1v","title":"A Systematic Review of Neural Network Applications for Groundwater Level Prediction","year":2024,"lang":"en","type":"review","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"West African Science Service Centre on Climate Change and Adapted Land Use; International Development Research Centre","keywords":"Mean squared error; Metric (unit); Artificial neural network; Computer science; Systematic review; Data mining; Groundwater; Machine learning; Artificial intelligence; Statistics; Mathematics; Engineering","score_opus":0.09101870811890667,"score_gpt":0.3305593938640515,"score_spread":0.2395406857451448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401111564","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041009102,0.9976901,0.00071061373,0.00033272954,0.000120498946,0.00009745059,0.00029657627,0.000013193787,0.000328765],"genre_scores_gemma":[0.0050737327,0.9925768,0.0015113595,0.0002657973,0.00006358927,0.00019041637,0.00020036205,0.0000070728966,0.000110933805],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9957308,0.0017140263,0.0014241877,0.00037110902,0.0006835719,0.00007624468],"domain_scores_gemma":[0.97734493,0.018981649,0.0015817177,0.000295384,0.0016896258,0.000106779786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067912224,0.0015751693,0.0036062647,0.0057234317,0.00039942894,0.0019942664,0.0017222073,0.0014127224,0.0048107067],"category_scores_gemma":[0.04422956,0.00063635793,0.006244232,0.006056925,0.0004739657,0.0015315004,0.0010668188,0.0011418719,0.0005151596],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001583101,0.000029256455,0.0006410939,0.76594967,0.0058388854,0.00007973438,0.00013131529,0.0011233648,0.00021093957,0.0008632107,0.0036810816,0.22129324],"study_design_scores_gemma":[0.00015835435,0.0003890885,0.004288278,0.8276372,0.048051562,0.00036827658,0.00026192362,0.0011551611,0.0005445588,0.0025148878,0.11454636,0.00008432648],"about_ca_topic_score_codex":0.010117357,"about_ca_topic_score_gemma":0.023850223,"teacher_disagreement_score":0.010117357,"about_ca_system_score_codex":0.0017966159,"about_ca_system_score_gemma":0.008749556,"threshold_uncertainty_score":0.03591585},"labels":[],"label_agreement":null},{"id":"W4401281272","doi":"10.1016/j.jhydrol.2024.131767","title":"Two-stage meta-ensembling machine learning model for enhanced water quality forecasting","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Computer science; Boosting (machine learning); Artificial intelligence; Benchmark (surveying); Machine learning; Multilayer perceptron; Gradient boosting; Hyperparameter; Genetic algorithm; Extreme learning machine; Principal component analysis; Data pre-processing; Multi-objective optimization; Preprocessor; Data mining; Artificial neural network; Random forest","score_opus":0.13373728375680619,"score_gpt":0.3398877619549514,"score_spread":0.20615047819814522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401281272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09586402,0.00089591235,0.89852273,0.0003222579,0.00018548331,0.000054288786,0.000115600786,0.0009769982,0.0030627348],"genre_scores_gemma":[0.88269407,0.00016117732,0.11295212,0.0001584742,0.00007349156,0.000121879486,0.00021085616,0.0000551116,0.0035728535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997247,0.00009359141,0.00002297652,0.000069201626,0.000049268336,0.00004033674],"domain_scores_gemma":[0.99912304,0.00045289678,0.000048642767,0.00009593088,0.00023096919,0.00004857305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014358186,0.000650805,0.0014307486,0.00047248587,0.0005630479,0.00073415996,0.0018470902,0.0015025473,0.002173315],"category_scores_gemma":[0.0021886858,0.00046087865,0.000765235,0.00043238164,0.00040227597,0.0010036186,0.0008282145,0.0011202098,0.00044328626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013396083,0.00008216404,0.0012078019,0.000035018133,0.000084413536,0.000070962364,0.000047188787,0.9445651,0.0019807522,0.002434279,0.00082957593,0.048528716],"study_design_scores_gemma":[0.0000030618883,0.000009369056,0.000050601906,0.0000012025628,0.0000046618593,0.0000045736574,7.736581e-7,0.9995178,0.00012500765,0.00023532691,0.000045717497,0.0000019142306],"about_ca_topic_score_codex":0.0083206715,"about_ca_topic_score_gemma":0.009153681,"teacher_disagreement_score":0.0083206715,"about_ca_system_score_codex":0.00050368736,"about_ca_system_score_gemma":0.00108947,"threshold_uncertainty_score":0.016544461},"labels":[],"label_agreement":null},{"id":"W4401397343","doi":"10.1007/s00704-024-05121-3","title":"Correction to: Hydrologic interpretation of machine learning models for 10-daily streamflow simulation in climate sensitive upper Indus catchments","year":2024,"lang":"en","type":"article","venue":"Theoretical and Applied Climatology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Indus; Streamflow; Interpretation (philosophy); Hydrology (agriculture); Environmental science; Stream flow; Hydrological modelling; Climatology; Geology; Computer science; Drainage basin; Geography; Cartography; Geomorphology","score_opus":0.011401172324297116,"score_gpt":0.25888739175509673,"score_spread":0.24748621943079963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401397343","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006717483,0.0004377211,0.0021220804,0.018789567,0.9685551,0.000071983195,0.0058578607,0.0016186647,0.0018753647],"genre_scores_gemma":[0.098851256,0.0047429204,0.024059055,0.048132785,0.43996295,0.0010031392,0.029358871,0.008192862,0.34569615],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956161,0.0006581018,0.0011218007,0.0007117304,0.00139055,0.0005016874],"domain_scores_gemma":[0.9336269,0.010431901,0.0022624428,0.0055917767,0.045242894,0.002844011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003217917,0.0023833604,0.0031480256,0.005402507,0.0027438854,0.0047730654,0.004323378,0.00584601,0.18143037],"category_scores_gemma":[0.062094536,0.0016020112,0.0020973014,0.0045367754,0.0018914678,0.0029974396,0.0030092301,0.0071567753,0.06597558],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076916695,0.000014447548,0.00017953182,0.00019533621,0.00002257606,0.00014775593,0.00003152533,0.00026670613,0.00009694534,0.00055096875,0.9921502,0.00626703],"study_design_scores_gemma":[0.00030934621,0.00006339317,0.0061628423,0.00034297782,0.00005936248,0.0005081359,0.00023757516,0.004080972,0.0009986166,0.0031922942,0.983931,0.00011351953],"about_ca_topic_score_codex":0.019056598,"about_ca_topic_score_gemma":0.02383114,"teacher_disagreement_score":0.18143037,"about_ca_system_score_codex":0.0033612107,"about_ca_system_score_gemma":0.005031774,"threshold_uncertainty_score":0.60694504},"labels":[],"label_agreement":null},{"id":"W4401411401","doi":"10.52151/jae2024613.1852","title":"Reliability of Artificial Intelligence-based Models Compared to Numerical Model for Predicting Groundwater Level under Changing Climate","year":2024,"lang":"en","type":"article","venue":"Journal of Agricultural Engineering (India)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reliability (semiconductor); Environmental science; Groundwater; Reliability engineering; Climate change; Computer science; Engineering; Ecology; Geotechnical engineering","score_opus":0.056457039916391664,"score_gpt":0.25644759431703984,"score_spread":0.19999055440064817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401411401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84608567,0.0013682256,0.14317356,0.000631766,0.0001880649,0.000094225594,0.00045617652,0.0013271063,0.0066751307],"genre_scores_gemma":[0.9927939,0.0001947165,0.0064754896,0.000026372956,0.000011480634,0.00002384239,0.00017064245,0.000025541587,0.00027816012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987233,0.00056591904,0.00011354399,0.00021824877,0.00030306476,0.00007576099],"domain_scores_gemma":[0.99470204,0.0030521462,0.00053995836,0.0005685234,0.0010473268,0.00008994227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029876374,0.00091589463,0.00073707866,0.0008907545,0.00032833093,0.0013504236,0.0007778658,0.0008597067,0.00077194953],"category_scores_gemma":[0.011565092,0.00041312506,0.00070996943,0.0006710974,0.00047026126,0.0013520946,0.0007247646,0.0006854816,0.00024926697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025104158,0.00006846543,0.016952323,0.00008527179,0.00016717202,0.000069264875,0.000059625723,0.95596945,0.0018868301,0.00085375836,0.00032008885,0.023316748],"study_design_scores_gemma":[0.000007007353,0.00004687373,0.0014763372,0.000009750165,0.000023266248,0.000009417867,0.00001699261,0.99712294,0.0007982701,0.0003528924,0.00012795399,0.000008323517],"about_ca_topic_score_codex":0.012516646,"about_ca_topic_score_gemma":0.0051749386,"teacher_disagreement_score":0.012516646,"about_ca_system_score_codex":0.0007405554,"about_ca_system_score_gemma":0.0008600082,"threshold_uncertainty_score":0.024887562},"labels":[],"label_agreement":null},{"id":"W4401437379","doi":"10.1061/jhyeff.heeng-6142","title":"Discussion of “Runoff Predictions in a Semiarid Watershed by Convolutional Neural Networks Improved with Metaheuristic Algorithms and Forced with Reanalysis and Climate Data”","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Agriculture and Agri-Food Canada","funders":"","keywords":"Watershed; Surface runoff; Algorithm; Computer science; Environmental science; Convolutional neural network; Climate change; Hydrology (agriculture); Artificial neural network; Hydrological modelling; Climatology; Machine learning; Geology; Ecology","score_opus":0.006937987403542201,"score_gpt":0.2033103967015463,"score_spread":0.1963724092980041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401437379","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105825715,0.004903721,0.49310288,0.28157008,0.011317853,0.00024011648,0.0010737501,0.0008828423,0.10108301],"genre_scores_gemma":[0.85825765,0.0026150849,0.071065396,0.026973087,0.006128372,0.0002316628,0.0004400298,0.00022355943,0.03406509],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996321,0.00013975392,0.00002229604,0.00006513692,0.00010945428,0.00003122381],"domain_scores_gemma":[0.9990773,0.0005658932,0.000056229666,0.00004598865,0.00022489099,0.000029747207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020498654,0.00044502027,0.00031745428,0.0003697237,0.0009874278,0.001578982,0.0023113736,0.0031333847,0.0029680366],"category_scores_gemma":[0.0067337384,0.00021856358,0.0009139233,0.00047006385,0.001496243,0.001820462,0.00070264,0.0014235278,0.0002995875],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019862704,0.000090539244,0.0025451467,0.00022553331,0.0002614915,0.0010601956,0.00027171438,0.47719577,0.004572399,0.44395062,0.043942697,0.025685212],"study_design_scores_gemma":[0.000073282434,0.0000785795,0.002131636,0.00010185715,0.00008718088,0.00017553075,0.00018666199,0.69224995,0.005255908,0.25355938,0.046044406,0.000055695706],"about_ca_topic_score_codex":0.009849656,"about_ca_topic_score_gemma":0.008139675,"teacher_disagreement_score":0.009849656,"about_ca_system_score_codex":0.0013902382,"about_ca_system_score_gemma":0.0009282871,"threshold_uncertainty_score":0.019584656},"labels":[],"label_agreement":null},{"id":"W4401478873","doi":"10.2139/ssrn.4922112","title":"Prediction of Carbon Dioxide Emissions from Atlantic Canadian Potato Fields Using Advanced Hybridized Machine Learning Algorithms – Nexus of Field Data and Modelling","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; University of British Columbia; Wilfrid Laurier University; University of Prince Edward Island","funders":"","keywords":"Nexus (standard); Field (mathematics); Carbon dioxide; Computer science; Algorithm; Environmental science; Machine learning; Artificial intelligence; Data mining; Chemistry; Mathematics","score_opus":0.029419669406414207,"score_gpt":0.2504944119919224,"score_spread":0.2210747425855082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401478873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898545,0.00011861668,0.006634812,0.00014534328,0.000019287358,0.00001782721,0.0010991781,0.0001988457,0.0019117234],"genre_scores_gemma":[0.9954495,0.000042253407,0.002683944,0.000013593759,0.000004444634,0.00000802298,0.0010387931,0.000011253201,0.00074829167],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998865,0.000016476215,0.000004359613,0.00003751963,0.000027134469,0.000027899803],"domain_scores_gemma":[0.9996063,0.00015850924,0.000024278754,0.00003244181,0.000154399,0.000024064399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036569094,0.00050181866,0.00026510615,0.0005029313,0.00043058666,0.00067391817,0.00053589593,0.0004895278,0.00071434793],"category_scores_gemma":[0.0011636812,0.00022817533,0.00038318054,0.0007942519,0.0003001879,0.00042582044,0.0002522317,0.00046499717,0.00015376593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015135024,0.00011188949,0.0405191,0.000031964315,0.000076598815,0.000047661764,0.000028830162,0.9282966,0.0027615419,0.0004759323,0.0012300294,0.026268393],"study_design_scores_gemma":[0.000009964893,0.000010536,0.0208724,0.0000023085863,0.000009749702,0.0000048963316,0.000021285336,0.9774845,0.0011382414,0.00020435218,0.00023320576,0.000008495929],"about_ca_topic_score_codex":0.804694,"about_ca_topic_score_gemma":0.81437284,"teacher_disagreement_score":0.195306,"about_ca_system_score_codex":0.0031929095,"about_ca_system_score_gemma":0.0030217164,"threshold_uncertainty_score":0.3929124},"labels":[],"label_agreement":null},{"id":"W4401769135","doi":"10.53555/sfs.v10i1.2963","title":"Surface Water Area Detection And Extraction By Using Different Techniques Of Remote Sensing And GIS.","year":2023,"lang":"en","type":"article","venue":"Journal of Survey in Fisheries Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Remote sensing; Extraction (chemistry); Computer science; Surface water; Environmental science; Geography; Environmental engineering; Chromatography; Chemistry","score_opus":0.14805090039890254,"score_gpt":0.2853484884279022,"score_spread":0.1372975880289997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31881824,0.0008786856,0.65380013,0.0002931263,0.00015248275,0.00039718923,0.0057187285,0.006499435,0.013442054],"genre_scores_gemma":[0.53716916,0.00039926803,0.45264697,0.00006929119,0.000033695353,0.00027373148,0.004589468,0.00015282324,0.004665619],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99973077,0.000030708983,0.000022343922,0.000071658105,0.00011610434,0.000028475475],"domain_scores_gemma":[0.9997837,0.000045758887,0.000033090822,0.000027208738,0.00009905255,0.000011231539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034392046,0.00056361896,0.00026938206,0.0032239181,0.00020648664,0.00048690545,0.00038884638,0.00033580587,0.0016910954],"category_scores_gemma":[0.0005852827,0.00025893893,0.00051227305,0.002544506,0.00015005772,0.0009735595,0.00036659915,0.00023829029,0.0008439204],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001471275,0.00016701935,0.04778213,0.00046840814,0.00012801703,0.00023055065,0.00035300144,0.014023676,0.10828278,0.0016186194,0.0052072285,0.82159144],"study_design_scores_gemma":[0.00006503066,0.00025584645,0.26959175,0.00008142574,0.00017272188,0.0010042322,0.0012474104,0.57124484,0.11160706,0.004468141,0.040101323,0.0001602366],"about_ca_topic_score_codex":0.004229908,"about_ca_topic_score_gemma":0.0052197543,"teacher_disagreement_score":0.004229908,"about_ca_system_score_codex":0.00020904528,"about_ca_system_score_gemma":0.0003656721,"threshold_uncertainty_score":0.008410573},"labels":[],"label_agreement":null},{"id":"W4401769322","doi":"10.1007/s00024-024-03552-7","title":"Air and Water Temperature Trend Analysis at the Confluence of the Sava and Danube Rivers in Belgrade, Serbia","year":2024,"lang":"en","type":"article","venue":"Pure and Applied Geophysics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Confluence; Air temperature; Hydrology (agriculture); Environmental science; Geography; Physical geography; Climatology; Geology; Meteorology; Geotechnical engineering","score_opus":0.004771278698324321,"score_gpt":0.18811392359484913,"score_spread":0.1833426448965248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769322","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99834514,0.00015873149,0.00008233491,0.00002300948,0.0000071887684,0.0000030464978,0.0007371208,0.000014671577,0.000628914],"genre_scores_gemma":[0.99851257,0.00008266203,0.00016361685,0.000005214262,0.0000028313032,0.000003950183,0.00090932794,0.0000043730884,0.00031540586],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99983025,0.000031990578,0.000015526004,0.000051945546,0.000023181712,0.000047141868],"domain_scores_gemma":[0.99984,0.000029559014,0.000029652045,0.0000141299315,0.00005835786,0.000028220233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030634293,0.0002016753,0.0004420166,0.0012183227,0.0004322749,0.0010676445,0.00029240668,0.0004093528,0.00077914033],"category_scores_gemma":[0.0003050725,0.00016615963,0.00033572922,0.001302625,0.00038620716,0.0002631728,0.0003496862,0.00022464865,0.00018674266],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003869977,0.00015535923,0.9621614,0.000100318175,0.00039385192,0.0008649126,0.0013429332,0.009830183,0.005976526,0.00057461025,0.0018568487,0.016356077],"study_design_scores_gemma":[0.0000058211067,0.000018847459,0.9959246,0.000014620646,0.000031591742,0.00003628999,0.000817889,0.0018909718,0.00016263331,0.00001480315,0.0010768926,0.000004984843],"about_ca_topic_score_codex":0.23438753,"about_ca_topic_score_gemma":0.32222617,"teacher_disagreement_score":0.23438753,"about_ca_system_score_codex":0.0009396623,"about_ca_system_score_gemma":0.0010389838,"threshold_uncertainty_score":0.46604645},"labels":[],"label_agreement":null},{"id":"W4401988943","doi":"10.1016/j.jwpe.2024.106067","title":"Comparison of novel physics-guided machine learning models with empirical equations for predicting longitudinal dispersion coefficient in diverse natural river systems","year":2024,"lang":"en","type":"article","venue":"Journal of Water Process Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Dispersion (optics); Natural (archaeology); Empirical modelling; Physics; Statistical physics; Computer science; Optics; Geology; Simulation","score_opus":0.0786413473218229,"score_gpt":0.310874714552991,"score_spread":0.23223336723116808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401988943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7192028,0.0005969105,0.2755315,0.0004806283,0.00011586313,0.000091875205,0.0003606961,0.0010290933,0.0025906386],"genre_scores_gemma":[0.9707818,0.00014881506,0.027996678,0.000049371567,0.000027841064,0.00006964261,0.00025840075,0.000037441318,0.0006299115],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977034,0.00007863699,0.000027202044,0.00006232182,0.000040944644,0.000020515427],"domain_scores_gemma":[0.9972796,0.0018981441,0.00021052008,0.00011598846,0.00044541265,0.000050348815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001367314,0.00064369483,0.0006079954,0.0006069859,0.0003906245,0.00074164267,0.0012871394,0.0010006293,0.000762976],"category_scores_gemma":[0.0040594824,0.00028566824,0.0006002431,0.0005285824,0.00034817363,0.001195413,0.0004670704,0.0008080809,0.00015522122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037922273,0.00008844293,0.0027838086,0.00002188872,0.00003339758,0.000012845485,0.000018306908,0.9817136,0.00032004688,0.0006423922,0.00017857277,0.014148691],"study_design_scores_gemma":[0.000002821555,0.0000053393073,0.00021015522,9.57306e-7,0.0000023788964,0.0000014215609,0.0000016001646,0.9995726,0.000064358755,0.00011770205,0.000019121708,0.0000015425763],"about_ca_topic_score_codex":0.02218201,"about_ca_topic_score_gemma":0.016002178,"teacher_disagreement_score":0.02218201,"about_ca_system_score_codex":0.0010550512,"about_ca_system_score_gemma":0.0013520374,"threshold_uncertainty_score":0.044105828},"labels":[],"label_agreement":null},{"id":"W4402068747","doi":"10.1016/j.atech.2024.100559","title":"Prediction of carbon dioxide emissions from Atlantic Canadian potato fields using advanced hybridized machine learning algorithms – Nexus of field data and modelling","year":2024,"lang":"en","type":"article","venue":"Smart Agricultural Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; University of British Columbia, Okanagan Campus; University of British Columbia; University of Prince Edward Island","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nexus (standard); Field (mathematics); Carbon dioxide; Environmental science; Algorithm; Computer science; Machine learning; Meteorology; Chemistry; Mathematics; Geography","score_opus":0.025666203621030767,"score_gpt":0.22832606462695676,"score_spread":0.20265986100592598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402068747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97979957,0.00031841767,0.014217425,0.00012165528,0.000021140175,0.00005407479,0.0032233722,0.00059198943,0.001652428],"genre_scores_gemma":[0.9794743,0.00013771903,0.013456113,0.000026826945,0.0000058046394,0.000034541943,0.005593066,0.000020377824,0.0012510776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984205,0.00001878459,0.000008425533,0.000057973124,0.00003795359,0.00003478094],"domain_scores_gemma":[0.99962723,0.00010691183,0.000032077005,0.000029081151,0.0001815204,0.000023260063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005028443,0.0009143701,0.00035897677,0.0006646386,0.0004803412,0.0006655333,0.0007465588,0.00044397239,0.0006236965],"category_scores_gemma":[0.0008706184,0.00028495365,0.0006139199,0.0009066409,0.00023730741,0.00033731823,0.000308031,0.00050208205,0.00016620844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023925002,0.00021323217,0.061992224,0.0000935744,0.00014813269,0.00011533791,0.000048065507,0.8618647,0.00414548,0.00041248393,0.0023069684,0.06842049],"study_design_scores_gemma":[0.000009592556,0.000019194988,0.017964363,0.0000035001833,0.000013835575,0.0000057382285,0.000024663732,0.980495,0.0009819382,0.00009088327,0.0003824167,0.000008905172],"about_ca_topic_score_codex":0.8019281,"about_ca_topic_score_gemma":0.8338436,"teacher_disagreement_score":0.1980719,"about_ca_system_score_codex":0.003624157,"about_ca_system_score_gemma":0.0036984624,"threshold_uncertainty_score":0.39847672},"labels":[],"label_agreement":null},{"id":"W4402087070","doi":"10.1007/s13762-024-05944-7","title":"Near real-time significant wave height prediction along the coastline of Queensland using advanced hybrid machine learning models","year":2024,"lang":"en","type":"article","venue":"International Journal of Environmental Science and Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Environmental science; Geology; Meteorology; Computer science; Geography","score_opus":0.013035261738004003,"score_gpt":0.2280192036029553,"score_spread":0.2149839418649513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402087070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99702007,0.000032592387,0.0016161453,0.000098284014,0.000011640663,0.000005454043,0.000210238,0.00007964065,0.00092589896],"genre_scores_gemma":[0.9984647,0.000013922928,0.0007738026,0.0000045580805,0.0000028321015,0.0000024267513,0.00017782656,0.0000028739312,0.0005569947],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999255,0.000011248118,0.0000034792913,0.000020749749,0.000018367524,0.000020667927],"domain_scores_gemma":[0.99979,0.000061114995,0.000032775453,0.000015831316,0.00007039285,0.000029862402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017510344,0.00023793499,0.00018646047,0.00031982805,0.00029171444,0.0003764182,0.00039245983,0.00034180755,0.0008765924],"category_scores_gemma":[0.0005615914,0.00019009114,0.00022214805,0.00038903786,0.00020989469,0.00030276724,0.00023764819,0.00032115137,0.00017315555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005176874,0.00029759435,0.1868663,0.00010122415,0.00014084227,0.0006736899,0.0004754229,0.7291432,0.018761517,0.00078476843,0.00248179,0.059755985],"study_design_scores_gemma":[0.000020333498,0.000054579814,0.10476647,0.0000069024404,0.000017063678,0.000017937458,0.00013410578,0.8937967,0.0006712609,0.0001486022,0.00035176871,0.000014255006],"about_ca_topic_score_codex":0.18160677,"about_ca_topic_score_gemma":0.26538032,"teacher_disagreement_score":0.18160677,"about_ca_system_score_codex":0.0008285756,"about_ca_system_score_gemma":0.0007870327,"threshold_uncertainty_score":0.36109942},"labels":[],"label_agreement":null},{"id":"W4402097638","doi":"10.1016/j.coldregions.2024.104305","title":"A comprehensive review of AI-based methods used for forecasting ice jam floods occurrence, severity, timing, and location","year":2024,"lang":"en","type":"review","venue":"Cold Regions Science and Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval","funders":"Environment and Climate Change Canada","keywords":"Environmental science; Meteorology; Climatology; Geology; Geography","score_opus":0.13750744219631403,"score_gpt":0.4127565936757182,"score_spread":0.2752491514794042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402097638","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013905333,0.9828219,0.010093993,0.0009817332,0.00050252205,0.0000898454,0.0009134437,0.00013596495,0.0030700748],"genre_scores_gemma":[0.009504796,0.9791019,0.0091710165,0.000317624,0.00031015943,0.00009968049,0.0008066077,0.000022772907,0.00066548755],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894553,0.00026854075,0.0002825279,0.00015692298,0.00030751232,0.00003895705],"domain_scores_gemma":[0.99518436,0.0035567342,0.00040585257,0.00011429337,0.00068459875,0.000054151413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020111937,0.0016047041,0.0012118609,0.0041388827,0.0003358883,0.0015479744,0.001519161,0.0010382255,0.0043072747],"category_scores_gemma":[0.007554348,0.00046968696,0.0023388169,0.0042134966,0.0002991819,0.0017760482,0.00055301766,0.0009063015,0.0012155303],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008804793,0.000086974855,0.0021592174,0.08534438,0.00074378814,0.0002209998,0.00022210526,0.009179194,0.0012230974,0.0040890346,0.021614805,0.8750284],"study_design_scores_gemma":[0.000052892898,0.00061962183,0.013361934,0.07598581,0.004383372,0.001117875,0.00052404014,0.019909222,0.0026123684,0.01010771,0.8710426,0.00028252203],"about_ca_topic_score_codex":0.00779557,"about_ca_topic_score_gemma":0.008583687,"teacher_disagreement_score":0.00779557,"about_ca_system_score_codex":0.00074788724,"about_ca_system_score_gemma":0.0032715423,"threshold_uncertainty_score":0.015500367},"labels":[],"label_agreement":null},{"id":"W4402200495","doi":"10.3390/engproc2024069041","title":"Sequence-to-Sequence Deep Learning for Urban Water Demand Forecasting","year":2024,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Computer science; Deep learning; Sequence learning; Artificial intelligence; Demand forecasting; Operations research; Engineering; Chemistry","score_opus":0.06049387865245728,"score_gpt":0.277702228522868,"score_spread":0.21720834987041074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402200495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3028326,0.001746796,0.6845934,0.0011522127,0.00021294541,0.000057782065,0.0009850892,0.0026702706,0.0057488442],"genre_scores_gemma":[0.96613085,0.00030608845,0.03037451,0.0001078358,0.000026562437,0.000030214715,0.00066574704,0.000029623017,0.002328398],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990153,0.00002361513,0.0000057986326,0.000026952483,0.000020188576,0.000021902539],"domain_scores_gemma":[0.99966145,0.00019312963,0.000029146784,0.000022356868,0.000075948454,0.000017928238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043591636,0.00057989656,0.0002863685,0.0003798773,0.00015217168,0.00040719874,0.00050135533,0.0004398949,0.0015669842],"category_scores_gemma":[0.001540796,0.00024178658,0.0002851284,0.0005776808,0.0002160726,0.0009175534,0.00043379853,0.0011986609,0.00033857443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007762204,0.00009673347,0.0019609146,0.000047821417,0.000041986157,0.000034863024,0.000033891352,0.88024783,0.0027909647,0.0024102966,0.001655509,0.11060157],"study_design_scores_gemma":[0.0000013008028,0.000008105507,0.0001491951,0.0000017849386,0.0000018843613,0.0000017632889,0.0000030794301,0.998212,0.00048734306,0.0010191522,0.000113097536,0.0000013623353],"about_ca_topic_score_codex":0.017693277,"about_ca_topic_score_gemma":0.017730003,"teacher_disagreement_score":0.017693277,"about_ca_system_score_codex":0.00080273964,"about_ca_system_score_gemma":0.0008149577,"threshold_uncertainty_score":0.03518057},"labels":[],"label_agreement":null},{"id":"W4402261593","doi":"10.1109/igarss53475.2024.10642642","title":"An Attention-Aided Convolutional Neural Network for Global Sea Surface Wind Speed Estimation from Gnss-R Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"GNSS applications; Convolutional neural network; Wind speed; Computer science; Artificial neural network; Artificial intelligence; Remote sensing; Meteorology; Global Positioning System; Telecommunications; Geology; Geography","score_opus":0.054867019561832917,"score_gpt":0.31345806492972844,"score_spread":0.2585910453678955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402261593","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26727232,0.0026402823,0.71704614,0.0007355594,0.00041769416,0.00010835077,0.00053690205,0.0041546565,0.0070881047],"genre_scores_gemma":[0.92656213,0.0005420716,0.0667021,0.00027559808,0.00009546759,0.0000541089,0.00076157873,0.000048560945,0.004958446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998822,0.000010621314,0.000006158094,0.000035187844,0.000029518033,0.000036140565],"domain_scores_gemma":[0.99982125,0.00005789976,0.00001688051,0.000019183586,0.00007372323,0.0000110409455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003355508,0.0006721289,0.00034884512,0.00044188704,0.00021415793,0.00031687645,0.0007736517,0.00051525095,0.00127433],"category_scores_gemma":[0.0007797509,0.000231221,0.00041945314,0.00051660603,0.00016620368,0.0005963447,0.00048756055,0.00064475206,0.00029765067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029976768,0.00018521638,0.003930355,0.0000967076,0.00013710556,0.00020149618,0.000046242007,0.37706456,0.03820413,0.0015107415,0.0055669034,0.5727568],"study_design_scores_gemma":[0.000005815789,0.00003261545,0.00085919746,0.0000037191487,0.000022128677,0.000017470069,0.0000039513375,0.9947936,0.0035380905,0.00030472016,0.00041395842,0.000004642702],"about_ca_topic_score_codex":0.02237668,"about_ca_topic_score_gemma":0.026798006,"teacher_disagreement_score":0.02237668,"about_ca_system_score_codex":0.00060164125,"about_ca_system_score_gemma":0.00072063436,"threshold_uncertainty_score":0.0444929},"labels":[],"label_agreement":null},{"id":"W4402404799","doi":"10.1016/j.hydroa.2024.100185","title":"How much X is in XAI: Responsible use of “Explainable” artificial intelligence in hydrology and water resources","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrology X","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Australian Research Council; Westpac Scholars Trust; University of Melbourne","keywords":"Water resources; Hydrology (agriculture); Water resource management; Environmental science; Engineering; Geotechnical engineering; Ecology; Biology","score_opus":0.03787428450128096,"score_gpt":0.26227714418210707,"score_spread":0.2244028596808261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402404799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017312167,0.032340184,0.60827005,0.27154034,0.0061661033,0.00014419714,0.0004386348,0.0024424337,0.06134589],"genre_scores_gemma":[0.5671551,0.03125408,0.31295076,0.042776745,0.008513319,0.0005188092,0.00071021763,0.0031492661,0.032971717],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99233454,0.0041285683,0.00046242418,0.0015393882,0.0012160289,0.0003189279],"domain_scores_gemma":[0.97720474,0.013800271,0.0020031508,0.0046970076,0.0015576909,0.0007370188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01678534,0.0012974457,0.0015007184,0.0020181946,0.0031824063,0.013681446,0.0030432553,0.0056397766,0.007422258],"category_scores_gemma":[0.039698165,0.00097314134,0.0019910433,0.0023139908,0.018969715,0.029737934,0.008964871,0.009541376,0.0022858265],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011040607,0.00007050366,0.0025611143,0.00037247594,0.00018198582,0.000304481,0.0026197422,0.0060969153,0.00091448147,0.8751459,0.021820752,0.08980117],"study_design_scores_gemma":[0.000019534127,0.000030108224,0.0005082122,0.00028320486,0.0000376121,0.00008644478,0.00031056363,0.010221383,0.0006482546,0.9393361,0.048466235,0.000052369745],"about_ca_topic_score_codex":0.0035818014,"about_ca_topic_score_gemma":0.0026162434,"teacher_disagreement_score":0.01678534,"about_ca_system_score_codex":0.002611188,"about_ca_system_score_gemma":0.003567438,"threshold_uncertainty_score":0.08877039},"labels":[],"label_agreement":null},{"id":"W4402486348","doi":"10.3390/hydrology11090151","title":"Machine Learning Model for River Discharge Forecast: A Case Study of the Ottawa River in Canada","year":2024,"lang":"en","type":"article","venue":"Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hydrology (agriculture); Discharge; Environmental science; Water discharge; Meteorology; Climatology; Geology; Geography; Drainage basin; Geotechnical engineering; Cartography","score_opus":0.02134855924654426,"score_gpt":0.23736043148606534,"score_spread":0.21601187223952106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402486348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9698654,0.00024521718,0.021651115,0.0007124347,0.000023213051,0.00010410703,0.001129282,0.00032856426,0.005940796],"genre_scores_gemma":[0.98970234,0.000100893456,0.006290063,0.000023906909,0.0000045843603,0.000027501914,0.00040462954,0.000012239087,0.0034338403],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985874,0.000026031628,0.000008241897,0.000032391323,0.000032639484,0.000041917127],"domain_scores_gemma":[0.9996451,0.00017036412,0.000021911277,0.0000136725785,0.0001238193,0.00002513029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004153756,0.0005263923,0.0003929941,0.00042382473,0.0009802656,0.0008726902,0.00084953377,0.0007456917,0.0013332391],"category_scores_gemma":[0.0011102384,0.0001589504,0.000346384,0.00085153437,0.00042188127,0.00032516604,0.0002778526,0.0006162995,0.00012039703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004610839,0.000046036774,0.015262154,0.00003599181,0.000018653867,0.00031598323,0.000083725856,0.96903056,0.00040745112,0.001389175,0.0009075464,0.012456571],"study_design_scores_gemma":[0.000006826137,0.000014229794,0.00303681,0.000003525159,0.0000068282075,0.000014766689,0.00009242834,0.99579453,0.00022167437,0.0002443183,0.0005576686,0.0000064955807],"about_ca_topic_score_codex":0.94569033,"about_ca_topic_score_gemma":0.9306345,"teacher_disagreement_score":0.054309666,"about_ca_system_score_codex":0.009593156,"about_ca_system_score_gemma":0.007414196,"threshold_uncertainty_score":0.10925895},"labels":[],"label_agreement":null},{"id":"W4402495899","doi":"10.3390/engproc2024069120","title":"Enhancing Water Demand Forecasting: Leveraging LSTM Networks for Accurate Predictions","year":2024,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Demand forecasting; Artificial intelligence; Machine learning; Operations research; Engineering","score_opus":0.037895804397768226,"score_gpt":0.2537543344612501,"score_spread":0.21585853006348188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402495899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14855514,0.00071989105,0.8388067,0.00089443085,0.0002569204,0.000063521584,0.0005314161,0.0035829188,0.006588969],"genre_scores_gemma":[0.9334883,0.00023356854,0.063426375,0.00015438952,0.00008595301,0.000052200096,0.00042047707,0.00007906967,0.0020597347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998122,0.000042239128,0.0000131141405,0.00005632531,0.00004286029,0.00003328566],"domain_scores_gemma":[0.999579,0.00022849557,0.000036560195,0.00004280896,0.00009727319,0.000015854806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005696874,0.0008957389,0.00034508028,0.000375609,0.00021276032,0.0006886684,0.0007114771,0.0006466034,0.0013514201],"category_scores_gemma":[0.0021910311,0.00028868872,0.0002984887,0.00048883585,0.00021555403,0.0015604991,0.0006680682,0.001007284,0.0006308405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015445738,0.00014214862,0.0020210324,0.00008252935,0.000076783464,0.00010856082,0.00009592333,0.79267406,0.012154444,0.0014746307,0.0022665279,0.1887488],"study_design_scores_gemma":[0.0000017959625,0.000009068705,0.00013925506,0.0000033622603,0.0000051024804,0.000004734277,0.000004078544,0.9975612,0.0013896978,0.0006362293,0.00024269566,0.0000027638819],"about_ca_topic_score_codex":0.00719897,"about_ca_topic_score_gemma":0.009385002,"teacher_disagreement_score":0.00719897,"about_ca_system_score_codex":0.00047659583,"about_ca_system_score_gemma":0.00058675476,"threshold_uncertainty_score":0.014314115},"labels":[],"label_agreement":null},{"id":"W4402535636","doi":"10.1016/j.envres.2024.120015","title":"Enhanced predictive modeling of dissolved oxygen concentrations in riverine systems using novel hybrid temporal pattern attention deep neural networks","year":2024,"lang":"en","type":"article","venue":"Environmental Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Environmental science; Artificial neural network; Computer science; Artificial intelligence","score_opus":0.0558563803721759,"score_gpt":0.30994148436607627,"score_spread":0.2540851039939004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402535636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51900095,0.00089075125,0.47359395,0.00064126076,0.00019017549,0.00002943579,0.00034427663,0.00072085793,0.0045883134],"genre_scores_gemma":[0.98998255,0.000092477094,0.008668179,0.000041254436,0.000028965342,0.000013458116,0.00011083121,0.000013451803,0.0010489146],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999317,0.000009896773,0.00000406989,0.000023561131,0.000014966829,0.000015779984],"domain_scores_gemma":[0.9998054,0.00008852952,0.000025743224,0.0000137148,0.00005407672,0.000012569455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002762967,0.00039707453,0.0003808732,0.00025230963,0.0001949893,0.0005041997,0.000711802,0.00049834227,0.0007204322],"category_scores_gemma":[0.00067355693,0.0002790627,0.000367947,0.00032284006,0.00021894026,0.00069614407,0.0004936876,0.000711529,0.00011111036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048432463,0.00005042788,0.0016070491,0.00001572342,0.00003683652,0.000029905408,0.000015152909,0.97110295,0.0023057444,0.0008715159,0.00035542253,0.023560831],"study_design_scores_gemma":[6.1808765e-7,0.0000015918685,0.00008104242,2.1916485e-7,9.929504e-7,6.8164803e-7,4.5532178e-7,0.99972075,0.00007425036,0.00010541696,0.000013440469,4.9755664e-7],"about_ca_topic_score_codex":0.020310381,"about_ca_topic_score_gemma":0.020053625,"teacher_disagreement_score":0.020310381,"about_ca_system_score_codex":0.00051533594,"about_ca_system_score_gemma":0.00052480766,"threshold_uncertainty_score":0.040384293},"labels":[],"label_agreement":null},{"id":"W4402698033","doi":"10.1007/s11356-024-35002-1","title":"Coupling artificial neural network and sperm swarm optimization for soil temperature prediction at multiple depths","year":2024,"lang":"en","type":"article","venue":"Environmental Science and Pollution Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Mean squared error; Artificial neural network; Wind speed; Environmental science; Multilayer perceptron; Approximation error; Irrigation; Computer science; Meteorology; Soil science; Statistics; Mathematics; Machine learning; Algorithm; Ecology; Geography","score_opus":0.03910922522757475,"score_gpt":0.29829807655293633,"score_spread":0.25918885132536157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402698033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27711216,0.0007339279,0.71625614,0.00038239994,0.0002695209,0.00006521424,0.0000838806,0.000295542,0.0048013176],"genre_scores_gemma":[0.9761888,0.00009871701,0.021654965,0.000063012325,0.00005532782,0.00005559933,0.000059115962,0.000019387784,0.0018051682],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974364,0.000074853764,0.000020516916,0.0000688987,0.000056880013,0.000035214587],"domain_scores_gemma":[0.9990982,0.000574931,0.000087350054,0.000029484707,0.00017247233,0.000037642454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008918415,0.00065164384,0.0009822068,0.0005214645,0.0003872121,0.00067275664,0.00087182946,0.0012798011,0.00097190065],"category_scores_gemma":[0.0023501127,0.00049061904,0.00057207554,0.00070094626,0.00045569535,0.00084366434,0.0007759798,0.00075429643,0.00013133201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027140288,0.000023697568,0.00048518318,0.000012213257,0.000023426668,0.000010224519,0.000010052552,0.9917202,0.00033814163,0.00033288464,0.000092416,0.0069243317],"study_design_scores_gemma":[0.0000014664624,0.0000059261715,0.000055188106,4.731937e-7,0.0000016183525,5.8062335e-7,0.0000010063146,0.9997824,0.00004347968,0.00009277159,0.000014311586,8.2659005e-7],"about_ca_topic_score_codex":0.016802883,"about_ca_topic_score_gemma":0.0105452,"teacher_disagreement_score":0.016802883,"about_ca_system_score_codex":0.00068402925,"about_ca_system_score_gemma":0.00094256975,"threshold_uncertainty_score":0.033410132},"labels":[],"label_agreement":null},{"id":"W4402860367","doi":"10.22541/essoar.172736277.74497104/v1","title":"High-resolution national-scale water modeling is enhanced by multiscale differentiable physics-informed machine learning","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Differentiable function; Resolution (logic); Scale (ratio); Computer science; Artificial intelligence; Physics; Mathematics; Mathematical analysis; Quantum mechanics","score_opus":0.018561629257579253,"score_gpt":0.24445642252966568,"score_spread":0.22589479327208642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402860367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5754038,0.00023003465,0.40554678,0.0015686604,0.00014862452,0.00007611078,0.00084109115,0.0071619195,0.009022946],"genre_scores_gemma":[0.93495804,0.000054647644,0.06311804,0.0001244492,0.000027810003,0.000044649732,0.0006130507,0.00015347842,0.0009057149],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997938,0.000061023155,0.000009998427,0.000059151644,0.00005028592,0.000025711422],"domain_scores_gemma":[0.99942696,0.00020316606,0.00005992184,0.00016026605,0.000102749924,0.00004703503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068624696,0.0006318402,0.0005694105,0.00031554067,0.00034716405,0.00065463234,0.0011065075,0.00091845216,0.0018512398],"category_scores_gemma":[0.002503187,0.00042190132,0.000711936,0.00038999514,0.00048725877,0.0017011086,0.0010811152,0.0013121839,0.00041093925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019995454,0.000041759486,0.0023490516,0.000009915739,0.00002749168,0.000025809473,0.000016482358,0.9833703,0.00086072116,0.00091944536,0.0005612029,0.011797809],"study_design_scores_gemma":[0.0000015686006,0.0000022930956,0.0001093727,3.7607873e-7,7.866033e-7,8.2417944e-7,0.0000011563235,0.99955696,0.00009094942,0.00017536711,0.0000592676,0.0000011122206],"about_ca_topic_score_codex":0.024322262,"about_ca_topic_score_gemma":0.027187714,"teacher_disagreement_score":0.024322262,"about_ca_system_score_codex":0.00085007393,"about_ca_system_score_gemma":0.00087916845,"threshold_uncertainty_score":0.04836142},"labels":[],"label_agreement":null},{"id":"W4402968940","doi":"10.1016/j.heliyon.2024.e37965","title":"Daily river flow simulation using ensemble disjoint aggregating M5-Prime model","year":2024,"lang":"en","type":"article","venue":"Heliyon","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Prince Edward Island","funders":"Natural Environment Research Council; Ministry of Environment; Korea Environmental Industry and Technology Institute; Ministry of Education - Singapore; University of Warwick","keywords":"Prime (order theory); Disjoint sets; Flow (mathematics); Mathematics; Computer science; Hydrology (agriculture); Geology; Geotechnical engineering; Combinatorics; Geometry","score_opus":0.04387888383445709,"score_gpt":0.28338700843083864,"score_spread":0.23950812459638154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402968940","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8776476,0.00031335157,0.11501224,0.00043554002,0.00007426806,0.000048888607,0.0010271874,0.00070352113,0.0047373236],"genre_scores_gemma":[0.9890777,0.00006205666,0.009713253,0.000036960144,0.000013715823,0.000028555167,0.00045907305,0.000010567056,0.00059814117],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998679,0.00004161277,0.0000065226363,0.000037142345,0.000023265928,0.000023543773],"domain_scores_gemma":[0.99967873,0.00013239597,0.000039893155,0.000035090878,0.00008729901,0.00002652307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061788486,0.0005270786,0.0005238611,0.0003288171,0.00031103514,0.00051057903,0.0007858512,0.0006656798,0.00066349655],"category_scores_gemma":[0.0011383735,0.0002173713,0.0006611919,0.00036138188,0.00026192772,0.00045205356,0.00048546967,0.00067900826,0.00011744811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002667625,0.00001876753,0.0026388394,0.0000070412743,0.000014949315,0.000019706033,0.00000919591,0.99228853,0.00022605849,0.00028209225,0.00021650411,0.0042516254],"study_design_scores_gemma":[0.0000011145344,0.0000032059786,0.00018023916,4.13078e-7,0.0000012836902,8.4510316e-7,0.0000014642205,0.99970776,0.000039324903,0.00004003789,0.000023462186,7.497002e-7],"about_ca_topic_score_codex":0.042057287,"about_ca_topic_score_gemma":0.02840216,"teacher_disagreement_score":0.042057287,"about_ca_system_score_codex":0.0005436932,"about_ca_system_score_gemma":0.00076074165,"threshold_uncertainty_score":0.08362496},"labels":[],"label_agreement":null},{"id":"W4403217079","doi":"10.2139/ssrn.4980387","title":"Enhancing Turbidity Modeling in the Mississippi River Using Machine Learning and Sentinel-2 Satellite Remote Sensing Data: A Generalizability Analysis","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Waterloo","funders":"","keywords":"Generalizability theory; Turbidity; Remote sensing; Satellite; Environmental science; Computer science; Geology; Engineering; Oceanography; Mathematics; Statistics","score_opus":0.05008717008496576,"score_gpt":0.29694691958730246,"score_spread":0.2468597495023367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403217079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9320957,0.00016867835,0.06442629,0.0008211492,0.000039216477,0.000069561975,0.00027250228,0.0003833023,0.0017235457],"genre_scores_gemma":[0.9868695,0.00006060775,0.012273615,0.00008617639,0.000029771116,0.000017843864,0.00033994546,0.00003816702,0.00028432856],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745065,0.0015800874,0.00009601576,0.0005410022,0.00024847392,0.000083794286],"domain_scores_gemma":[0.9803231,0.013616564,0.0010248019,0.0024281244,0.0024466692,0.00016080966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0105323605,0.00063933886,0.000522667,0.0006401968,0.00059609354,0.0012529088,0.0008195177,0.0010174792,0.00080829265],"category_scores_gemma":[0.034684617,0.00039849486,0.0011077136,0.00077713345,0.00058047025,0.002347077,0.0015409668,0.0010586734,0.00017971158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075428846,0.00045443996,0.120218955,0.00010262183,0.0007240734,0.00009378463,0.00026320008,0.8067089,0.0074302256,0.0015967541,0.0008427843,0.060809966],"study_design_scores_gemma":[0.000045484026,0.00013308825,0.015796153,0.000009523238,0.00013260455,0.000010411591,0.00006508293,0.979483,0.0027479145,0.0013756473,0.00018606223,0.000015143372],"about_ca_topic_score_codex":0.03957535,"about_ca_topic_score_gemma":0.025623895,"teacher_disagreement_score":0.03957535,"about_ca_system_score_codex":0.0010037965,"about_ca_system_score_gemma":0.0013156848,"threshold_uncertainty_score":0.07868999},"labels":[],"label_agreement":null},{"id":"W4403506978","doi":"10.1088/1748-9326/ad880a","title":"Seasonal prediction of North Atlantic sea surface temperature anomalies using the LSTM machine learning method","year":2024,"lang":"en","type":"article","venue":"Environmental Research Letters","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"National Science Foundation","keywords":"Sea surface temperature; Climatology; Oceanography; Tropical Atlantic; Environmental science; Geology; Artificial intelligence; Machine learning; Meteorology; Computer science; Geography","score_opus":0.036724540596887074,"score_gpt":0.30007887241397163,"score_spread":0.26335433181708456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403506978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80220246,0.0003254537,0.19288212,0.00041200666,0.00013193024,0.000022125818,0.0004622765,0.0008452368,0.0027162598],"genre_scores_gemma":[0.9842913,0.00006495067,0.014790708,0.000016315062,0.000013512924,0.000011863711,0.00019441423,0.000010748575,0.0006062599],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99993336,0.000018376288,0.000004405084,0.00001926373,0.000014409854,0.000010189468],"domain_scores_gemma":[0.9998374,0.00006715746,0.000022704422,0.000013354359,0.00004922073,0.0000101535325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028854894,0.00032176034,0.00020054662,0.00026898042,0.000157074,0.00024249974,0.00026649135,0.0002606736,0.00071424],"category_scores_gemma":[0.0009216184,0.00010663479,0.00022061412,0.0003417183,0.00009752829,0.0004210319,0.00017379202,0.0003865044,0.00012342683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009533639,0.00007255232,0.013105307,0.000033067343,0.00006916266,0.00006501657,0.000033579814,0.8821425,0.009787963,0.00082832976,0.0015852319,0.092182],"study_design_scores_gemma":[6.952756e-7,0.0000028343836,0.00051323423,5.0475876e-7,0.0000013170929,0.0000010206963,0.0000015181913,0.999092,0.00027903053,0.00007663539,0.000030316374,8.884724e-7],"about_ca_topic_score_codex":0.0141667975,"about_ca_topic_score_gemma":0.012328173,"teacher_disagreement_score":0.0141667975,"about_ca_system_score_codex":0.0003279246,"about_ca_system_score_gemma":0.0004669776,"threshold_uncertainty_score":0.028168678},"labels":[],"label_agreement":null},{"id":"W4403538275","doi":"10.1016/j.envsoft.2024.106247","title":"A Machine Learning-based framework and open-source software for Non Intrusive Water Monitoring","year":2024,"lang":"en","type":"article","venue":"Environmental Modelling & Software","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Open source software; Software; Open source; Software engineering; Artificial intelligence; Operating system","score_opus":0.019080346002798603,"score_gpt":0.24136375962935525,"score_spread":0.22228341362655665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403538275","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029466858,0.00012730616,0.68530774,0.00033967712,0.00012038137,0.000525902,0.01073835,0.29588157,0.004012447],"genre_scores_gemma":[0.06943072,0.0004251244,0.83615625,0.0008547402,0.00012335426,0.0033334994,0.04624526,0.034616247,0.00881482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985782,0.00018126387,0.00014095078,0.0004204808,0.000547781,0.00013127761],"domain_scores_gemma":[0.99784625,0.00079488446,0.00022806205,0.00047606477,0.00048104895,0.00017368804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023886613,0.0017088515,0.00091508264,0.0020720668,0.00073444337,0.0017539756,0.003664245,0.0008881912,0.01574681],"category_scores_gemma":[0.008519637,0.0011042394,0.0021140862,0.0020521875,0.0010351953,0.0031311053,0.0035657366,0.0032365695,0.01307228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006914385,0.0010758997,0.018385299,0.0025315178,0.0005758148,0.00075902813,0.00081558514,0.08935055,0.017381977,0.03872624,0.37471625,0.45499045],"study_design_scores_gemma":[0.00021784705,0.00013180154,0.0107190795,0.00028198463,0.00008044252,0.00048129255,0.00009306221,0.64432085,0.026199793,0.066178136,0.25107193,0.00022384092],"about_ca_topic_score_codex":0.008569845,"about_ca_topic_score_gemma":0.008836482,"teacher_disagreement_score":0.01574681,"about_ca_system_score_codex":0.0012725494,"about_ca_system_score_gemma":0.0037510346,"threshold_uncertainty_score":0.052678287},"labels":[],"label_agreement":null},{"id":"W4403755545","doi":"10.2139/ssrn.5000043","title":"Improved Streamflow Prediction Accuracy in Boreal Climate Watershed Using a Lstm Model: A Comparative Study","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Streamflow; Watershed; Climatology; Boreal; Stream flow; Environmental science; Climate change; Taiga; Physical geography; Meteorology; Hydrology (agriculture); Geography; Geology; Machine learning; Computer science; Cartography; Oceanography; Forestry; Drainage basin; Archaeology","score_opus":0.038575385479628486,"score_gpt":0.3098789354503793,"score_spread":0.27130354997075085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403755545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918073,0.00028149816,0.0060409354,0.00013894297,0.000060392566,0.000008458844,0.00026482058,0.0002487852,0.0011488497],"genre_scores_gemma":[0.9972018,0.000082516766,0.002212625,0.000013699425,0.000014290077,0.00000387736,0.00024380133,0.000012362056,0.00021501012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997273,0.0000682715,0.00002432281,0.000091354654,0.00004672044,0.000042042524],"domain_scores_gemma":[0.99906856,0.00043649747,0.000057891273,0.00009071099,0.0003021584,0.000044212047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012691681,0.00052590785,0.0005218954,0.0004144672,0.00033380822,0.000830066,0.0006831338,0.0007600833,0.0007845004],"category_scores_gemma":[0.0024320083,0.00017427874,0.00049695384,0.0006412495,0.0002450471,0.0014067302,0.00029796074,0.00045597847,0.00014088456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015462028,0.00076029834,0.06234311,0.00015575193,0.0003658593,0.00017802397,0.00016224655,0.78136766,0.015771298,0.00091596117,0.0020390148,0.13439451],"study_design_scores_gemma":[0.000021431231,0.00013523219,0.012008636,0.000005062477,0.00006237328,0.000012762753,0.000034179695,0.9852991,0.002052395,0.0001624319,0.00019245534,0.000014023345],"about_ca_topic_score_codex":0.03613154,"about_ca_topic_score_gemma":0.019769762,"teacher_disagreement_score":0.03613154,"about_ca_system_score_codex":0.00058085937,"about_ca_system_score_gemma":0.000825792,"threshold_uncertainty_score":0.07184243},"labels":[],"label_agreement":null},{"id":"W4403781088","doi":"10.48550/arxiv.2409.15213","title":"HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Concordia University; Canada Excellence Research Chairs, Government of Canada","keywords":"Lidar; Transformer; Computer science; Artificial intelligence; Graph; Computer vision; Machine learning; Geology; Remote sensing; Engineering; Electrical engineering; Theoretical computer science; Voltage","score_opus":0.033964564170713855,"score_gpt":0.17961795710412204,"score_spread":0.14565339293340818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403781088","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04416954,0.0002126458,0.9470207,0.00026053237,0.00007166328,0.000068308065,0.00034912323,0.0057805055,0.0020670267],"genre_scores_gemma":[0.70785123,0.0001644192,0.28603926,0.0002385819,0.000055160628,0.00007977353,0.0013007341,0.00031054515,0.00396044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998142,0.000026005902,0.00000620513,0.00007350649,0.000053595555,0.00002646183],"domain_scores_gemma":[0.99963963,0.00011037934,0.00003804094,0.00007772484,0.000091872316,0.00004234694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003905711,0.00067052717,0.00045545158,0.0009386864,0.00027897942,0.0007824688,0.0016479801,0.0008563628,0.0017036201],"category_scores_gemma":[0.0013925768,0.00037076973,0.0005398942,0.0009601452,0.00053432095,0.0015726337,0.0010549874,0.0010042666,0.00063429715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014391232,0.00018830824,0.0028412135,0.000056121633,0.00008238252,0.0000919538,0.00006218132,0.57636154,0.009392204,0.0074656485,0.006434346,0.3968802],"study_design_scores_gemma":[0.000004398584,0.0000087145645,0.0001312672,0.0000012424845,0.000001996029,0.000006425919,0.0000036300314,0.99718755,0.00068387605,0.0017028559,0.00026523607,0.0000028236063],"about_ca_topic_score_codex":0.024159852,"about_ca_topic_score_gemma":0.028052801,"teacher_disagreement_score":0.024159852,"about_ca_system_score_codex":0.0010216073,"about_ca_system_score_gemma":0.00095661834,"threshold_uncertainty_score":0.048038423},"labels":[],"label_agreement":null},{"id":"W4404524549","doi":"10.1016/j.jenvman.2024.123305","title":"Machine learning models for prediction of nutrient concentrations in surface water in an agricultural watershed","year":2024,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ministry of the Environment, Conservation and Parks; University of Guelph","funders":"","keywords":"Watershed; Agriculture; Nutrient; Surface water; Environmental science; Water quality; Hydrology (agriculture); Agricultural engineering; Water resource management; Machine learning; Environmental engineering; Computer science; Engineering; Ecology; Biology","score_opus":0.01940810971268389,"score_gpt":0.2141128197977494,"score_spread":0.1947047100850655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404524549","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88897943,0.0014110341,0.10447884,0.0005421704,0.000043858716,0.00013564523,0.0014242806,0.0008542014,0.0021304984],"genre_scores_gemma":[0.98074096,0.0003336352,0.016843619,0.000035000554,0.000015750247,0.00008747639,0.0009073661,0.000012311591,0.0010238122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967027,0.00008799706,0.00003296741,0.00008252979,0.00007934095,0.000046800273],"domain_scores_gemma":[0.99869776,0.00091875833,0.00013869854,0.000025424913,0.00019335604,0.000025949083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011623063,0.00087522174,0.00060251006,0.0008957334,0.00038736276,0.0008211213,0.0009052692,0.0007440708,0.0006721904],"category_scores_gemma":[0.003374248,0.00024076703,0.0005822359,0.001208609,0.0002856805,0.0004910738,0.00037383358,0.00075650704,0.00018510428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051193296,0.000054239674,0.009151519,0.000029676707,0.00003616568,0.000037044585,0.000028075377,0.9733589,0.00039101907,0.00020672334,0.00028345015,0.016372014],"study_design_scores_gemma":[0.0000022751778,0.0000071825434,0.0010025181,0.0000022177837,0.0000033745869,0.0000021174556,0.000008856503,0.9987066,0.00009187581,0.00011128929,0.000059796366,0.0000019172337],"about_ca_topic_score_codex":0.21923965,"about_ca_topic_score_gemma":0.140196,"teacher_disagreement_score":0.21923965,"about_ca_system_score_codex":0.0021976011,"about_ca_system_score_gemma":0.0019551858,"threshold_uncertainty_score":0.4359271},"labels":[],"label_agreement":null},{"id":"W4404584729","doi":"10.1007/s43832-024-00109-6","title":"Review of machine learning algorithms used in groundwater availability studies in Africa: analysis of geological and climate input variables","year":2024,"lang":"en","type":"article","venue":"Discover Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"West African Science Service Centre on Climate Change and Adapted Land Use; International Development Research Centre","keywords":"Groundwater; Algorithm; Computer science; Environmental science; Machine learning; Artificial intelligence; Geology; Geotechnical engineering","score_opus":0.04862110595107995,"score_gpt":0.29502507064537026,"score_spread":0.24640396469429032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404584729","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030836412,0.9803191,0.011605776,0.0010178458,0.00035465186,0.000041440413,0.0002252029,0.000049382365,0.003302985],"genre_scores_gemma":[0.019017998,0.963784,0.015525071,0.00031844882,0.00033560372,0.00005801154,0.00028226004,0.00001836283,0.00066022185],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99877673,0.0004162871,0.00030251985,0.00015769586,0.00030579994,0.000041013598],"domain_scores_gemma":[0.9885451,0.009462264,0.0005334898,0.00013876188,0.0012611757,0.00005926647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031773339,0.0007535438,0.0010719263,0.0044036633,0.00029609737,0.0014486271,0.0009284764,0.0008038235,0.0015768192],"category_scores_gemma":[0.010222333,0.00033025,0.0011655416,0.0074970787,0.0003322813,0.0015233343,0.0003416852,0.0007663979,0.0006066542],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000755963,0.00006090215,0.0028308711,0.03820708,0.00039841753,0.00016742593,0.0002333612,0.0061451388,0.0010979174,0.0062402915,0.009417264,0.9351258],"study_design_scores_gemma":[0.00003781663,0.00069527444,0.02427049,0.059026916,0.0022189948,0.0016109181,0.001033375,0.023814043,0.007632143,0.017572245,0.8618876,0.00020008927],"about_ca_topic_score_codex":0.002477273,"about_ca_topic_score_gemma":0.0023505464,"teacher_disagreement_score":0.0044036633,"about_ca_system_score_codex":0.00072757114,"about_ca_system_score_gemma":0.0015989816,"threshold_uncertainty_score":0.016803503},"labels":[],"label_agreement":null},{"id":"W4404749486","doi":"10.1061/jhyeff.heeng-6280","title":"Data-Driven Gray Box Modeling for Predicting Basin-Scale Groundwater Variations in Central Taiwan","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Smiths Detection (Canada)","funders":"","keywords":"Gray (unit); Structural basin; Scale (ratio); Groundwater; Hydrological modelling; Hydrology (agriculture); Geology; Environmental science; Cartography; Geomorphology; Climatology; Geography; Geotechnical engineering","score_opus":0.025262931175078367,"score_gpt":0.24366263131623728,"score_spread":0.21839970014115892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404749486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81118935,0.0003004489,0.18529977,0.00028712332,0.00003534811,0.000048685997,0.0005994025,0.0006596576,0.001580221],"genre_scores_gemma":[0.9880391,0.00007480575,0.011151214,0.00002395299,0.0000056467125,0.000033416807,0.00024418518,0.000019292935,0.00040840704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99989545,0.00003130483,0.0000071377794,0.000033729368,0.000013669443,0.00001867515],"domain_scores_gemma":[0.9996432,0.0002072318,0.000046475925,0.000025546395,0.00005607131,0.000021404783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046844524,0.000611123,0.00042770116,0.00051272195,0.00022414158,0.00061932375,0.0007513064,0.00061334675,0.0005252938],"category_scores_gemma":[0.0012255126,0.0003588399,0.0005477084,0.00059050944,0.00037601526,0.00054121297,0.00050272065,0.00041621906,0.000060914033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016341086,0.0000129877835,0.0025650598,0.000009812354,0.000013648866,0.00003326372,0.000015768272,0.99364376,0.0006212461,0.00037167565,0.00005106748,0.0026453545],"study_design_scores_gemma":[8.162161e-7,0.0000022237448,0.00018842574,5.6853725e-7,0.0000011758915,8.3174797e-7,0.0000025753343,0.9996191,0.00007058564,0.00009240415,0.000019991481,0.0000012775386],"about_ca_topic_score_codex":0.055958457,"about_ca_topic_score_gemma":0.029078495,"teacher_disagreement_score":0.055958457,"about_ca_system_score_codex":0.00081502466,"about_ca_system_score_gemma":0.0010394765,"threshold_uncertainty_score":0.11126548},"labels":[],"label_agreement":null},{"id":"W4404753959","doi":"10.1007/s11269-024-04037-x","title":"Assessing the Impact of Rainfall Nowcasts on an Encoder-Decoder LSTM Model for Short-Term Flash Flood Prediction","year":2024,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Flash flood; Term (time); Flash (photography); Nowcasting; Flood myth; Computer science; Meteorology; Environmental science; Climatology; Geology; Geography","score_opus":0.042608970350337415,"score_gpt":0.3200303655802326,"score_spread":0.27742139522989523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404753959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97735745,0.0005517623,0.016869351,0.00086959463,0.00027119572,0.000032548094,0.0008494534,0.0005541046,0.002644436],"genre_scores_gemma":[0.99458426,0.00010384248,0.0039588055,0.00007363646,0.00002675932,0.000009588443,0.0005907511,0.000021543918,0.0006308618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974936,0.000089354,0.000019078292,0.000052302414,0.00003922474,0.000050668736],"domain_scores_gemma":[0.99588495,0.0032282548,0.00009388774,0.00013475966,0.00050803757,0.00015009615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018795461,0.0007526862,0.00043754186,0.000291564,0.0003208879,0.00070493144,0.00064655417,0.0012557721,0.0021277352],"category_scores_gemma":[0.0078061516,0.00041451838,0.00038203964,0.00026510414,0.00031958695,0.0014703493,0.00063560123,0.0017555001,0.00033263664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013955537,0.0002516994,0.0067992066,0.00009714294,0.00016154328,0.000109580265,0.00003766269,0.951226,0.0045805844,0.0007987038,0.0014683941,0.033073988],"study_design_scores_gemma":[0.000030313173,0.00007453076,0.0013245271,0.000005400396,0.000027098566,0.0000052127334,0.000012621007,0.9968195,0.0013933824,0.00021468289,0.000085277024,0.0000074881464],"about_ca_topic_score_codex":0.046039116,"about_ca_topic_score_gemma":0.044552322,"teacher_disagreement_score":0.046039116,"about_ca_system_score_codex":0.000888614,"about_ca_system_score_gemma":0.0014809086,"threshold_uncertainty_score":0.091542244},"labels":[],"label_agreement":null},{"id":"W4404878833","doi":"10.1016/j.envc.2024.101056","title":"Robust prediction of chlorophyll-A from nitrogen and phosphorus content in Philippine and global lakes using fine-tuned, explainable machine learning","year":2024,"lang":"en","type":"article","venue":"Environmental Challenges","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Philippine Council for Industry, Energy, and Emerging Technology Research and Development; Department of Science and Technology, Philippines; University of the Philippines","keywords":"Phosphorus; Nitrogen; Chlorophyll a; Content (measure theory); Computer science; Environmental science; Artificial intelligence; Mathematics; Chemistry; Materials science; Metallurgy","score_opus":0.05659747086337839,"score_gpt":0.21349444955609256,"score_spread":0.15689697869271418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404878833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81922185,0.00027508577,0.17702785,0.00044064052,0.000023142142,0.000056694113,0.0004053253,0.0014018734,0.0011476225],"genre_scores_gemma":[0.981908,0.000041435953,0.017285824,0.000038746995,0.000008159791,0.00002634568,0.0003467268,0.000029412291,0.0003153362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957854,0.0001754122,0.000026929032,0.00013685123,0.000038053062,0.00004423423],"domain_scores_gemma":[0.99814117,0.0010219067,0.00027783948,0.00017383715,0.00032940772,0.00005585538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024144792,0.0008486498,0.0004236636,0.00059314765,0.00028344686,0.0007744067,0.0006517227,0.00072622835,0.00044032958],"category_scores_gemma":[0.005001715,0.00041692588,0.000982642,0.00040543597,0.00034108508,0.0007915594,0.0005390347,0.000886545,0.00013540815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036762103,0.000047537276,0.008598495,0.000021215892,0.00008093561,0.000034919532,0.000036077232,0.9795706,0.0015929084,0.00023362748,0.00013614135,0.009610816],"study_design_scores_gemma":[0.0000035458784,0.00001733669,0.0027635922,0.0000023641871,0.000008076769,0.0000036488582,0.0000063423463,0.99641114,0.00051624223,0.00021030263,0.000050117647,0.0000072033704],"about_ca_topic_score_codex":0.029386671,"about_ca_topic_score_gemma":0.022986766,"teacher_disagreement_score":0.029386671,"about_ca_system_score_codex":0.0010785265,"about_ca_system_score_gemma":0.0012146096,"threshold_uncertainty_score":0.058431268},"labels":[],"label_agreement":null},{"id":"W4405079415","doi":"10.1007/s12145-024-01623-w","title":"Application of machine learning and deep learning for predicting groundwater levels in the West Coast Aquifer System, South Africa","year":2024,"lang":"en","type":"article","venue":"Earth Science Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"University of the Western Cape","keywords":"Groundwater recharge; Groundwater; Aquifer; Support vector machine; Machine learning; Artificial intelligence; Mean squared error; Random forest; Artificial neural network; Deep learning; Computer science; Hydrology (agriculture); Data mining; Geology; Statistics; Geotechnical engineering; Mathematics","score_opus":0.017936133787386375,"score_gpt":0.23533868987319873,"score_spread":0.21740255608581235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405079415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99066997,0.0001595776,0.007584936,0.00022974769,0.000011437537,0.000028264636,0.00028876486,0.000100560384,0.000926783],"genre_scores_gemma":[0.9959221,0.000053335418,0.0036158503,0.000006447486,0.0000021843987,0.000009296563,0.00010964558,0.000002838251,0.00027833122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998778,0.000033912034,0.000013251816,0.00002664369,0.000029043093,0.00001930706],"domain_scores_gemma":[0.9996252,0.00018163538,0.000052587442,0.000017826964,0.00010277766,0.000020036516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034958206,0.00054250157,0.0002486529,0.00070016144,0.00030303551,0.00046007647,0.0003473238,0.00045263633,0.00058116147],"category_scores_gemma":[0.0010303741,0.0001757094,0.00036573314,0.00058220926,0.00017931052,0.0005049815,0.00035447284,0.00035389294,0.000092001355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018836981,0.00013954936,0.10317605,0.0001293868,0.00009595424,0.00071278884,0.00024722877,0.8138082,0.008071774,0.00072168943,0.0006344895,0.072074495],"study_design_scores_gemma":[0.0000071019576,0.000047047764,0.016065443,0.000014537736,0.000011994187,0.000025973075,0.00016516839,0.98052615,0.0025975641,0.00024511688,0.0002856228,0.000008230609],"about_ca_topic_score_codex":0.060112085,"about_ca_topic_score_gemma":0.05305829,"teacher_disagreement_score":0.060112085,"about_ca_system_score_codex":0.0009796232,"about_ca_system_score_gemma":0.00074374006,"threshold_uncertainty_score":0.11952442},"labels":[],"label_agreement":null},{"id":"W4405109538","doi":"10.1680/jenes.23.00104","title":"Trend analysis and learning-based groundwater level modelling over a tropical river basin","year":2024,"lang":"en","type":"article","venue":"Journal of Environmental Engineering and Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Groundwater; Drainage basin; Environmental science; Structural basin; Hydrology (agriculture); Water resource management; Geography; Geology; Cartography; Geomorphology","score_opus":0.013056876704261925,"score_gpt":0.20136553854356684,"score_spread":0.18830866183930492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405109538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9339974,0.00010775831,0.06239237,0.0001801347,0.000013019105,0.000026693046,0.0010026693,0.0003487845,0.0019311684],"genre_scores_gemma":[0.9914818,0.00007428715,0.0075774738,0.0000064720393,0.0000048486186,0.000013661994,0.00035142992,0.00001298735,0.0004770742],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99988496,0.000025228588,0.00001378897,0.000041070343,0.000013904953,0.000020916312],"domain_scores_gemma":[0.99969614,0.00015478751,0.000053724063,0.000018987865,0.000060474715,0.000015987189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003970647,0.0003348789,0.0003028472,0.00060284603,0.00024146774,0.0006145856,0.00046563562,0.0003848143,0.0007105752],"category_scores_gemma":[0.0011275832,0.00019177403,0.00046388304,0.0011330756,0.00021714489,0.0005351071,0.00031066913,0.00035413893,0.00008859348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016153148,0.0000111006675,0.007767244,0.000012355001,0.000012484316,0.000022851806,0.00002110176,0.98415405,0.00032183906,0.0004298308,0.00008923207,0.0071418067],"study_design_scores_gemma":[0.0000010546551,0.000005037552,0.0014970814,0.000001152338,0.0000022439865,0.0000030334422,0.000010592793,0.998104,0.000083112434,0.00022720602,0.0000636154,0.0000019878626],"about_ca_topic_score_codex":0.061685048,"about_ca_topic_score_gemma":0.03943469,"teacher_disagreement_score":0.061685048,"about_ca_system_score_codex":0.00081588706,"about_ca_system_score_gemma":0.00075476663,"threshold_uncertainty_score":0.122651994},"labels":[],"label_agreement":null},{"id":"W4405807634","doi":"10.1016/j.rineng.2024.103840","title":"Prediction of three vital rainfall characteristics: Advanced hybrid tree- or lazy-based learner?","year":2024,"lang":"en","type":"article","venue":"Results in Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Prince Edward Island","funders":"National Research Foundation of Korea; Ministry of Environment; Korea Environmental Industry and Technology Institute; Ministry of Education - Singapore","keywords":"Computer science; Tree (set theory); Mathematics","score_opus":0.018392567189501767,"score_gpt":0.21727092521788013,"score_spread":0.19887835802837836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405807634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.686126,0.0006794463,0.30871257,0.00027698049,0.00006266102,0.00007566656,0.0002779035,0.0009250393,0.0028637124],"genre_scores_gemma":[0.98073363,0.00010131988,0.017644778,0.000041212035,0.000013809963,0.000030226623,0.00022601323,0.000013007429,0.0011959766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982893,0.000036338806,0.000012087163,0.00005534442,0.000036279907,0.000031087715],"domain_scores_gemma":[0.9996574,0.00015886496,0.00004576668,0.000024894922,0.00008955325,0.000023596398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007541012,0.00039605497,0.0006742792,0.00036334927,0.00019296168,0.00054755155,0.0007712539,0.00048400983,0.00067197904],"category_scores_gemma":[0.0010945242,0.00014814115,0.00043850788,0.00036299246,0.00014890321,0.00061146705,0.00042436246,0.00042458603,0.0001891232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001940148,0.0001488663,0.014938845,0.0000439839,0.00008975154,0.000081426886,0.00005188257,0.87343824,0.0023815415,0.0007422896,0.00079680333,0.107092395],"study_design_scores_gemma":[0.0000033335775,0.000027633758,0.000556576,0.0000016254709,0.0000054763627,0.000007751931,0.000006121198,0.99878293,0.00038641458,0.00015198218,0.00006764266,0.0000023646269],"about_ca_topic_score_codex":0.006472474,"about_ca_topic_score_gemma":0.0062614465,"teacher_disagreement_score":0.006472474,"about_ca_system_score_codex":0.00030494106,"about_ca_system_score_gemma":0.0006798335,"threshold_uncertainty_score":0.0128695965},"labels":[],"label_agreement":null},{"id":"W4405865318","doi":"10.1016/j.wroa.2024.100297","title":"Effectiveness of three machine learning models for prediction of daily streamflow and uncertainty assessment","year":2024,"lang":"en","type":"article","venue":"Water Research X","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Streamflow; Machine learning; Computer science; Artificial intelligence; Geography; Cartography","score_opus":0.09157816675049053,"score_gpt":0.3473567677343218,"score_spread":0.25577860098383126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405865318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58220196,0.0016245504,0.40491164,0.0013975617,0.00021472605,0.00012266792,0.00048672024,0.0011077595,0.007932445],"genre_scores_gemma":[0.9752959,0.00019241092,0.023646459,0.0000652055,0.000019853147,0.000036437705,0.00022295973,0.00001791408,0.0005029013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988336,0.0004106707,0.000118065465,0.000225841,0.0003125571,0.00009919577],"domain_scores_gemma":[0.99478984,0.0035791497,0.00043356765,0.00021226125,0.00085896975,0.00012632702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044120606,0.0013466593,0.0007199672,0.0011398895,0.0004934335,0.00196174,0.0012185182,0.0010796229,0.000707847],"category_scores_gemma":[0.011151436,0.00040739286,0.0009554519,0.00068506034,0.00057452,0.003032423,0.0010450543,0.0012673651,0.00014780056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001787348,0.000083242354,0.0073890076,0.00007157473,0.00013937574,0.00005262,0.000043492902,0.9452372,0.0008339941,0.003090115,0.0003312945,0.042549394],"study_design_scores_gemma":[0.0000030394892,0.00002700789,0.0004918107,0.0000063651664,0.000011554961,0.000007717278,0.000008707921,0.9978662,0.0005372749,0.000976198,0.000058112826,0.0000061116616],"about_ca_topic_score_codex":0.0118766,"about_ca_topic_score_gemma":0.00901926,"teacher_disagreement_score":0.0118766,"about_ca_system_score_codex":0.0018240989,"about_ca_system_score_gemma":0.0020740249,"threshold_uncertainty_score":0.023614943},"labels":[],"label_agreement":null},{"id":"W4406118966","doi":"10.1061/jhyeff.heeng-6270","title":"Discussion of “Application of a Hybrid Model Based on Secondary Decomposition and ELM Neural Network in Water Level Prediction”","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval","funders":"","keywords":"Artificial neural network; Decomposition; Computer science; Hydrological modelling; Environmental science; Artificial intelligence; Climatology; Geology; Ecology","score_opus":0.00771417261225705,"score_gpt":0.21861963299614584,"score_spread":0.2109054603838888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406118966","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028577272,0.0010997887,0.90792406,0.027438259,0.003691033,0.00013532683,0.00019754433,0.00057683885,0.030359933],"genre_scores_gemma":[0.72249603,0.0012494752,0.22709525,0.008545171,0.0023057258,0.00027911723,0.00019903904,0.0001485185,0.037681613],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99956685,0.00017213411,0.000029029852,0.00007185615,0.0001264136,0.000033655953],"domain_scores_gemma":[0.99942386,0.00021087234,0.00002946643,0.00006541604,0.00024883804,0.000021504424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020063529,0.00037807482,0.0003365597,0.00031209944,0.0005823764,0.0010719544,0.0018407737,0.0025458254,0.0036982286],"category_scores_gemma":[0.0040876833,0.00019490324,0.00073385396,0.0003258826,0.000928629,0.0013768466,0.00067731657,0.0011258653,0.00067234837],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021866942,0.00013797978,0.0033140609,0.00029600816,0.00026284737,0.0011144937,0.00022604858,0.44443956,0.013096767,0.42195216,0.02650661,0.08843471],"study_design_scores_gemma":[0.000030763073,0.0000823436,0.00086725067,0.000041748655,0.000035676534,0.00015110234,0.000057269775,0.8807287,0.006326646,0.09355196,0.018093642,0.00003277999],"about_ca_topic_score_codex":0.0052384166,"about_ca_topic_score_gemma":0.0044744955,"teacher_disagreement_score":0.0052384166,"about_ca_system_score_codex":0.0005067516,"about_ca_system_score_gemma":0.00065824715,"threshold_uncertainty_score":0.012371838},"labels":[],"label_agreement":null},{"id":"W4406445616","doi":"10.1016/s0967-0653(97)86812-3","title":"10.1016/s0967-0653(97)86812-3","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Range (aeronautics); Tidal range; Flow (mathematics); Geology; Environmental science; Oceanography; Mechanics; Physics; Estuary; Aerospace engineering; Engineering","score_opus":0.01017059208742541,"score_gpt":0.17635090005383305,"score_spread":0.16618030796640765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406445616","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005887503,0.00048164575,0.0011910081,0.00045783844,0.00032183662,0.00013984152,0.0012437395,0.0011545225,0.9944207],"genre_scores_gemma":[0.0007929761,0.00021540499,0.0005502959,0.00022816377,0.00006671886,0.00006790091,0.0005116922,0.00019104347,0.99737585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99923587,0.000066136454,0.00007122225,0.00027310953,0.00021003916,0.00014370905],"domain_scores_gemma":[0.997535,0.0007870793,0.00017670389,0.0003433496,0.00055538886,0.0006024787],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013020136,0.0026867418,0.001749071,0.0029694652,0.001787786,0.0037323728,0.003296874,0.005294185,0.9880177],"category_scores_gemma":[0.0019546843,0.0009305545,0.0014048571,0.0030765922,0.0017851332,0.0056619076,0.0029130464,0.0027915956,0.99167436],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039070944,0.00024529663,0.0009813796,0.00058310997,0.00004522605,0.0002459607,0.00010428038,0.0005900232,0.0020543956,0.0056678047,0.33261797,0.6564739],"study_design_scores_gemma":[0.000069640584,0.00015724609,0.0008189874,0.00042405137,0.000021950047,0.0003472555,0.0001227906,0.00045341562,0.00047572597,0.00081965275,0.9962559,0.00003332386],"about_ca_topic_score_codex":0.0041958615,"about_ca_topic_score_gemma":0.0033675951,"teacher_disagreement_score":0.011982322,"about_ca_system_score_codex":0.0010697687,"about_ca_system_score_gemma":0.0009921418,"threshold_uncertainty_score":0.017091215},"labels":[],"label_agreement":null},{"id":"W4406505632","doi":"10.1016/s0967-0653(98)81657-8","title":"10.1016/s0967-0653(98)81657-8","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Environmental science; Water quality; Physics; Biology; Ecology","score_opus":0.008586232574342535,"score_gpt":0.1755143276771541,"score_spread":0.16692809510281156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406505632","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005699544,0.00045647888,0.0010287106,0.0004500576,0.00029834468,0.00013309275,0.001101522,0.0011012483,0.9948605],"genre_scores_gemma":[0.00077361264,0.00020883318,0.0005102407,0.00024148884,0.0000655521,0.00006887171,0.0004717182,0.00018517835,0.9974745],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999265,0.00006438634,0.00007069527,0.00026204385,0.0001979471,0.00013992474],"domain_scores_gemma":[0.99744034,0.0008196511,0.00018239839,0.00035036574,0.00055659754,0.0006506316],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013230407,0.0026438762,0.0017248826,0.0029745717,0.0018928509,0.0036611783,0.0032844485,0.005454135,0.9882951],"category_scores_gemma":[0.002065533,0.0009376652,0.0014062572,0.0029101174,0.0018965835,0.0059204292,0.0030127843,0.0028079788,0.99193734],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039519323,0.0002487805,0.001026046,0.00058687007,0.000044226777,0.00024931453,0.00011344654,0.0005559573,0.0019423898,0.00565739,0.3460207,0.64315975],"study_design_scores_gemma":[0.00007212473,0.00016425873,0.00085832423,0.00045250377,0.000021634716,0.0003526041,0.00013971014,0.00043888044,0.00043126688,0.0008553009,0.9961809,0.00003256567],"about_ca_topic_score_codex":0.004293676,"about_ca_topic_score_gemma":0.0032683625,"teacher_disagreement_score":0.011704922,"about_ca_system_score_codex":0.001031337,"about_ca_system_score_gemma":0.0009830999,"threshold_uncertainty_score":0.016695559},"labels":[],"label_agreement":null},{"id":"W4406585375","doi":"10.1016/s0967-0653(98)84291-9","title":"10.1016/s0967-0653(98)84291-9","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Trophic level; Environmental science; Structural basin; Seasonality; Geography; Climatology; Ecology; Biology; Geology; Geomorphology","score_opus":0.008583455812164312,"score_gpt":0.1754593702516269,"score_spread":0.1668759144394626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406585375","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061519287,0.00047822326,0.0010580665,0.0004731912,0.00029769604,0.0001442802,0.0012188113,0.0011569059,0.9945576],"genre_scores_gemma":[0.0008184241,0.0002254789,0.00056698633,0.0002620347,0.00006767387,0.000075338285,0.0005094856,0.00019777079,0.99727684],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992568,0.00006653012,0.00007158486,0.0002676106,0.00019524457,0.00014226769],"domain_scores_gemma":[0.99740773,0.00087461027,0.00018365718,0.00035265204,0.0005321313,0.0006492808],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013852193,0.0027326492,0.0018148965,0.003027678,0.0019880335,0.0036783863,0.0032849247,0.005662061,0.98865217],"category_scores_gemma":[0.00214344,0.0009805182,0.001419128,0.0029821412,0.0019764786,0.0061265803,0.0030936878,0.002943826,0.9920586],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041183215,0.00027270318,0.001056423,0.00060534885,0.00004618241,0.0002606859,0.00011886765,0.0005943632,0.0019410414,0.0055779614,0.34987798,0.6392366],"study_design_scores_gemma":[0.000082579434,0.0001809217,0.0009818309,0.00048954604,0.000024147084,0.0003764161,0.00015333423,0.00049207016,0.00047168956,0.0009149075,0.99579537,0.000037084665],"about_ca_topic_score_codex":0.004420302,"about_ca_topic_score_gemma":0.0034302997,"teacher_disagreement_score":0.01134783,"about_ca_system_score_codex":0.001049857,"about_ca_system_score_gemma":0.0009923569,"threshold_uncertainty_score":0.016186297},"labels":[],"label_agreement":null},{"id":"W4406767015","doi":"10.1007/978-3-031-77389-1_11","title":"HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Transformer; Lidar; Artificial intelligence; Graph; Machine learning; Remote sensing; Electrical engineering; Theoretical computer science; Geology; Engineering; Voltage","score_opus":0.00896373670907442,"score_gpt":0.22041959936987796,"score_spread":0.21145586266080355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406767015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050390135,0.0004484264,0.9820888,0.00011993825,0.000115051924,0.000038810715,0.00034352415,0.006921739,0.004884645],"genre_scores_gemma":[0.19983491,0.0009526515,0.7658616,0.00029651241,0.00016446791,0.00012031124,0.0023956874,0.001732581,0.028641345],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998431,0.000013108358,0.0000048425404,0.000054400967,0.00007054041,0.000013941803],"domain_scores_gemma":[0.9998869,0.000028415192,0.00000689318,0.000030287678,0.00003565117,0.000011832524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020924349,0.0005914546,0.00048704445,0.0005845805,0.0001819607,0.0007837875,0.0015014433,0.0006782393,0.0061092135],"category_scores_gemma":[0.00043933064,0.0004517462,0.00041812332,0.0009121504,0.0004227786,0.001308314,0.0010028133,0.0008620108,0.0031316932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010001319,0.000088036795,0.00036158858,0.00008173246,0.000042302476,0.00005193334,0.00003201715,0.08453242,0.013524425,0.010570483,0.024755754,0.86585927],"study_design_scores_gemma":[0.000014261032,0.00003053233,0.00044319694,0.000010730486,0.000009823867,0.00006761166,0.000010340836,0.96140206,0.009807202,0.01523715,0.012949501,0.000017608245],"about_ca_topic_score_codex":0.0052739414,"about_ca_topic_score_gemma":0.00820625,"teacher_disagreement_score":0.0061092135,"about_ca_system_score_codex":0.00041804323,"about_ca_system_score_gemma":0.00047134393,"threshold_uncertainty_score":0.02043736},"labels":[],"label_agreement":null},{"id":"W4406939387","doi":"10.2139/ssrn.5117066","title":"Evaluation of Deep Learning Methods for Forecasting Turbidity in River Networks Using Sentinel-2 Remote Sensing Data","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Turbidity; Remote sensing; Deep learning; Computer science; Artificial intelligence; Environmental science; Meteorology; Geology; Geography; Oceanography","score_opus":0.13229237386939988,"score_gpt":0.39329490736576295,"score_spread":0.26100253349636304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406939387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9384952,0.0029516206,0.04925022,0.0012515624,0.00045256948,0.00015029094,0.0016157583,0.0014635519,0.0043692384],"genre_scores_gemma":[0.97607213,0.0005033061,0.019462014,0.00013178887,0.00006835057,0.000062454485,0.002074968,0.000062443585,0.0015625589],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924314,0.00028866003,0.00008131213,0.0001527854,0.00014762628,0.00008654938],"domain_scores_gemma":[0.99449867,0.0037139887,0.00022078732,0.0003021736,0.0010664045,0.00019801517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048273774,0.0018119506,0.00084828166,0.0009555316,0.000435664,0.0009828227,0.0012688435,0.0018728649,0.0012935097],"category_scores_gemma":[0.008961199,0.000457066,0.0007217877,0.00075621845,0.0005066673,0.0013761931,0.00103356,0.0013558497,0.00037359382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092009694,0.000671956,0.010436316,0.0002086673,0.00031508814,0.000057042053,0.000048180213,0.8873573,0.0017715081,0.0006697615,0.0029375649,0.09460651],"study_design_scores_gemma":[0.000023855842,0.0000825559,0.00072709075,0.000009647201,0.000017151415,0.0000036026208,0.0000103826405,0.99816763,0.0007048725,0.0001702217,0.00007885514,0.000004079969],"about_ca_topic_score_codex":0.035373997,"about_ca_topic_score_gemma":0.020668669,"teacher_disagreement_score":0.035373997,"about_ca_system_score_codex":0.0012253947,"about_ca_system_score_gemma":0.0013510212,"threshold_uncertainty_score":0.07033616},"labels":[],"label_agreement":null},{"id":"W4407291306","doi":"10.1080/15715124.2024.2444680","title":"Decomposing streamflow for improved river flow prediction accuracy of machine learning models","year":2025,"lang":"en","type":"article","venue":"International Journal of River Basin Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Institute for Catastrophic Loss Reduction","keywords":"Streamflow; Stream flow; Flow (mathematics); Hydrology (agriculture); Environmental science; Machine learning; Computer science; Geology; Mathematics; Geotechnical engineering; Drainage basin; Geography; Cartography","score_opus":0.015601405879596549,"score_gpt":0.26150710934297056,"score_spread":0.245905703463374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407291306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17159526,0.0007146042,0.8229161,0.00034614993,0.00007960882,0.000071733164,0.00027227655,0.0013758393,0.0026284184],"genre_scores_gemma":[0.8694044,0.0003417109,0.12822716,0.000091738104,0.000041103795,0.00008077519,0.0005898539,0.0000786886,0.0011445308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99971896,0.00009941275,0.000019886835,0.000053460288,0.00006744499,0.000040807],"domain_scores_gemma":[0.99940133,0.00029472465,0.000051293286,0.00008233254,0.00013992046,0.000030399542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011797037,0.00082023104,0.00061050564,0.0007052953,0.0002746366,0.0005649697,0.0005400767,0.0004583022,0.0012569693],"category_scores_gemma":[0.0030399498,0.00024175155,0.00044130048,0.000571356,0.00024359004,0.0009461905,0.000652587,0.00093013886,0.00033501655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110163186,0.00010343142,0.004176706,0.000050401857,0.000059978258,0.00005453546,0.000045950183,0.7518915,0.0077782394,0.0034699352,0.0013206333,0.23093857],"study_design_scores_gemma":[0.0000014284876,0.000007958739,0.0003100302,0.0000027990498,0.000002724288,0.000003434678,0.0000028622126,0.9978999,0.0007812138,0.00081295456,0.00017282757,0.0000018321409],"about_ca_topic_score_codex":0.006474148,"about_ca_topic_score_gemma":0.0059650852,"teacher_disagreement_score":0.006474148,"about_ca_system_score_codex":0.00042642182,"about_ca_system_score_gemma":0.00097091496,"threshold_uncertainty_score":0.012872934},"labels":[],"label_agreement":null},{"id":"W4407597404","doi":"10.1016/j.jhydrol.2025.132872","title":"Introducing time series features based dynamic weights estimation framework for hydrologic forecast merging","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"United Nations University Institute for Water, Environment, and Health; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Series (stratigraphy); Hydrological modelling; Estimation; Time series; Computer science; Meteorology; Hydrology (agriculture); Data mining; Geology; Climatology; Machine learning; Geography","score_opus":0.005586714792324686,"score_gpt":0.2537010031811119,"score_spread":0.24811428838878719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407597404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065132855,0.00009287541,0.99253654,0.000058753136,0.000028858793,0.000023300548,0.00007121691,0.00030301916,0.0003721788],"genre_scores_gemma":[0.5273126,0.0004872917,0.46798927,0.00011414894,0.00028880825,0.00028109053,0.0010075431,0.00020694971,0.0023123443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992773,0.00013210322,0.00006529825,0.0001890183,0.00025892467,0.00007730907],"domain_scores_gemma":[0.999111,0.0002726276,0.0001966956,0.00006820079,0.00029713777,0.000054356104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014998727,0.0012609732,0.000787559,0.0014490562,0.0004734994,0.0010441492,0.0015373366,0.00078436465,0.0013607091],"category_scores_gemma":[0.0045381323,0.00052795676,0.0010553926,0.0014115208,0.00040440977,0.002058975,0.0012766072,0.0013040508,0.00033128908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073669835,0.000063462016,0.003548122,0.00007070901,0.00014072817,0.00010478816,0.00013473864,0.7689283,0.0058994405,0.013136331,0.0015138906,0.20638579],"study_design_scores_gemma":[0.0000032239568,0.000011394244,0.00030667573,0.0000028852987,0.0000096340955,0.0000086455875,0.0000052083583,0.9962992,0.0005935722,0.0022539184,0.00049748487,0.000008186688],"about_ca_topic_score_codex":0.014357989,"about_ca_topic_score_gemma":0.010243839,"teacher_disagreement_score":0.014357989,"about_ca_system_score_codex":0.00070803665,"about_ca_system_score_gemma":0.0015409419,"threshold_uncertainty_score":0.028548837},"labels":[],"label_agreement":null},{"id":"W4407853950","doi":"10.1016/j.scitotenv.2025.178901","title":"A spatiotemporal CNN-LSTM deep learning model for predicting soil temperature in diverse large-scale regional climates","year":2025,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Research Council Canada; National Research Council","keywords":"Scale (ratio); Deep learning; Climatology; Computer science; Artificial intelligence; Environmental science; Geology; Cartography; Geography","score_opus":0.013620328925561065,"score_gpt":0.22742939688666805,"score_spread":0.213809067961107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407853950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.596328,0.002261177,0.38116604,0.0018066915,0.0005997719,0.000045699468,0.0056067877,0.0033955069,0.008790285],"genre_scores_gemma":[0.9751203,0.00032159957,0.01886644,0.00013194658,0.0000723754,0.000021187027,0.0019719761,0.000055907432,0.003438279],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99993837,0.000004781296,0.0000032529108,0.000028792889,0.000008671981,0.000016076263],"domain_scores_gemma":[0.9998965,0.000026591895,0.00001499286,0.000012255421,0.000036351004,0.000013199607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018988247,0.00056193245,0.00036330477,0.00030565943,0.00020711843,0.00037794997,0.0009617323,0.0005950244,0.001522984],"category_scores_gemma":[0.0006212842,0.00029165798,0.0004716091,0.00065717526,0.00018269014,0.00062571303,0.00046571487,0.0007390498,0.00038608364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108446984,0.00009099681,0.0064530284,0.00003747727,0.00009899319,0.000105217034,0.000023290106,0.9059108,0.0046713715,0.0018644847,0.0043919566,0.076243944],"study_design_scores_gemma":[0.0000014795077,0.0000031237532,0.0002964154,0.000001025795,0.0000045441457,0.000002894686,0.0000017540991,0.9991328,0.0001552532,0.0003059892,0.000093152674,0.0000015071035],"about_ca_topic_score_codex":0.050181095,"about_ca_topic_score_gemma":0.05786897,"teacher_disagreement_score":0.050181095,"about_ca_system_score_codex":0.0007023357,"about_ca_system_score_gemma":0.00083457923,"threshold_uncertainty_score":0.099778},"labels":[],"label_agreement":null},{"id":"W4407922091","doi":"10.18280/ijdne.200120","title":"Applications of Artificial Intelligence Methods for Irrigation Water Quality Index: Review","year":2025,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Anbar","keywords":"Index (typography); Water quality; Irrigation; Quality (philosophy); Agricultural engineering; Environmental science; Computer science; Artificial intelligence; Engineering; Water resource management; Ecology; Biology; Physics; World Wide Web","score_opus":0.03863778009736214,"score_gpt":0.3906349074255233,"score_spread":0.3519971273281612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407922091","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002873277,0.99732673,0.00084199925,0.00042790596,0.00020210554,0.000020480395,0.00004232897,0.000011189021,0.0008399249],"genre_scores_gemma":[0.0028497265,0.99536693,0.0010889954,0.00019664611,0.0001935313,0.00002544832,0.000054167132,0.0000037136133,0.00022089032],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990414,0.00021021749,0.00023473383,0.0001606516,0.00031842067,0.000034574507],"domain_scores_gemma":[0.9951668,0.0034052455,0.00045412756,0.00007902579,0.0008343369,0.00006046626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017810117,0.0010137956,0.0013324718,0.00471481,0.00028592383,0.0015501302,0.0012526709,0.0011432503,0.0028055564],"category_scores_gemma":[0.00650675,0.0003848209,0.0017002182,0.005056034,0.00060097355,0.0017586162,0.0005520541,0.0010417774,0.0007656165],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048260903,0.00008327602,0.0011831435,0.058988385,0.00039151905,0.00014429206,0.000120659904,0.0016877328,0.0005189498,0.0044884947,0.017586827,0.9147584],"study_design_scores_gemma":[0.000034673863,0.00034276326,0.009078301,0.05816427,0.002062885,0.0015906573,0.00030481868,0.0035472633,0.0015756603,0.008618214,0.9145356,0.00014487733],"about_ca_topic_score_codex":0.0028572648,"about_ca_topic_score_gemma":0.002913415,"teacher_disagreement_score":0.00471481,"about_ca_system_score_codex":0.00083744497,"about_ca_system_score_gemma":0.001973885,"threshold_uncertainty_score":0.009419024},"labels":[],"label_agreement":null},{"id":"W4408154884","doi":"10.1038/s41598-025-90628-6","title":"A hybrid framework: singular value decomposition and kernel ridge regression optimized using mathematical-based fine-tuning for enhancing river water level forecasting","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Singular value decomposition; Ridge; Regression; Kernel (algebra); Decomposition; Value (mathematics); Computer science; Regression analysis; Kernel regression; Statistics; Mathematics; Econometrics; Artificial intelligence; Machine learning; Geology; Ecology; Biology; Paleontology","score_opus":0.04240019828538733,"score_gpt":0.2973488065235226,"score_spread":0.25494860823813525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408154884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010850071,0.00017509656,0.9879099,0.00005579407,0.000022783306,0.000012253361,0.000020931955,0.0003674407,0.00058562844],"genre_scores_gemma":[0.52100664,0.00040308153,0.47508276,0.00012603868,0.00009376347,0.00013695846,0.0002854171,0.00023364752,0.0026315998],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996259,0.000121827135,0.000022094584,0.000078356534,0.000111057394,0.000040710853],"domain_scores_gemma":[0.9995925,0.00016107965,0.000058082762,0.000047279398,0.00011922482,0.000021839922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011041741,0.0007886408,0.0010075566,0.00052271463,0.00020993454,0.0007665203,0.00093002093,0.00070460234,0.0007893502],"category_scores_gemma":[0.0017599058,0.00040529895,0.000854872,0.0006822226,0.00041193527,0.00080965564,0.0007213744,0.00085580035,0.0003737614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059086906,0.00007762243,0.0011018845,0.00007706473,0.00008525742,0.00005344725,0.000040977706,0.8840195,0.009770734,0.008472191,0.0011426266,0.095099546],"study_design_scores_gemma":[0.0000015112286,0.000009372677,0.00005436232,0.0000014514283,0.0000027604463,0.0000034814636,0.0000014219129,0.99905473,0.0002331667,0.00048214715,0.00015310707,0.0000024589385],"about_ca_topic_score_codex":0.0047439705,"about_ca_topic_score_gemma":0.0043599596,"teacher_disagreement_score":0.0047439705,"about_ca_system_score_codex":0.0002886334,"about_ca_system_score_gemma":0.0009510779,"threshold_uncertainty_score":0.009432673},"labels":[],"label_agreement":null},{"id":"W4408160114","doi":"10.1016/j.ijsrc.2025.02.004","title":"Prediction of suspended sediment concentration in fluvial flows using novel hybrid deep learning model","year":2025,"lang":"en","type":"article","venue":"International Journal of Sediment Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Environment Research Council; University of Warwick","keywords":"Fluvial; Sediment; Geology; Algorithm; Sediment transport; Hydrology (agriculture); Geomorphology; Computer science; Geotechnical engineering","score_opus":0.09135728526906586,"score_gpt":0.3655849242289328,"score_spread":0.2742276389598669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408160114","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7491796,0.0010087338,0.2439542,0.0005485679,0.00011466267,0.000047931208,0.00065783784,0.0013098029,0.0031786803],"genre_scores_gemma":[0.9850428,0.00012087505,0.0128130745,0.00009585815,0.000024524374,0.00003754586,0.0004948592,0.000011370835,0.0013590425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998492,0.000023771017,0.000012985902,0.000053999465,0.000028064747,0.00003200321],"domain_scores_gemma":[0.9997464,0.000094377705,0.000031992593,0.000013395949,0.00009601573,0.00001787806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061754015,0.00091298245,0.00053671334,0.0006557048,0.00025389047,0.0007178597,0.00081064453,0.0008226293,0.0005544831],"category_scores_gemma":[0.00075249793,0.0003386942,0.000697924,0.0004307605,0.00029940417,0.0006910013,0.0006076081,0.0007514445,0.00015787221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068392284,0.00009895505,0.0065202303,0.000022131737,0.0000763158,0.000052044994,0.00002215945,0.9607478,0.0017872357,0.0003709304,0.00049205264,0.029741826],"study_design_scores_gemma":[0.0000017852315,0.000006363536,0.0002524914,0.0000010256143,0.0000030967087,0.000001592812,0.000001539964,0.999519,0.000114517614,0.00007176655,0.000025125395,0.0000017226379],"about_ca_topic_score_codex":0.02731769,"about_ca_topic_score_gemma":0.0217683,"teacher_disagreement_score":0.02731769,"about_ca_system_score_codex":0.0007799374,"about_ca_system_score_gemma":0.0009323046,"threshold_uncertainty_score":0.054317415},"labels":[],"label_agreement":null},{"id":"W4408418095","doi":"10.5194/egusphere-2025-846","title":"A novel hybrid fine-tuning method for supercharging deep learning model development for hydrological prediction","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University","funders":"Natural Resources Canada","keywords":"Computer science; Deep learning; Artificial intelligence","score_opus":0.0610815415135946,"score_gpt":0.30314624208672886,"score_spread":0.24206470057313426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408418095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027997281,0.0002281536,0.9626091,0.000120175435,0.0000822117,0.00008344521,0.00012332098,0.0067637507,0.0019924864],"genre_scores_gemma":[0.39996547,0.000127475,0.59335405,0.00033341057,0.000059594615,0.0002655928,0.00071416964,0.0007446593,0.0044355667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996074,0.00005234019,0.000025117768,0.00013507257,0.0001314034,0.000048598074],"domain_scores_gemma":[0.9994816,0.00014686538,0.000041092244,0.000112842295,0.00017806742,0.00003949508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008030625,0.000928503,0.00060644787,0.00066280353,0.00039667898,0.0006300597,0.0019886522,0.0007411361,0.004103258],"category_scores_gemma":[0.0018198488,0.0005205192,0.0007801809,0.0005028563,0.0003708113,0.0012405798,0.0011939541,0.0014037618,0.0012900635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015245566,0.00021586413,0.0022932577,0.00009808875,0.00012731212,0.00014456443,0.00012962295,0.47174084,0.026757348,0.003760055,0.0057562916,0.48882428],"study_design_scores_gemma":[0.000008311747,0.0000131180805,0.00008439463,0.000002666582,0.000005682202,0.0000099921,0.0000044187327,0.99558,0.0029271853,0.0006561778,0.00070387364,0.0000041571834],"about_ca_topic_score_codex":0.009235067,"about_ca_topic_score_gemma":0.017178409,"teacher_disagreement_score":0.009235067,"about_ca_system_score_codex":0.0007665502,"about_ca_system_score_gemma":0.0014822221,"threshold_uncertainty_score":0.018362582},"labels":[],"label_agreement":null},{"id":"W4408418184","doi":"10.5194/egusphere-2025-846-v1","title":"A novel hybrid fine-tuning method for supercharging deep learning model development for hydrological prediction","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Resources Canada","keywords":"Deep learning; Computer science; Artificial intelligence; Development (topology); Hybrid learning; Machine learning; Mathematics","score_opus":0.0610815415135946,"score_gpt":0.30314624208672886,"score_spread":0.24206470057313426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408418184","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027997281,0.0002281536,0.9626091,0.000120175435,0.0000822117,0.00008344521,0.00012332098,0.0067637507,0.0019924864],"genre_scores_gemma":[0.39996547,0.000127475,0.59335405,0.00033341057,0.000059594615,0.0002655928,0.00071416964,0.0007446593,0.0044355667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996074,0.00005234019,0.000025117768,0.00013507257,0.0001314034,0.000048598074],"domain_scores_gemma":[0.9994816,0.00014686538,0.000041092244,0.000112842295,0.00017806742,0.00003949508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008030625,0.000928503,0.00060644787,0.00066280353,0.00039667898,0.0006300597,0.0019886522,0.0007411361,0.004103258],"category_scores_gemma":[0.0018198488,0.0005205192,0.0007801809,0.0005028563,0.0003708113,0.0012405798,0.0011939541,0.0014037618,0.0012900635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015245566,0.00021586413,0.0022932577,0.00009808875,0.00012731212,0.00014456443,0.00012962295,0.47174084,0.026757348,0.003760055,0.0057562916,0.48882428],"study_design_scores_gemma":[0.000008311747,0.0000131180805,0.00008439463,0.000002666582,0.000005682202,0.0000099921,0.0000044187327,0.99558,0.0029271853,0.0006561778,0.00070387364,0.0000041571834],"about_ca_topic_score_codex":0.009235067,"about_ca_topic_score_gemma":0.017178409,"teacher_disagreement_score":0.009235067,"about_ca_system_score_codex":0.0007665502,"about_ca_system_score_gemma":0.0014822221,"threshold_uncertainty_score":0.018362582},"labels":[],"label_agreement":null},{"id":"W4408427947","doi":"10.5194/egusphere-egu25-12640","title":"Weather Generator Based on Generative AI for Interdisciplinary Probabilistic Downscaling Using Convection-Permitting Model Outputs and Potential Utility in Equitable, Community-focused Climate Scenario-ing","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Downscaling; Probabilistic logic; Climate model; Generator (circuit theory); Generative grammar; Climatology; Computer science; Meteorology; Environmental science; Climate change; Artificial intelligence; Geography; Geology; Oceanography","score_opus":0.05672148926187801,"score_gpt":0.32007970998546836,"score_spread":0.26335822072359033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408427947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026453005,0.00008596017,0.9688297,0.00020771449,0.000055220196,0.000039980227,0.00016701792,0.0010449298,0.0031165986],"genre_scores_gemma":[0.77271384,0.0001446752,0.22313005,0.00014166208,0.00006752686,0.00014649636,0.0006002616,0.0002623074,0.0027932147],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998079,0.00006140171,0.000010774943,0.00005396712,0.00004561978,0.000020423706],"domain_scores_gemma":[0.99919325,0.0004944438,0.00006710542,0.00010446019,0.00009771196,0.000043082593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007306945,0.0004374641,0.00030532968,0.00044033022,0.0002553256,0.0005996644,0.00084351393,0.0004579526,0.002457605],"category_scores_gemma":[0.002551961,0.00026261839,0.00065129675,0.00044024942,0.00050505996,0.0008197755,0.00095416204,0.0010944704,0.0003984806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003807349,0.000026738404,0.00093436416,0.000024929946,0.000027438351,0.00004029059,0.0000608433,0.93811476,0.00216112,0.015031443,0.00070901937,0.042831037],"study_design_scores_gemma":[0.0000017768997,0.000004207203,0.00006054015,0.000001606977,0.0000017880544,0.0000032606163,0.000002089419,0.99425477,0.00033360592,0.0051049152,0.00022920025,0.0000021939459],"about_ca_topic_score_codex":0.0041606156,"about_ca_topic_score_gemma":0.00525534,"teacher_disagreement_score":0.0041606156,"about_ca_system_score_codex":0.0005643481,"about_ca_system_score_gemma":0.0006225654,"threshold_uncertainty_score":0.008272767},"labels":[],"label_agreement":null},{"id":"W4408428086","doi":"10.5194/egusphere-egu25-12547","title":"What is the role of machine learning when we want to simulate hydrological processes?","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.020079470618959563,"score_gpt":0.2604607432817481,"score_spread":0.24038127266278855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408428086","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002788526,0.012273283,0.0034944462,0.96686023,0.0146117145,0.000005530034,0.00006138999,0.000037483496,0.0023770698],"genre_scores_gemma":[0.049021386,0.043212444,0.011725671,0.7761724,0.11076097,0.00013747299,0.00014648975,0.00042036994,0.008402867],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98375547,0.009990366,0.0006052839,0.0019903367,0.003204571,0.00045393303],"domain_scores_gemma":[0.9011914,0.083969966,0.0020439434,0.0021021676,0.0093257865,0.0013666137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019427907,0.0009966452,0.0015048655,0.0014270261,0.0029528192,0.008157649,0.0035664213,0.015530789,0.004199992],"category_scores_gemma":[0.105394095,0.00043139418,0.0010535712,0.0012396584,0.018528892,0.018975427,0.002316165,0.032725666,0.0034444456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014421578,0.00004897728,0.0007925849,0.0010121671,0.00013342232,0.00018211086,0.001683123,0.0038200698,0.00038503302,0.38937718,0.5360299,0.066391274],"study_design_scores_gemma":[0.000045406206,0.00004542466,0.00029967356,0.0013593507,0.000030496323,0.00010067805,0.0010825687,0.004774171,0.00053030666,0.51803035,0.47359863,0.00010295563],"about_ca_topic_score_codex":0.009516717,"about_ca_topic_score_gemma":0.0061760647,"teacher_disagreement_score":0.019427907,"about_ca_system_score_codex":0.006189094,"about_ca_system_score_gemma":0.004127497,"threshold_uncertainty_score":0.10274583},"labels":[],"label_agreement":null},{"id":"W4408429048","doi":"10.5194/egusphere-egu25-14665","title":"Harnessing Machine Learning for Water Quality Prediction in Agricultural Watersheds","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ministry of the Environment, Conservation and Parks; Université du Québec à Montréal; University of Guelph","funders":"","keywords":"Agriculture; Water quality; Quality (philosophy); Computer science; Machine learning; Artificial intelligence; Agricultural engineering; Engineering; Geography","score_opus":0.036704299518880885,"score_gpt":0.28261536724566066,"score_spread":0.2459110677267798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408429048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3496415,0.0028109362,0.63939595,0.0018485175,0.0001627118,0.00014185684,0.0007196188,0.002119665,0.003159245],"genre_scores_gemma":[0.969003,0.0004692166,0.028908694,0.00020246994,0.00008022062,0.000087120854,0.0005811475,0.000027851711,0.00064025464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957806,0.00011036328,0.000034734538,0.00014705361,0.00007012862,0.000059712456],"domain_scores_gemma":[0.9982034,0.0012651988,0.00018131718,0.00007143503,0.00022206549,0.000056538123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012656733,0.0009448062,0.0011106377,0.001040263,0.000320131,0.0011905903,0.0012152125,0.0012467633,0.00063353736],"category_scores_gemma":[0.0048525888,0.0004068342,0.00088158314,0.0011713716,0.00058960065,0.0011890795,0.0009284127,0.0012871762,0.00022417044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003592161,0.00008196569,0.004911689,0.000039367456,0.00004560229,0.00003051356,0.00002129215,0.95520777,0.00029175795,0.0005028879,0.00027017033,0.038561106],"study_design_scores_gemma":[0.000001318613,0.0000050583917,0.00021251109,0.0000018029872,0.0000018576796,0.0000012319119,0.0000024936642,0.9991411,0.00007970526,0.000509216,0.00004232921,0.0000013551846],"about_ca_topic_score_codex":0.01431827,"about_ca_topic_score_gemma":0.008422402,"teacher_disagreement_score":0.01431827,"about_ca_system_score_codex":0.001089592,"about_ca_system_score_gemma":0.000967296,"threshold_uncertainty_score":0.02846986},"labels":[],"label_agreement":null},{"id":"W4408430378","doi":"10.5194/egusphere-egu25-14223","title":"On the advancing frontier of deep learning in hydrology:&amp;#160; a hydrologic applications perspective","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Waterloo","funders":"","keywords":"Frontier; Perspective (graphical); Hydrology (agriculture); Hydrological modelling; Environmental science; Geology; Computer science; Geography; Artificial intelligence; Climatology; Archaeology; Geotechnical engineering","score_opus":0.015263560584704077,"score_gpt":0.2677436371206251,"score_spread":0.252480076535921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408430378","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012132767,0.05859781,0.5314584,0.30664608,0.0034564007,0.00004244443,0.000969659,0.0013543536,0.085342064],"genre_scores_gemma":[0.46596855,0.15478958,0.24896498,0.04358738,0.013263768,0.00014319124,0.0012811812,0.0011612652,0.0708402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993086,0.0002468514,0.000035741807,0.00011520972,0.00022453711,0.0000690123],"domain_scores_gemma":[0.9970902,0.001853628,0.000093991686,0.00018972924,0.0005693118,0.00020306678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021700447,0.0006810598,0.00042592804,0.00097498717,0.0007370657,0.004800472,0.0012537069,0.0021722422,0.005651869],"category_scores_gemma":[0.0058268444,0.00031223337,0.0004050829,0.0017874101,0.0035292814,0.007473337,0.0024783786,0.0062225456,0.00228199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060443326,0.000050739134,0.001371675,0.00040954223,0.00002661568,0.00011947573,0.00028032143,0.027657146,0.0010066272,0.65344864,0.06734129,0.24822752],"study_design_scores_gemma":[0.0000070030255,0.000024307437,0.0005607916,0.00026821223,0.000008960697,0.00006637421,0.00019152659,0.07991505,0.0013781816,0.77024966,0.14730194,0.00002797403],"about_ca_topic_score_codex":0.0068603493,"about_ca_topic_score_gemma":0.006560385,"teacher_disagreement_score":0.0068603493,"about_ca_system_score_codex":0.002272989,"about_ca_system_score_gemma":0.0016698352,"threshold_uncertainty_score":0.018907368},"labels":[],"label_agreement":null},{"id":"W4408436864","doi":"10.5194/egusphere-egu25-7022","title":"ClimateEU: A high-resolution database of historical and future climate for Europe developed with deep neural networks","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Alberta","funders":"","keywords":"Artificial neural network; High resolution; Computer science; Resolution (logic); Artificial intelligence; Data science; Database; Geography; Remote sensing","score_opus":0.02262702544069482,"score_gpt":0.24175397678479946,"score_spread":0.21912695134410465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408436864","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029530274,0.0008566016,0.031812984,0.00030572532,0.00024030823,0.00009084706,0.91986716,0.010725304,0.00657089],"genre_scores_gemma":[0.04899698,0.00060375885,0.029677697,0.000103745086,0.000045352925,0.00019983185,0.9178816,0.0010922385,0.0013988728],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994691,0.000079244455,0.000086670145,0.00015678602,0.00015252424,0.000055806406],"domain_scores_gemma":[0.99888116,0.00021745526,0.00015228588,0.00033703682,0.00029412322,0.0001179095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096827484,0.0009774812,0.00074892846,0.0031012192,0.000312696,0.0014236064,0.0018725235,0.00090504414,0.01006155],"category_scores_gemma":[0.0036675117,0.00046730155,0.00091110286,0.005376542,0.00019638216,0.001798423,0.00159346,0.0012166579,0.0057318094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005027359,0.00031190613,0.058099672,0.0019003315,0.0008832711,0.0008327188,0.000449294,0.16238292,0.0050941017,0.01674443,0.59029955,0.16249907],"study_design_scores_gemma":[0.0003000534,0.00010713446,0.058988016,0.0005258894,0.00022439874,0.00039826278,0.00040429097,0.15369216,0.008427828,0.017812608,0.7588486,0.00027082488],"about_ca_topic_score_codex":0.012513558,"about_ca_topic_score_gemma":0.014327748,"teacher_disagreement_score":0.012513558,"about_ca_system_score_codex":0.00052344805,"about_ca_system_score_gemma":0.001076749,"threshold_uncertainty_score":0.03365928},"labels":[],"label_agreement":null},{"id":"W4408440186","doi":"10.5194/egusphere-egu25-4387","title":"Runoff Forecasting in Unmeasured Catchments and Rapid Flash Flood Prediction Based on Deep Learning.","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Flash flood; Surface runoff; Flood forecasting; Flood myth; Environmental science; Deep learning; Flash (photography); Computer science; Meteorology; Predictive modelling; Machine learning; Hydrology (agriculture); Artificial intelligence; Geography; Geology; Geotechnical engineering","score_opus":0.023737527084489386,"score_gpt":0.23302223144566958,"score_spread":0.20928470436118018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408440186","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73601156,0.002079767,0.24694034,0.0014376177,0.00022803995,0.00009816906,0.0045341235,0.0038226144,0.004847682],"genre_scores_gemma":[0.9725021,0.00032782025,0.023369469,0.00010812066,0.000051789066,0.000033067397,0.00253964,0.000046607474,0.0010212092],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998815,0.000021528225,0.000007897189,0.00003919664,0.000026969325,0.000022929358],"domain_scores_gemma":[0.99967897,0.00016219271,0.000035523357,0.000032658616,0.000058615446,0.00003200875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045369423,0.00085240015,0.00036131215,0.0005702358,0.0001565393,0.0005140944,0.0007409341,0.0005107375,0.00095307577],"category_scores_gemma":[0.0017836408,0.00019025925,0.00036131937,0.00073901634,0.00019910508,0.0011000439,0.00064788,0.0007667997,0.00023444452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001922251,0.00016990732,0.02014456,0.00012927037,0.00012094766,0.00015656267,0.00006137646,0.8237303,0.0044408967,0.0013214078,0.005907929,0.14362472],"study_design_scores_gemma":[0.000006150262,0.000013617406,0.0015176168,0.0000039233614,0.000005914062,0.0000061140036,0.000010094594,0.9965346,0.00074920343,0.00093307527,0.00021608174,0.0000035273144],"about_ca_topic_score_codex":0.015648378,"about_ca_topic_score_gemma":0.024439687,"teacher_disagreement_score":0.015648378,"about_ca_system_score_codex":0.0007253993,"about_ca_system_score_gemma":0.0008088471,"threshold_uncertainty_score":0.031114578},"labels":[],"label_agreement":null},{"id":"W4408510803","doi":"10.1061/jhyeff.heeng-6403","title":"Discussion of “Application of Hybrid AI Models for Accurate Prediction of Scour Depths under Submerged Circular Vertical Jet”","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrologic Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval","funders":"","keywords":"Jet (fluid); Geology; Marine engineering; Environmental science; Engineering; Aerospace engineering","score_opus":0.01486928490758011,"score_gpt":0.24305438339963442,"score_spread":0.22818509849205432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408510803","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09284002,0.0022122469,0.8142572,0.030029181,0.0056697824,0.00016273085,0.0005463106,0.0009062421,0.053376332],"genre_scores_gemma":[0.9177187,0.0010808939,0.0629979,0.0032340437,0.001454929,0.00010671458,0.00025207974,0.00009519774,0.013059548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995672,0.00013920772,0.000032591128,0.000078508856,0.00014577844,0.000036741378],"domain_scores_gemma":[0.9989359,0.00051669515,0.000048835456,0.00010828473,0.00036182176,0.000028591505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018720789,0.00043094985,0.00039178078,0.0002494515,0.0006833815,0.0015687429,0.0018733277,0.0020164654,0.0023827006],"category_scores_gemma":[0.004980608,0.00019197473,0.00072442566,0.00039736647,0.00088552386,0.0016750842,0.0007328609,0.0013065385,0.00034373032],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002733167,0.00007962143,0.004469293,0.00026856607,0.00022245529,0.00081631856,0.00027086303,0.7391318,0.016619273,0.16873296,0.01467279,0.054442804],"study_design_scores_gemma":[0.000020213878,0.00006683675,0.00081632327,0.00003090422,0.000027686781,0.00006621804,0.000084453975,0.9557195,0.0062750513,0.02809174,0.008774427,0.00002664362],"about_ca_topic_score_codex":0.010262716,"about_ca_topic_score_gemma":0.004480638,"teacher_disagreement_score":0.010262716,"about_ca_system_score_codex":0.00061033835,"about_ca_system_score_gemma":0.0006660555,"threshold_uncertainty_score":0.020406008},"labels":[],"label_agreement":null},{"id":"W4408554517","doi":"10.1016/j.asr.2025.03.037","title":"River salinity mapping through machine learning and statistical modeling using Landsat 8 OLI imagery","year":2025,"lang":"en","type":"article","venue":"Advances in Space Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Wilfrid Laurier University; University of Ottawa","funders":"U.S. Geological Survey","keywords":"Remote sensing; Salinity; Satellite imagery; Statistical analysis; Computer science; Environmental science; Geology; Statistics; Oceanography; Mathematics","score_opus":0.08388250595620567,"score_gpt":0.415912481397982,"score_spread":0.3320299754417763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408554517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30065885,0.00045379394,0.69245565,0.00043707516,0.00005159096,0.000115551484,0.00044271382,0.0026115633,0.0027732914],"genre_scores_gemma":[0.8740001,0.0002889782,0.12397693,0.0000491798,0.000028938373,0.0000837886,0.0005349943,0.00004225186,0.0009948581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996953,0.00008992885,0.00002811038,0.00007451241,0.0000866671,0.000025463538],"domain_scores_gemma":[0.99948895,0.00022154483,0.00010015297,0.000034815173,0.00014052437,0.000014000755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096588704,0.0006661078,0.00041301697,0.001230683,0.00023484253,0.0007588233,0.00050820765,0.00033674357,0.00051401777],"category_scores_gemma":[0.0020720027,0.00029628602,0.0008510128,0.001103139,0.00020190465,0.0009180523,0.00039610913,0.00045149226,0.00023522507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062827785,0.00014225388,0.025848653,0.00010121393,0.00016813651,0.00008092629,0.000073459145,0.7577698,0.0037223077,0.0015306529,0.0012447663,0.20925508],"study_design_scores_gemma":[0.0000015575313,0.000010840794,0.0018936655,0.0000044281924,0.000009587088,0.000007219474,0.000009963985,0.99699235,0.0005028624,0.0004069363,0.00015529203,0.0000053724043],"about_ca_topic_score_codex":0.013270179,"about_ca_topic_score_gemma":0.0113040665,"teacher_disagreement_score":0.013270179,"about_ca_system_score_codex":0.0006765556,"about_ca_system_score_gemma":0.0008367642,"threshold_uncertainty_score":0.026385844},"labels":[],"label_agreement":null},{"id":"W4408948502","doi":"10.3389/fenvs.2025.1543852","title":"Regression-based machine learning models for nitrate and chloride prediction in surface water in a small agricultural sand plain sub-watershed in southwestern Ontario, Canada","year":2025,"lang":"en","type":"article","venue":"Frontiers in Environmental Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ministry of the Environment, Conservation and Parks; Université du Québec à Montréal; University of Guelph","funders":"","keywords":"Watershed; Nitrate; Agriculture; Hydrology (agriculture); Environmental science; Surface water; Geology; Machine learning; Geography; Archaeology; Environmental engineering; Ecology; Geotechnical engineering; Computer science","score_opus":0.008898137932366561,"score_gpt":0.1744443739821476,"score_spread":0.16554623604978103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408948502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994642,0.00023072759,0.0027013884,0.00015075771,0.00000769789,0.000046739184,0.0012592933,0.000106396205,0.0008549208],"genre_scores_gemma":[0.99294454,0.0001879912,0.00321392,0.000023327606,0.000003988828,0.00003293531,0.0018430064,0.00000892597,0.0017413052],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975485,0.000024464342,0.000019750274,0.0000735625,0.000071450195,0.000055829332],"domain_scores_gemma":[0.99942917,0.00014646098,0.00007204255,0.000016050219,0.00030302076,0.0000332971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044715367,0.0006232805,0.00042301163,0.00057394477,0.0008023779,0.0007547526,0.0010051257,0.00041087638,0.000631032],"category_scores_gemma":[0.0013668389,0.0002342488,0.00042845344,0.0012427103,0.00030427313,0.00028491725,0.00025734506,0.00036431386,0.00014874173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033574275,0.00031871872,0.4365452,0.0002149107,0.00020321051,0.0005051989,0.00059810444,0.4837332,0.0059858095,0.00043383625,0.004459183,0.06666694],"study_design_scores_gemma":[0.000025048474,0.000032940487,0.14785849,0.000014087577,0.000030270989,0.000020250025,0.00046708723,0.8496741,0.00074619544,0.000099455436,0.0010085785,0.000023444894],"about_ca_topic_score_codex":0.9818065,"about_ca_topic_score_gemma":0.98293996,"teacher_disagreement_score":0.018193483,"about_ca_system_score_codex":0.011678305,"about_ca_system_score_gemma":0.010114634,"threshold_uncertainty_score":0.08473247},"labels":[],"label_agreement":null},{"id":"W4409380514","doi":"10.1038/s43247-025-02265-6","title":"Publisher Correction: An interpretable machine learning model for seasonal precipitation forecasting","year":2025,"lang":"en","type":"article","venue":"Communications Earth & Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Precipitation; Artificial intelligence; Computer science; Machine learning; Climatology; Meteorology; Environmental science; Econometrics; Geography; Mathematics; Geology","score_opus":0.04753683820578212,"score_gpt":0.269525892039157,"score_spread":0.2219890538333749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409380514","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042767954,0.0012395658,0.010192686,0.044924144,0.915201,0.00006090763,0.010362809,0.003179633,0.014411531],"genre_scores_gemma":[0.038265634,0.0069822744,0.023011927,0.029710881,0.22022167,0.00038103858,0.022850577,0.007845143,0.65073085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741626,0.00038197107,0.00038205815,0.0004401431,0.0012240899,0.0001554437],"domain_scores_gemma":[0.96139854,0.0067515993,0.0011791347,0.003537197,0.026116997,0.0010165363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002494597,0.0016308716,0.0013454317,0.0035057915,0.0019362414,0.004389193,0.0037428897,0.00359767,0.20447898],"category_scores_gemma":[0.062696,0.00071017747,0.0014462969,0.0041411296,0.001372579,0.0029775994,0.0018941505,0.0067935023,0.118638106],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023864595,0.000003128417,0.000088621055,0.000071347764,0.000008981439,0.00009066721,0.000012642713,0.00030892907,0.000035943747,0.001267736,0.9898755,0.008212677],"study_design_scores_gemma":[0.00004788376,0.000021986181,0.00055935385,0.00026336574,0.00002509268,0.00024331718,0.000051005696,0.0029561853,0.0004649149,0.004276521,0.99105036,0.000039963496],"about_ca_topic_score_codex":0.015532059,"about_ca_topic_score_gemma":0.018269805,"teacher_disagreement_score":0.20447898,"about_ca_system_score_codex":0.0021831703,"about_ca_system_score_gemma":0.004028108,"threshold_uncertainty_score":0.6840503},"labels":[],"label_agreement":null},{"id":"W4409481488","doi":"10.2139/ssrn.5219170","title":"Quantifying Uncertainty from Spatial Data Inputs Using Hydrological Processes and Fuzzy Entropy","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Fuzzy logic; Uncertainty analysis; Entropy (arrow of time); Spatial analysis; Environmental science; Econometrics; Data mining; Computer science; Statistics; Mathematics; Artificial intelligence; Physics","score_opus":0.06394480462199498,"score_gpt":0.3082855153151819,"score_spread":0.2443407106931869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409481488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.116616555,0.00035402377,0.8804932,0.00037943388,0.00004589067,0.000024690706,0.00019147954,0.00011718223,0.0017775298],"genre_scores_gemma":[0.95173377,0.0003321126,0.04723713,0.00003542328,0.00007308909,0.000028463295,0.00014820408,0.000019911917,0.00039188034],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989838,0.00030724352,0.0001032826,0.00013168174,0.00041698792,0.000056922323],"domain_scores_gemma":[0.992922,0.005874828,0.00046757984,0.00029211244,0.0003605482,0.00008297027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031126104,0.0006472086,0.0006363316,0.001981487,0.0003476627,0.002340717,0.00041344555,0.0007101494,0.00075263914],"category_scores_gemma":[0.012561748,0.00038649002,0.0006684325,0.001926818,0.0010331008,0.0036512443,0.0012894026,0.0009430233,0.000063102045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007291258,0.00003093502,0.004887453,0.00010222367,0.00012756555,0.00012625924,0.00011833424,0.9059333,0.002272996,0.035658326,0.00024658904,0.050423145],"study_design_scores_gemma":[0.0000021539583,0.000010906422,0.0009397675,0.000010457582,0.000013225321,0.000012123143,0.000016012074,0.95548,0.0008374024,0.042567108,0.00010264203,0.000008253085],"about_ca_topic_score_codex":0.002400833,"about_ca_topic_score_gemma":0.0019867413,"teacher_disagreement_score":0.0031126104,"about_ca_system_score_codex":0.0009772293,"about_ca_system_score_gemma":0.00065618736,"threshold_uncertainty_score":0.016461253},"labels":[],"label_agreement":null},{"id":"W4409753769","doi":"10.2139/ssrn.5229785","title":"Integrated Machine Learning and Hydrodynamic Modeling for Agricultural Land Flood Under Climate Change Scenarios","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Flood myth; Climate change; Agriculture; Environmental science; Environmental resource management; Hydrology (agriculture); Environmental planning; Geography; Engineering; Geology; Geotechnical engineering; Oceanography; Archaeology","score_opus":0.018592110923474806,"score_gpt":0.24800865595778684,"score_spread":0.22941654503431202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409753769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76571447,0.0005501137,0.22137196,0.0016714286,0.00018634142,0.000054231863,0.0011658837,0.0008753005,0.008410271],"genre_scores_gemma":[0.98863834,0.000101487625,0.009372654,0.00003317674,0.000054983982,0.000027324691,0.00030993138,0.000029569925,0.0014325241],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998672,0.000050080555,0.000007789011,0.000032131862,0.000020388134,0.000022392498],"domain_scores_gemma":[0.99931574,0.00048258668,0.000049110247,0.000033642365,0.00008232117,0.00003661036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005958382,0.00038113634,0.0006787048,0.00049873197,0.0003499762,0.00069994194,0.000570238,0.0009425765,0.001937043],"category_scores_gemma":[0.002317782,0.00036724805,0.0005651149,0.0007982232,0.0002944292,0.0013187741,0.00050280214,0.001028131,0.00019578313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018199817,0.000017853128,0.00054332364,0.000005863886,0.000012446578,0.0000061020437,0.000004140257,0.99510324,0.00009329656,0.0004490104,0.000121558594,0.003624924],"study_design_scores_gemma":[0.0000015711314,0.000002530806,0.00011335879,3.3545368e-7,0.0000013121737,4.4680837e-7,8.9228445e-7,0.99943346,0.00002755722,0.00039691635,0.0000207829,8.6569486e-7],"about_ca_topic_score_codex":0.026476521,"about_ca_topic_score_gemma":0.015002144,"teacher_disagreement_score":0.026476521,"about_ca_system_score_codex":0.00086269574,"about_ca_system_score_gemma":0.0009677274,"threshold_uncertainty_score":0.05264485},"labels":[],"label_agreement":null},{"id":"W4409799804","doi":"10.11159/icgre25.153","title":"A Comparative Analysis of Deep Learning Approaches for Rainfall Forecasting in Taiwan","year":2025,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Civil, Structural, and Environmental Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Technology forecasting; Machine learning","score_opus":0.01814694128596842,"score_gpt":0.21994612615428424,"score_spread":0.20179918486831583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409799804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96347755,0.0032457768,0.026289057,0.0010348671,0.00011050811,0.000042458767,0.0005652967,0.0005006775,0.0047337166],"genre_scores_gemma":[0.99238694,0.00068481086,0.005729087,0.000053588064,0.000016820475,0.000016958784,0.00059041847,0.000013306014,0.00050805276],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996307,0.000109227745,0.000046046167,0.00007277816,0.00008033413,0.000060919232],"domain_scores_gemma":[0.998722,0.0007254017,0.000083468454,0.00008962308,0.00030775034,0.00007170701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001807099,0.00083324575,0.00039066607,0.0012665457,0.00024712965,0.0006750392,0.00067007716,0.00060815096,0.00065896683],"category_scores_gemma":[0.0039218063,0.00017878744,0.00044785408,0.0011549911,0.00019479104,0.0014529147,0.00063642923,0.00060845795,0.0001273154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053652184,0.00022998183,0.046637416,0.00027536802,0.00027563862,0.00019136333,0.00015511477,0.7523701,0.0020626795,0.0017644111,0.0021700691,0.19333139],"study_design_scores_gemma":[0.000011888737,0.00012965889,0.0062279906,0.000024602365,0.000037527865,0.0000139171425,0.00010600824,0.9913186,0.0010060846,0.0006270059,0.00048590612,0.000010800792],"about_ca_topic_score_codex":0.031850748,"about_ca_topic_score_gemma":0.02680456,"teacher_disagreement_score":0.031850748,"about_ca_system_score_codex":0.0013123638,"about_ca_system_score_gemma":0.0009848924,"threshold_uncertainty_score":0.06333071},"labels":[],"label_agreement":null},{"id":"W4410049345","doi":"10.1007/s12145-025-01856-3","title":"Predicting groundwater levels in coastal aquifers using deep learning models: a comparative study of sedimentary and metamorphic aquifers in nova scotia","year":2025,"lang":"en","type":"article","venue":"Earth Science Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Aquifer; Nova scotia; Geology; Metamorphic rock; Sedimentary rock; Groundwater; Geochemistry; Oceanography; Geotechnical engineering","score_opus":0.07435063622025058,"score_gpt":0.2923124458920515,"score_spread":0.21796180967180095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410049345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99878734,0.000027601642,0.00013775022,0.00004993371,0.0000019912927,0.0000052181344,0.00033072178,0.0000081743265,0.00065122114],"genre_scores_gemma":[0.9989202,0.000031184325,0.00016711334,0.000008359021,8.2846e-7,0.0000022635027,0.0002948107,0.0000022109336,0.00057301804],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998896,0.000016816426,0.0000072618905,0.00002502464,0.000021813812,0.00003948555],"domain_scores_gemma":[0.99939895,0.00014794263,0.000085038824,0.000034865065,0.00024265607,0.000090477864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002122734,0.000247544,0.00019695389,0.0005499754,0.0005787367,0.00062749325,0.0004319054,0.00027753916,0.0005150165],"category_scores_gemma":[0.0009941789,0.00018305633,0.00028211044,0.0009456709,0.00047094625,0.00026819273,0.00038865974,0.00025933274,0.00011100953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036600203,0.00015437789,0.92608076,0.000050575785,0.00013413646,0.00091212004,0.0007736424,0.051446915,0.0030078113,0.00053597556,0.0011053307,0.015432381],"study_design_scores_gemma":[0.000022444061,0.000043331926,0.921082,0.000021017235,0.00003509247,0.00007468124,0.0019312873,0.07514948,0.0007058813,0.00013625539,0.00078247243,0.000015981812],"about_ca_topic_score_codex":0.94090486,"about_ca_topic_score_gemma":0.96938443,"teacher_disagreement_score":0.059095144,"about_ca_system_score_codex":0.005622542,"about_ca_system_score_gemma":0.0029801796,"threshold_uncertainty_score":0.11888629},"labels":[],"label_agreement":null},{"id":"W4410114559","doi":"10.1109/icjece.2025.3558882","title":"Rainfall Classification Using Machine Learning Algorithms on Data Mining Platforms","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Electrical and Computer Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.03333418804503878,"score_gpt":0.2272608257516971,"score_spread":0.1939266377066583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410114559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40172753,0.0012296307,0.5380661,0.0011517828,0.0003617263,0.0011004856,0.009066552,0.033210255,0.014085974],"genre_scores_gemma":[0.6148534,0.00048885244,0.37234825,0.00018517324,0.00009191838,0.0005933041,0.00812318,0.0002595839,0.0030563392],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987845,0.00022687706,0.00019286838,0.000311497,0.00040715843,0.0000770283],"domain_scores_gemma":[0.997426,0.0011145559,0.00024521523,0.00043004818,0.0007065624,0.00007772569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013243045,0.00077050424,0.00059178536,0.0027638555,0.00046518247,0.0014432652,0.0011784335,0.00050755724,0.0022009097],"category_scores_gemma":[0.007156772,0.00033788182,0.00069829857,0.0028918365,0.00023260011,0.002207977,0.000890368,0.00077928137,0.001289523],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000642357,0.0007086503,0.021848435,0.00035147625,0.00033808654,0.00036352008,0.00032122675,0.14742664,0.0133031905,0.005383829,0.014162117,0.7951505],"study_design_scores_gemma":[0.000061707164,0.00013173326,0.010408569,0.00005778742,0.000040540242,0.00011281936,0.00017352313,0.9571917,0.015427757,0.0077863284,0.008570911,0.000036521535],"about_ca_topic_score_codex":0.0051364717,"about_ca_topic_score_gemma":0.0034792887,"teacher_disagreement_score":0.0051364717,"about_ca_system_score_codex":0.0008617493,"about_ca_system_score_gemma":0.00070207135,"threshold_uncertainty_score":0.010213137},"labels":[],"label_agreement":null},{"id":"W4410241996","doi":"10.18280/mmep.120407","title":"Flow Series Generation from Water Depth Data Using Statistical and Machine Learning Models: The Tocache Station Case","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Series (stratigraphy); Computer science; Flow (mathematics); Machine learning; Artificial intelligence; Geology; Mathematics; Geometry","score_opus":0.11616773320167446,"score_gpt":0.24297667409801815,"score_spread":0.1268089408963437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410241996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8783294,0.000115380666,0.11711089,0.00034581043,0.000019458237,0.00015368905,0.00069432374,0.00048796044,0.002743108],"genre_scores_gemma":[0.96874994,0.00006429012,0.030011993,0.000010450471,0.0000073491015,0.000096253636,0.00037707723,0.000015659703,0.00066705677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961674,0.0001995333,0.000025117502,0.00005656798,0.000068341855,0.00003353051],"domain_scores_gemma":[0.9981844,0.001289604,0.00014815567,0.00014037616,0.00019190183,0.00004549174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014776102,0.00041517863,0.00031806505,0.0009071905,0.00032050232,0.0006031308,0.0006739814,0.00083071564,0.00088229607],"category_scores_gemma":[0.005373386,0.00023615539,0.00052229996,0.0016319652,0.0003766569,0.000634692,0.00052547693,0.00045957702,0.00013868268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001381656,0.00014218311,0.015073267,0.00004438064,0.000036409652,0.00036159228,0.00013639116,0.94521827,0.00073574955,0.0034236878,0.00038198003,0.034307957],"study_design_scores_gemma":[0.0000106538955,0.000032341017,0.0018662877,0.0000029900866,0.0000052732757,0.000017320905,0.000027829465,0.99675804,0.0004151451,0.00064278947,0.0002139382,0.000007319578],"about_ca_topic_score_codex":0.034884315,"about_ca_topic_score_gemma":0.020881295,"teacher_disagreement_score":0.034884315,"about_ca_system_score_codex":0.00087258825,"about_ca_system_score_gemma":0.00080839597,"threshold_uncertainty_score":0.06936252},"labels":[],"label_agreement":null},{"id":"W4410309320","doi":"10.3390/environments12050158","title":"Recent Advances in Remote Sensing and Artificial Intelligence for River Water Quality Forecasting: A Review","year":2025,"lang":"en","type":"review","venue":"Environments","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quality (philosophy); Computer science; Water quality; Remote sensing; Environmental science; Data science; Geography; Ecology","score_opus":0.12810494428934885,"score_gpt":0.36944145321372723,"score_spread":0.24133650892437838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410309320","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015279007,0.99750453,0.00050606165,0.00037306856,0.00023562979,0.0000069998136,0.00003584723,0.000014008301,0.0011711034],"genre_scores_gemma":[0.0008707215,0.9979522,0.00048395933,0.00015770097,0.0002175238,0.0000075920434,0.00004453441,0.000002790305,0.00026295366],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997255,0.000049819955,0.000042487874,0.000061528415,0.000099943456,0.000020636204],"domain_scores_gemma":[0.99838126,0.0010653279,0.0001383381,0.000039366016,0.00031295946,0.000062775354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010326456,0.0010647643,0.0012891999,0.0026846537,0.00023514232,0.0010187519,0.0010450532,0.0012104546,0.004883241],"category_scores_gemma":[0.001952597,0.0003799814,0.000886086,0.004400514,0.0004634466,0.0016579555,0.0007234797,0.0015581183,0.0018851111],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004205402,0.00006329774,0.00031398472,0.019835846,0.00014243554,0.00008950032,0.00005007239,0.00096120755,0.00078366074,0.0041459645,0.023285016,0.950287],"study_design_scores_gemma":[0.000016807919,0.00011913468,0.0014212505,0.0066165235,0.00033598722,0.00045868926,0.000074259166,0.00060973864,0.0004711983,0.004160085,0.9856647,0.00005159041],"about_ca_topic_score_codex":0.0022202462,"about_ca_topic_score_gemma":0.0022655935,"teacher_disagreement_score":0.004883241,"about_ca_system_score_codex":0.00049703056,"about_ca_system_score_gemma":0.0013859035,"threshold_uncertainty_score":0.016336024},"labels":[],"label_agreement":null},{"id":"W4410524685","doi":"10.5194/egusphere-2025-2083","title":"Synergistic identification of hydrogeological parameters and pollution source information for groundwater point and areal source contamination based on machine learning surrogate-artificial hummingbird algorithm","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities","keywords":"Hummingbird; Pollution; Contamination; Hydrogeology; Identification (biology); Groundwater; Algorithm; Groundwater pollution; Environmental science; Point source; Point (geometry); Computer science; Nonpoint source pollution; Point source pollution; Artificial intelligence; Environmental engineering; Engineering; Mathematics; Geotechnical engineering; Ecology; Biology; Aquifer","score_opus":0.015279343061122098,"score_gpt":0.23206544841353552,"score_spread":0.2167861053524134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410524685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12578888,0.0001562564,0.8722264,0.00011606177,0.000025402554,0.00003442109,0.00003273289,0.0002826261,0.0013372076],"genre_scores_gemma":[0.8371778,0.00007918027,0.161648,0.000041753447,0.000012252813,0.00006680879,0.0000823408,0.000017794191,0.00087401544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997453,0.0001085743,0.0000125691795,0.00004485564,0.00006831845,0.000020449887],"domain_scores_gemma":[0.99952626,0.00021372367,0.00007470898,0.0000305302,0.00013296501,0.000021763088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092525705,0.0005399732,0.00061919034,0.0006230013,0.00028274296,0.0005297824,0.0005787398,0.00073587365,0.00050512544],"category_scores_gemma":[0.0016682873,0.00028279552,0.0005559241,0.0004166732,0.00039572018,0.00059868186,0.0005803893,0.0004940164,0.00010803482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042025877,0.000042174917,0.001614716,0.000026750522,0.00004158208,0.000031606687,0.00003254006,0.9645452,0.0036107989,0.0011136404,0.00011957945,0.028779434],"study_design_scores_gemma":[0.000001439294,0.000007741786,0.000095925934,8.7073926e-7,0.0000016035901,0.0000032794235,0.0000013064079,0.99945754,0.0002772114,0.00011627791,0.00003561487,0.0000013106182],"about_ca_topic_score_codex":0.004379223,"about_ca_topic_score_gemma":0.0033057434,"teacher_disagreement_score":0.004379223,"about_ca_system_score_codex":0.00041312227,"about_ca_system_score_gemma":0.00089184876,"threshold_uncertainty_score":0.008707464},"labels":[],"label_agreement":null},{"id":"W4410542931","doi":"10.1007/s12665-025-12253-w","title":"Prediction of two groundwater sustainability indicators in semi-arid aquifers using machine learning","year":2025,"lang":"en","type":"article","venue":"Environmental Earth Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Aquifer; Groundwater; Biogeosciences; Arid; Environmental engineering science; Sustainability; Hydrology (agriculture); Water resource management; Geology; Environmental science; Earth science; Geotechnical engineering; Ecology","score_opus":0.014195092173443974,"score_gpt":0.24394885793661916,"score_spread":0.2297537657631752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410542931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99098325,0.000032020867,0.008144044,0.00008626445,0.0000056270956,0.0000065272407,0.00019637152,0.00006944366,0.00047643323],"genre_scores_gemma":[0.99849594,0.000010487758,0.0012646787,0.0000031544996,0.000001900605,0.0000025552226,0.000108084074,0.0000011733488,0.00011206386],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990606,0.000023512404,0.000008436606,0.00002153541,0.00001569432,0.000024737536],"domain_scores_gemma":[0.99917185,0.00049705943,0.00011221439,0.000026596683,0.00013003127,0.000062244086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042338157,0.00030870808,0.00023657434,0.0006610665,0.0001910003,0.00040337368,0.00025012498,0.00039098965,0.00042733335],"category_scores_gemma":[0.0012648773,0.00011350919,0.00021848733,0.00067125354,0.00022881321,0.00043500628,0.00024354777,0.000289702,0.000061676714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029572932,0.00024554026,0.14449285,0.00003889304,0.00006789111,0.000114757226,0.00006130281,0.8119957,0.0029064359,0.0007087506,0.00073400297,0.038338218],"study_design_scores_gemma":[0.0000062428985,0.000016182472,0.011221866,0.0000012507105,0.0000042779657,0.0000037405966,0.000019732033,0.9878578,0.00051210535,0.000314879,0.00003853457,0.000003314067],"about_ca_topic_score_codex":0.02282002,"about_ca_topic_score_gemma":0.022520943,"teacher_disagreement_score":0.02282002,"about_ca_system_score_codex":0.0007773156,"about_ca_system_score_gemma":0.0005111315,"threshold_uncertainty_score":0.045374393},"labels":[],"label_agreement":null},{"id":"W4410660774","doi":"10.1109/access.2025.3573091","title":"A Systematic Analysis of Meteorological Parameters in Predicting Rainfall Events","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Climatology; Environmental science; Weather forecasting; Meteorology; Computer science; Geology; Geography","score_opus":0.028335649817179048,"score_gpt":0.31059469505485376,"score_spread":0.2822590452376747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410660774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8925941,0.018882062,0.07275801,0.00082975527,0.00030690324,0.00030126455,0.0069681853,0.00050514203,0.0068546403],"genre_scores_gemma":[0.9740495,0.0067341765,0.01599903,0.00008610987,0.000077533805,0.000062379055,0.0024808345,0.00004889203,0.00046157732],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988463,0.0004376144,0.00017010172,0.00024536214,0.00025565605,0.000044883822],"domain_scores_gemma":[0.9925962,0.00415277,0.0012315698,0.0008565951,0.001046629,0.000116293624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021413167,0.0005720998,0.0004916457,0.0024062193,0.00031663064,0.00096395094,0.0003851591,0.00039494765,0.00047730372],"category_scores_gemma":[0.009862234,0.00031490266,0.00074223126,0.0036880143,0.0002745081,0.0013618253,0.00051877054,0.0006509059,0.00030388086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012221209,0.00009826706,0.7893903,0.0011953798,0.00089180464,0.00022217337,0.00026552277,0.027557123,0.006918163,0.0014767066,0.0019187003,0.16994356],"study_design_scores_gemma":[0.000016706214,0.00023022751,0.8623412,0.00080091046,0.00090408564,0.00025074347,0.0005888021,0.111431435,0.007466385,0.0021076372,0.013748215,0.00011358611],"about_ca_topic_score_codex":0.0043319194,"about_ca_topic_score_gemma":0.009848707,"teacher_disagreement_score":0.0043319194,"about_ca_system_score_codex":0.00024910187,"about_ca_system_score_gemma":0.0008364314,"threshold_uncertainty_score":0.011324465},"labels":[],"label_agreement":null},{"id":"W4411190807","doi":"10.38124/ijisrt/25may2351","title":"Varuna: A Python-Based System for Water Quality Index Calculation","year":2025,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Python (programming language); Index (typography); Computer science; Programming language","score_opus":0.022230708992136732,"score_gpt":0.28993661414101396,"score_spread":0.2677059051488772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411190807","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031678583,0.00010031024,0.26108435,0.00021322777,0.00013671261,0.00020391129,0.018651726,0.7107082,0.0057337456],"genre_scores_gemma":[0.116305575,0.00054855924,0.54511845,0.0015587563,0.00016421525,0.0027394514,0.09209762,0.22164439,0.019822987],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993173,0.00010003335,0.000078841374,0.00017909499,0.00023908124,0.000085618565],"domain_scores_gemma":[0.9986517,0.0005132449,0.0001069557,0.00020996542,0.00040814318,0.00011012291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013874037,0.0015665069,0.0007315135,0.0013422442,0.0005639492,0.0018886477,0.0033097866,0.0005592641,0.049501896],"category_scores_gemma":[0.0059938375,0.00097383,0.0011926952,0.0013783475,0.00053428864,0.0023049158,0.0025996813,0.0025415581,0.023423104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080172427,0.00032210333,0.008290897,0.0018447537,0.0003662334,0.0004183689,0.0007303181,0.040841114,0.01394335,0.018209316,0.6722821,0.24194969],"study_design_scores_gemma":[0.0003856901,0.000097811026,0.007238107,0.0002292245,0.00008719253,0.00032413923,0.00012977915,0.55007595,0.02965922,0.04642143,0.36501116,0.00034015533],"about_ca_topic_score_codex":0.005297064,"about_ca_topic_score_gemma":0.004742487,"teacher_disagreement_score":0.049501896,"about_ca_system_score_codex":0.0007822307,"about_ca_system_score_gemma":0.0016582261,"threshold_uncertainty_score":0.16560036},"labels":[],"label_agreement":null},{"id":"W4411245323","doi":"10.1007/s11004-025-10194-5","title":"Graph Neural Network Framework for Spatiotemporal Groundwater Level Forecasting","year":2025,"lang":"en","type":"article","venue":"Mathematical Geosciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université du Québec à Chicoutimi; Institut National de la Recherche Scientifique","funders":"Natural Resources Canada","keywords":"Hydrogeology; Groundwater; Graph; Artificial neural network; Computer science; Geology; Data mining; Artificial intelligence; Theoretical computer science; Geotechnical engineering","score_opus":0.07875439601610788,"score_gpt":0.2945342704497974,"score_spread":0.2157798744336895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411245323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011940212,0.00075452117,0.9827439,0.00059564656,0.00009884859,0.000015127394,0.00046298548,0.00037627033,0.0030123738],"genre_scores_gemma":[0.80305016,0.0021369439,0.17943421,0.00025792886,0.00025404873,0.00013641553,0.0012506256,0.00013497498,0.013344663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998536,0.000054274267,0.0000071672066,0.000038855564,0.000029346142,0.000016809103],"domain_scores_gemma":[0.99949646,0.00030864554,0.000041462255,0.00003120041,0.00010000092,0.000022228203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004521266,0.0005233839,0.0006780322,0.00086417,0.00027098018,0.00073779194,0.0011499433,0.0008746431,0.0027038404],"category_scores_gemma":[0.0017770783,0.000259075,0.00042644746,0.0013335013,0.00045359955,0.001192902,0.00052110356,0.0010125561,0.00044237514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001605123,0.000013123916,0.00022093156,0.000022299659,0.000022332433,0.000023693985,0.000010316889,0.95190287,0.00021429948,0.030183498,0.0013756049,0.015995005],"study_design_scores_gemma":[8.513735e-7,0.0000014073449,0.000020703455,0.0000010479785,0.0000017651959,0.0000011947034,0.0000010019049,0.99033934,0.000018055945,0.009466407,0.00014727948,9.282796e-7],"about_ca_topic_score_codex":0.03106816,"about_ca_topic_score_gemma":0.020794734,"teacher_disagreement_score":0.03106816,"about_ca_system_score_codex":0.00092970027,"about_ca_system_score_gemma":0.0008454521,"threshold_uncertainty_score":0.06177461},"labels":[],"label_agreement":null},{"id":"W4411333668","doi":"10.1016/j.asej.2025.103511","title":"Beyond conventional modeling: A cutting-edge hybrid IAER-AMT decision-tree-based algorithm for high-resolution river turbidity prediction","year":2025,"lang":"en","type":"article","venue":"Ain Shams Engineering Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Waterloo; University of Prince Edward Island","funders":"Department of Energy, Environment and Climate Action; Gouvernement de l'Île-du-Prince-Édouard; Natural Sciences and Engineering Research Council of Canada; RUDN University; University of Waterloo; University of Prince Edward Island; Atlantic Canada Opportunities Agency; Razi University; University of Guelph","keywords":"Algorithm; Decision tree; Turbidity; Enhanced Data Rates for GSM Evolution; Resolution (logic); Computer science; Tree (set theory); Geology; Artificial intelligence; Mathematics","score_opus":0.01080633737682015,"score_gpt":0.22332965401216562,"score_spread":0.21252331663534546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411333668","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026692674,0.0003973478,0.9703935,0.00019479412,0.00005403896,0.00006378297,0.00007352867,0.0009593894,0.0011709515],"genre_scores_gemma":[0.45495668,0.00028912534,0.54137164,0.0003881342,0.000092474285,0.0003237334,0.00047360762,0.00015438,0.0019502633],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993705,0.0002225309,0.000045572906,0.00014059551,0.00015311297,0.00006769827],"domain_scores_gemma":[0.9990914,0.00052773353,0.000067364155,0.000044926528,0.00022601415,0.000042470892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017843158,0.0010089263,0.001429339,0.0007959714,0.00051093637,0.000981913,0.0016529056,0.0013198428,0.0016533054],"category_scores_gemma":[0.0030911847,0.00047908188,0.0012431944,0.0009666087,0.00029885033,0.0010925917,0.0010875184,0.0013375347,0.0004819099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016626412,0.00012693356,0.0019901516,0.000074908945,0.0001381908,0.000104185136,0.00008268946,0.8036015,0.0020876857,0.00254193,0.001510466,0.18757515],"study_design_scores_gemma":[0.0000034867885,0.000013110087,0.00004191565,0.0000023077605,0.0000049748755,0.0000057269854,0.0000023203086,0.9993249,0.00008188002,0.00040687088,0.00011087244,0.0000016475433],"about_ca_topic_score_codex":0.0052601537,"about_ca_topic_score_gemma":0.0046956325,"teacher_disagreement_score":0.0052601537,"about_ca_system_score_codex":0.00042369994,"about_ca_system_score_gemma":0.0011703862,"threshold_uncertainty_score":0.010459065},"labels":[],"label_agreement":null},{"id":"W4411386858","doi":"10.1016/j.wroa.2025.100367","title":"Unstructured mesh-based graph neural networks for estimating the spatiotemporal distribution of a human-induced chemical in freshwater","year":2025,"lang":"en","type":"article","venue":"Water Research X","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"National Research Foundation of Korea; Ministry of Science and ICT, South Korea; Ministry of Trade, Industry and Energy; Korea Institute for Advancement of Technology; Institute for Korea Spent Nuclear Fuel","keywords":"Artificial neural network; Computer science; Graph; Artificial intelligence; Theoretical computer science","score_opus":0.05873875452164426,"score_gpt":0.348277254201989,"score_spread":0.28953849968034473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411386858","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3681594,0.00040130108,0.62542206,0.0004385531,0.00010075971,0.00009001465,0.00078089663,0.0012263696,0.0033805624],"genre_scores_gemma":[0.9280934,0.00013808964,0.069319285,0.00009431384,0.00002018483,0.000083248495,0.000654552,0.000040995477,0.0015560122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998653,0.000036698115,0.000006868594,0.000044878605,0.000025359677,0.000020783615],"domain_scores_gemma":[0.9995115,0.00027609026,0.000052548472,0.000028460925,0.000109064626,0.000022405826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039716467,0.0005763604,0.0003419355,0.00056967954,0.00024822867,0.00039880894,0.000988287,0.00064208824,0.0008517133],"category_scores_gemma":[0.0018607201,0.00031473787,0.00054662937,0.00049605744,0.0003612319,0.0005330665,0.00046893425,0.0005476544,0.00013858895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017085213,0.000009356551,0.0011841259,0.000007886312,0.000011816986,0.000013615855,0.000007725477,0.9920908,0.00032869997,0.0005025094,0.00015320265,0.005673131],"study_design_scores_gemma":[7.309241e-7,0.000002227415,0.00008963741,4.837093e-7,8.2071216e-7,7.9106314e-7,0.0000015665695,0.9995602,0.000050053673,0.00027229064,0.000020603355,6.617944e-7],"about_ca_topic_score_codex":0.047326956,"about_ca_topic_score_gemma":0.041510843,"teacher_disagreement_score":0.047326956,"about_ca_system_score_codex":0.0011522454,"about_ca_system_score_gemma":0.0008411955,"threshold_uncertainty_score":0.09410298},"labels":[],"label_agreement":null},{"id":"W4412067535","doi":"10.3390/rs17132306","title":"Impacts of Climate Change on Oceans and Ocean-Based Solutions: A Comprehensive Review from the Deep Learning Perspective","year":2025,"lang":"en","type":"review","venue":"Remote Sensing","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Perspective (graphical); Climate change; Environmental science; Oceanography; Climatology; Geology; Computer science; Artificial intelligence","score_opus":0.06627252926144304,"score_gpt":0.3208411256011837,"score_spread":0.25456859633974066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412067535","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016140276,0.99758995,0.0003865542,0.000590614,0.00016391603,0.0000049687487,0.000044540702,0.000011238361,0.0010468578],"genre_scores_gemma":[0.0010516774,0.99817884,0.00025811524,0.00017890666,0.00009728935,0.0000053318936,0.000034916175,0.000002374551,0.00019259637],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997503,0.000052901225,0.000040648294,0.000048292317,0.00008272166,0.00002508533],"domain_scores_gemma":[0.998871,0.00080244953,0.00009861892,0.00002249624,0.00016578319,0.000039632578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008670614,0.0009456064,0.0011495656,0.0022618058,0.00023272434,0.0010595794,0.00081937603,0.0012598861,0.004313105],"category_scores_gemma":[0.0019986816,0.00033644418,0.0009176614,0.0031516566,0.00040402656,0.0017070182,0.00083880627,0.0013741062,0.0012709378],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004558656,0.000050819992,0.0003051585,0.0415214,0.00023918951,0.000103070146,0.00007545772,0.0017015173,0.0007224348,0.008485316,0.018878363,0.9278717],"study_design_scores_gemma":[0.000013344773,0.00012650498,0.0013476588,0.017453467,0.00053102325,0.00042617205,0.000112439375,0.0008279324,0.0005566575,0.0066760723,0.9718874,0.000041425323],"about_ca_topic_score_codex":0.0019459687,"about_ca_topic_score_gemma":0.0031681044,"teacher_disagreement_score":0.004313105,"about_ca_system_score_codex":0.0005254461,"about_ca_system_score_gemma":0.0018672859,"threshold_uncertainty_score":0.014428794},"labels":[],"label_agreement":null},{"id":"W4412125611","doi":"10.22541/au.175208933.31059664/v1","title":"Knowledge Distillation for Deep Learning-Based Hydrological Prediction and Forecasting","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"Natural Resources Canada","keywords":"Distillation; Computer science; Artificial intelligence; Deep learning; Machine learning; Chemistry","score_opus":0.04191905099354637,"score_gpt":0.2735684809529412,"score_spread":0.2316494299593948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412125611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10350528,0.0013714641,0.88627976,0.0009945963,0.00013442579,0.00006102445,0.0004691666,0.00414212,0.003042086],"genre_scores_gemma":[0.84116197,0.00047246003,0.15444468,0.00030274448,0.00005916924,0.000097426026,0.0008913162,0.000106989515,0.0024633547],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997497,0.000058386824,0.000020272595,0.000080769765,0.000056655197,0.000034260953],"domain_scores_gemma":[0.99929583,0.00039176203,0.00006115741,0.000111223664,0.00010787428,0.000032173582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008334792,0.0009599321,0.0005532591,0.0005836046,0.00034621087,0.00067089795,0.0011189971,0.00080464926,0.0017240519],"category_scores_gemma":[0.0032730354,0.00037159244,0.00047418484,0.0007523631,0.00055143697,0.0019193251,0.0013701578,0.001973531,0.00041943934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011151428,0.0001478518,0.0012178026,0.000079243815,0.00006988308,0.000053134037,0.00006729993,0.76338834,0.0054373206,0.0035235619,0.0019796602,0.22392435],"study_design_scores_gemma":[0.000003571366,0.000014519052,0.000094840485,0.000003873082,0.0000044743692,0.0000039745228,0.0000044139106,0.99578434,0.0018429654,0.0019211988,0.00031861506,0.0000031989684],"about_ca_topic_score_codex":0.014154975,"about_ca_topic_score_gemma":0.015140018,"teacher_disagreement_score":0.014154975,"about_ca_system_score_codex":0.001030753,"about_ca_system_score_gemma":0.00128341,"threshold_uncertainty_score":0.028145134},"labels":[],"label_agreement":null},{"id":"W4412389309","doi":"10.1175/jhm-d-25-0023.1","title":"Local- and Large-Scale Hydrologic Forecast Merging through Time Series Features–Based Dynamic Weights Estimation Framework","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrometeorology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"United Nations University Institute for Water, Environment, and Health; McMaster University","funders":"","keywords":"Scale (ratio); Hydrometeorology; Hydrological modelling; Series (stratigraphy); Estimation; Environmental science; Time series; Computer science; Climatology; Meteorology; Precipitation; Machine learning; Geology; Geography; Cartography","score_opus":0.0046522338845638115,"score_gpt":0.24093349711866788,"score_spread":0.23628126323410406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412389309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20994188,0.00011020279,0.7879927,0.00014698759,0.000034207183,0.000039678416,0.00010358896,0.00058668054,0.001043942],"genre_scores_gemma":[0.8988706,0.000039074188,0.10005396,0.000028737459,0.000032102398,0.000035310954,0.0002016994,0.000046820387,0.00069168373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993783,0.00017058899,0.000041829753,0.00018106516,0.00015659799,0.00007157671],"domain_scores_gemma":[0.9988637,0.00039691429,0.00023260001,0.00012749538,0.00029476787,0.00008458445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020493884,0.0006257807,0.0006304411,0.00094559975,0.00032946508,0.00079729164,0.0010509108,0.00050276663,0.00085114094],"category_scores_gemma":[0.0040559713,0.00037978552,0.0007009783,0.00089896744,0.00035351847,0.001687942,0.0010979751,0.00094286253,0.00013632383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060940998,0.00008505721,0.0045392583,0.000012293907,0.000111928064,0.00003379656,0.000057020363,0.92997354,0.0019901206,0.0022650657,0.00023971668,0.060631137],"study_design_scores_gemma":[0.000001963524,0.0000075395296,0.0004221858,8.399903e-7,0.0000057291677,0.0000016813374,0.0000038732896,0.9987804,0.0003079853,0.0003855383,0.00007937525,0.0000029086777],"about_ca_topic_score_codex":0.022347037,"about_ca_topic_score_gemma":0.0182306,"teacher_disagreement_score":0.022347037,"about_ca_system_score_codex":0.0007417458,"about_ca_system_score_gemma":0.0010395899,"threshold_uncertainty_score":0.04443389},"labels":[],"label_agreement":null},{"id":"W4412420842","doi":"10.1016/j.jhydrol.2025.133834","title":"Climate teleconnection-driven stochastic simulation for future water-related risk management","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Ministry of Science and ICT, South Korea; Ministry of the Interior and Safety; National Research Foundation of Korea","keywords":"Teleconnection; Environmental science; Climatology; Climate change; Climate model; Risk management; Meteorology; Geology; Geography; Economics; El Niño Southern Oscillation; Oceanography","score_opus":0.005777182237377438,"score_gpt":0.24797651800502082,"score_spread":0.24219933576764338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412420842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6645302,0.0005692438,0.30699685,0.002112669,0.00054442085,0.00013625913,0.003066683,0.0014539665,0.020589776],"genre_scores_gemma":[0.98287994,0.00011123199,0.014447156,0.00008627839,0.000045366378,0.000055022672,0.00049132225,0.00007168758,0.001812062],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998573,0.00006561984,0.000008981652,0.000026407533,0.000021695909,0.000020007003],"domain_scores_gemma":[0.9988991,0.0006869592,0.00008607311,0.000052371586,0.00017531271,0.00010019003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006704192,0.0004279883,0.00052009965,0.0005159742,0.00050140533,0.0006987209,0.000925959,0.0010966758,0.0037239478],"category_scores_gemma":[0.002796715,0.00037709074,0.00054813246,0.0006510197,0.00039851328,0.0007253129,0.00056248496,0.0012509718,0.00024573845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011514013,0.000012267969,0.00041702067,0.0000034971647,0.0000083897985,0.000010934733,0.0000043040845,0.99740714,0.00007179847,0.0011361967,0.00020411119,0.00071291596],"study_design_scores_gemma":[0.0000023074954,0.0000014572565,0.0000367361,3.7859635e-7,9.354724e-7,7.0951756e-7,8.9205184e-7,0.9996791,0.000013173574,0.00021693812,0.00004651116,8.5728743e-7],"about_ca_topic_score_codex":0.046645164,"about_ca_topic_score_gemma":0.025788179,"teacher_disagreement_score":0.046645164,"about_ca_system_score_codex":0.0011334518,"about_ca_system_score_gemma":0.0014489423,"threshold_uncertainty_score":0.09274733},"labels":[],"label_agreement":null},{"id":"W4412590550","doi":"10.1016/b978-0-443-33631-7.00004-4","title":"Prediagnosis of flooding using real-time monitoring of climate parameters","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Ottawa; Université Laval","funders":"","keywords":"Flooding (psychology); Environmental science; Meteorology; Geography; Psychology","score_opus":0.02603914385857216,"score_gpt":0.2542911736212434,"score_spread":0.22825202976267128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412590550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06257643,0.0022460395,0.825332,0.00068982766,0.00043841676,0.00007580513,0.0028627624,0.008691355,0.09708736],"genre_scores_gemma":[0.6045916,0.0029720024,0.32722497,0.0001800167,0.00034133822,0.00006921119,0.0034416686,0.000471715,0.060707375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992764,0.00001165782,0.000006793504,0.0000210154,0.000028508828,0.0000044126355],"domain_scores_gemma":[0.9996941,0.00015294287,0.000038122045,0.000045442168,0.000053840078,0.000015575153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030620105,0.0002697969,0.00017925122,0.0007450855,0.00010623176,0.0008636758,0.00045440425,0.0004396109,0.00723712],"category_scores_gemma":[0.0009181368,0.00014308772,0.00021980621,0.0006699408,0.00018373971,0.00081162533,0.00021204037,0.0002566159,0.0019419112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013167917,0.000042126067,0.012608669,0.00021387465,0.000026002492,0.00022609193,0.00011112573,0.045353934,0.016722504,0.009342833,0.018530646,0.89669055],"study_design_scores_gemma":[0.000024464054,0.00016568898,0.037608966,0.00016457701,0.00007910367,0.0010486713,0.00018960157,0.7722595,0.040521577,0.035171326,0.11269906,0.00006754014],"about_ca_topic_score_codex":0.002409307,"about_ca_topic_score_gemma":0.0039996477,"teacher_disagreement_score":0.00723712,"about_ca_system_score_codex":0.00015945849,"about_ca_system_score_gemma":0.00026882865,"threshold_uncertainty_score":0.024210513},"labels":[],"label_agreement":null},{"id":"W4412592632","doi":"10.1016/b978-0-443-33631-7.00002-0","title":"Integration of hydrometric upstream runoff and Optimal Pruned Extreme Learning Machine for real-time flood forecasting","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Ottawa; Université Laval","funders":"","keywords":"Upstream (networking); Flood myth; Surface runoff; Flood forecasting; Extreme learning machine; Hydrology (agriculture); Computer science; Environmental science; Real-time computing; Artificial intelligence; Geology; Geography; Geotechnical engineering; Ecology; Archaeology; Biology; Computer network","score_opus":0.026766814006347412,"score_gpt":0.23165570128785734,"score_spread":0.20488888728150992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412592632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026411936,0.00051028474,0.96934885,0.000118304044,0.00009012226,0.000014810482,0.00003181676,0.0006586681,0.0028152922],"genre_scores_gemma":[0.6641337,0.00044989566,0.32856166,0.00009252804,0.00013978367,0.0000604203,0.0001887601,0.00015951728,0.0062136953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997358,0.000060528524,0.000022096694,0.00005627338,0.00009930602,0.000026101334],"domain_scores_gemma":[0.9996518,0.00016276907,0.000024950472,0.00004655307,0.0000992616,0.000014746155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007004788,0.00047401854,0.0007372037,0.0004636936,0.00020982468,0.00069222925,0.0010403998,0.00074857776,0.0023062495],"category_scores_gemma":[0.0018495665,0.00044483048,0.0005136974,0.0007550835,0.00031755934,0.0010973628,0.00087827083,0.0010030876,0.00043804746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057841273,0.00007038124,0.0005535338,0.000041213767,0.000062919535,0.000053433654,0.00003571898,0.75916743,0.0032627769,0.0043417877,0.0010719941,0.23128088],"study_design_scores_gemma":[0.000001082992,0.000008130957,0.00011637661,0.000002254133,0.0000036824763,0.0000062580602,0.0000016472854,0.99792093,0.000299714,0.0014171685,0.00022074503,0.0000020204222],"about_ca_topic_score_codex":0.002579542,"about_ca_topic_score_gemma":0.0042963945,"teacher_disagreement_score":0.002579542,"about_ca_system_score_codex":0.00031998084,"about_ca_system_score_gemma":0.00039609312,"threshold_uncertainty_score":0.0077151656},"labels":[],"label_agreement":null},{"id":"W4412592729","doi":"10.1016/b978-0-443-33631-7.00014-7","title":"Hybrid AI-Powered Models and Cloud-Based Solutions for Hydroclimatic Forecasting and Sustainable Soil and Water Management – Nonlinear modeling approach","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval","funders":"","keywords":"Cloud computing; Nonlinear system; Environmental science; Meteorology; Climatology; Computer science; Geology; Geography; Physics","score_opus":0.0312983933834631,"score_gpt":0.226142576003894,"score_spread":0.1948441826204309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412592729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021029724,0.0031633961,0.9028741,0.0011711025,0.00046777402,0.000038076574,0.00046353007,0.0009159978,0.06987625],"genre_scores_gemma":[0.72629136,0.006566174,0.18561584,0.00036012343,0.0004878147,0.00013129316,0.0009072128,0.0002753988,0.07936483],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999466,0.000011036844,0.0000029276061,0.000009759889,0.000023835171,0.0000057684147],"domain_scores_gemma":[0.99988675,0.00005364854,0.000009182219,0.000013129648,0.000029762963,0.000007443544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016178566,0.00048898195,0.00032967087,0.00024389282,0.0002010105,0.0009771404,0.00080208323,0.0005695435,0.003913063],"category_scores_gemma":[0.00039327066,0.00021958814,0.00038477522,0.00080361526,0.0002334181,0.0011876079,0.0005361826,0.00089223037,0.0008542512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000267605,0.000039201466,0.00030521737,0.00008958222,0.00004551246,0.000055333407,0.000039435257,0.8544615,0.002851293,0.04298479,0.005390377,0.093710996],"study_design_scores_gemma":[0.0000021314033,0.0000070040896,0.000099120036,0.000007909366,0.0000052237147,0.000012076169,0.000008516285,0.98151565,0.0004187314,0.013095618,0.0048231874,0.0000048688335],"about_ca_topic_score_codex":0.007162968,"about_ca_topic_score_gemma":0.0075893137,"teacher_disagreement_score":0.007162968,"about_ca_system_score_codex":0.0005486283,"about_ca_system_score_gemma":0.00040876606,"threshold_uncertainty_score":0.01424253},"labels":[],"label_agreement":null},{"id":"W4412592740","doi":"10.1016/b978-0-443-33631-7.00009-3","title":"Mining and refining hydroclimatic data for hybrid AI-driven sustainability models","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval","funders":"","keywords":"Refining (metallurgy); Sustainability; Environmental science; Computer science; Materials science; Ecology; Metallurgy","score_opus":0.041071376152153255,"score_gpt":0.27785568283842843,"score_spread":0.23678430668627518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412592740","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025226843,0.00066430354,0.9554334,0.00042398408,0.000114480885,0.00004505157,0.0021837603,0.0028121434,0.013095979],"genre_scores_gemma":[0.37540996,0.0014016192,0.6062337,0.00014055915,0.00010076608,0.00014345368,0.00496369,0.0004382371,0.011167914],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998889,0.000022395889,0.000009890481,0.000028064147,0.000043309406,0.0000074488144],"domain_scores_gemma":[0.999426,0.00037005675,0.00003344319,0.00007031517,0.000085477106,0.000014783655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046657023,0.0006144825,0.00033354515,0.00079235825,0.00019701569,0.0011930065,0.0007713693,0.00037645607,0.004591579],"category_scores_gemma":[0.0017975054,0.00042686085,0.0006098624,0.0013824096,0.00025078046,0.0011514435,0.00064329617,0.0008378081,0.001225065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022676506,0.000026476857,0.0015416371,0.000112141875,0.00007348807,0.00006118757,0.000056044395,0.78762823,0.0026714576,0.008486224,0.0056151985,0.19370519],"study_design_scores_gemma":[0.0000016991049,0.0000036722797,0.00027751244,0.000012601192,0.0000061871365,0.000010803069,0.000012257976,0.9859379,0.0007834988,0.009696529,0.0032528688,0.0000044693493],"about_ca_topic_score_codex":0.008712051,"about_ca_topic_score_gemma":0.01604071,"teacher_disagreement_score":0.008712051,"about_ca_system_score_codex":0.00046692617,"about_ca_system_score_gemma":0.00046286292,"threshold_uncertainty_score":0.01732266},"labels":[],"label_agreement":null},{"id":"W4412592799","doi":"10.1016/b978-0-443-33631-7.00005-6","title":"R for machine learning in Earth sciences","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval","funders":"","keywords":"Earth (classical element); Astrobiology; Computer science; Physics; Astronomy","score_opus":0.0241358497100475,"score_gpt":0.25127412357868995,"score_spread":0.22713827386864244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412592799","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005969459,0.009273115,0.7300635,0.0056538265,0.003992648,0.00018391147,0.016940081,0.06070287,0.17259303],"genre_scores_gemma":[0.012912151,0.009307754,0.57941204,0.003852607,0.003550542,0.0013808636,0.01862636,0.05035213,0.3206055],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806076,0.00068399764,0.00018621258,0.00038247113,0.0006137241,0.00007288581],"domain_scores_gemma":[0.9910946,0.0057158563,0.0005004002,0.0015882438,0.0009211258,0.00017986391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002689251,0.0023090204,0.002072256,0.0028217246,0.00046615547,0.0032690787,0.0017367831,0.0023765415,0.2227158],"category_scores_gemma":[0.018896446,0.00095617416,0.0011242754,0.0031063433,0.0010914312,0.0033359844,0.0017122974,0.0033851827,0.2145054],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020993994,0.00001992946,0.00020226507,0.0009556445,0.000083332714,0.00010524232,0.00005239244,0.0024507581,0.00075062556,0.06523614,0.7028458,0.22727698],"study_design_scores_gemma":[0.000037157617,0.000016765669,0.00042488318,0.00048119912,0.00006181144,0.00032230112,0.000020994576,0.01258546,0.0015603817,0.1488653,0.8355851,0.00003862252],"about_ca_topic_score_codex":0.0015671356,"about_ca_topic_score_gemma":0.0021253787,"teacher_disagreement_score":0.2227158,"about_ca_system_score_codex":0.00055837695,"about_ca_system_score_gemma":0.0015206554,"threshold_uncertainty_score":0.74505854},"labels":[],"label_agreement":null},{"id":"W4413075649","doi":"10.14796/jwmm.h556","title":"Prediction of Streamflow in the Brahmani River using GEP, SVM, and MLR Models","year":2025,"lang":"en","type":"article","venue":"Journal of Water Management Modeling","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Science and Engineering Research Board; National Institute of Technology Rourkela; Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Streamflow; Mean squared error; Support vector machine; Gene expression programming; Regression; Linear regression; Coefficient of determination; Environmental science; Statistics; Mathematics; Computer science; Machine learning; Geography; Drainage basin","score_opus":0.044768980385900416,"score_gpt":0.23364205176223468,"score_spread":0.18887307137633427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413075649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7299538,0.00056632754,0.26523826,0.000566233,0.00003864013,0.000054049375,0.00042239286,0.00096038444,0.0021998489],"genre_scores_gemma":[0.9719829,0.00018588912,0.026440462,0.000037130092,0.00000955393,0.00004481385,0.00032507282,0.000022740092,0.00095150934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973255,0.0000872919,0.00001796429,0.00007689375,0.000050193434,0.00003511198],"domain_scores_gemma":[0.9995353,0.00031355047,0.00005412381,0.000018247416,0.00006697353,0.00001183361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006087738,0.000599072,0.00058696675,0.00050461316,0.00018512881,0.0007503107,0.00060857163,0.000493761,0.0003216039],"category_scores_gemma":[0.0013018785,0.00021141153,0.0006287444,0.0006446372,0.00024273616,0.0005327239,0.00029699248,0.0007180216,0.00011958968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074521704,0.000076066564,0.01586988,0.00006190416,0.000059648697,0.00014190073,0.00008311808,0.9354109,0.0033428504,0.0008616413,0.0003494686,0.043668028],"study_design_scores_gemma":[0.0000016340928,0.000015312156,0.0018994309,0.0000026068662,0.0000049829196,0.000011120576,0.000012972401,0.99730206,0.000433964,0.0002322975,0.00007993403,0.0000037411178],"about_ca_topic_score_codex":0.010074952,"about_ca_topic_score_gemma":0.0068777497,"teacher_disagreement_score":0.010074952,"about_ca_system_score_codex":0.0005589835,"about_ca_system_score_gemma":0.00061441894,"threshold_uncertainty_score":0.020032585},"labels":[],"label_agreement":null},{"id":"W4413195685","doi":"10.1007/978-3-031-87931-9_16","title":"Streamflow Forecasting in the Downstream Catchment of Mahanadi River Basin Using AI and Quantum Computing","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ford Motor Company (Canada)","funders":"","keywords":"Streamflow; Drainage basin; Hydrology (agriculture); Downstream (manufacturing); Environmental science; Climatology; Structural basin; Geology; Geography; Geomorphology; Cartography; Engineering; Geotechnical engineering","score_opus":0.03279099685035769,"score_gpt":0.24635076929003175,"score_spread":0.21355977243967406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413195685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32633686,0.0034069677,0.60824776,0.0022822735,0.0003828856,0.000060090053,0.0008906506,0.0017689356,0.056623578],"genre_scores_gemma":[0.897091,0.0017038061,0.08171317,0.0000836956,0.00008704908,0.00002770296,0.00045522247,0.0000804071,0.01875793],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999713,0.000005518129,0.0000018361717,0.000007969572,0.000009462079,0.000004006309],"domain_scores_gemma":[0.99993443,0.000034656867,0.000003984485,0.0000047366866,0.000017906765,0.0000043677787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009969826,0.00013645142,0.00016140477,0.00024131262,0.00025542642,0.00046824972,0.00037617068,0.00019488596,0.0012610315],"category_scores_gemma":[0.0002693484,0.00009990468,0.00019159364,0.0006230123,0.0001471454,0.0005285885,0.00015451993,0.00037443993,0.00016154288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000615475,0.00004066882,0.0048389006,0.000117447824,0.0000355278,0.00016627656,0.00020312566,0.64688146,0.010637083,0.030270718,0.010447107,0.29630014],"study_design_scores_gemma":[0.0000019892743,0.00000717613,0.0014051897,0.000005248152,0.0000046104483,0.000012500721,0.000030584495,0.9878429,0.0011605924,0.0074664196,0.0020570245,0.0000056909284],"about_ca_topic_score_codex":0.0205749,"about_ca_topic_score_gemma":0.03638279,"teacher_disagreement_score":0.0205749,"about_ca_system_score_codex":0.00044595005,"about_ca_system_score_gemma":0.0005118038,"threshold_uncertainty_score":0.040910304},"labels":[],"label_agreement":null},{"id":"W4413284012","doi":"10.1007/s42452-025-06817-5","title":"A systematic review of neural network applications for groundwater level prediction","year":2025,"lang":"en","type":"review","venue":"Discover Applied Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"West African Science Service Centre on Climate Change and Adapted Land Use; International Development Research Centre","keywords":"Artificial neural network; Groundwater; Computer science; Environmental science; Artificial intelligence; Geology; Geotechnical engineering","score_opus":0.06133496577062432,"score_gpt":0.32203421977467706,"score_spread":0.26069925400405275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413284012","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007174637,0.9968346,0.00095263263,0.00044147336,0.00017359403,0.00015567994,0.0003804784,0.000014520842,0.00032965714],"genre_scores_gemma":[0.011212741,0.98559046,0.002014332,0.0003886244,0.00008095547,0.0003114132,0.00027142518,0.000010079641,0.0001199291],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99274045,0.0028180776,0.0025523778,0.0005562102,0.0012261553,0.000106843945],"domain_scores_gemma":[0.96805924,0.024424393,0.003293737,0.00050799834,0.0035592667,0.00015530174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009755285,0.0014494199,0.0040103295,0.0077780928,0.0004247309,0.0020486368,0.0019078591,0.001400339,0.0034762002],"category_scores_gemma":[0.053497188,0.0006591508,0.0071722455,0.0072010453,0.00057148427,0.0016999196,0.0011791476,0.0010775026,0.00035974453],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017538732,0.000030574836,0.0009414076,0.8127238,0.0076222643,0.00009934155,0.00013156954,0.0012783725,0.00024618622,0.00079543795,0.0028946847,0.17306094],"study_design_scores_gemma":[0.00013187317,0.00035883303,0.0040753507,0.89051,0.042271294,0.00029519448,0.00021310049,0.0012175582,0.00053864624,0.0016650596,0.058659244,0.000063903506],"about_ca_topic_score_codex":0.007740206,"about_ca_topic_score_gemma":0.019652026,"teacher_disagreement_score":0.009755285,"about_ca_system_score_codex":0.002210224,"about_ca_system_score_gemma":0.009775702,"threshold_uncertainty_score":0.051591516},"labels":[],"label_agreement":null},{"id":"W4413301319","doi":"10.30564/re.v7i3.10453","title":"Sustainable Groundwater Management in Water-Scarce Regions: A Spatial Machine Learning Analysis from Rajshahi, Bangladesh","year":2025,"lang":"en","type":"article","venue":"Research in Ecology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Groundwater; Water resource management; Environmental science; Environmental planning; Geography; Engineering","score_opus":0.030095131962288354,"score_gpt":0.32019922425946934,"score_spread":0.290104092297181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413301319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959066,0.00008902846,0.0008420075,0.00038329264,0.0000032127164,0.000028587341,0.00080872315,0.000019441235,0.0019191226],"genre_scores_gemma":[0.9970444,0.00023015853,0.00091535284,0.000029656909,0.0000032755827,0.000022875985,0.0010933916,0.0000062923004,0.00065459317],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997161,0.00010626242,0.000027115746,0.0000467529,0.000041631854,0.000062063],"domain_scores_gemma":[0.99926656,0.00035528842,0.00007174474,0.000049499784,0.00020472138,0.0000521658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004885349,0.00046698537,0.00038863646,0.0011420078,0.00068198337,0.0009262312,0.00056755287,0.0005438679,0.0012613629],"category_scores_gemma":[0.0016014354,0.00023260365,0.00058555277,0.0026193885,0.0005405917,0.0005984691,0.00068876654,0.0005180506,0.0003024089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042148007,0.0007145617,0.60030025,0.00052287953,0.0005173971,0.0053862617,0.0043652277,0.2869759,0.0045674983,0.0052517117,0.0052071386,0.08576963],"study_design_scores_gemma":[0.000078794445,0.00033292331,0.6021835,0.00015427529,0.00026562205,0.0005777469,0.023938246,0.35787988,0.0019507598,0.0032884902,0.009175158,0.00017458519],"about_ca_topic_score_codex":0.30729103,"about_ca_topic_score_gemma":0.31114298,"teacher_disagreement_score":0.30729103,"about_ca_system_score_codex":0.0026540374,"about_ca_system_score_gemma":0.0014916912,"threshold_uncertainty_score":0.6110048},"labels":[],"label_agreement":null},{"id":"W4413310815","doi":"10.1029/2025wr040670","title":"Predicting Nitrous Oxide Emission From China's Waterbodies With Multiple Deep Learning Algorithms","year":2025,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China","keywords":"Nitrous oxide; Algorithm; China; Environmental science; Computer science; Chemistry; Geography","score_opus":0.022054800759015062,"score_gpt":0.27967744735742567,"score_spread":0.2576226465984106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413310815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98786247,0.00018963763,0.010398531,0.0001719145,0.000021283164,0.00001165104,0.000489637,0.00026197932,0.00059283775],"genre_scores_gemma":[0.99618787,0.000057524696,0.0028194056,0.000021908,0.000007714503,0.000010431671,0.00053993607,0.000007418668,0.00034779435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998361,0.000018761544,0.0000106861935,0.00006428468,0.000029309265,0.000040766543],"domain_scores_gemma":[0.9998149,0.000041010717,0.000030634223,0.00001415469,0.00006892189,0.000030362713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005215115,0.0011263372,0.0004259506,0.0009859336,0.00033473686,0.00051673164,0.0007277906,0.0005732583,0.0005122842],"category_scores_gemma":[0.0005461958,0.00035188012,0.00079190836,0.000838493,0.00028061174,0.0007301554,0.0006583598,0.00044551835,0.000084259336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120065415,0.0001764208,0.10815335,0.000058773545,0.00015078303,0.00018000267,0.00006191789,0.83804566,0.006508295,0.00026090365,0.00096710696,0.04531678],"study_design_scores_gemma":[0.000005100574,0.000012470294,0.008144068,0.000002320844,0.000011963276,0.0000026147134,0.000012940826,0.99084854,0.0007485292,0.00011836869,0.0000880914,0.0000049522905],"about_ca_topic_score_codex":0.08588213,"about_ca_topic_score_gemma":0.07448323,"teacher_disagreement_score":0.08588213,"about_ca_system_score_codex":0.001566938,"about_ca_system_score_gemma":0.0014744378,"threshold_uncertainty_score":0.17076445},"labels":[],"label_agreement":null},{"id":"W4413321517","doi":"10.1109/antem64578.2025.11114147","title":"Performance Evaluation of Three Deep Learning Models for River ICE Segmentation From Aerial Images","year":2025,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Artificial intelligence; Computer science; Aerial imagery; Image segmentation; Deep learning; Computer vision; Aerial image; Remote sensing; Geology; Image (mathematics)","score_opus":0.04963318412799464,"score_gpt":0.2827326325634446,"score_spread":0.23309944843544997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413321517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9278855,0.003752145,0.054952364,0.0007484021,0.00034049712,0.00010631097,0.0013705639,0.0041894806,0.0066547315],"genre_scores_gemma":[0.96439725,0.0005006355,0.029074943,0.00021314457,0.00003410128,0.00004670329,0.0025609883,0.000071525064,0.0031005833],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996593,0.00006113329,0.000027203978,0.00010167813,0.00006049908,0.00009012711],"domain_scores_gemma":[0.9993531,0.00025484298,0.000050209517,0.000049622195,0.00022202761,0.00007016923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015315827,0.001705651,0.00061255664,0.0013001009,0.00043835532,0.0008545817,0.0011022456,0.0011069746,0.0009821189],"category_scores_gemma":[0.002002685,0.00031610823,0.00069729873,0.0007436441,0.00039406118,0.0011260766,0.0005993739,0.00091721345,0.00035811303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011002443,0.00044310486,0.019634666,0.0001981769,0.0003801788,0.0001569204,0.0001065166,0.67054635,0.0073219175,0.00091143814,0.005329438,0.293871],"study_design_scores_gemma":[0.000008718033,0.000084738516,0.0014157643,0.00001189637,0.000026317268,0.000012863877,0.000035912726,0.99474585,0.0031776885,0.000180715,0.0002918196,0.000007845103],"about_ca_topic_score_codex":0.054247744,"about_ca_topic_score_gemma":0.056391492,"teacher_disagreement_score":0.054247744,"about_ca_system_score_codex":0.0018129341,"about_ca_system_score_gemma":0.0015905692,"threshold_uncertainty_score":0.10786396},"labels":[],"label_agreement":null},{"id":"W4413414210","doi":"10.1038/s42003-025-08714-4","title":"Publisher Correction: fNIRS reproducibility varies with data quality, analysis pipelines, and researcher experience","year":2025,"lang":"en","type":"erratum","venue":"Communications Biology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Université de Montréal; University of Manitoba; Western University","funders":"","keywords":"Reproducibility; Quality (philosophy); Pipeline transport; Computer science; Data quality; Data science; Statistics; Engineering; Mathematics; Mechanical engineering; Operations management; Philosophy; Epistemology","score_opus":0.19890322823836545,"score_gpt":0.4203565557844873,"score_spread":0.22145332754612182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413414210","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057239475,0.0010954083,0.0041935463,0.05908068,0.924017,0.00004405701,0.0017901075,0.001887526,0.0073192962],"genre_scores_gemma":[0.049717017,0.009794243,0.034491718,0.10561513,0.2690316,0.0005023095,0.010828689,0.020760164,0.49925902],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9875683,0.001658823,0.0024370414,0.0015168047,0.0062780236,0.00054087694],"domain_scores_gemma":[0.87169665,0.029287428,0.0052236887,0.010221476,0.081338994,0.002231812],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010086397,0.0020505278,0.0017404591,0.005142265,0.0054241926,0.0065185633,0.003346474,0.004996746,0.07214477],"category_scores_gemma":[0.14394893,0.0014018747,0.0011039359,0.0043137805,0.003752801,0.0033466932,0.0034894662,0.009673477,0.05415917],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003910998,0.0000059170857,0.000184059,0.00015917377,0.000014087556,0.00032146167,0.00011029672,0.000057286383,0.00018612332,0.0013560189,0.98293245,0.014634089],"study_design_scores_gemma":[0.000024755469,0.000017955741,0.00078118156,0.00039056398,0.00003975541,0.00082576886,0.00019683315,0.0004201923,0.0010892864,0.0024346712,0.9937202,0.00005886114],"about_ca_topic_score_codex":0.0171081,"about_ca_topic_score_gemma":0.021756476,"teacher_disagreement_score":0.9899136,"about_ca_system_score_codex":0.003724082,"about_ca_system_score_gemma":0.0071852654,"threshold_uncertainty_score":0.24134833},"labels":[],"label_agreement":null},{"id":"W4413429513","doi":"10.3390/w17172506","title":"A DeepAR-Based Modeling Framework for Probabilistic Mid–Long-Term Streamflow Prediction","year":2025,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"China Scholarship Council; Natural Science Foundation of Hubei Province; National Natural Science Foundation of China; University of Regina","keywords":"Streamflow; Term (time); Probabilistic logic; Environmental science; Computer science; Hydrology (agriculture); Geology; Artificial intelligence; Geotechnical engineering; Geography; Drainage basin; Physics; Cartography","score_opus":0.023321863378685463,"score_gpt":0.263845222587225,"score_spread":0.2405233592085395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413429513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015325838,0.0003606076,0.98081446,0.00026032762,0.00005388696,0.0000271047,0.0005042474,0.0013239041,0.0013296747],"genre_scores_gemma":[0.75228655,0.0010252119,0.23987943,0.0002779917,0.0002013916,0.0002489125,0.0024676484,0.00028651237,0.0033264004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997813,0.00004901505,0.000018016828,0.00006160824,0.000057568748,0.00003249146],"domain_scores_gemma":[0.9995846,0.00016221174,0.00005610129,0.000026705644,0.00013696867,0.00003340387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094592315,0.0009652596,0.00072748936,0.00066073675,0.0003590769,0.0012237378,0.0015875228,0.0009807616,0.0015899129],"category_scores_gemma":[0.0014052425,0.00060582685,0.0010938576,0.0007940665,0.0004457388,0.0011249535,0.0010630236,0.0017170486,0.0005119462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012043652,0.000011441479,0.00029538653,0.000014115412,0.000025810119,0.000027746468,0.000009568561,0.98743033,0.0005618754,0.0027803301,0.00033212217,0.008499189],"study_design_scores_gemma":[0.0000010688656,0.000002604615,0.000038325565,0.0000013563576,0.0000026948603,0.0000027491492,0.0000012094117,0.9988813,0.00006579711,0.0008865401,0.00011404241,0.0000023355435],"about_ca_topic_score_codex":0.027014736,"about_ca_topic_score_gemma":0.021973971,"teacher_disagreement_score":0.027014736,"about_ca_system_score_codex":0.0007939882,"about_ca_system_score_gemma":0.0019054972,"threshold_uncertainty_score":0.05371499},"labels":[],"label_agreement":null},{"id":"W4413471057","doi":"10.2166/hydro.2025.009","title":"The application of data-driven modelling for the water quality index: a case study in Canada","year":2025,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Regina","funders":"Natural Science Foundation of Anhui Province","keywords":"Index (typography); Environmental science; Quality (philosophy); Water quality; Computer science; Statistics; Data mining; Mathematics; Physics; World Wide Web","score_opus":0.058954034231872815,"score_gpt":0.3199619047247628,"score_spread":0.26100787049289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413471057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820701,0.00013050786,0.012108201,0.0007026406,0.000014116817,0.00016912424,0.0012841851,0.00012478718,0.0033962727],"genre_scores_gemma":[0.988492,0.000087121516,0.009781241,0.000044287124,0.0000031292298,0.00004613348,0.00055034255,0.000014276991,0.0009813625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99921966,0.00028520357,0.00004149887,0.00011558739,0.00021076754,0.00012740516],"domain_scores_gemma":[0.9975193,0.0012172557,0.00011441915,0.00012361705,0.0009189985,0.00010647029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019040728,0.0005187819,0.00042592522,0.0009634868,0.0013530331,0.0016386533,0.001290981,0.0008047601,0.00068468536],"category_scores_gemma":[0.0046518017,0.00027533635,0.00078369374,0.0023164682,0.00077008543,0.0005022285,0.0006386915,0.00090796273,0.00006755989],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016626979,0.00030602407,0.08186926,0.00012853346,0.00014271346,0.00091595197,0.0003860421,0.8871936,0.0012581969,0.0044255136,0.0017281616,0.02147976],"study_design_scores_gemma":[0.000024421837,0.0000423946,0.02079553,0.0000134164875,0.000027965536,0.000029300336,0.0005532566,0.9754484,0.00093579106,0.0008201179,0.0012779664,0.000031471507],"about_ca_topic_score_codex":0.94337994,"about_ca_topic_score_gemma":0.9234553,"teacher_disagreement_score":0.05662006,"about_ca_system_score_codex":0.021405017,"about_ca_system_score_gemma":0.014436999,"threshold_uncertainty_score":0.15530503},"labels":[],"label_agreement":null},{"id":"W4413635137","doi":"10.1007/978-3-031-88862-5_2","title":"Quantifying Scaling-Up Uncertainty in Soil Data Using Fuzzy C-Means Clustering: A Framework for Application to Hydrological Modeling","year":2025,"lang":"en","type":"book-chapter","venue":"Environmental science and engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Scaling; Fuzzy logic; Cluster analysis; Computer science; Data mining; Environmental science; Fuzzy clustering; Hydrology (agriculture); Mathematics; Artificial intelligence; Geology; Geotechnical engineering","score_opus":0.0628881076803027,"score_gpt":0.2797658519521686,"score_spread":0.21687774427186587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413635137","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00269502,0.00041627017,0.9946101,0.00012660207,0.00003800725,0.000021452259,0.00010734377,0.00026890906,0.0017163673],"genre_scores_gemma":[0.0835221,0.0008470372,0.9123312,0.00009374403,0.000093436196,0.00007673438,0.00033260888,0.00022923054,0.002474007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989158,0.00019526953,0.000056695786,0.0001799228,0.0005968203,0.00005547467],"domain_scores_gemma":[0.9980642,0.0009938255,0.00015569518,0.00021065859,0.00053212646,0.000043534794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025113763,0.0011262064,0.0011069672,0.0023047656,0.00081495824,0.002357133,0.0019968096,0.0014170288,0.0016638982],"category_scores_gemma":[0.0059717847,0.00057019695,0.0013736403,0.004196214,0.0009937524,0.0021169642,0.0013572811,0.0016856889,0.00045289053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032885855,0.000048475125,0.0013375817,0.00021444088,0.00016726606,0.000092481416,0.00024676532,0.54263693,0.004184965,0.09833726,0.0081295455,0.34457135],"study_design_scores_gemma":[0.0000015006232,0.000011494682,0.00058727636,0.000027845015,0.000019694973,0.000037455415,0.00003686987,0.93294454,0.0017430775,0.06136995,0.003194157,0.000026191372],"about_ca_topic_score_codex":0.014216203,"about_ca_topic_score_gemma":0.020055875,"teacher_disagreement_score":0.014216203,"about_ca_system_score_codex":0.0018786131,"about_ca_system_score_gemma":0.0016469981,"threshold_uncertainty_score":0.028266907},"labels":[],"label_agreement":null},{"id":"W4413875697","doi":"10.1007/s40899-025-01276-7","title":"From data to decision: leveraging machine learning and water quality index for groundwater quality evaluation","year":2025,"lang":"en","type":"article","venue":"Sustainable Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Newcastle University","keywords":"Index (typography); Groundwater; Water quality; Quality (philosophy); Hydrogeology; Computer science; Environmental science; Water resource management; Environmental economics; Engineering; Economics; Geotechnical engineering","score_opus":0.053555599968077475,"score_gpt":0.34193588293021265,"score_spread":0.2883802829621352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413875697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4358888,0.0031211707,0.5483215,0.0030354392,0.00028312852,0.0003821475,0.0011584857,0.0026958687,0.0051134164],"genre_scores_gemma":[0.94010323,0.0003280101,0.05790051,0.00026578864,0.000078615696,0.0000920056,0.0005484365,0.000028138853,0.00065523735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986405,0.0005714139,0.00012865373,0.00025638755,0.00027702627,0.00012606358],"domain_scores_gemma":[0.99683857,0.0021603187,0.00025618426,0.00018654481,0.0004468065,0.00011153684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003310457,0.0013746702,0.0010727599,0.0018780135,0.00029240944,0.0016290653,0.00108766,0.001177529,0.0008843409],"category_scores_gemma":[0.008009167,0.00030683458,0.00092088286,0.0015068831,0.00039722826,0.0019943072,0.001067471,0.0014290866,0.0002765228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029003114,0.00061263726,0.031596944,0.0001933329,0.00035187305,0.00023059986,0.00013395687,0.6912708,0.0024293023,0.001546754,0.002300038,0.26904374],"study_design_scores_gemma":[0.0000040959344,0.000059775102,0.0010128026,0.00001031421,0.000016655984,0.0000083080695,0.000020092353,0.9966364,0.000672469,0.0013287247,0.00022202644,0.000008324169],"about_ca_topic_score_codex":0.008419937,"about_ca_topic_score_gemma":0.008985879,"teacher_disagreement_score":0.008419937,"about_ca_system_score_codex":0.0010078412,"about_ca_system_score_gemma":0.0011589791,"threshold_uncertainty_score":0.017507553},"labels":[],"label_agreement":null},{"id":"W4414036714","doi":"10.1016/j.jhydrol.2025.134208","title":"A nonlinear autoregressive recurrent forward harmonic network for rainfall forecasting","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoregressive model; Nonlinear system; Computer science; Harmonic; Nonlinear autoregressive exogenous model; Meteorology; Econometrics; Mathematics; Physics; Acoustics","score_opus":0.02485359666661788,"score_gpt":0.2784485755854235,"score_spread":0.2535949789188056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414036714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021798665,0.00039778187,0.9744255,0.00012936916,0.00013750985,0.0000373527,0.00015457641,0.000581214,0.0023380364],"genre_scores_gemma":[0.6827412,0.00058955647,0.30609652,0.00010083515,0.00018447866,0.00014455794,0.0005895098,0.000103933766,0.00944938],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99988616,0.000037557926,0.000007650509,0.000029004472,0.000027005046,0.000012618274],"domain_scores_gemma":[0.9997887,0.000106651576,0.000012349525,0.00001550692,0.000064813976,0.0000119381975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048704376,0.00029112957,0.0004975617,0.00032017098,0.00027533004,0.00043880957,0.00073284406,0.0005225281,0.0023832652],"category_scores_gemma":[0.0008118389,0.00021950797,0.00033279014,0.00042742316,0.0001980412,0.0006081533,0.00042458985,0.0006089877,0.0005078333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001246518,0.000059185404,0.00050984166,0.000048988437,0.000055311313,0.000055743207,0.000030080557,0.81681406,0.0040443437,0.0058265408,0.0020485136,0.17038277],"study_design_scores_gemma":[0.000001761466,0.0000043530895,0.000027020662,5.6949574e-7,0.0000025277718,0.0000015686119,8.224682e-7,0.9993678,0.000111633584,0.00036403892,0.000116709714,0.0000013679758],"about_ca_topic_score_codex":0.010924887,"about_ca_topic_score_gemma":0.009521654,"teacher_disagreement_score":0.010924887,"about_ca_system_score_codex":0.00036668795,"about_ca_system_score_gemma":0.00048221866,"threshold_uncertainty_score":0.021722555},"labels":[],"label_agreement":null},{"id":"W4414110306","doi":"10.1007/s00382-025-07853-y","title":"Monthly rainfall forecasting using deep learning methods in big databases: a case study of northwestern Iran","year":2025,"lang":"en","type":"article","venue":"Climate Dynamics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Undersampling; Deep belief network; Random forest; Oversampling; Multilayer perceptron; Deep learning","score_opus":0.08868136152116039,"score_gpt":0.36287611176365603,"score_spread":0.2741947502424956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414110306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.989066,0.000222619,0.006487903,0.00081126485,0.000040305804,0.000023232898,0.0012299648,0.0002916228,0.0018271102],"genre_scores_gemma":[0.9949956,0.00012264113,0.0037488027,0.000022434639,0.00001577395,0.000008104416,0.00070818746,0.000009864894,0.0003685421],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997799,0.000050307088,0.000019433846,0.000044522287,0.000058122303,0.000047664416],"domain_scores_gemma":[0.99888796,0.00060820725,0.00009701811,0.00009761823,0.00023517973,0.000074004914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074755726,0.0004671238,0.00037527576,0.000781905,0.00041401133,0.0007005756,0.00093474524,0.0006268194,0.0007567645],"category_scores_gemma":[0.0017152679,0.0001905868,0.00033930584,0.0018317115,0.00034368722,0.0010006827,0.00042369164,0.0005415004,0.00011797126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047861083,0.0007730253,0.16589983,0.00016335421,0.00022907993,0.0024831556,0.0004414648,0.71419334,0.001958424,0.0027082704,0.010146716,0.10052471],"study_design_scores_gemma":[0.000032882137,0.000042700616,0.030535186,0.000009711704,0.000039974584,0.00008646154,0.0007465139,0.96434605,0.001228554,0.0015109642,0.0014044644,0.00001655426],"about_ca_topic_score_codex":0.07813253,"about_ca_topic_score_gemma":0.067251734,"teacher_disagreement_score":0.07813253,"about_ca_system_score_codex":0.0014913795,"about_ca_system_score_gemma":0.00094160886,"threshold_uncertainty_score":0.15535551},"labels":[],"label_agreement":null},{"id":"W4414129056","doi":"10.1007/s11802-025-5937-5","title":"Iceberg Draft Prediction Using Several Tree-Based Machine Learning Models","year":2025,"lang":"en","type":"article","venue":"Journal of Ocean University of China","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Iceberg; Subsea; Submarine pipeline; Arctic; Random forest","score_opus":0.01593375431721941,"score_gpt":0.1989967691052114,"score_spread":0.183063014787992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414129056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85098237,0.0013074864,0.13831702,0.0007013631,0.00040476912,0.000069730035,0.0011459235,0.0009499003,0.0061214915],"genre_scores_gemma":[0.9867423,0.00018373637,0.01120936,0.000039131297,0.00004964704,0.000030818817,0.00071680057,0.000019856649,0.0010084725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997453,0.00006440998,0.000023101002,0.00007736055,0.000042024076,0.000047666133],"domain_scores_gemma":[0.99824226,0.0010691924,0.00011235917,0.000060846167,0.00042261722,0.000092800205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010520979,0.00077580597,0.0011409101,0.0016119097,0.0005761948,0.0008616803,0.000799789,0.0009147261,0.0013362863],"category_scores_gemma":[0.0027483462,0.00027868222,0.0009055242,0.0013145349,0.00026734947,0.0013479545,0.0003578992,0.0009712443,0.00030445302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013464865,0.00012339286,0.0067554675,0.000025373962,0.000065691514,0.00003191827,0.000018214583,0.9553632,0.00027623738,0.00048998743,0.0011309574,0.035584852],"study_design_scores_gemma":[0.0000023403395,0.000005102756,0.0002961368,8.541926e-7,0.000004687395,7.465629e-7,0.0000017462944,0.9995235,0.000036544847,0.00010568595,0.000020956262,0.0000016777844],"about_ca_topic_score_codex":0.033302765,"about_ca_topic_score_gemma":0.023444524,"teacher_disagreement_score":0.033302765,"about_ca_system_score_codex":0.0008530461,"about_ca_system_score_gemma":0.0011492945,"threshold_uncertainty_score":0.06621784},"labels":[],"label_agreement":null},{"id":"W4414390982","doi":"10.3390/geosciences15090370","title":"Hydrothermal Modeling of Groundwater–Surface Water Interactions Under an Evolving Climate","year":2025,"lang":"en","type":"article","venue":"Geosciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada; Environment and Climate Change Canada","keywords":"Permafrost; Groundwater; Climate change; Hydrology (agriculture); Global warming; Groundwater flow; Streamflow; Aquifer; STREAMS","score_opus":0.02579205142214879,"score_gpt":0.27516689048196113,"score_spread":0.24937483905981234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414390982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9493365,0.00019926678,0.035329264,0.0006074434,0.00004192191,0.00004207218,0.0011557031,0.0003289036,0.012958978],"genre_scores_gemma":[0.994144,0.000076574026,0.0031748244,0.000021930942,0.000009889764,0.000018246648,0.00017821611,0.0000144250525,0.002361889],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999511,0.000011756659,0.000002573901,0.0000145488175,0.00000652071,0.0000134067695],"domain_scores_gemma":[0.9998379,0.000069404305,0.000021759286,0.000008986498,0.000036859434,0.000025065885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015751255,0.00030302771,0.00024275256,0.00027291803,0.0004187821,0.0007966692,0.00057250046,0.00073734147,0.0019059017],"category_scores_gemma":[0.00060302106,0.00023757592,0.00029205144,0.00032606345,0.00044779558,0.0004040015,0.00033977066,0.0003847464,0.00013321356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015556727,0.00001222574,0.0027850494,0.000008335752,0.000009360507,0.00002838409,0.00001946656,0.9932546,0.00095511373,0.000995632,0.00016369719,0.0017525563],"study_design_scores_gemma":[0.0000032191085,0.0000030029407,0.0004934957,6.829677e-7,0.0000017816864,0.0000015464863,0.00000803388,0.999126,0.00006758103,0.00014528698,0.00014741429,0.0000019740005],"about_ca_topic_score_codex":0.46347213,"about_ca_topic_score_gemma":0.32284662,"teacher_disagreement_score":0.46347213,"about_ca_system_score_codex":0.0020472296,"about_ca_system_score_gemma":0.0017771891,"threshold_uncertainty_score":0.92154884},"labels":[],"label_agreement":null},{"id":"W4414517423","doi":"10.1016/j.hydroa.2025.100208","title":"Fuzzy-based input method for uncertainty quantification in a deterministic model comparison with ChatGPT for peak flow prediction","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology X","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Fuzzy logic; Uncertainty analysis; Uncertainty quantification; Representation (politics); Watershed; Measurement uncertainty; Hydrological modelling; Sensitivity analysis","score_opus":0.032594420156276505,"score_gpt":0.3258446782406061,"score_spread":0.2932502580843296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414517423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13731071,0.00031771816,0.8510527,0.00036535814,0.00009635718,0.0001714337,0.0005761039,0.0012068697,0.00890274],"genre_scores_gemma":[0.87911654,0.00010969762,0.118608765,0.000053895845,0.000015091704,0.00014075704,0.00031883043,0.00008026062,0.0015561413],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999395,0.00017502796,0.000049199323,0.000105562365,0.00023895646,0.000036167043],"domain_scores_gemma":[0.99799144,0.0012301713,0.0001067663,0.00016571605,0.00047286777,0.000033102457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019199245,0.00076268485,0.00068834756,0.00088001235,0.00044580575,0.0012526995,0.0011871443,0.0008170884,0.002444082],"category_scores_gemma":[0.004718257,0.0003861278,0.0009458276,0.00067490345,0.0004508211,0.0010445004,0.0008801491,0.0012068955,0.00020775806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011086073,0.000036002915,0.0010986686,0.000071897724,0.00004194493,0.000028646546,0.000035173904,0.9630454,0.001658925,0.0044380445,0.00025995972,0.02917439],"study_design_scores_gemma":[0.0000047925587,0.000017482784,0.00021805277,0.0000048541824,0.0000071247555,0.000004830902,0.000005712712,0.9979321,0.0009513201,0.00068791304,0.00016024518,0.0000055817454],"about_ca_topic_score_codex":0.022873731,"about_ca_topic_score_gemma":0.014386445,"teacher_disagreement_score":0.022873731,"about_ca_system_score_codex":0.001412754,"about_ca_system_score_gemma":0.0013295588,"threshold_uncertainty_score":0.045481205},"labels":[],"label_agreement":null},{"id":"W4414542912","doi":"10.3390/su17198685","title":"Continuous Wavelet Analysis of Water Quality Time Series in a Rapidly Urbanizing Mixed-Land-Use Watershed in Ontario, Canada","year":2025,"lang":"en","type":"article","venue":"Sustainability","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ministry of the Environment, Conservation and Parks; Credit Valley Hospital; University of Guelph","funders":"","keywords":"Water quality; Wavelet; Watershed; Hydrology (agriculture); Continuous wavelet transform; Wavelet transform; Time series; Water resources","score_opus":0.008066657527293793,"score_gpt":0.22390245588322386,"score_spread":0.21583579835593006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414542912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984731,0.000035661185,0.00032065724,0.00006799902,0.0000016634478,0.0000067995293,0.00034048478,0.0000071982386,0.00074645143],"genre_scores_gemma":[0.9988882,0.000044997694,0.00029936378,0.000008183481,9.2016336e-7,0.000004020051,0.00029316844,0.0000022795252,0.00045885352],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985564,0.0000092451355,0.0000062539966,0.000032031996,0.000051217594,0.00004566727],"domain_scores_gemma":[0.9996877,0.000039139963,0.000036394675,0.000011814314,0.00017861443,0.000046397126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017390508,0.00014162672,0.00017545038,0.00060858234,0.0008460468,0.00069454405,0.00039291242,0.00018936247,0.00046557284],"category_scores_gemma":[0.0007530682,0.00009661772,0.00012778635,0.0019978676,0.0004195093,0.00019771575,0.0003001484,0.00021098864,0.00006284076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020211673,0.0001025038,0.9350256,0.000066986395,0.000068286296,0.00084627076,0.0028792638,0.009888301,0.009173397,0.0007667266,0.00211745,0.038863134],"study_design_scores_gemma":[0.000004391682,0.0000073981864,0.98313427,0.00000610608,0.000009899206,0.000022054428,0.0017132194,0.014100176,0.00024280969,0.000065538145,0.0006847263,0.000009427574],"about_ca_topic_score_codex":0.98342115,"about_ca_topic_score_gemma":0.989181,"teacher_disagreement_score":0.016578853,"about_ca_system_score_codex":0.0085354,"about_ca_system_score_gemma":0.0070557627,"threshold_uncertainty_score":0.061928928},"labels":[],"label_agreement":null},{"id":"W4414956415","doi":"10.1109/cmss66566.2025.11182335","title":"Comparative Machine Learning Framework for Rainfall Forecasting and Agricultural Loss Estimation","year":2025,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Warning system; Estimation; Climate change; Random forest; Agriculture; Livelihood; Resilience (materials science); Food security","score_opus":0.03353127783090611,"score_gpt":0.28824622763457114,"score_spread":0.25471494980366505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414956415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008942147,0.0006823762,0.9879511,0.00023426951,0.00004609012,0.0000398002,0.000183339,0.00052454445,0.0013962688],"genre_scores_gemma":[0.61712706,0.0010484002,0.37461212,0.00024101073,0.000320282,0.00059949316,0.0011336947,0.00016626269,0.004751639],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986436,0.0007465173,0.00006989335,0.0002712754,0.0001842481,0.00008447222],"domain_scores_gemma":[0.99670225,0.0024818063,0.00023708351,0.00013415865,0.00037902387,0.00006576198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045065354,0.001093869,0.0013456009,0.0021353848,0.00042439258,0.0013153465,0.0026567022,0.001621042,0.003741261],"category_scores_gemma":[0.009658843,0.00059913314,0.0010794943,0.0021416864,0.00070886506,0.0012203691,0.0011800117,0.0014259443,0.00064660836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056958717,0.00003805804,0.0009846499,0.000063374224,0.00008839338,0.00007245195,0.000032472304,0.94446343,0.00025150378,0.0181633,0.00081213284,0.03497329],"study_design_scores_gemma":[0.000002096601,0.0000121305,0.0000939925,0.000003211646,0.000003499002,0.000006933497,0.0000023652822,0.9967024,0.00003353359,0.002887784,0.00024958185,0.0000024497353],"about_ca_topic_score_codex":0.0118633965,"about_ca_topic_score_gemma":0.006061974,"teacher_disagreement_score":0.0118633965,"about_ca_system_score_codex":0.0014580473,"about_ca_system_score_gemma":0.0013991179,"threshold_uncertainty_score":0.023833096},"labels":[],"label_agreement":null},{"id":"W4414997386","doi":"10.1007/s12145-025-02021-6","title":"Scientific machine learning in hydrology: a unified perspective","year":2025,"lang":"en","type":"article","venue":"Earth Science Informatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Novelty; CLARITY; Perspective (graphical); Consistency (knowledge bases); Conceptual framework","score_opus":0.011658618481729608,"score_gpt":0.2516735450703519,"score_spread":0.24001492658862228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414997386","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060694395,0.15473443,0.7005197,0.08398393,0.0037366778,0.000049554703,0.00053845864,0.00031600602,0.050051846],"genre_scores_gemma":[0.44412795,0.22371002,0.26698342,0.009992053,0.03784454,0.00050568685,0.0006096427,0.00036034462,0.01586633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99701834,0.0013700367,0.0003034333,0.0003858717,0.0007988725,0.00012348228],"domain_scores_gemma":[0.9889408,0.0081317555,0.000581037,0.0008737559,0.0010865008,0.0003861092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006819235,0.0015456489,0.0030317612,0.0076458706,0.0011694445,0.011159574,0.0030112881,0.004962118,0.0035600113],"category_scores_gemma":[0.010193739,0.0009849609,0.0014967682,0.005741459,0.009555423,0.01883166,0.0037175296,0.007759751,0.0010074971],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011385954,0.000031604046,0.0002548337,0.0002861281,0.00005359811,0.0000453956,0.00012287557,0.0052343584,0.00011806084,0.9761544,0.0028323643,0.014855015],"study_design_scores_gemma":[0.000007952393,0.000023495792,0.00018182522,0.00018027195,0.000028137574,0.000037698872,0.000078405996,0.02236663,0.00011026238,0.962201,0.014766535,0.000017700679],"about_ca_topic_score_codex":0.0029185573,"about_ca_topic_score_gemma":0.0023673454,"teacher_disagreement_score":0.011159574,"about_ca_system_score_codex":0.003072675,"about_ca_system_score_gemma":0.0023153168,"threshold_uncertainty_score":0.03606397},"labels":[],"label_agreement":null},{"id":"W4415532040","doi":"10.1016/j.jhydrol.2025.134447","title":"Quantifying uncertainty in flowrate modelling using spatially defined fuzzy entropy based on hydrological processes in a catchment","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fuzzy logic; Watershed; Entropy (arrow of time); Monte Carlo method; Surface runoff; Uncertainty analysis; Hydrology (agriculture); Categorical variable; Probability distribution","score_opus":0.04888407733027448,"score_gpt":0.2916073816417832,"score_spread":0.2427233043115087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415532040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08567538,0.00007655564,0.91253984,0.00009006791,0.000009776718,0.000024072628,0.000049502665,0.00008137765,0.0014535184],"genre_scores_gemma":[0.94610447,0.00009955148,0.053303987,0.000015022085,0.00001478087,0.000031219566,0.000045693054,0.000013933934,0.0003714396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994536,0.00018964935,0.000040763618,0.000076234806,0.0001992258,0.000040522682],"domain_scores_gemma":[0.99907255,0.00061367755,0.000126841,0.000066027285,0.000093066694,0.000027883234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013278946,0.0005112472,0.0004248255,0.0012831258,0.00035931318,0.0015220939,0.00057506893,0.0005122613,0.0005103316],"category_scores_gemma":[0.0030326867,0.00025822644,0.0007151254,0.0008218795,0.00091061776,0.0017371658,0.0009935721,0.00049144233,0.00004136994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012976832,0.00000838286,0.0013061386,0.000014246567,0.000020424362,0.000045384222,0.00005239098,0.97501105,0.0016523827,0.013425145,0.00004232252,0.0084091965],"study_design_scores_gemma":[9.712711e-7,0.0000046711534,0.000410525,0.0000035973158,0.000004478606,0.000009469154,0.000009102559,0.9931757,0.00060010527,0.0056887963,0.0000862588,0.0000063023926],"about_ca_topic_score_codex":0.005116044,"about_ca_topic_score_gemma":0.004404623,"teacher_disagreement_score":0.005116044,"about_ca_system_score_codex":0.0012026386,"about_ca_system_score_gemma":0.00074778177,"threshold_uncertainty_score":0.010172546},"labels":[],"label_agreement":null},{"id":"W4415547721","doi":"10.1016/j.ese.2025.100632","title":"A hierarchical transformer and graph neural network model for high-accuracy watershed nitrate prediction","year":2025,"lang":"en","type":"article","venue":"Environmental Science and Ecotechnology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Science and Technology of the People's Republic of China; Ministry of Natural Resources; Ministry of Science and Technology","keywords":"Interpretability; Artificial neural network; Watershed; Water quality; Graph; Transformer; Multivariate statistics; Fuzzy logic","score_opus":0.00856923500480631,"score_gpt":0.20924749499643125,"score_spread":0.20067825999162495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415547721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13556261,0.00061719294,0.85552245,0.0007227635,0.00009849969,0.000049622933,0.00065671816,0.0012595772,0.0055105183],"genre_scores_gemma":[0.95417124,0.0002441704,0.041067164,0.00011194544,0.000023907089,0.0000646153,0.0004437227,0.000055595086,0.0038177094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998832,0.000026209527,0.0000067052283,0.000038467835,0.00002591846,0.000019648965],"domain_scores_gemma":[0.9997106,0.00014962615,0.000033451885,0.0000139933,0.00007171866,0.000020457117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036819262,0.00054200203,0.0005543549,0.00041556073,0.00023356348,0.00054714957,0.0010900815,0.0007611695,0.0016466876],"category_scores_gemma":[0.0012363401,0.00031799136,0.00057097845,0.0005397911,0.0005045415,0.0008504247,0.0006776258,0.0009234639,0.00022971426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000227211,0.000011817075,0.00031577016,0.000010845343,0.000009355157,0.000019926041,0.0000080486225,0.99069136,0.00049880205,0.0020104132,0.00029146287,0.0061093885],"study_design_scores_gemma":[9.267743e-7,0.0000018225206,0.000022502434,3.3538473e-7,9.534033e-7,7.926667e-7,4.6127454e-7,0.99944335,0.00003207267,0.00047352593,0.000022665581,6.351569e-7],"about_ca_topic_score_codex":0.03216531,"about_ca_topic_score_gemma":0.026442522,"teacher_disagreement_score":0.03216531,"about_ca_system_score_codex":0.0011493405,"about_ca_system_score_gemma":0.0011048223,"threshold_uncertainty_score":0.0639562},"labels":[],"label_agreement":null},{"id":"W4415624701","doi":"10.1109/rtsi64020.2025.11212227","title":"A Framework for Short-Term Forecasting of Extreme Weather Events","year":2025,"lang":"","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Warning system; Precipitation; Control chart; Extreme learning machine; Extreme weather; Chart; Process (computing); Quality (philosophy); Statistical process control","score_opus":0.09496800199499562,"score_gpt":0.31154181041889073,"score_spread":0.21657380842389512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415624701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029548635,0.00016874312,0.99519354,0.00012611774,0.000037500024,0.000021537062,0.00018488003,0.0006328552,0.0006800134],"genre_scores_gemma":[0.41379777,0.0008037777,0.5811247,0.00014629938,0.00021349327,0.0002835214,0.0015002302,0.00013535385,0.0019948499],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938047,0.00014931877,0.000050815168,0.00015906485,0.00020030301,0.000060017996],"domain_scores_gemma":[0.9985537,0.00063854264,0.00022957959,0.00012325624,0.00038055543,0.000074292446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018052832,0.0008161767,0.0007687697,0.0015672082,0.00047827332,0.0015672724,0.0016004994,0.0008213886,0.0012997048],"category_scores_gemma":[0.0042944853,0.00032090957,0.00094384764,0.0012801809,0.0006557988,0.0015657926,0.0007639891,0.0012504476,0.00045092363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033499575,0.00004088846,0.001293655,0.00004363147,0.000050224353,0.000058298785,0.00004477453,0.9069193,0.0009883766,0.0406187,0.0018976522,0.048011],"study_design_scores_gemma":[0.0000024480528,0.00000902253,0.00014865476,0.0000046781847,0.0000036712386,0.000007650329,0.0000034520738,0.98958886,0.00013061549,0.009197323,0.00089771446,0.000005960736],"about_ca_topic_score_codex":0.01869558,"about_ca_topic_score_gemma":0.010312782,"teacher_disagreement_score":0.01869558,"about_ca_system_score_codex":0.001049613,"about_ca_system_score_gemma":0.0018967711,"threshold_uncertainty_score":0.03717357},"labels":[],"label_agreement":null},{"id":"W4415700244","doi":"10.1080/02626667.2025.2581264","title":"Enhancing long-term water quality forecasting with a hybrid deep-learning approach integrating MODWT, CNN, and GRU","year":2025,"lang":"en","type":"article","venue":"Hydrological Sciences Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue; University of Waterloo","funders":"","keywords":"Quality (philosophy); Water quality; Automation; Key (lock); Work (physics)","score_opus":0.03420564455226331,"score_gpt":0.2756350293391229,"score_spread":0.24142938478685955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415700244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13637629,0.00073658733,0.8556665,0.0005408267,0.00021238766,0.000048163743,0.0002903636,0.0021617848,0.0039669643],"genre_scores_gemma":[0.9252136,0.00034481374,0.072044514,0.00015119986,0.00006581539,0.000042971835,0.00030473006,0.000051452236,0.0017808801],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985516,0.000018353483,0.000010841895,0.000045605146,0.000043855824,0.000026130328],"domain_scores_gemma":[0.9997445,0.0000709173,0.000039257964,0.000029827344,0.00009740533,0.000018248904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005280932,0.00082864944,0.0005814426,0.000587192,0.0002106849,0.0005698286,0.000847489,0.0005754755,0.0006482626],"category_scores_gemma":[0.0010903203,0.00031852114,0.0005656915,0.0007593687,0.00026020902,0.0012309367,0.0006333753,0.0007448657,0.000257154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007710508,0.00012484431,0.0043596397,0.00006784244,0.00009166678,0.000093363014,0.000040680105,0.79356575,0.010975321,0.0020759865,0.0016158012,0.18691202],"study_design_scores_gemma":[9.99018e-7,0.0000076033,0.00020445415,0.0000016176044,0.000004250706,0.00000378782,0.0000022043898,0.9987525,0.0006036802,0.00029710055,0.00011937152,0.000002462343],"about_ca_topic_score_codex":0.014186877,"about_ca_topic_score_gemma":0.015569827,"teacher_disagreement_score":0.014186877,"about_ca_system_score_codex":0.000571301,"about_ca_system_score_gemma":0.0007277716,"threshold_uncertainty_score":0.028208613},"labels":[],"label_agreement":null},{"id":"W4415813562","doi":"10.3390/app152111656","title":"Advancing Machine Learning-Based Streamflow Prediction Through Event Greedy Selection, Asymmetric Loss Function, and Rainfall Forecasting Uncertainty","year":2025,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Streamflow; Flood forecasting; Probabilistic logic; Reliability (semiconductor); Storm; Flood myth","score_opus":0.012236273567501023,"score_gpt":0.23436367478994843,"score_spread":0.22212740122244742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415813562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1455656,0.00013610368,0.8520549,0.00035137625,0.000029041834,0.00003208188,0.00008602949,0.00048219963,0.0012627445],"genre_scores_gemma":[0.93035984,0.00009447277,0.06863193,0.00007990061,0.000048842543,0.000047398633,0.00011898517,0.000039580234,0.0005791214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948967,0.00017813018,0.000033466382,0.0000981366,0.00014444515,0.00005610522],"domain_scores_gemma":[0.99724543,0.0019052319,0.00029837334,0.00017651216,0.00028494722,0.000089486646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021419208,0.00066184124,0.0007571183,0.0005453442,0.000333186,0.0007581536,0.0009675292,0.00057584094,0.0005429692],"category_scores_gemma":[0.005772319,0.00029225866,0.00036776374,0.0005363017,0.0005616227,0.0014855143,0.0009536049,0.001071622,0.00011763607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037107213,0.000032007763,0.0010837638,0.000010043298,0.000012611832,0.00002536547,0.000016477597,0.9764747,0.0009811096,0.0022751223,0.00017576876,0.018875958],"study_design_scores_gemma":[0.0000013207025,0.000004902729,0.000051775216,5.556387e-7,9.723669e-7,0.0000015127437,7.140995e-7,0.9989297,0.00028267218,0.00069717667,0.000027711481,0.0000010302251],"about_ca_topic_score_codex":0.0036158997,"about_ca_topic_score_gemma":0.0031606907,"teacher_disagreement_score":0.0036158997,"about_ca_system_score_codex":0.0007652704,"about_ca_system_score_gemma":0.00096107775,"threshold_uncertainty_score":0.011327684},"labels":[],"label_agreement":null},{"id":"W4415900844","doi":"10.1016/j.acags.2025.100303","title":"A systematic review of machine learning models for groundwater level prediction","year":2025,"lang":"en","type":"review","venue":"Applied Computing and Geosciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Feature selection; Hyperparameter optimization; Particle swarm optimization; Hyperparameter; Feature (linguistics); Support vector machine; Artificial neural network; Random forest; Cluster analysis","score_opus":0.055125676089326614,"score_gpt":0.286898949937134,"score_spread":0.23177327384780738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415900844","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049866486,0.9942502,0.0026339854,0.001028237,0.00023602054,0.00008294445,0.0007128685,0.000041357034,0.0005157341],"genre_scores_gemma":[0.0064084507,0.98764986,0.004151937,0.000539598,0.00022816673,0.00021798373,0.0006119437,0.000015890999,0.00017619994],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9948807,0.0020553186,0.0013758553,0.0004970784,0.0010957916,0.00009527754],"domain_scores_gemma":[0.9641115,0.030466435,0.0024145588,0.00054614997,0.0022940375,0.000167302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008437577,0.0018449102,0.0036044898,0.0092236865,0.00045465384,0.0024092726,0.0023085384,0.0016776898,0.005294117],"category_scores_gemma":[0.040446814,0.00071540725,0.0049786447,0.009258136,0.0005182751,0.002453413,0.0011069936,0.0014503043,0.00097402476],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014387976,0.00006897616,0.0019803054,0.4330324,0.0040336805,0.00018672488,0.0002096591,0.0040382743,0.00032234503,0.003428705,0.017455745,0.5350993],"study_design_scores_gemma":[0.00016046494,0.0005399591,0.009505039,0.57143676,0.02507365,0.0007281802,0.00039888846,0.0070270784,0.0007653642,0.009737931,0.37443855,0.00018822365],"about_ca_topic_score_codex":0.0062128133,"about_ca_topic_score_gemma":0.013635483,"teacher_disagreement_score":0.0092236865,"about_ca_system_score_codex":0.0016633106,"about_ca_system_score_gemma":0.009327841,"threshold_uncertainty_score":0.04462266},"labels":[],"label_agreement":null},{"id":"W4415989033","doi":"10.2139/ssrn.5714989","title":"An Explainable Optimization-Driven Framework for Accurate and Interpretable Groundwater-Level Prediction Toward Sustainable Management","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Ottawa","funders":"","keywords":"Groundwater recharge; Mean squared error; Groundwater; Baseline (sea); Bayesian probability; Precipitation; Hydrogeology; Hyperparameter; Sustainable management","score_opus":0.02005282082196004,"score_gpt":0.27440417508053716,"score_spread":0.25435135425857713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415989033","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005703692,0.00008458818,0.9925418,0.00026056482,0.00002426848,0.000014381724,0.00011653981,0.00025410418,0.001000031],"genre_scores_gemma":[0.5723839,0.00032389362,0.42303413,0.00021861006,0.00015541639,0.00018987231,0.0005235053,0.0002372415,0.002933447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972576,0.00010943197,0.000015457059,0.000060283197,0.000064031934,0.000024985846],"domain_scores_gemma":[0.9991248,0.0005425863,0.00009137721,0.000073752795,0.00013202854,0.000035457106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000865113,0.00065655896,0.0005847243,0.00051697326,0.00030962922,0.0011424795,0.0013330869,0.0010535115,0.0025640444],"category_scores_gemma":[0.0032204755,0.000482121,0.00074883783,0.0005922734,0.0007434403,0.0009940597,0.001161041,0.0014585569,0.00030260015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021860082,0.00002178784,0.00030000697,0.000029860359,0.000029566307,0.000044024695,0.000033065047,0.94985956,0.0011777098,0.035030745,0.0006015486,0.012850292],"study_design_scores_gemma":[0.0000015997812,0.0000030003623,0.000025831749,0.0000012394189,0.0000015834821,0.0000016202993,0.0000013025493,0.9906866,0.000084289524,0.009028035,0.00016313916,0.0000017037364],"about_ca_topic_score_codex":0.0083186105,"about_ca_topic_score_gemma":0.007801381,"teacher_disagreement_score":0.0083186105,"about_ca_system_score_codex":0.00071647135,"about_ca_system_score_gemma":0.0012525974,"threshold_uncertainty_score":0.016540349},"labels":[],"label_agreement":null},{"id":"W4416067819","doi":"10.5194/egusphere-2025-4653","title":"An ensemble groundwater prediction (EGP) system to forecast groundwater levels in alluvial aquifers in Switzerland","year":2025,"lang":"","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Groundwater; Hydrogeology; Aquifer; Precipitation; Irrigation; Hydrology (agriculture); Quantitative precipitation forecast; Warning system; Water resources","score_opus":0.03139294534506256,"score_gpt":0.26671072299738013,"score_spread":0.23531777765231757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416067819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9786133,0.0002361335,0.016365187,0.00020808364,0.00006631625,0.000031344585,0.0017651486,0.0016387553,0.0010756869],"genre_scores_gemma":[0.99546295,0.000035272347,0.0031137406,0.000010363131,0.000010160645,0.000011210721,0.001196816,0.000013265737,0.00014616748],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987125,0.00003362103,0.000009486539,0.00003877363,0.000026235473,0.00002058641],"domain_scores_gemma":[0.9996458,0.00010404191,0.000039151386,0.00003763702,0.00012393507,0.000049320297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040523137,0.0009908803,0.00044381074,0.00057797384,0.0002683994,0.00044734124,0.00046494373,0.00053129974,0.0006705045],"category_scores_gemma":[0.0009789263,0.00021164224,0.00038776084,0.0004955619,0.00013462384,0.0005962873,0.00048848276,0.00038534234,0.00014192954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023767757,0.00012625357,0.030699976,0.000051234492,0.00009534882,0.00016112758,0.00006067113,0.93285346,0.0038445024,0.00016579915,0.0021073027,0.029596793],"study_design_scores_gemma":[0.000010029849,0.000030291973,0.0042464584,0.000002222707,0.000008817661,0.000004547999,0.000011257125,0.99506277,0.0004286017,0.00007098226,0.00011824213,0.0000058753303],"about_ca_topic_score_codex":0.058151398,"about_ca_topic_score_gemma":0.046624046,"teacher_disagreement_score":0.058151398,"about_ca_system_score_codex":0.00060309115,"about_ca_system_score_gemma":0.0005890437,"threshold_uncertainty_score":0.11562586},"labels":[],"label_agreement":null},{"id":"W4416161504","doi":"10.1061/jidedh.ireng-10634","title":"Discussion of “Comparison of the Self-Organizing Map and the Adaptive Neuro-Fuzzy Inference System in Predicting the Paddy Crop Water Stress Index”","year":2025,"lang":"en","type":"article","venue":"Journal of Irrigation and Drainage Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval","funders":"","keywords":"Water stress; Crop; Inference; Stress (linguistics); Crop production","score_opus":0.0064929843929115135,"score_gpt":0.21245646083156872,"score_spread":0.2059634764386572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416161504","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066920735,0.010316899,0.6761383,0.12916568,0.017010735,0.00046698912,0.0010389092,0.0008083101,0.09813356],"genre_scores_gemma":[0.75772256,0.0039720465,0.17883717,0.02400454,0.0069205184,0.0005173115,0.00037317164,0.00013326538,0.027519338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985061,0.0006628105,0.00010754106,0.00017548357,0.00048829557,0.00005976042],"domain_scores_gemma":[0.9936801,0.004484147,0.00015079517,0.00016354257,0.0014546659,0.000066794564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005981314,0.0003764376,0.00043760505,0.0009353947,0.0007579308,0.002379217,0.001931154,0.0027499238,0.004541285],"category_scores_gemma":[0.023032773,0.00018520138,0.0008406907,0.000715644,0.0013990406,0.0017241226,0.0005408615,0.0014338543,0.0007005789],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069300807,0.00020310399,0.0073258015,0.00093859626,0.0007690766,0.0013541505,0.000961178,0.14621669,0.009005439,0.634025,0.04761986,0.1508882],"study_design_scores_gemma":[0.00020555875,0.00076273124,0.01251111,0.00058319094,0.00036637715,0.00065172976,0.0012029415,0.5167971,0.023797836,0.31427377,0.1285798,0.00026777334],"about_ca_topic_score_codex":0.007615871,"about_ca_topic_score_gemma":0.0058368444,"teacher_disagreement_score":0.007615871,"about_ca_system_score_codex":0.0008284982,"about_ca_system_score_gemma":0.0008731193,"threshold_uncertainty_score":0.031632602},"labels":[],"label_agreement":null},{"id":"W4416339228","doi":"10.18280/isi.300913","title":"Comparative Study of One-Class Support Vector Machine, Bayesian Network, Ridge Classifier for Meteorological Data Analysis","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Support vector machine; Ridge; Pattern recognition (psychology); Classifier (UML)","score_opus":0.06470922087658759,"score_gpt":0.3068837158644758,"score_spread":0.24217449498788823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416339228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66532665,0.007747657,0.31826365,0.00071944133,0.00036570232,0.00017253851,0.00043565573,0.0015844329,0.0053842594],"genre_scores_gemma":[0.9309277,0.001695117,0.06411279,0.00008523645,0.000112443464,0.00007097918,0.0005798494,0.0000921189,0.0023237893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706,0.0010470719,0.00027067453,0.00047313113,0.0009584087,0.00019079201],"domain_scores_gemma":[0.98906726,0.0069846874,0.00038672372,0.0004739926,0.0028873258,0.00020006036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056660515,0.0006847643,0.0015544764,0.002033187,0.0005817178,0.0016457567,0.00078180217,0.0010989001,0.0011468984],"category_scores_gemma":[0.013784393,0.00020622594,0.00081034517,0.0011985353,0.00033794416,0.0023291546,0.0005727379,0.00079065893,0.00043927436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029107407,0.0009431218,0.021893302,0.00054030603,0.0004965399,0.00014129339,0.00024689687,0.14883034,0.0066901753,0.0034504922,0.0030261127,0.81083065],"study_design_scores_gemma":[0.000020770181,0.00030055302,0.004733567,0.0000172159,0.00009575446,0.000049834056,0.000104128296,0.9911548,0.0021509987,0.00086262263,0.00049110025,0.000018753935],"about_ca_topic_score_codex":0.0066165715,"about_ca_topic_score_gemma":0.005627831,"teacher_disagreement_score":0.0066165715,"about_ca_system_score_codex":0.0007132394,"about_ca_system_score_gemma":0.0014262486,"threshold_uncertainty_score":0.029965281},"labels":[],"label_agreement":null},{"id":"W4416426723","doi":"10.1016/j.gsd.2025.101550","title":"Groundwater level forecasting in response to climate change scenarios in southwestern Saskatchewan using wavelet decomposition and artificial neural networks","year":2025,"lang":"en","type":"article","venue":"Groundwater for Sustainable Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Global Water Futures; Canada First Research Excellence Fund","keywords":"Groundwater; Climate change; Artificial neural network; Decomposition; Hydrology (agriculture); Wavelet","score_opus":0.04673065023997231,"score_gpt":0.2746606290093338,"score_spread":0.2279299787693615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416426723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895615,0.00007090783,0.007981309,0.00015720326,0.000011461078,0.000022383043,0.00079959095,0.00008550376,0.0013101758],"genre_scores_gemma":[0.9940718,0.00008456078,0.004352822,0.00002546995,0.0000015800397,0.000015524158,0.0006837636,0.000006219729,0.00075830333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999162,0.000016594026,0.000009226002,0.000021308735,0.000019152103,0.000017569677],"domain_scores_gemma":[0.99976796,0.000058511134,0.00003077967,0.000016836942,0.00010784613,0.000018095592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022846312,0.00035308264,0.00014529939,0.00050843414,0.00023566034,0.00040341058,0.00035243644,0.00029304103,0.00053525047],"category_scores_gemma":[0.000630558,0.00017577273,0.00026641614,0.0009734746,0.00016983693,0.0002924468,0.000295877,0.00027833806,0.00009269819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017288762,0.00009661386,0.1381953,0.00005001389,0.00013952068,0.00033370662,0.00011602268,0.7891338,0.009432501,0.0007844433,0.0016346404,0.059910584],"study_design_scores_gemma":[0.000008277107,0.000011643806,0.03176851,0.00000598455,0.000015298489,0.0000068415034,0.000099637364,0.96648705,0.001091533,0.00020280152,0.00029043297,0.000012038997],"about_ca_topic_score_codex":0.57050556,"about_ca_topic_score_gemma":0.7352364,"teacher_disagreement_score":0.42949444,"about_ca_system_score_codex":0.00290184,"about_ca_system_score_gemma":0.002627411,"threshold_uncertainty_score":0.86404765},"labels":[],"label_agreement":null},{"id":"W4416443596","doi":"10.1016/j.ejrh.2025.102961","title":"Improving estuarine discharge forecasting with a KAN-augmented LSTM model: A case study of the Yangtze River Estuary","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology Regional Studies","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Natural Science Foundation of Jiangxi Province; Ontario Ministry of Natural Resources and Forestry","keywords":"Estuary; Yangtze river; Artificial neural network; Adaptability; Limiting; Nonlinear system; Streamflow; Deep learning; Stream flow","score_opus":0.04503780182809926,"score_gpt":0.27992526197352996,"score_spread":0.23488746014543072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416443596","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95906687,0.00065639644,0.03474429,0.0009445702,0.00012398089,0.00002786118,0.0009937796,0.0010975215,0.0023448123],"genre_scores_gemma":[0.9919344,0.00018568231,0.0062489044,0.000046225756,0.000020102689,0.0000126114855,0.0005366541,0.000021561073,0.0009939194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987566,0.000029189197,0.000011590857,0.000039346967,0.000023983053,0.000020240683],"domain_scores_gemma":[0.99971884,0.000116579715,0.00002651938,0.000019614079,0.000098629316,0.000019697945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051741744,0.0008585124,0.00036725172,0.00046265338,0.00037400736,0.0005253627,0.0006108467,0.000599439,0.00066001236],"category_scores_gemma":[0.0012362001,0.0002098937,0.0004867959,0.0008916135,0.00026299196,0.0008533209,0.0005292703,0.0006516824,0.0001567867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013597329,0.00009144115,0.025051842,0.000121369834,0.000086114924,0.0007315344,0.00020303209,0.89712906,0.003984215,0.00086807343,0.00362524,0.06797212],"study_design_scores_gemma":[0.0000067456504,0.00001916251,0.0042635654,0.0000050147396,0.000014172302,0.000014324626,0.000062418396,0.9940268,0.0008351291,0.00034832937,0.00039456945,0.00000974943],"about_ca_topic_score_codex":0.06763286,"about_ca_topic_score_gemma":0.07094312,"teacher_disagreement_score":0.06763286,"about_ca_system_score_codex":0.0010164948,"about_ca_system_score_gemma":0.00096784916,"threshold_uncertainty_score":0.13447839},"labels":[],"label_agreement":null},{"id":"W4416563932","doi":"10.1016/j.jwpe.2025.109161","title":"Water quality estimation and algae bloom prediction using machine learning – A case study","year":2025,"lang":"en","type":"article","venue":"Journal of Water Process Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Eutrophication; Water quality; Random forest; Support vector machine; Algal bloom; Surface runoff; Nutrient; Algae; Artificial neural network","score_opus":0.016776385666253005,"score_gpt":0.2739802217347997,"score_spread":0.2572038360685467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416563932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97522855,0.00022852185,0.019202087,0.0006948177,0.000027265805,0.000076888806,0.00028863968,0.00018320704,0.004069876],"genre_scores_gemma":[0.99010426,0.00010609145,0.007971616,0.000023301978,0.000010757461,0.00001594447,0.00013740284,0.000013930937,0.0016167816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953306,0.00017550714,0.000026751602,0.00007410866,0.000119602635,0.00007094938],"domain_scores_gemma":[0.99774015,0.0016300874,0.00011453073,0.0001418809,0.0002734792,0.000099942175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011461546,0.00045441615,0.0004276516,0.0005835763,0.0006633413,0.0008801038,0.0008477883,0.0017988536,0.0013627373],"category_scores_gemma":[0.0029746988,0.00028767655,0.0006927866,0.0009854833,0.00053947914,0.00079996814,0.00049256603,0.0006586626,0.00020518739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008803303,0.0019040031,0.07043204,0.00019142534,0.00016607739,0.00803246,0.0004300766,0.8229296,0.0067073624,0.0030194088,0.00275061,0.08255654],"study_design_scores_gemma":[0.000068340865,0.0002458504,0.01254636,0.000009232028,0.00004200276,0.00037250112,0.00033545407,0.97948885,0.0043517537,0.0012860403,0.0012282898,0.000025368898],"about_ca_topic_score_codex":0.03343628,"about_ca_topic_score_gemma":0.028000595,"teacher_disagreement_score":0.03343628,"about_ca_system_score_codex":0.0011577168,"about_ca_system_score_gemma":0.0006728272,"threshold_uncertainty_score":0.06648332},"labels":[],"label_agreement":null},{"id":"W4416722535","doi":"10.21203/rs.3.rs-7109251/v1","title":"Machine Learning-Driven Rainfall Forecasting Model for Sustainable and Adaptive Infrastructure Planning","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of Manitoba","funders":"","keywords":"Mean squared error; Resilience (materials science); Green infrastructure; Artificial neural network; Psychological resilience; Multivariate statistics; Percentile; Covariance; Evapotranspiration","score_opus":0.08959707112480363,"score_gpt":0.36088045862458934,"score_spread":0.2712833874997857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416722535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10368105,0.00043004463,0.88597435,0.0016875549,0.00023776581,0.000057585665,0.0009663758,0.00094927684,0.0060160407],"genre_scores_gemma":[0.94875306,0.0002089205,0.04184328,0.00013965301,0.00011406346,0.000108496664,0.0006663334,0.00006444014,0.0081017325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984956,0.000040622177,0.000008251314,0.00004739183,0.00002739689,0.000026724369],"domain_scores_gemma":[0.999348,0.00039022788,0.00005080048,0.00003139239,0.00014776997,0.000031942167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006432728,0.00034114197,0.0007503987,0.0004082184,0.0003189417,0.0006579207,0.0009268228,0.0010621768,0.0037144735],"category_scores_gemma":[0.0023487392,0.00038132718,0.0004891197,0.0007998366,0.00030247294,0.000862692,0.00040974907,0.0013210443,0.00041108538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014855581,0.000013354762,0.00022791854,0.000007846743,0.000008753741,0.000008426791,0.0000047869157,0.9909594,0.00016260806,0.0014304414,0.0004709548,0.0066906465],"study_design_scores_gemma":[7.693228e-7,0.0000010246565,0.000021859827,3.7055287e-7,5.8434296e-7,5.367503e-7,4.1432014e-7,0.99949265,0.000020569336,0.00042698707,0.000033702272,4.847683e-7],"about_ca_topic_score_codex":0.024320213,"about_ca_topic_score_gemma":0.016570177,"teacher_disagreement_score":0.024320213,"about_ca_system_score_codex":0.0010926281,"about_ca_system_score_gemma":0.0013544287,"threshold_uncertainty_score":0.048357308},"labels":[],"label_agreement":null},{"id":"W4416860169","doi":"10.1016/j.ejrh.2025.103007","title":"Enhancing combined sewer flow prediction in data-limited urban areas using a semi-supervised learning framework","year":2025,"lang":"en","type":"article","venue":"Journal of Hydrology Regional Studies","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Wilfrid Laurier University; McGill University; Institut National de la Recherche Scientifique; United Nations University Institute for Water, Environment, and Health","funders":"Institut national de la recherche scientifique","keywords":"Benchmark (surveying); Artificial neural network; Combined sewer; Scalability; Key (lock); Cluster analysis; Predictive modelling; Flooding (psychology)","score_opus":0.05839427306579566,"score_gpt":0.3097245248225957,"score_spread":0.25133025175680007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416860169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40797776,0.00030402406,0.58672386,0.0003805848,0.00004324596,0.00009151905,0.0005726507,0.0018278797,0.0020786182],"genre_scores_gemma":[0.9651181,0.000044331264,0.033394966,0.00004390656,0.000022823262,0.00004753556,0.00052646815,0.000024351322,0.0007775294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970263,0.00009329847,0.00001878009,0.00009873566,0.00005053728,0.00003591807],"domain_scores_gemma":[0.9992054,0.000355203,0.00008876426,0.0000803335,0.00022587422,0.0000444548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086248736,0.00062349526,0.0005525187,0.00048652638,0.00022869522,0.0006587687,0.0010266961,0.000622969,0.0005759817],"category_scores_gemma":[0.0016508263,0.00024959826,0.00065372617,0.00032059583,0.00031654103,0.0007245516,0.00066596473,0.00063608575,0.00020178745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009442156,0.00020391615,0.0070643523,0.000044888897,0.00009363057,0.00006282673,0.00006981829,0.9269841,0.00192785,0.00051867217,0.00070424,0.062231388],"study_design_scores_gemma":[0.000001896302,0.000007640407,0.00034494206,0.0000012555518,0.0000025659117,0.0000023242133,0.0000048119387,0.9991812,0.00025383048,0.00014755578,0.00005075414,0.000001302642],"about_ca_topic_score_codex":0.018119872,"about_ca_topic_score_gemma":0.017564364,"teacher_disagreement_score":0.018119872,"about_ca_system_score_codex":0.00050276786,"about_ca_system_score_gemma":0.0010160673,"threshold_uncertainty_score":0.036028802},"labels":[],"label_agreement":null},{"id":"W4416958233","doi":"10.1038/s41598-025-28592-4","title":"Dynamic graph learning framework based seasonal and trend decomposition approach for potato crop evapotranspiration prediction","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; University of British Columbia; University of Guelph; University of British Columbia, Okanagan Campus; Memorial University of Newfoundland; University of Prince Edward Island","funders":"","keywords":"Graph; Evapotranspiration; Time series; Multivariate statistics; Dynamic data; Data modeling","score_opus":0.010252139507239447,"score_gpt":0.2580488696203124,"score_spread":0.247796730113073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416958233","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11383589,0.00062317715,0.88002723,0.00037528633,0.00006408668,0.00004041572,0.0008174099,0.0016166605,0.002599773],"genre_scores_gemma":[0.90690684,0.00045355322,0.087774634,0.000092705166,0.000049746257,0.00006475229,0.0014840354,0.00012108746,0.0030526596],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998091,0.000030324136,0.000011462116,0.00008189938,0.000036316575,0.000030924464],"domain_scores_gemma":[0.99976057,0.00008171861,0.000046128323,0.000021747564,0.00007304916,0.000016796595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042407753,0.00066973176,0.00047496293,0.001344478,0.00021907664,0.0005107684,0.0007348025,0.0005621119,0.001065663],"category_scores_gemma":[0.0009332813,0.00024627958,0.00088024803,0.0012320053,0.00024022773,0.0011974245,0.00044728984,0.000722426,0.0002853084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012724253,0.00011579202,0.008521373,0.00007527433,0.0001401947,0.00016062474,0.00012318956,0.7995706,0.005235022,0.006741485,0.0025267494,0.17666242],"study_design_scores_gemma":[0.0000014949438,0.000008390726,0.0007451407,0.000001869293,0.0000075681683,0.000007666878,0.00000924326,0.99691087,0.0002508739,0.001793961,0.00025937296,0.0000034888008],"about_ca_topic_score_codex":0.01790759,"about_ca_topic_score_gemma":0.019477196,"teacher_disagreement_score":0.01790759,"about_ca_system_score_codex":0.000686436,"about_ca_system_score_gemma":0.0006678327,"threshold_uncertainty_score":0.035606682},"labels":[],"label_agreement":null},{"id":"W4417227211","doi":"10.1144/gh2025-4","title":"Unravelling the power of neural networks for flood prediction across complex hydrological systems","year":2025,"lang":"en","type":"article","venue":"GeoHorizons","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Science Foundation","keywords":"Flood myth; Hydrometeorology; Artificial neural network; Flooding (psychology); Feature (linguistics); Interpolation (computer graphics); Warning system; Reliability (semiconductor); Set (abstract data type)","score_opus":0.02632417619365111,"score_gpt":0.2681598292556399,"score_spread":0.24183565306198881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417227211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5182243,0.0045339554,0.4674337,0.0027829506,0.00012740395,0.00005165249,0.00038037737,0.0009833403,0.005482375],"genre_scores_gemma":[0.9572556,0.0012137232,0.040378626,0.00007833975,0.000045031804,0.0000201663,0.00014298446,0.00003396801,0.00083151617],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983835,0.000053626965,0.000011370018,0.000047151243,0.00003128126,0.000018314326],"domain_scores_gemma":[0.99886334,0.00086228224,0.00007595798,0.00006163426,0.00010866065,0.000028051303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010890181,0.0009545375,0.0003576603,0.0003830896,0.00023781638,0.0010079257,0.00065184943,0.0005757948,0.0008848319],"category_scores_gemma":[0.0040152594,0.00039328999,0.00039971765,0.00046686767,0.00047003114,0.002231614,0.00066611136,0.0014937674,0.00015043796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003948772,0.000029257573,0.004517834,0.00006907863,0.000083962725,0.00004954273,0.000071516326,0.9278445,0.0025104163,0.0025465486,0.0003095343,0.061928317],"study_design_scores_gemma":[0.0000013549754,0.000012652769,0.0004879797,0.0000064602027,0.0000056386666,0.000004751019,0.00001175912,0.99719465,0.00035701643,0.0017980639,0.00011681778,0.000002758254],"about_ca_topic_score_codex":0.014830555,"about_ca_topic_score_gemma":0.020863598,"teacher_disagreement_score":0.014830555,"about_ca_system_score_codex":0.00059363066,"about_ca_system_score_gemma":0.00064446364,"threshold_uncertainty_score":0.029488444},"labels":[],"label_agreement":null},{"id":"W6889963137","doi":"10.3205/19ifssh1490","title":"Assessment of age-related differences in decomposition-based quantitative electromyography in the first dorsal interosseous (FDI) and abductor digiti minimi (ADM) muscles","year":2020,"lang":"en","type":"article","venue":"German Medical Science (German Research Foundation)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Electromyography; Motor unit; Dorsum; Measure (data warehouse); Neuromuscular disease","score_opus":0.0691088827427989,"score_gpt":0.4087763683277228,"score_spread":0.3396674855849239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889963137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946233,0.00069922337,0.002777568,0.000028285995,0.00003517638,0.000027795113,0.0007042231,0.000029129307,0.0010753127],"genre_scores_gemma":[0.99686337,0.00020552267,0.0010742327,0.000020812196,0.000013938111,0.000037479822,0.000528908,0.000007770721,0.0012481514],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997744,0.000035067605,0.000030710176,0.00008735451,0.00004779557,0.000024678811],"domain_scores_gemma":[0.99897456,0.00021285635,0.00035471492,0.0000764663,0.00028064422,0.000100693236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007137885,0.00041347079,0.00021730519,0.0006657137,0.0001010452,0.0002089014,0.00011302671,0.00036437897,0.0019737536],"category_scores_gemma":[0.001732125,0.000100289835,0.0001892179,0.00025555526,0.0001251875,0.00029734464,0.00024727438,0.00020493985,0.0006169163],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035562334,0.0004171614,0.7811398,0.00018460266,0.00028791672,0.0005736437,0.00049469556,0.00077550515,0.13079579,0.00019228927,0.00088005187,0.08070227],"study_design_scores_gemma":[0.000013765324,0.0011166963,0.991983,0.000012316419,0.000048083566,0.0005657845,0.00008633772,0.00058881426,0.0048675514,0.000060326867,0.0006485793,0.000008674961],"about_ca_topic_score_codex":0.0006163535,"about_ca_topic_score_gemma":0.0005491635,"teacher_disagreement_score":0.0019737536,"about_ca_system_score_codex":0.00011326073,"about_ca_system_score_gemma":0.0000830017,"threshold_uncertainty_score":0.0066028237},"labels":[],"label_agreement":null},{"id":"W6901935439","doi":"10.6084/m9.figshare.12257744","title":"Additional file 1 of Evaluating soil nutrients of Dacrydium pectinatum in China using machine learning techniques","year":2020,"lang":"en","type":"article","venue":"Open MIND","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Artificial neural network; Table (database); Soil nutrients; China","score_opus":0.06051189985831263,"score_gpt":0.3148566227657805,"score_spread":0.2543447229074679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901935439","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006450724,0.000014811083,0.0003613061,0.00008790659,0.000021781121,0.00006711342,0.9975726,0.00024383383,0.0009855127],"genre_scores_gemma":[0.023697676,0.00012827296,0.0058404403,0.00027045343,0.00006747628,0.001570714,0.95684713,0.00042312386,0.011154773],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968886,0.00004320348,0.000061391525,0.00008014352,0.000086106746,0.000040283514],"domain_scores_gemma":[0.99578995,0.0022977768,0.00024369262,0.00027295193,0.0012690496,0.00012652292],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008081383,0.00070282316,0.0007787414,0.0015485266,0.00051000214,0.00082275155,0.00143415,0.00067350466,0.7509383],"category_scores_gemma":[0.007856993,0.00032322257,0.0006297367,0.0039156326,0.00015250519,0.0013356158,0.0005539052,0.0005250233,0.078210935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002750196,0.00013182631,0.0064245723,0.0034643775,0.000058237674,0.000119614415,0.00007793256,0.0025674615,0.0003072364,0.0010066037,0.96431214,0.021254966],"study_design_scores_gemma":[0.004812245,0.00038429047,0.09040303,0.0021401057,0.0002965589,0.00035707073,0.0010780849,0.018237907,0.0026560526,0.013129173,0.86627316,0.00023236452],"about_ca_topic_score_codex":0.018384382,"about_ca_topic_score_gemma":0.02834504,"teacher_disagreement_score":0.7509383,"about_ca_system_score_codex":0.00091438193,"about_ca_system_score_gemma":0.0015604501,"threshold_uncertainty_score":0.35525626},"labels":[],"label_agreement":null},{"id":"W6902300300","doi":"10.6084/m9.figshare.3363421","title":"On the importance of training methods and ensemble aggregation for runoff prediction by means of artificial neural networks","year":2016,"lang":"en","type":"article","venue":"Figshare","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial neural network; Metaheuristic; Training (meteorology); Point (geometry); Ensemble forecasting; Training set","score_opus":0.07462841217960606,"score_gpt":0.29866892112801185,"score_spread":0.2240405089484058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902300300","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0377472,0.045716077,0.8264331,0.030770319,0.020768482,0.00022806317,0.00015134526,0.0005768395,0.03760849],"genre_scores_gemma":[0.47149527,0.047542132,0.4126163,0.0039269207,0.038050726,0.0002674772,0.00024352172,0.0004205919,0.025437018],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833655,0.0008560517,0.00009446904,0.00017339463,0.0005015041,0.000037962673],"domain_scores_gemma":[0.9875896,0.008781754,0.00045982635,0.00044055472,0.002576076,0.00015217254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005799114,0.00055732124,0.0006687307,0.00063900626,0.00032091202,0.0021571019,0.00081901654,0.0009745377,0.0018091085],"category_scores_gemma":[0.018593322,0.0001439032,0.00035575285,0.0009742067,0.00055085885,0.0021982235,0.0005551941,0.0016973563,0.0005650653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020120121,0.000081009086,0.0036167968,0.00064121943,0.00014716435,0.00027190027,0.0002151701,0.116264716,0.0037347982,0.02753635,0.04519674,0.80209297],"study_design_scores_gemma":[0.000046758745,0.00026133764,0.0071327724,0.0005587362,0.00015770651,0.0004470442,0.00044623,0.80215466,0.0075724903,0.04653936,0.13458489,0.0000980478],"about_ca_topic_score_codex":0.00093086803,"about_ca_topic_score_gemma":0.0015012088,"teacher_disagreement_score":0.005799114,"about_ca_system_score_codex":0.00047100373,"about_ca_system_score_gemma":0.00044537292,"threshold_uncertainty_score":0.030669034},"labels":[],"label_agreement":null},{"id":"W6910266382","doi":"10.48308/envs.2022.35101","title":"Evaluating the performance of artificial intelligence models for temperature downscaling (Study area: Ardabil province)","year":2022,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Downscaling; Mean squared error; HadCM3; Perceptron; Baseline (sea); Correlation coefficient; Multilayer perceptron; General Circulation Model","score_opus":0.4060069487582183,"score_gpt":0.5396118819339808,"score_spread":0.1336049331757625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6910266382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99136204,0.00035725787,0.0050259777,0.00012934249,0.000036889087,0.000057454796,0.0005464328,0.00018086603,0.0023038075],"genre_scores_gemma":[0.9941222,0.00017394617,0.0039854706,0.000015756768,0.000009906435,0.000043984677,0.0011062281,0.000011577113,0.00053082505],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996984,0.00009279954,0.00001927758,0.00007449474,0.000067693036,0.00004729036],"domain_scores_gemma":[0.9990306,0.00042985752,0.00010568461,0.000066928085,0.0003111248,0.00005598604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013013937,0.00075390725,0.0004131617,0.0005823056,0.00029902792,0.00065437757,0.0006934716,0.00042532998,0.00084246893],"category_scores_gemma":[0.0025158452,0.00018188056,0.0005792814,0.0006310122,0.00021686741,0.00048497433,0.0003432789,0.00045919776,0.00017006607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053221424,0.0005862307,0.11142169,0.00015900981,0.0002721667,0.00009739672,0.00009031516,0.8246223,0.0018014881,0.0006093077,0.0022820819,0.057525817],"study_design_scores_gemma":[0.000035568577,0.00022522412,0.03128338,0.000014725403,0.00006183689,0.000014058691,0.000081932834,0.9665731,0.0010989473,0.00014947662,0.0004505,0.000011185853],"about_ca_topic_score_codex":0.2019632,"about_ca_topic_score_gemma":0.095217295,"teacher_disagreement_score":0.2019632,"about_ca_system_score_codex":0.0017739774,"about_ca_system_score_gemma":0.0015259635,"threshold_uncertainty_score":0.40157527},"labels":[],"label_agreement":null},{"id":"W6920390302","doi":"10.60692/kqnsq-x7j53","title":"Groundwater level prediction using machine learning models: A comprehensive review","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Field (mathematics); Predictive modelling; Resource (disambiguation); Groundwater; Water resources; Groundwater resources; Hydrological modelling","score_opus":0.15428411009820642,"score_gpt":0.23232460885195536,"score_spread":0.07804049875374894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920390302","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082561217,0.99139786,0.004959608,0.0008629235,0.00027668368,0.000021203303,0.00022250993,0.00005968971,0.0013739303],"genre_scores_gemma":[0.0062460424,0.9897984,0.0029775358,0.00019162742,0.0002797959,0.000024049803,0.00023851555,0.00001060198,0.00023338264],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995351,0.00010663916,0.00008907019,0.000097193624,0.0001484054,0.000023674833],"domain_scores_gemma":[0.9966912,0.002499745,0.00023943417,0.000054970533,0.00047403225,0.000040605853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018281005,0.0012504101,0.0014193165,0.002580305,0.00020846925,0.0014264706,0.0013951447,0.0011300655,0.0022563331],"category_scores_gemma":[0.005257734,0.00040369466,0.0016188178,0.0040868237,0.00026107006,0.0017899973,0.00058370194,0.0011283176,0.00089848746],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006751262,0.00008986564,0.0015167614,0.033128846,0.00050166214,0.00011352718,0.00007326665,0.013756796,0.0005109301,0.0053385696,0.021386689,0.9235155],"study_design_scores_gemma":[0.00005824331,0.0005374154,0.007897728,0.048261,0.0035031904,0.000984337,0.00031549425,0.04433537,0.0025918311,0.02093458,0.87029934,0.0002814796],"about_ca_topic_score_codex":0.0040419437,"about_ca_topic_score_gemma":0.0030321951,"teacher_disagreement_score":0.0040419437,"about_ca_system_score_codex":0.0006051911,"about_ca_system_score_gemma":0.0019672033,"threshold_uncertainty_score":0.009668052},"labels":[],"label_agreement":null},{"id":"W6920907268","doi":"10.6084/m9.figshare.28485792.v1","title":"Improving multi-model ensemble streamflow forecasts by combining lumped, distributed and deep learning hydrological models","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Streamflow; Artificial neural network; Deep learning; Hydrological modelling; Flood forecasting; Stream flow; Ensemble forecasting","score_opus":0.029398783256678412,"score_gpt":0.24278767648150953,"score_spread":0.21338889322483112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920907268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5257799,0.00063646946,0.462787,0.00092137454,0.0001598442,0.00006229272,0.00074247847,0.003078697,0.0058319694],"genre_scores_gemma":[0.9547931,0.00010969631,0.043672368,0.0000793579,0.000027127075,0.00002135498,0.0003566513,0.000037974725,0.0009023966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983954,0.00003876526,0.000011050838,0.000049781138,0.000035821453,0.000024918938],"domain_scores_gemma":[0.99953604,0.00020983354,0.000046758476,0.00006052832,0.00011691621,0.000029978211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095864787,0.00059126155,0.00045849968,0.0006131878,0.00024402683,0.00074585766,0.0006832773,0.0004118047,0.0009953333],"category_scores_gemma":[0.0023347493,0.00024762636,0.00043988173,0.0006145897,0.00019649904,0.0017195533,0.00081186864,0.0008009891,0.00019219323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008521425,0.00009188505,0.0053576767,0.000030100678,0.00012477241,0.000025999263,0.000039364037,0.88911,0.002569738,0.0009266637,0.00083883316,0.10079974],"study_design_scores_gemma":[0.0000046124596,0.000009150194,0.0005211509,0.000001777631,0.000007945521,0.0000021033609,0.000004800556,0.9985417,0.00039473557,0.00039320547,0.0001157997,0.0000029408416],"about_ca_topic_score_codex":0.031102935,"about_ca_topic_score_gemma":0.047432777,"teacher_disagreement_score":0.031102935,"about_ca_system_score_codex":0.0008655026,"about_ca_system_score_gemma":0.0010029089,"threshold_uncertainty_score":0.061843753},"labels":[],"label_agreement":null},{"id":"W6923316544","doi":"10.14288/1.0445568","title":"Seasonal forecasting of streamflow in a mountainous catchment in British Columbia","year":2024,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Streamflow; Flood forecasting; Snowpack; Drainage basin; Forecast skill; Inflow; Hydropower; Seasonality; Climate change","score_opus":0.011359374041224663,"score_gpt":0.18111947161987443,"score_spread":0.16976009757864977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6923316544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978624,0.000058140096,0.00012599469,0.00006254081,0.0000024866945,0.000010799329,0.0006403125,0.000033724533,0.0012036022],"genre_scores_gemma":[0.99796367,0.00007853195,0.00026452038,0.000011194234,0.000001124115,0.000008265833,0.0005972702,0.0000043291757,0.0010711718],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992406,0.0000067092765,0.0000052807454,0.000020253634,0.000020441044,0.00002329057],"domain_scores_gemma":[0.99977857,0.00003375586,0.00002087276,0.000009092947,0.000100535835,0.000057090525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010021269,0.00020000641,0.00016273191,0.00054644415,0.00074652117,0.0008382905,0.00043857348,0.0002375603,0.0015578171],"category_scores_gemma":[0.0005922777,0.00014378209,0.00012737066,0.0010327391,0.00022952245,0.0001803474,0.00031437443,0.00024220443,0.00015335182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030802516,0.00014663077,0.815277,0.000096879696,0.00010389492,0.0011171077,0.000814111,0.11241972,0.0068169953,0.0005008943,0.005606194,0.056792527],"study_design_scores_gemma":[0.000023418997,0.00002183886,0.81931096,0.00002606506,0.000022013124,0.000050290757,0.001140989,0.17639294,0.0006641559,0.00008946421,0.002234693,0.00002318513],"about_ca_topic_score_codex":0.9672356,"about_ca_topic_score_gemma":0.981934,"teacher_disagreement_score":0.032764375,"about_ca_system_score_codex":0.0066591557,"about_ca_system_score_gemma":0.0049522347,"threshold_uncertainty_score":0.06591463},"labels":[],"label_agreement":null},{"id":"W6931336155","doi":"10.5281/zenodo.5127825","title":"FIGURES 38–42 in Surirella subrotunda sp. nov. and Surirella parahelvetica sp. nov., two new diatom (Bacillariophyta) species from Lake Prespa, Macedonia","year":2014,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Museum of Nature","funders":"","keywords":"Keel; Diatom; Scale (ratio); Starfish; Allee effect","score_opus":0.02530539188013536,"score_gpt":0.22509504549818884,"score_spread":0.19978965361805348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931336155","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26240554,0.015931405,0.013868194,0.0020016923,0.0031000038,0.0009895657,0.06593319,0.003842269,0.6319282],"genre_scores_gemma":[0.7062726,0.004834925,0.027099798,0.0006767563,0.0003815241,0.0006731071,0.08008739,0.00057481346,0.1793991],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99991775,0.0000061883443,0.000010145278,0.000029262197,0.000022936225,0.000013746644],"domain_scores_gemma":[0.9998779,0.000022655788,0.00004080781,0.000014391078,0.000027989161,0.000016228261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000747674,0.00041825112,0.00018524447,0.002174302,0.0006200348,0.0004870426,0.00046418543,0.0004176654,0.04124445],"category_scores_gemma":[0.0004631112,0.00019490771,0.00025902386,0.0016702532,0.000395954,0.0007987432,0.00055260083,0.00042915385,0.010637776],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054259755,0.00014040308,0.058578078,0.0029433733,0.00009858298,0.0068227146,0.0065589813,0.0015070221,0.03507177,0.003518385,0.20902643,0.6751916],"study_design_scores_gemma":[0.0000312609,0.0000350894,0.19545749,0.00027366812,0.000046923604,0.0023962748,0.0010959866,0.00046169807,0.001560037,0.00037949486,0.7982448,0.000017272176],"about_ca_topic_score_codex":0.025381742,"about_ca_topic_score_gemma":0.06122135,"teacher_disagreement_score":0.04124445,"about_ca_system_score_codex":0.000855802,"about_ca_system_score_gemma":0.00044090438,"threshold_uncertainty_score":0.13797641},"labels":[],"label_agreement":null},{"id":"W6931430311","doi":"10.5281/zenodo.4027940","title":"Small, Thick, and Slow: Thinking about data and research publication in the Humanities in the age of Open and FAIR","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Field (mathematics); Context (archaeology); Digital humanities; Work (physics)","score_opus":0.24161106082458378,"score_gpt":0.310727881758956,"score_spread":0.06911682093437221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931430311","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054403115,0.0205972,0.025131114,0.8745917,0.006297746,0.000034483142,0.00022426448,0.0002463059,0.06743686],"genre_scores_gemma":[0.6587321,0.049220134,0.051694386,0.15527388,0.029358158,0.00037410628,0.00036881317,0.0016724378,0.053306013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97672105,0.014690366,0.0011055971,0.0022493745,0.0039540827,0.0012795893],"domain_scores_gemma":[0.8055501,0.14124551,0.009605594,0.011759629,0.017533202,0.014305996],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.05958236,0.00065767183,0.0009774477,0.010070188,0.011490826,0.03693366,0.00336316,0.011927412,0.015298458],"category_scores_gemma":[0.15337272,0.0010139627,0.0006774815,0.00828628,0.07513314,0.09797009,0.011017114,0.017369006,0.0024152638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051557312,0.000017151837,0.0015054508,0.00013942063,0.000019655019,0.00013862753,0.013815386,0.0002428063,0.000059428185,0.8938261,0.06253374,0.027650662],"study_design_scores_gemma":[0.000010937309,0.0000105943345,0.00029791155,0.00040854036,0.000011095199,0.00010822785,0.012031568,0.0004410925,0.00010148099,0.81750095,0.16903871,0.000038761224],"about_ca_topic_score_codex":0.010748114,"about_ca_topic_score_gemma":0.010178988,"teacher_disagreement_score":0.99663687,"about_ca_system_score_codex":0.009153654,"about_ca_system_score_gemma":0.008860499,"threshold_uncertainty_score":0.31510544},"labels":[],"label_agreement":null},{"id":"W6957859946","doi":"10.60692/89x97-f0e08","title":"Groundwater level prediction using machine learning models: A comprehensive review","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Field (mathematics); Predictive modelling; Resource (disambiguation); Groundwater; Water resources; Groundwater resources; Hydrological modelling","score_opus":0.15428411009820642,"score_gpt":0.23232460885195536,"score_spread":0.07804049875374894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957859946","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082561217,0.99139786,0.004959608,0.0008629235,0.00027668368,0.000021203303,0.00022250993,0.00005968971,0.0013739303],"genre_scores_gemma":[0.0062460424,0.9897984,0.0029775358,0.00019162742,0.0002797959,0.000024049803,0.00023851555,0.00001060198,0.00023338264],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995351,0.00010663916,0.00008907019,0.000097193624,0.0001484054,0.000023674833],"domain_scores_gemma":[0.9966912,0.002499745,0.00023943417,0.000054970533,0.00047403225,0.000040605853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018281005,0.0012504101,0.0014193165,0.002580305,0.00020846925,0.0014264706,0.0013951447,0.0011300655,0.0022563331],"category_scores_gemma":[0.005257734,0.00040369466,0.0016188178,0.0040868237,0.00026107006,0.0017899973,0.00058370194,0.0011283176,0.00089848746],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006751262,0.00008986564,0.0015167614,0.033128846,0.00050166214,0.00011352718,0.00007326665,0.013756796,0.0005109301,0.0053385696,0.021386689,0.9235155],"study_design_scores_gemma":[0.00005824331,0.0005374154,0.007897728,0.048261,0.0035031904,0.000984337,0.00031549425,0.04433537,0.0025918311,0.02093458,0.87029934,0.0002814796],"about_ca_topic_score_codex":0.0040419437,"about_ca_topic_score_gemma":0.0030321951,"teacher_disagreement_score":0.0040419437,"about_ca_system_score_codex":0.0006051911,"about_ca_system_score_gemma":0.0019672033,"threshold_uncertainty_score":0.009668052},"labels":[],"label_agreement":null},{"id":"W6968407505","doi":"10.5281/zenodo.15701508","title":"Fig. 2. A, Typical zigzag defoliation with a in Elm zigzag sawfly, APROCeROS leUCOPODa (Hymenoptera: Argidae), recorded for the first time in North America through community science","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University; Natural Resources Canada; Canadian Food Inspection Agency; Canadian Forest Service","funders":"","keywords":"Zigzag; Community structure; Larva","score_opus":0.03281164390775611,"score_gpt":0.23878521987306514,"score_spread":0.20597357596530902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968407505","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.738951,0.0003207494,0.0012625507,0.00030645228,0.000059981936,0.00028950637,0.066819295,0.00072854734,0.19126195],"genre_scores_gemma":[0.92073727,0.0002995901,0.003035687,0.00013783464,0.00001230683,0.000044835284,0.021759465,0.00005761562,0.05391542],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99996984,0.0000022511786,0.0000010226557,0.0000068663394,0.000010913374,0.000009059075],"domain_scores_gemma":[0.99990547,0.000005361095,0.000015738962,0.0000063495777,0.00003987097,0.000027324055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000040280258,0.00018566832,0.000055828677,0.00088907394,0.00054400635,0.00018431334,0.00011950384,0.00013068678,0.017704502],"category_scores_gemma":[0.000114944654,0.00005282503,0.000070678754,0.00089591474,0.00015191855,0.00009080725,0.00014605965,0.0001398366,0.0026146874],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025403875,0.00009600511,0.6948983,0.00020229218,0.00003722183,0.0029879033,0.0021553575,0.0010814536,0.022079242,0.00072579714,0.15505563,0.12042676],"study_design_scores_gemma":[0.0000048105194,0.00001414334,0.9718793,0.00001523886,0.0000034197683,0.0005364813,0.00074379245,0.00026776717,0.00044808193,0.000024667434,0.026058415,0.0000037367272],"about_ca_topic_score_codex":0.4257938,"about_ca_topic_score_gemma":0.8059769,"teacher_disagreement_score":0.57420623,"about_ca_system_score_codex":0.00078581227,"about_ca_system_score_gemma":0.0005249342,"threshold_uncertainty_score":0.8466308},"labels":[],"label_agreement":null},{"id":"W6969753804","doi":"10.5683/sp3/tayp6v","title":"Data: fruit size of Indomalayan plants","year":2022,"lang":"en","type":"dataset","venue":"Borealis","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Frugivore; Trait; Biological dispersal; Seed dispersal; Taxon; Plant evolution; Seed dispersal syndrome; Evolutionary dynamics","score_opus":0.04350496428782355,"score_gpt":0.2764049653669549,"score_spread":0.23290000107913136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6969753804","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050096083,0.000047429992,0.000032418713,0.000025705403,0.000007739722,0.0000049418472,0.994048,0.00008902874,0.00073504774],"genre_scores_gemma":[0.0063674976,0.000031917272,0.00014820174,0.000011061095,0.0000038056398,0.000031838383,0.9926973,0.000019910787,0.0006885018],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9997837,0.000014922202,0.000023549896,0.000088346605,0.000047675785,0.000041728003],"domain_scores_gemma":[0.9994136,0.00008953636,0.00012934653,0.0001237479,0.00016848053,0.000075211814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028239677,0.0008402734,0.0005684502,0.0015418115,0.00038211138,0.0007744786,0.0010126821,0.00056475005,0.017639562],"category_scores_gemma":[0.0011511692,0.00027026908,0.00046914507,0.0026090157,0.00015985414,0.00039838091,0.0006401675,0.0005473053,0.015376694],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004759548,0.000117781456,0.10259695,0.0020885756,0.0002900582,0.0002705332,0.0003690236,0.0013542239,0.0024135709,0.0007662048,0.87231433,0.0169429],"study_design_scores_gemma":[0.0001822632,0.000036351998,0.50097924,0.00023604659,0.00011693201,0.00024741693,0.00040896956,0.001331454,0.0014737836,0.00037532215,0.49455512,0.00005706659],"about_ca_topic_score_codex":0.047445443,"about_ca_topic_score_gemma":0.07955575,"teacher_disagreement_score":0.047445443,"about_ca_system_score_codex":0.0007193571,"about_ca_system_score_gemma":0.00060552196,"threshold_uncertainty_score":0.094338596},"labels":[],"label_agreement":null},{"id":"W6977756599","doi":"10.6084/m9.figshare.28485792","title":"Improving multi-model ensemble streamflow forecasts by combining lumped, distributed and deep learning hydrological models","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Streamflow; Artificial neural network; Deep learning; Hydrological modelling; Flood forecasting; Stream flow; Ensemble forecasting","score_opus":0.029398783256678412,"score_gpt":0.24278767648150953,"score_spread":0.21338889322483112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977756599","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5257799,0.00063646946,0.462787,0.00092137454,0.0001598442,0.00006229272,0.00074247847,0.003078697,0.0058319694],"genre_scores_gemma":[0.9547931,0.00010969631,0.043672368,0.0000793579,0.000027127075,0.00002135498,0.0003566513,0.000037974725,0.0009023966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983954,0.00003876526,0.000011050838,0.000049781138,0.000035821453,0.000024918938],"domain_scores_gemma":[0.99953604,0.00020983354,0.000046758476,0.00006052832,0.00011691621,0.000029978211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095864787,0.00059126155,0.00045849968,0.0006131878,0.00024402683,0.00074585766,0.0006832773,0.0004118047,0.0009953333],"category_scores_gemma":[0.0023347493,0.00024762636,0.00043988173,0.0006145897,0.00019649904,0.0017195533,0.00081186864,0.0008009891,0.00019219323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008521425,0.00009188505,0.0053576767,0.000030100678,0.00012477241,0.000025999263,0.000039364037,0.88911,0.002569738,0.0009266637,0.00083883316,0.10079974],"study_design_scores_gemma":[0.0000046124596,0.000009150194,0.0005211509,0.000001777631,0.000007945521,0.0000021033609,0.000004800556,0.9985417,0.00039473557,0.00039320547,0.0001157997,0.0000029408416],"about_ca_topic_score_codex":0.031102935,"about_ca_topic_score_gemma":0.047432777,"teacher_disagreement_score":0.031102935,"about_ca_system_score_codex":0.0008655026,"about_ca_system_score_gemma":0.0010029089,"threshold_uncertainty_score":0.061843753},"labels":[],"label_agreement":null},{"id":"W6990791742","doi":"","title":"Ensemble learning for decision making in sustainable infrastructure","year":2019,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut national de la recherche scientifique; McGill University","keywords":"Ensemble learning; Exploit; Ensemble forecasting; Generalization; Sustainable development; Support vector machine; Analytics; Flood forecasting","score_opus":0.0105628126895568,"score_gpt":0.25128995056162723,"score_spread":0.24072713787207042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990791742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015980348,0.0046665277,0.9712477,0.0018418606,0.00016874299,0.000044534045,0.00012710075,0.00016837439,0.005754797],"genre_scores_gemma":[0.7503796,0.006493603,0.23583177,0.000466151,0.00082651747,0.000326149,0.0003708328,0.00009176506,0.005213566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757224,0.0014474425,0.00010554482,0.00033117362,0.0003945726,0.00014899913],"domain_scores_gemma":[0.99412835,0.0047913576,0.00029233156,0.00023681586,0.00042531572,0.00012581036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052458094,0.0008905165,0.002057628,0.0010616392,0.00071423734,0.0020977268,0.0013619264,0.0013781348,0.0021007843],"category_scores_gemma":[0.010818908,0.0005579795,0.0011632695,0.0016623227,0.0013982507,0.0024750496,0.002034604,0.0028639077,0.00030150873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033630608,0.000029090435,0.0005830952,0.00009138252,0.00012336245,0.000045094235,0.00009761389,0.8605932,0.00015149853,0.09647013,0.0013679047,0.040413976],"study_design_scores_gemma":[0.000005230256,0.000013890008,0.00011076726,0.0000202147,0.000009656368,0.000004934145,0.00001482263,0.90177435,0.000060753828,0.09715163,0.0008256801,0.000008068782],"about_ca_topic_score_codex":0.008642315,"about_ca_topic_score_gemma":0.0063354988,"teacher_disagreement_score":0.008642315,"about_ca_system_score_codex":0.0018829502,"about_ca_system_score_gemma":0.0015748738,"threshold_uncertainty_score":0.027742803},"labels":[],"label_agreement":null},{"id":"W7014643396","doi":"","title":"Prévision hydrologique à court terme par réseaux de neurones artificiels pour différentes combinaisons, spatialisations et sources des intrants.","year":2022,"lang":"fr","type":"dissertation","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Limiting; Variable (mathematics)","score_opus":0.015906114024489708,"score_gpt":0.22742420875432465,"score_spread":0.21151809472983493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7014643396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6426673,0.00088324316,0.340017,0.0008292551,0.00018728178,0.00008040935,0.00103522,0.0010283303,0.013271974],"genre_scores_gemma":[0.95642626,0.00041180218,0.033722337,0.00006745097,0.000015984642,0.000068045825,0.0004060899,0.00013065017,0.008751443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997284,0.000039762876,0.00001610494,0.000093608534,0.00008125299,0.000040900388],"domain_scores_gemma":[0.9992397,0.00034189195,0.00007410408,0.000094225754,0.00020384113,0.000046319226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006382868,0.0006385661,0.0004937464,0.00042413315,0.00047799078,0.0016423428,0.0010480658,0.00092486397,0.00300491],"category_scores_gemma":[0.001689224,0.00040992742,0.0010964554,0.00053382025,0.00068757555,0.0018295802,0.00077020476,0.001407888,0.00044298763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022035089,0.00008617313,0.009104935,0.00012492189,0.00011291534,0.00021334953,0.00027188953,0.9399703,0.015814275,0.008239807,0.0007506609,0.025090434],"study_design_scores_gemma":[0.000012119563,0.00006307957,0.0025756932,0.000014317207,0.00003369111,0.000038971313,0.00008616103,0.9846998,0.007821311,0.0029714152,0.0016564025,0.000026997935],"about_ca_topic_score_codex":0.052518807,"about_ca_topic_score_gemma":0.061613653,"teacher_disagreement_score":0.052518807,"about_ca_system_score_codex":0.0025607967,"about_ca_system_score_gemma":0.001451784,"threshold_uncertainty_score":0.104426265},"labels":[],"label_agreement":null},{"id":"W7018506629","doi":"","title":"Development of a genetic algorithm-based solution algorithm for 1-D convection-diffusion analyses","year":2007,"lang":"en","type":"article","venue":"NPARC","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genetic algorithm; Development (topology); Process (computing); Selection (genetic algorithm); Algorithm design","score_opus":0.04253054734126994,"score_gpt":0.299326936526772,"score_spread":0.25679638918550207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018506629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061483276,0.000039763047,0.990906,0.000069032445,0.000044236076,0.000084425265,0.00002983931,0.00070428464,0.00197401],"genre_scores_gemma":[0.057274505,0.000052392897,0.9401898,0.00006167055,0.000025928377,0.00022126583,0.00011731764,0.00014533,0.0019117877],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968755,0.00007689491,0.000018466484,0.000058661466,0.00013281978,0.0000255632],"domain_scores_gemma":[0.99904996,0.0003836078,0.000044585773,0.000049080663,0.00044187048,0.00003100921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091724354,0.00062355114,0.00061945216,0.00088364095,0.0006400433,0.0007061532,0.0013672366,0.001307378,0.0038586115],"category_scores_gemma":[0.0032188732,0.00044861826,0.0005748415,0.00081721996,0.00038575404,0.00064170954,0.0006032843,0.0011902058,0.0011487007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050303046,0.0000911924,0.00081737275,0.000079582736,0.000056197703,0.0000611984,0.00008252496,0.72221255,0.0072716568,0.007824741,0.0023643323,0.25908828],"study_design_scores_gemma":[0.000010064774,0.00001110022,0.000063879306,0.0000039399683,0.000004933106,0.0000083871355,0.0000043906675,0.99753296,0.0010163803,0.00062138017,0.00071920577,0.0000034867387],"about_ca_topic_score_codex":0.009938497,"about_ca_topic_score_gemma":0.007845891,"teacher_disagreement_score":0.009938497,"about_ca_system_score_codex":0.00060990633,"about_ca_system_score_gemma":0.0015670917,"threshold_uncertainty_score":0.019761324},"labels":[],"label_agreement":null},{"id":"W7023623019","doi":"","title":"Oklahoma Firefighter (Oklahoma City, Okla.), Vol. 37, No. 10, Ed. 1 Tuesday, December 1, 2020","year":2020,"lang":"en","type":"other","venue":"The Gateway to Oklahoma History","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"State (computer science); Information system; Quarter (Canadian coin); Product (mathematics)","score_opus":0.016989885411362537,"score_gpt":0.2118796341891162,"score_spread":0.19488974877775367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023623019","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015440049,0.005575332,0.0005907762,0.004482982,0.004214518,0.0001093228,0.017731735,0.0012660417,0.9644853],"genre_scores_gemma":[0.0016972991,0.0032431027,0.00026570016,0.00044797454,0.00019251414,0.000031176347,0.0026139072,0.00019091235,0.9913174],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99988663,0.0000088921,0.0000074479453,0.00002086996,0.000046972997,0.00002925816],"domain_scores_gemma":[0.99971503,0.0000267365,0.000022128796,0.000023079625,0.00012430419,0.00008869695],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002562306,0.0010499366,0.0003727676,0.001195339,0.0022830563,0.0032143784,0.0004308603,0.000766207,0.58644056],"category_scores_gemma":[0.0008129772,0.00036594694,0.00025948932,0.002001055,0.0003228819,0.001735835,0.0010683032,0.00095746905,0.5200315],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011743983,0.000010156391,0.00018708444,0.000031448766,6.536938e-7,0.000018963818,0.000020951333,0.000026840646,0.00007915861,0.0002041145,0.96685565,0.032553203],"study_design_scores_gemma":[0.0000036156275,0.00000534164,0.0012385172,0.00007269471,0.0000019768463,0.000016394752,0.000120058896,0.000035001496,0.0000606147,0.00013342085,0.9983084,0.0000039259057],"about_ca_topic_score_codex":0.08764754,"about_ca_topic_score_gemma":0.2545457,"teacher_disagreement_score":0.58644056,"about_ca_system_score_codex":0.0015389366,"about_ca_system_score_gemma":0.0033271352,"threshold_uncertainty_score":0.5898923},"labels":[],"label_agreement":null},{"id":"W7024463943","doi":"","title":"Spring Flood Forecasting Based on the WRF-TSRM Mode","year":2018,"lang":"en","type":"article","venue":"University of Zagreb University Computing Centre (SRCE)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mode (computer interface); Flood myth; Flood forecasting; Spring (device)","score_opus":0.015175681799539233,"score_gpt":0.17119383663377336,"score_spread":0.15601815483423412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024463943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.909429,0.00029655048,0.059375554,0.00024543714,0.00024967937,0.000085917534,0.008984048,0.0049676574,0.0163662],"genre_scores_gemma":[0.9741476,0.00007111765,0.019469468,0.000013558642,0.000054776305,0.000032471937,0.003978236,0.00006507639,0.002167632],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980813,0.00003747621,0.000014105301,0.00005081733,0.000052063824,0.000037423422],"domain_scores_gemma":[0.99961394,0.000084179286,0.000041731262,0.00006094628,0.00015921843,0.000040099814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003812772,0.00045689064,0.0005508347,0.0011183642,0.00019588601,0.0005165984,0.0005516738,0.00034071587,0.0038938406],"category_scores_gemma":[0.0014820937,0.00012590723,0.0003345802,0.000986394,0.00008778649,0.0006139077,0.00026204312,0.00032767362,0.0011191671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013751658,0.00037142757,0.0817793,0.00018904798,0.00016168226,0.00021208098,0.00016884728,0.52647674,0.014531965,0.0015047028,0.014049252,0.35917985],"study_design_scores_gemma":[0.00001759956,0.00003701076,0.012572052,0.000004624388,0.000016454918,0.000015977901,0.00002048473,0.9852337,0.0011622662,0.00017202715,0.0007372084,0.000010511622],"about_ca_topic_score_codex":0.015984865,"about_ca_topic_score_gemma":0.015459081,"teacher_disagreement_score":0.015984865,"about_ca_system_score_codex":0.0002733654,"about_ca_system_score_gemma":0.00044493756,"threshold_uncertainty_score":0.03178364},"labels":[],"label_agreement":null},{"id":"W7033011386","doi":"","title":"The perspectival challenge to representationalism","year":2006,"lang":"en","type":"article","venue":"Scholarly Commons (University of the Pacific)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Stony Brook University; Simon Fraser University; Monash University; National University of Singapore; Baylor University; University of Connecticut; John Carroll University; University of Southern California; Colby College; Louisiana State University; University of Memphis; Chapman University; Wake Forest University; Acadia University; Colgate University; Coastal Carolina University; Dartmouth College; Grand Valley State University; Duquesne University; Fordham University; Eastern Michigan University; DePaul University; Georgetown University; Yale University; University of Wisconsin-Madison; Tulane University; University of Illinois at Urbana-Champaign; Colorado State University; University of Toronto; Macquarie University; Morgan State University; University of Pittsburgh; Washington University in St. Louis; University of Leeds; University of Dayton; Villanova University; Franklin and Marshall College; John Jay College of Criminal Justice; Southern Connecticut State University; Appalachian State University; Emory University; Rice University; George Washington University; University of Pennsylvania; Princeton University; University of California, Los Angeles; North Carolina State University; University of Waterloo; Texas Tech University; Florida State University; Purdue University; Harvard University; Trent University; Rollins College; York University; University of Missouri; Syracuse University; Wellesley College","keywords":"Direct and indirect realism; Perception; Exposition (narrative); Interpretation (philosophy); Subject (documents)","score_opus":0.015208777663806771,"score_gpt":0.20032902771113684,"score_spread":0.18512025004733007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033011386","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012781587,0.0066658854,0.12706159,0.39003238,0.0030858137,0.000054327385,0.00032293776,0.00034595732,0.4596495],"genre_scores_gemma":[0.899011,0.0031325861,0.033029076,0.024307556,0.0057560564,0.00037592486,0.00023682279,0.00048540867,0.033665553],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9885529,0.007167523,0.00038417339,0.0012341558,0.0020064295,0.0006547933],"domain_scores_gemma":[0.98448205,0.008723822,0.0007451843,0.003359977,0.0020334998,0.0006554071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013107503,0.0006453878,0.0010275083,0.0021401248,0.008111286,0.01443799,0.002977285,0.0073836176,0.009225125],"category_scores_gemma":[0.03039754,0.0006751209,0.0010346407,0.0017805293,0.054169495,0.021661395,0.007845078,0.017001105,0.0013132985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025166632,0.0000022710567,0.000011106847,0.000008244254,0.0000018876281,0.000005296958,0.0007174362,0.00004992881,0.000016400678,0.9970553,0.0014037063,0.0007258865],"study_design_scores_gemma":[0.000006910613,0.0000017627148,0.000015480096,0.000017522689,0.0000021095848,0.000015713935,0.00031162868,0.0002716019,0.000032478307,0.9860675,0.0132531645,0.00000411749],"about_ca_topic_score_codex":0.006227941,"about_ca_topic_score_gemma":0.0032026018,"teacher_disagreement_score":0.01443799,"about_ca_system_score_codex":0.0069596916,"about_ca_system_score_gemma":0.004212781,"threshold_uncertainty_score":0.06931996},"labels":[],"label_agreement":null},{"id":"W7033342879","doi":"","title":"Pollution from urban land use in the Grand and Saugeen Watersheds","year":2018,"lang":"en","type":"report","venue":"The Atrium (University of Guelph)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pollutant; Pollution; Urban area; Land use; Hydrology (agriculture); Air pollution; Estimation; River pollution","score_opus":0.035505870128616064,"score_gpt":0.21994646746936408,"score_spread":0.18444059734074802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033342879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99935097,0.000026846856,0.000025842213,0.00001718702,5.4525765e-7,0.0000056032172,0.0001467749,0.000001809794,0.00042440236],"genre_scores_gemma":[0.99861753,0.00008216149,0.00011121253,0.0000104361325,0.0000021445628,0.000016664173,0.00050247164,0.0000020151263,0.00065532007],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997688,0.000059298087,0.000010217819,0.000045129287,0.000055412707,0.00006111043],"domain_scores_gemma":[0.9996815,0.0000617084,0.00010187023,0.000019879168,0.000058715512,0.00007636761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020904667,0.0001491162,0.00011545447,0.0010940082,0.00046034777,0.00071276823,0.0001663045,0.00016672892,0.00088562095],"category_scores_gemma":[0.0005014266,0.00018229272,0.00013557287,0.0015670162,0.0008208726,0.00029402753,0.0005755446,0.00017401109,0.0001045737],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093643874,0.000034106866,0.9902866,0.000014361753,0.000023066506,0.0007087447,0.0016892105,0.00050651527,0.00091980107,0.00017379022,0.00040100692,0.0051491885],"study_design_scores_gemma":[0.0000029494142,0.000033018347,0.9976834,0.0000032516043,0.0000041447374,0.00008069867,0.0011538794,0.00014406371,0.00013369384,0.000022674963,0.0007347904,0.000003343457],"about_ca_topic_score_codex":0.22682807,"about_ca_topic_score_gemma":0.514841,"teacher_disagreement_score":0.7731719,"about_ca_system_score_codex":0.0015134476,"about_ca_system_score_gemma":0.0010434615,"threshold_uncertainty_score":0.4510156},"labels":[],"label_agreement":null},{"id":"W7033367333","doi":"","title":"\"Pour une écologie juridique. Éléments pour une critique de la soumission de la normativité juridique à l'ordre économique contemporain\"","year":2022,"lang":"fr","type":"article","venue":"Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B))","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"General interest; Social impact; Promotion (chess)","score_opus":0.016207230073446075,"score_gpt":0.22907950639049598,"score_spread":0.2128722763170499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033367333","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010736684,0.028493246,0.03220004,0.6073087,0.0052649407,0.00012355502,0.00042894584,0.00015416212,0.31528974],"genre_scores_gemma":[0.720352,0.021212205,0.02160178,0.12570097,0.0063102082,0.0009265556,0.00034789668,0.00032528292,0.1032231],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96978027,0.016585898,0.0012006164,0.0038291402,0.007285757,0.0013183935],"domain_scores_gemma":[0.96648973,0.021237329,0.0027501797,0.0023119512,0.005925994,0.0012848339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030595977,0.00075341243,0.0011237956,0.0042297794,0.015100141,0.024645733,0.0035063731,0.009166248,0.0098244175],"category_scores_gemma":[0.04719149,0.0006401644,0.0009779568,0.00635486,0.0670952,0.021498624,0.007745229,0.017693823,0.0015829426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005877433,0.00000331873,0.00017185061,0.000032026273,0.000002317417,0.000008792538,0.0024371382,0.00006178367,0.0000071431177,0.9866153,0.0075639267,0.0030904585],"study_design_scores_gemma":[0.000019706076,0.000018786803,0.0018580799,0.0007447656,0.000016025877,0.00007988576,0.008518556,0.0005271922,0.00012804958,0.62419724,0.3638397,0.000052004918],"about_ca_topic_score_codex":0.058014467,"about_ca_topic_score_gemma":0.04569773,"teacher_disagreement_score":0.058014467,"about_ca_system_score_codex":0.019411432,"about_ca_system_score_gemma":0.026578374,"threshold_uncertainty_score":0.16180891},"labels":[],"label_agreement":null},{"id":"W7033680890","doi":"","title":"Safety.net? Care, Charity, and Medical Crowdfunding in Canada","year":2024,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Health care; Welfare; Politics; Personal care; Social media; Moral responsibility; Medical care","score_opus":0.00680042601953648,"score_gpt":0.15071231816083866,"score_spread":0.14391189214130218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033680890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71165746,0.006398643,0.00089805014,0.13853669,0.00058927864,0.00020929123,0.0026326277,0.00009550056,0.13898246],"genre_scores_gemma":[0.97724026,0.0027222168,0.00051687815,0.0052581653,0.00003971557,0.000044859913,0.0002948177,0.000033190845,0.013849906],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99548507,0.0006916437,0.0000924331,0.00032795517,0.0013028092,0.0021001827],"domain_scores_gemma":[0.98965,0.0019833574,0.0008198506,0.00019878168,0.0030953586,0.0042527467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027734966,0.00029200412,0.00042210956,0.002250379,0.03034003,0.008252273,0.0018619816,0.0014774962,0.0067849625],"category_scores_gemma":[0.009012082,0.00033102513,0.00038105118,0.006498553,0.01086692,0.0020853975,0.0050935345,0.0038790444,0.00024602798],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001970325,0.00019364263,0.10769511,0.00060835533,0.000060007133,0.0018632456,0.50613946,0.00087429234,0.00060119096,0.17498909,0.13157704,0.07520149],"study_design_scores_gemma":[0.000024294299,0.00004053928,0.093652025,0.00077544345,0.00004133959,0.00019001366,0.5868391,0.0007731923,0.00028223742,0.004777993,0.31246433,0.00013942058],"about_ca_topic_score_codex":0.99876714,"about_ca_topic_score_gemma":0.999408,"teacher_disagreement_score":0.28059846,"about_ca_system_score_codex":0.28059846,"about_ca_system_score_gemma":0.40366128,"threshold_uncertainty_score":0.8344038},"labels":[],"label_agreement":null},{"id":"W7034582089","doi":"","title":"USMCA Not A Win For America!","year":2019,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Compromise; Sovereignty; Copying; Silver bullet; Government (linguistics)","score_opus":0.008282294880687808,"score_gpt":0.18951824542641346,"score_spread":0.18123595054572567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034582089","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007786859,0.001725165,0.00039867577,0.04755917,0.0074662687,0.000027199318,0.004169684,0.0011056019,0.9367695],"genre_scores_gemma":[0.004092256,0.0005817961,0.00031190162,0.0074247154,0.0003459384,0.000021605421,0.0016537829,0.00034571477,0.9852224],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99945396,0.00005183402,0.00001434213,0.00007081142,0.00029399712,0.0001150249],"domain_scores_gemma":[0.99865556,0.000103757106,0.000050382332,0.00014345789,0.00068339886,0.0003634776],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006389076,0.0005535922,0.00033160252,0.00088722736,0.003434885,0.006520541,0.00048332545,0.003075333,0.40662622],"category_scores_gemma":[0.003568379,0.00031524058,0.00036112362,0.0019325562,0.0006063539,0.0051198853,0.0022122767,0.0034860305,0.24041218],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003783584,0.0000042002202,0.000050709703,0.000009379635,4.4308229e-7,0.000008925784,0.0000126045625,0.000005279478,0.000021590111,0.0030519166,0.9884737,0.008357499],"study_design_scores_gemma":[0.0000010106708,0.0000012394906,0.000100365716,0.000013941371,4.299502e-7,0.000006641976,0.0000370863,0.000011272659,0.000022399896,0.00044393755,0.9993604,0.0000013950382],"about_ca_topic_score_codex":0.039953418,"about_ca_topic_score_gemma":0.07782347,"teacher_disagreement_score":0.40662622,"about_ca_system_score_codex":0.002126962,"about_ca_system_score_gemma":0.004640328,"threshold_uncertainty_score":0.8463757},"labels":[],"label_agreement":null},{"id":"W7034739557","doi":"","title":"Understanding Canadian Winegrowers’ Perceptions of Climate Change and Their Implications for Adaptation Behaviors","year":2019,"lang":"en","type":"other","venue":"Brock University Digital Repository (Brock University)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Brock University","keywords":"Context (archaeology); Quality (philosophy); Population; Work (physics); Limiting","score_opus":0.04998258702832357,"score_gpt":0.20665058231472558,"score_spread":0.15666799528640202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034739557","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9520661,0.0010090822,0.0004596075,0.004503349,0.000060715098,0.00003829732,0.0005108764,0.000020460873,0.041331492],"genre_scores_gemma":[0.99239963,0.0012006116,0.00045441967,0.00033081873,0.0000059822123,0.000015038478,0.0002827296,0.0000073930782,0.005303269],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993179,0.00008110229,0.000013120177,0.00007026426,0.0003152526,0.00020248006],"domain_scores_gemma":[0.9981337,0.0003399669,0.00016170435,0.000047850976,0.00084621954,0.00047056563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012541644,0.0002448642,0.0002091348,0.0007683379,0.005021302,0.003793405,0.00060265185,0.00042752814,0.0052372194],"category_scores_gemma":[0.0033474774,0.0001285725,0.0002794517,0.0015589434,0.0014796758,0.0011161716,0.0010267529,0.0009391834,0.00023475793],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014370376,0.00021107319,0.49300244,0.00030662562,0.000075295706,0.00056634174,0.3220745,0.00096444157,0.0024978712,0.008113144,0.031279214,0.14076535],"study_design_scores_gemma":[0.000008700205,0.000036962065,0.5815472,0.00023814452,0.000038716746,0.00005156095,0.36394793,0.0013429126,0.00030284753,0.0011800623,0.051222704,0.00008231876],"about_ca_topic_score_codex":0.9875388,"about_ca_topic_score_gemma":0.9941122,"teacher_disagreement_score":0.02449446,"about_ca_system_score_codex":0.02449446,"about_ca_system_score_gemma":0.029389424,"threshold_uncertainty_score":0.1777206},"labels":[],"label_agreement":null},{"id":"W7034791249","doi":"","title":"Varför ”icke-farmakologisk förskrivning av antibiotika?” : Fenomenologisk undersökning av allmänläkares attityder och åsikter","year":2005,"lang":"en","type":"article","venue":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical prescription; Coping (psychology); Variety (cybernetics); Qualitative research; Health care; General practice; Public health; Primary care","score_opus":0.033443739263296274,"score_gpt":0.27218602406824194,"score_spread":0.23874228480494566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034791249","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7469054,0.033878658,0.0068939435,0.08516198,0.0015608234,0.00023116043,0.00018020865,0.0000691419,0.1251187],"genre_scores_gemma":[0.97025025,0.0080381725,0.0017653987,0.007305531,0.00014623022,0.000065339096,0.00005315543,0.00003966359,0.012336252],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9972314,0.0017479985,0.00010459788,0.00021798031,0.00034396848,0.0003540404],"domain_scores_gemma":[0.9967457,0.0019166189,0.00052724243,0.00009933236,0.00037354653,0.00033750528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00407475,0.00033110057,0.0003085139,0.00091956987,0.0046371776,0.003632078,0.0007574853,0.0016304812,0.0052339113],"category_scores_gemma":[0.005558034,0.00028631146,0.00030020563,0.0007183559,0.009577502,0.0034615463,0.0028953007,0.0024139362,0.0007116029],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011168263,0.00012790869,0.023994965,0.0010652747,0.00001974019,0.0047217933,0.8663325,0.00016028433,0.0022460718,0.03548787,0.016238749,0.04949317],"study_design_scores_gemma":[0.000009713441,0.000085464715,0.01754456,0.0017065286,0.00002209619,0.0044013276,0.7737651,0.00016336516,0.00083930173,0.006698658,0.1947198,0.000044086366],"about_ca_topic_score_codex":0.0091314865,"about_ca_topic_score_gemma":0.011923271,"teacher_disagreement_score":0.0091314865,"about_ca_system_score_codex":0.004745353,"about_ca_system_score_gemma":0.0041788314,"threshold_uncertainty_score":0.034430087},"labels":[],"label_agreement":null},{"id":"W7034898837","doi":"","title":"Vibrant Rock, Earth, and iPhone: Disrupting Extractivism in the Work of &#13;\\nMarcela Armas and François Quévillon.","year":2024,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Capitalism; Power (physics); Work (physics); Political ecology; Ecocriticism","score_opus":0.020047272753371252,"score_gpt":0.2619448715999637,"score_spread":0.24189759884659245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034898837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4917189,0.012225276,0.005953382,0.04989234,0.00084009644,0.000071807626,0.00012803022,0.00013036988,0.43903983],"genre_scores_gemma":[0.95213765,0.001721994,0.00089860475,0.002316254,0.00010669089,0.00003789411,0.000022392223,0.00007402232,0.042684477],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.998276,0.00089683034,0.000022891034,0.00020007878,0.00029867684,0.0003055114],"domain_scores_gemma":[0.9986833,0.0008761177,0.00009669438,0.00009881142,0.00008279706,0.00016241979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027151327,0.00044542557,0.00019215529,0.0007458118,0.015072062,0.00885155,0.0009016276,0.0017110892,0.004393984],"category_scores_gemma":[0.0024665804,0.0001993661,0.00028166216,0.00064149004,0.024239777,0.004011331,0.004261214,0.0021264984,0.00039419346],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089995876,0.00002890556,0.0019611022,0.00008847051,0.000008781497,0.00053797266,0.82052845,0.00013981356,0.0010454953,0.11844773,0.019874975,0.037248384],"study_design_scores_gemma":[0.000018985018,0.0000421899,0.0063687083,0.00030378843,0.000009031608,0.00042018265,0.3930102,0.00018970932,0.0006933741,0.009769833,0.5891416,0.00003243461],"about_ca_topic_score_codex":0.1286337,"about_ca_topic_score_gemma":0.29357752,"teacher_disagreement_score":0.1286337,"about_ca_system_score_codex":0.008956652,"about_ca_system_score_gemma":0.0043913755,"threshold_uncertainty_score":0.2557699},"labels":[],"label_agreement":null},{"id":"W7038435230","doi":"","title":"The Indian News, Volume 3 , Issue 4 (July 1959)","year":2013,"lang":"en","type":"other","venue":"WinnSpace (University of Winnipeg)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Public health; Research methodology; Health data","score_opus":0.006101998771332613,"score_gpt":0.17506880617011353,"score_spread":0.16896680739878092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7038435230","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015945272,0.017882815,0.0003084321,0.111140996,0.10109462,0.00016163605,0.009907619,0.0012675991,0.7566417],"genre_scores_gemma":[0.0031903884,0.0036675665,0.00015268291,0.01813887,0.0070385053,0.000036455014,0.0010800693,0.00019653454,0.96649873],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992963,0.000046861667,0.000040528947,0.00005969944,0.00039489055,0.00016175178],"domain_scores_gemma":[0.99838626,0.00029858906,0.00007977291,0.00011495266,0.00076796394,0.00035249692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006740023,0.00083972426,0.0005189681,0.0029490301,0.004028663,0.0061466442,0.0012831991,0.0031680637,0.14241104],"category_scores_gemma":[0.005008093,0.00046269264,0.0007217519,0.004442216,0.0010292717,0.0016431035,0.0016121415,0.00419935,0.079379655],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017560063,0.000009701981,0.00015578234,0.000056713016,0.0000021230712,0.000038728693,0.000046366324,0.000014947926,0.000026969876,0.00081666827,0.9867214,0.012093033],"study_design_scores_gemma":[0.000004246484,0.0000036487918,0.0010759062,0.00005770337,0.000003964993,0.000018274048,0.0000717319,0.0000153346,0.000041469575,0.00021084202,0.99849236,0.0000045510264],"about_ca_topic_score_codex":0.17166217,"about_ca_topic_score_gemma":0.3269747,"teacher_disagreement_score":0.17166217,"about_ca_system_score_codex":0.0035626376,"about_ca_system_score_gemma":0.007128172,"threshold_uncertainty_score":0.47641236},"labels":[],"label_agreement":null},{"id":"W7039225415","doi":"","title":"Microcystis aeruginos strain [D-Leu1] Mcyst-LR producer, from Buenos Aires province, Argentina","year":2014,"lang":"en","type":"article","venue":"Americanae (AECID Library)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Microcystis aeruginosa; Phylogenetic tree; Strain (injury); Colonization; Intergenic region","score_opus":0.0047448806035644605,"score_gpt":0.17354950985555975,"score_spread":0.1688046292519953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039225415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9773476,0.003481875,0.0015322857,0.00038128457,0.000088025,0.00023222859,0.009344495,0.00010386867,0.007488275],"genre_scores_gemma":[0.9602487,0.0031078055,0.007294155,0.00011514007,0.00004892599,0.00018942897,0.017379003,0.0000357623,0.011581074],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99977523,0.000008601951,0.000019038398,0.0000812747,0.000084538915,0.000031282238],"domain_scores_gemma":[0.9998945,0.000006680118,0.000025703714,0.000005120594,0.00004740585,0.000020536454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015674933,0.00063948083,0.0003409531,0.00067793747,0.0005219509,0.00037508822,0.00021830056,0.0002748438,0.001268072],"category_scores_gemma":[0.00018482139,0.00012239987,0.00018981911,0.00057375606,0.00014717627,0.00015295229,0.0002542199,0.00025224467,0.0003854379],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006304632,0.0001587415,0.035100844,0.00044120147,0.000031037678,0.00095457106,0.00037498315,0.00019219854,0.9327948,0.00013957922,0.0014326195,0.027748914],"study_design_scores_gemma":[0.00010260067,0.0011540948,0.78529364,0.00014967629,0.00014356196,0.004444192,0.0010847928,0.00093263865,0.13818659,0.00010879236,0.06835077,0.000048629765],"about_ca_topic_score_codex":0.05557101,"about_ca_topic_score_gemma":0.06546074,"teacher_disagreement_score":0.05557101,"about_ca_system_score_codex":0.00058396574,"about_ca_system_score_gemma":0.0007515458,"threshold_uncertainty_score":0.11049515},"labels":[],"label_agreement":null},{"id":"W7083416425","doi":"10.2139/ssrn.5519013","title":"Water level prediction of coastal inland river by integrating bimodal decomposition and hybrid deep learning model","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Deep learning; Hyperparameter; Flood myth; Water level; Artificial neural network; Residual; Convolutional neural network; Coastal flood; Deep water","score_opus":0.011377225269747666,"score_gpt":0.23370233984905492,"score_spread":0.22232511457930726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083416425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7618,0.00021065846,0.2338398,0.00027528626,0.00006826581,0.000011767461,0.0005311512,0.0005411421,0.0027219926],"genre_scores_gemma":[0.99045545,0.000035308898,0.008170022,0.000017554612,0.000009816921,0.0000055942655,0.00021613941,0.000013528425,0.0010765265],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999956,0.0000054944876,0.0000018681864,0.00001783004,0.0000060905268,0.000012709302],"domain_scores_gemma":[0.99990153,0.000023638879,0.000012191112,0.0000088629895,0.00003678238,0.000016906839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013549133,0.00033104751,0.0002977781,0.00027373002,0.00015166121,0.00036983387,0.00037432837,0.0003974512,0.001147184],"category_scores_gemma":[0.0003954053,0.00020419515,0.0003052456,0.0003578985,0.00012677003,0.0005217146,0.00036602435,0.00041942354,0.0001773238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014718859,0.00009512222,0.013882404,0.0000239479,0.000046072997,0.000056489345,0.000027719761,0.9273955,0.008665488,0.0010112574,0.0010039672,0.04764476],"study_design_scores_gemma":[0.0000011843172,0.0000023007267,0.00058423815,4.5018018e-7,0.0000017396866,0.0000010620049,0.0000012840961,0.99913543,0.00013739552,0.000117795746,0.000016069176,0.000001070759],"about_ca_topic_score_codex":0.017788436,"about_ca_topic_score_gemma":0.020231899,"teacher_disagreement_score":0.017788436,"about_ca_system_score_codex":0.0003023628,"about_ca_system_score_gemma":0.00046259872,"threshold_uncertainty_score":0.035369813},"labels":[],"label_agreement":null},{"id":"W7084261106","doi":"","title":"Remerciements","year":2025,"lang":"fr","type":"other","venue":"Industrias Culturais (Universidade de Coimbra)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Identity (music); Subject (documents); Context (archaeology)","score_opus":0.03093827460025983,"score_gpt":0.24600556686579203,"score_spread":0.2150672922655322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084261106","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013040191,0.013707286,0.045254435,0.26994184,0.13672215,0.0022320691,0.08900328,0.008652743,0.42144606],"genre_scores_gemma":[0.0838481,0.007793863,0.04002482,0.022018347,0.020191416,0.0014307791,0.026213916,0.0072022597,0.7912765],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97608966,0.0044343593,0.001188626,0.0026506344,0.014476383,0.0011604085],"domain_scores_gemma":[0.83780795,0.014612602,0.0028286197,0.012317608,0.11635743,0.016075892],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014901988,0.001539358,0.0019353706,0.0040398943,0.00298387,0.006904371,0.0030436765,0.001376726,0.3093397],"category_scores_gemma":[0.119756564,0.00040743774,0.001232702,0.003244623,0.0016729964,0.004164037,0.004171395,0.00402419,0.14752267],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008171288,0.00003900224,0.0008936267,0.00019181728,0.000016301947,0.00028701994,0.0018127352,0.000302388,0.00079819513,0.008709252,0.9243915,0.06247652],"study_design_scores_gemma":[0.000013745532,0.000018748395,0.0010434346,0.0002554305,0.000011523835,0.0002346348,0.0011178044,0.00026780096,0.00040212186,0.0026492442,0.9939633,0.000022200533],"about_ca_topic_score_codex":0.032213822,"about_ca_topic_score_gemma":0.03963117,"teacher_disagreement_score":0.6906603,"about_ca_system_score_codex":0.007001206,"about_ca_system_score_gemma":0.021169819,"threshold_uncertainty_score":0.98514307},"labels":[],"label_agreement":null},{"id":"W7084406892","doi":"10.15468/dl.7r8ggx","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Real world data; Identification (biology)","score_opus":0.013339326326276655,"score_gpt":0.2154965648163554,"score_spread":0.20215723849007874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084406892","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004751693,0.000028250452,0.00004871423,0.000040729756,0.000013303613,0.0000055275864,0.99865377,0.00047879881,0.000683309],"genre_scores_gemma":[0.0001743763,0.00003459663,0.00021117147,0.000044172688,0.00000411006,0.00003880252,0.99884963,0.00014543267,0.00049774675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991385,0.0001133983,0.000109671724,0.00030159368,0.00019661135,0.00014013254],"domain_scores_gemma":[0.9981592,0.00050040515,0.0001647162,0.00048335877,0.00047417526,0.00021821016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000769785,0.0018982792,0.0013675601,0.0042127166,0.00084366224,0.0023037845,0.0025816937,0.0018716976,0.14331728],"category_scores_gemma":[0.0051988885,0.00080664497,0.001159999,0.008347406,0.0003854524,0.0022202737,0.0021891263,0.0019327061,0.21572502],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023906932,0.000010166319,0.00032504604,0.0004012013,0.000012566342,0.000012731505,0.000017236736,0.00014587733,0.00008383304,0.00031957513,0.9972288,0.0014190571],"study_design_scores_gemma":[0.00007940227,0.000008221083,0.0017161004,0.00016191114,0.000013472003,0.000035630474,0.000067974164,0.00026108001,0.00019489556,0.00087299617,0.996572,0.000016403566],"about_ca_topic_score_codex":0.02006332,"about_ca_topic_score_gemma":0.034044378,"teacher_disagreement_score":0.14331728,"about_ca_system_score_codex":0.0014566975,"about_ca_system_score_gemma":0.0020134556,"threshold_uncertainty_score":0.4794441},"labels":[],"label_agreement":null},{"id":"W7097664326","doi":"","title":"Submitted to Journal of Water Resources Planning and Management","year":2002,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Streamflow; Teleconnection; Precipitation; Pacific decadal oscillation; Jackknife resampling; Water resources; Water year; Sea surface temperature; Feedforward neural network","score_opus":0.02482083427199245,"score_gpt":0.21833950667230542,"score_spread":0.19351867240031298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097664326","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008290596,0.012673197,0.012277311,0.057776865,0.0277913,0.00040509735,0.0070099393,0.00077521394,0.87300044],"genre_scores_gemma":[0.05352844,0.010468021,0.0047074025,0.0021948086,0.0052389144,0.00016194087,0.004646895,0.00041086646,0.9186427],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995204,0.000104772196,0.000049140217,0.00007704948,0.0001920689,0.00005660948],"domain_scores_gemma":[0.9985183,0.00021644912,0.00007685707,0.00021788746,0.00071028754,0.00026027474],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010853269,0.0004643883,0.0006666261,0.0012588833,0.0011983955,0.0041897455,0.00090625265,0.0011095691,0.26765674],"category_scores_gemma":[0.0036014374,0.00019594803,0.00033764658,0.002315948,0.0005105598,0.0020059024,0.001510059,0.0013490123,0.043477684],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070783404,0.00008127207,0.001132825,0.00013232925,0.000017341952,0.000102416365,0.00012599831,0.0014758657,0.0002085927,0.028383132,0.7268292,0.2414403],"study_design_scores_gemma":[0.000008482087,0.000016023407,0.00094266265,0.000086576045,0.0000053505137,0.00002659356,0.0001713753,0.0014640255,0.000090266076,0.008822785,0.98836017,0.00000559286],"about_ca_topic_score_codex":0.008496692,"about_ca_topic_score_gemma":0.011502031,"teacher_disagreement_score":0.73234326,"about_ca_system_score_codex":0.0013962428,"about_ca_system_score_gemma":0.0037366126,"threshold_uncertainty_score":0.895401},"labels":[],"label_agreement":null},{"id":"W7106690747","doi":"10.18280/mmep.121018","title":"The Modified Gamma Distribution and Machine Learning for Modeling and Classification of Groundwater Potability","year":2025,"lang":"","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Groundwater; Distribution (mathematics); Gamma distribution; Hydrology (agriculture)","score_opus":0.04251184405702122,"score_gpt":0.22851908869960155,"score_spread":0.18600724464258034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106690747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022085058,0.0019059401,0.9745491,0.00041735492,0.00005566534,0.00001746187,0.000117956864,0.00021467237,0.00063687324],"genre_scores_gemma":[0.8092512,0.0039801844,0.18107225,0.00019464831,0.00042115388,0.0001820183,0.00063597487,0.00015176163,0.0041108388],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900776,0.0005003205,0.00006657288,0.00019101237,0.00017268809,0.00006170617],"domain_scores_gemma":[0.99132895,0.0070819883,0.00049755885,0.0004526123,0.00053513475,0.000103764214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039655007,0.0009734302,0.0012844285,0.0030452383,0.0004751015,0.0014725898,0.0017549503,0.0014541813,0.0009781814],"category_scores_gemma":[0.012760263,0.0005566794,0.0012952085,0.0026534821,0.0020567353,0.00289018,0.0008639762,0.002310283,0.000303971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005919572,0.000029233192,0.0020848282,0.00006340014,0.00008759489,0.00005472151,0.000062628176,0.8990721,0.00055715424,0.042094607,0.0009012872,0.054933272],"study_design_scores_gemma":[0.000002252513,0.0000058821847,0.0002540571,0.0000054875964,0.000005178036,0.00001348782,0.000004864408,0.96166384,0.00014177554,0.03765904,0.00023555967,0.000008663495],"about_ca_topic_score_codex":0.009897325,"about_ca_topic_score_gemma":0.0038403778,"teacher_disagreement_score":0.009897325,"about_ca_system_score_codex":0.0017694042,"about_ca_system_score_gemma":0.0008822121,"threshold_uncertainty_score":0.020971775},"labels":[],"label_agreement":null},{"id":"W7114782518","doi":"10.1016/j.engappai.2025.113426","title":"A robust artificial intelligence informed over complete rational dilation wavelet transform technique coupled with deep learning for long-term rainfall prediction","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"Bureau of Meteorology, Australian Government; King Faisal University; Deanship of Scientific Research, King Khalid University","keywords":"Deep learning; Dilation (metric space); Robustness (evolution); Wavelet transform; Pattern recognition (psychology)","score_opus":0.029293603823554382,"score_gpt":0.26243344024757986,"score_spread":0.23313983642402547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7114782518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035460707,0.00049449265,0.9616561,0.00019870467,0.00007851711,0.000022775508,0.00007834433,0.0006298915,0.0013804984],"genre_scores_gemma":[0.7573543,0.00075896474,0.23586199,0.00019094342,0.0000834213,0.00008950362,0.0005324885,0.00008671126,0.0050417143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987376,0.00001804625,0.000010983824,0.000032025426,0.000040269144,0.000024953179],"domain_scores_gemma":[0.999858,0.000050537466,0.000019832607,0.00001435269,0.00004894272,0.000008286421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045109793,0.00053482,0.0004955317,0.00037995807,0.00018407272,0.00048452563,0.00075533835,0.00056296395,0.0012110468],"category_scores_gemma":[0.00076295447,0.00026029834,0.00069115934,0.0005831153,0.0002166062,0.0008142832,0.00057145016,0.0010537234,0.00034331915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121553254,0.00011006563,0.0017180666,0.000086530934,0.00011116017,0.0001621991,0.00005833012,0.58517116,0.024390362,0.006468975,0.0026444816,0.37895706],"study_design_scores_gemma":[0.0000014105489,0.000008980118,0.00009775611,0.000002038261,0.0000043380146,0.000005980263,0.000002315996,0.9983908,0.0007689487,0.0005150363,0.0002007775,0.0000016986385],"about_ca_topic_score_codex":0.004532348,"about_ca_topic_score_gemma":0.0046759113,"teacher_disagreement_score":0.004532348,"about_ca_system_score_codex":0.00031038496,"about_ca_system_score_gemma":0.00066627003,"threshold_uncertainty_score":0.009011924},"labels":[],"label_agreement":null},{"id":"W7115184623","doi":"10.3390/w17243551","title":"Prophet-Based Artificial Intelligence Versus Seasonal Auto-Regressive Models for Flood Forecasting with Exogenous Variables","year":2025,"lang":"en","type":"article","venue":"Water","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mean squared error; Flood myth; Seasonality; Flood forecasting; Mean square; Flood risk management; Estimation; Forecast skill","score_opus":0.0599380690575475,"score_gpt":0.25542287800412844,"score_spread":0.19548480894658093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115184623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17358392,0.0015816521,0.81252396,0.0006568087,0.00016180491,0.00008187029,0.00020006894,0.0007801437,0.01042974],"genre_scores_gemma":[0.9041684,0.00065704936,0.091296166,0.0001371163,0.00006848793,0.00007109857,0.00025992867,0.000047982474,0.0032937706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997187,0.00010965068,0.000021766655,0.00006210726,0.00007060573,0.0000171235],"domain_scores_gemma":[0.99894065,0.0007580523,0.000101392565,0.00007341082,0.00010880812,0.000017680031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012022422,0.0005765406,0.0004822081,0.00043996412,0.00019424668,0.00075444556,0.0007031725,0.00040949738,0.0010380335],"category_scores_gemma":[0.002642354,0.00020873158,0.00042619059,0.0005343841,0.0003726457,0.00081507664,0.00051320775,0.0009526091,0.00024114379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011573107,0.000032978853,0.0017261558,0.000074817566,0.00008429239,0.000044727192,0.000042709686,0.92620283,0.001468495,0.0074284812,0.0004525255,0.062326252],"study_design_scores_gemma":[0.0000028289505,0.000036786416,0.00026000422,0.000004685882,0.0000055557034,0.000011676886,0.0000052544387,0.9976278,0.00023535054,0.0015619666,0.00024423996,0.0000038384633],"about_ca_topic_score_codex":0.0047707283,"about_ca_topic_score_gemma":0.0056410204,"teacher_disagreement_score":0.0047707283,"about_ca_system_score_codex":0.00041064926,"about_ca_system_score_gemma":0.0006771649,"threshold_uncertainty_score":0.0094859},"labels":[],"label_agreement":null},{"id":"W7117129848","doi":"10.3126/injet.v3i1.87014","title":"Comparative Analysis of Traditional and Ensemble Models for Water Quality Index Prediction with Explainable AI","year":2025,"lang":"","type":"article","venue":"International Journal on Engineering Technology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Ensemble forecasting; Water quality; Ensemble learning; Pipeline (software); Index (typography); Random forest; Feature (linguistics)","score_opus":0.03006443010971537,"score_gpt":0.27989145976930796,"score_spread":0.24982702965959258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117129848","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71620214,0.0031785516,0.27233377,0.0008660109,0.00014324156,0.00011065937,0.0005030153,0.0009520862,0.005710504],"genre_scores_gemma":[0.96103925,0.00057668996,0.03675512,0.000082402796,0.000050740175,0.00007333545,0.0005212802,0.00004694149,0.0008541453],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984225,0.00080150546,0.0000957443,0.00022051482,0.00035602902,0.00010383751],"domain_scores_gemma":[0.99104124,0.0071346043,0.00030236243,0.00039389377,0.0010253425,0.000102561935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070894803,0.0009472164,0.0008085981,0.0012263405,0.00038654305,0.000984159,0.000931814,0.00063665677,0.0006891986],"category_scores_gemma":[0.010938963,0.00020492991,0.00072082184,0.0009791488,0.0002983351,0.0017229223,0.0009477869,0.0009530908,0.00017380844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031938843,0.00012234497,0.02328496,0.00010834855,0.00045781353,0.000075822194,0.00010505347,0.89108527,0.0008748076,0.001785634,0.0006920047,0.08108866],"study_design_scores_gemma":[0.000005423455,0.00007994411,0.0021643657,0.000009481097,0.00003224755,0.0000097376815,0.000023831726,0.996192,0.00047846857,0.00080145185,0.00019628314,0.000006818501],"about_ca_topic_score_codex":0.007908945,"about_ca_topic_score_gemma":0.008251614,"teacher_disagreement_score":0.007908945,"about_ca_system_score_codex":0.00073233905,"about_ca_system_score_gemma":0.0007350329,"threshold_uncertainty_score":0.03749323},"labels":[],"label_agreement":null},{"id":"W7117356171","doi":"10.1016/j.wroa.2025.100478","title":"Transferable soft-sensors for predicting nitrate in diverse watersheds","year":2025,"lang":"en","type":"article","venue":"Water Research X","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"South East Water","keywords":"Nitrate; Transferability; Artificial neural network; Linear regression; Data point; Training set; Aquatic ecosystem","score_opus":0.07853795755210921,"score_gpt":0.34603468911288393,"score_spread":0.2674967315607747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117356171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48786667,0.00052155525,0.502659,0.00032229052,0.00014572643,0.00014853646,0.0009860707,0.0034936448,0.0038563837],"genre_scores_gemma":[0.9498725,0.0001190144,0.047632974,0.00010219781,0.000022274367,0.000083772706,0.0005710164,0.00004655056,0.001549635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997249,0.00004292715,0.000015080579,0.00011724483,0.000072939765,0.00002675957],"domain_scores_gemma":[0.999595,0.00015779825,0.00006268969,0.000056287565,0.00010371664,0.000024581774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067955104,0.0012447466,0.0006039666,0.00036229638,0.00021620923,0.0007302424,0.0011899077,0.0007828298,0.0010702106],"category_scores_gemma":[0.0015693525,0.00040025095,0.00077123364,0.00034628366,0.00030566117,0.0011616145,0.0010411132,0.0011839021,0.00035128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022867351,0.00032502672,0.008214516,0.00015047951,0.00014302548,0.00009456535,0.00006530353,0.8550206,0.025697699,0.0007488573,0.0007534746,0.108557686],"study_design_scores_gemma":[0.0000046626064,0.00004640628,0.00069667265,0.000002703365,0.000007161145,0.0000072025823,0.000008548842,0.9953543,0.003328697,0.000406051,0.00012994932,0.000007635077],"about_ca_topic_score_codex":0.0070617357,"about_ca_topic_score_gemma":0.012267502,"teacher_disagreement_score":0.0070617357,"about_ca_system_score_codex":0.0006574384,"about_ca_system_score_gemma":0.0005839958,"threshold_uncertainty_score":0.014041305},"labels":[],"label_agreement":null},{"id":"W7117484197","doi":"10.1080/19942060.2025.2602582","title":"Precision water quality indices forecasting through an optimized hybrid SMW-LSSVM-R model enhanced by SATLDE and uncertainty analysis","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Computational Fluid Mechanics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Weighting; Water resources; Support vector machine; Mean squared error; Key (lock); Partial least squares regression; Extreme learning machine; Decomposition; Multivariate statistics; Feature selection","score_opus":0.013947009728195214,"score_gpt":0.2662467008884724,"score_spread":0.2522996911602772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117484197","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12691455,0.0005507559,0.86687696,0.0004107422,0.000085874715,0.00005668583,0.00015684227,0.0010609803,0.003886514],"genre_scores_gemma":[0.9432436,0.00022725089,0.05245862,0.00009619372,0.000039264778,0.0001150771,0.00029605458,0.00005929704,0.0034646718],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99973315,0.000054442833,0.000018721974,0.0000697962,0.0000922957,0.000031663385],"domain_scores_gemma":[0.99971133,0.00011322573,0.000035924484,0.000019567262,0.000105437386,0.000014518332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058950763,0.00063904765,0.000935327,0.0004876595,0.00030925983,0.0008863887,0.0009894387,0.00083854335,0.00085227384],"category_scores_gemma":[0.0011121163,0.0003692181,0.0008549226,0.00052241154,0.0003230867,0.0008294327,0.00069582637,0.0008651736,0.00021685357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038488462,0.00003891231,0.0014357032,0.000036565052,0.00004268056,0.000044536577,0.000022706268,0.96048963,0.0019842363,0.0011619324,0.00050556107,0.03419908],"study_design_scores_gemma":[0.0000013530757,0.0000043256737,0.00006467657,7.728637e-7,0.000001909672,0.000002318347,7.247399e-7,0.9996501,0.00012658349,0.00008990858,0.00005591097,0.0000014038532],"about_ca_topic_score_codex":0.012368265,"about_ca_topic_score_gemma":0.0088454485,"teacher_disagreement_score":0.012368265,"about_ca_system_score_codex":0.000540439,"about_ca_system_score_gemma":0.0010730348,"threshold_uncertainty_score":0.024592519},"labels":[],"label_agreement":null},{"id":"W7117570263","doi":"10.1016/j.jenvman.2025.128444","title":"Interpretable deep learning for dynamic rainfall-runoff prediction: Integrating adaptive signal decomposition and spatiotemporal feature extraction","year":2025,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada","keywords":"Decomposition; Particle swarm optimization; Feature extraction; Feature (linguistics); Pattern recognition (psychology); Visualization; Deep learning; SIGNAL (programming language)","score_opus":0.004583492507192762,"score_gpt":0.23857657868282378,"score_spread":0.23399308617563103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117570263","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050019693,0.00035830346,0.9476884,0.00033615064,0.000051287632,0.000016589538,0.00019101774,0.00069712807,0.0006413186],"genre_scores_gemma":[0.8409059,0.00044642008,0.15582922,0.00014534079,0.000084355954,0.00005456578,0.00051767315,0.000080884536,0.0019356266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99987006,0.00002374985,0.000010468852,0.000044009234,0.000025647381,0.000026031748],"domain_scores_gemma":[0.9996332,0.00018708134,0.000043982658,0.000041981075,0.0000740845,0.000019585297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005235316,0.00066651613,0.0005287714,0.00047157472,0.00018078902,0.000604771,0.00069381867,0.0006370616,0.001131682],"category_scores_gemma":[0.0016294871,0.00034369313,0.0005161684,0.0006606867,0.00027803786,0.0011225428,0.00080698624,0.0012512858,0.00028379163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015629013,0.00021471058,0.0022897667,0.00006246637,0.00009054622,0.00007755856,0.00004862748,0.5620557,0.016498564,0.0056382753,0.0023668422,0.4105006],"study_design_scores_gemma":[0.0000013314797,0.00000622359,0.00010697465,0.0000013962971,0.0000030392684,0.00000250555,0.0000016435965,0.9983981,0.0004914186,0.00091897947,0.00006705887,0.0000012774246],"about_ca_topic_score_codex":0.0055322284,"about_ca_topic_score_gemma":0.0068333526,"teacher_disagreement_score":0.0055322284,"about_ca_system_score_codex":0.0004167548,"about_ca_system_score_gemma":0.00067536667,"threshold_uncertainty_score":0.011000097},"labels":[],"label_agreement":null},{"id":"W7119993100","doi":"10.3126/jonc.v1i1-2.89125","title":"Spatio-Temporal Weather Prediction with Graph Neural Networks","year":2025,"lang":"","type":"article","venue":"Journal of NAST College","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Probabilistic logic; Graph; Adjacency list; Artificial neural network; Limiting; Weather forecasting; Statistical model; Convolutional neural network; Geospatial analysis","score_opus":0.009466766621080425,"score_gpt":0.21892573819764044,"score_spread":0.20945897157656002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7119993100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30452412,0.0017077967,0.68238175,0.0012093484,0.00029170353,0.000066076405,0.0017756363,0.0030312587,0.005012338],"genre_scores_gemma":[0.96447676,0.00033549443,0.032602996,0.00010200027,0.000047866142,0.00003590729,0.0009308977,0.000048436326,0.0014196106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998429,0.000031980002,0.000009456281,0.000060920254,0.000025713445,0.000029037314],"domain_scores_gemma":[0.9996061,0.00019564989,0.000060133018,0.00003210874,0.00008720713,0.00001873406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030768497,0.0007910244,0.0003976738,0.0007988669,0.00025625725,0.00060353073,0.0008713582,0.0006202358,0.0009774957],"category_scores_gemma":[0.0015616561,0.00042276795,0.0007744307,0.0009076297,0.0002950716,0.00089599844,0.0004974007,0.0008982603,0.00023199698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002582839,0.000014197565,0.0011761028,0.000013032095,0.00002729651,0.000023099312,0.0000095382675,0.9809849,0.00029836697,0.00079069065,0.0004973221,0.016139653],"study_design_scores_gemma":[6.933731e-7,0.0000017631156,0.00009856879,7.714921e-7,0.0000015491023,0.0000012952607,0.0000011638034,0.9992778,0.000043035976,0.0005349464,0.00003756709,8.9134863e-7],"about_ca_topic_score_codex":0.05750506,"about_ca_topic_score_gemma":0.050644577,"teacher_disagreement_score":0.05750506,"about_ca_system_score_codex":0.0010848782,"about_ca_system_score_gemma":0.0006099918,"threshold_uncertainty_score":0.11434072},"labels":[],"label_agreement":null},{"id":"W7123923582","doi":"10.2166/nh.2025.075","title":"How to out-perform default random forest regression: choosing hyperparameters for applications in large-sample hydrology","year":2025,"lang":"en","type":"article","venue":"Hydrology research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Regent College; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Random forest; Leverage (statistics); Hyperparameter; Water resources; Hydrological modelling; Deep learning","score_opus":0.06728013377302482,"score_gpt":0.3755970337498849,"score_spread":0.30831689997686007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123923582","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13120356,0.0030473208,0.8491649,0.0018217124,0.0003346088,0.00042942175,0.000841989,0.008965013,0.0041914247],"genre_scores_gemma":[0.54275775,0.0005932684,0.45124727,0.0006765294,0.00014533996,0.00043165454,0.0015479499,0.0013058622,0.0012943711],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976502,0.0015387826,0.0001355044,0.00028949953,0.00022606207,0.00015995155],"domain_scores_gemma":[0.99200153,0.005681112,0.00038143396,0.0007992897,0.00093558786,0.00020101336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010201444,0.0012678221,0.0010625938,0.0012003873,0.0007739877,0.001150054,0.0020667836,0.00149397,0.0032760717],"category_scores_gemma":[0.030363169,0.0005504996,0.00072317914,0.0010577051,0.0006582826,0.0021286842,0.00094257016,0.0026229585,0.0018366161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005694492,0.000446308,0.016171753,0.00035080942,0.0002748896,0.00014187621,0.00016763336,0.5545938,0.0055480083,0.0046801167,0.021776197,0.3952791],"study_design_scores_gemma":[0.000091070964,0.00005770468,0.0017949723,0.000107414926,0.000040750827,0.000037375594,0.00007041158,0.98591495,0.0033547822,0.0057359524,0.0027707259,0.000023829985],"about_ca_topic_score_codex":0.007379159,"about_ca_topic_score_gemma":0.010776909,"teacher_disagreement_score":0.010201444,"about_ca_system_score_codex":0.00049780036,"about_ca_system_score_gemma":0.001741394,"threshold_uncertainty_score":0.053951025},"labels":[],"label_agreement":null},{"id":"W7125000596","doi":"10.1109/iccica67008.2025.11337693","title":"Prediction and Analysis of Coastal Water Quality Using Ensemble Machine Learning Classifiers Based on Water Quality Index (WQI) Assessment","year":2025,"lang":"","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Xanadu Quantum Technologies (Canada)","funders":"","keywords":"Overfitting; Feature selection; Water quality; Random forest; Support vector machine; Decision tree; Ensemble learning; Generalizability theory; Sustainability","score_opus":0.05937893074080313,"score_gpt":0.3339919456330984,"score_spread":0.2746130148922953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125000596","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7136706,0.00048825648,0.2823937,0.00020497483,0.0001035721,0.00005233159,0.00045818242,0.0008500565,0.0017783851],"genre_scores_gemma":[0.9623358,0.00013165892,0.036396913,0.000023196511,0.000026548685,0.000028454346,0.00044075307,0.000011577596,0.00060518243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997156,0.00005164206,0.00002440054,0.00007977346,0.00008599588,0.00004246571],"domain_scores_gemma":[0.9991892,0.00031446168,0.00010531741,0.000091151844,0.00026657165,0.00003333701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009843924,0.0005548198,0.0007665137,0.0012721508,0.0003006112,0.0005507355,0.0004195247,0.00051387004,0.00040406795],"category_scores_gemma":[0.0017656955,0.0001581689,0.0006459302,0.000946547,0.00011972831,0.00066447293,0.00037138967,0.0005536065,0.00018085867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024101902,0.00033953603,0.043292847,0.000058608013,0.00018185316,0.00011756101,0.000083145685,0.65779877,0.011122293,0.0005004077,0.0015897639,0.28467414],"study_design_scores_gemma":[0.0000019648455,0.000034406705,0.0034911155,0.0000024838876,0.000012427019,0.0000074085483,0.0000105295785,0.99494666,0.0012884138,0.000116464216,0.00008409604,0.0000041938297],"about_ca_topic_score_codex":0.0068635475,"about_ca_topic_score_gemma":0.006059245,"teacher_disagreement_score":0.0068635475,"about_ca_system_score_codex":0.0003826713,"about_ca_system_score_gemma":0.00041114417,"threshold_uncertainty_score":0.013647139},"labels":[],"label_agreement":null},{"id":"W7131635173","doi":"10.5281/zenodo.18778729","title":"Machine Learning Models for Climate Prediction and Adaptation in Gabon","year":2003,"lang":"en","type":"article","venue":"Open MIND","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Climate change; Leverage (statistics); Random forest; Predictive modelling; Gradient boosting; Boosting (machine learning); Ensemble learning; Adaptation (eye)","score_opus":0.08383648068820242,"score_gpt":0.27708381318364594,"score_spread":0.1932473324954435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131635173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5750291,0.0024669054,0.41238508,0.0022252204,0.00012250239,0.00007354353,0.00058392924,0.0014010915,0.0057126516],"genre_scores_gemma":[0.95221096,0.00051639567,0.04398125,0.00006419833,0.00003773953,0.00008182418,0.0003128617,0.00003138624,0.0027634408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998355,0.0000774432,0.000010678688,0.000027885959,0.000022644977,0.000025838202],"domain_scores_gemma":[0.99941075,0.00040312982,0.00005037314,0.00002323206,0.000094915114,0.000017596503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011119621,0.000545698,0.00055371807,0.00059499126,0.0005216333,0.0010349783,0.0006415203,0.00062741287,0.00091801904],"category_scores_gemma":[0.0030347016,0.00025901053,0.00038113326,0.0006701183,0.00035281715,0.00071128726,0.00058900105,0.00080554455,0.00018559965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028497001,0.000010695981,0.0016345807,0.000012358805,0.000020385398,0.000018605742,0.000032012245,0.9826261,0.00018204638,0.0018864033,0.00022499847,0.0133233275],"study_design_scores_gemma":[0.0000018598657,0.0000029911766,0.00026840108,0.0000025254135,0.0000029425566,0.0000017169086,0.0000053989725,0.99813557,0.000076929,0.0013195853,0.0001802073,0.0000018255337],"about_ca_topic_score_codex":0.080996126,"about_ca_topic_score_gemma":0.087118626,"teacher_disagreement_score":0.080996126,"about_ca_system_score_codex":0.0015547933,"about_ca_system_score_gemma":0.0014501958,"threshold_uncertainty_score":0.16104937},"labels":[],"label_agreement":null},{"id":"W7131656214","doi":"10.5281/zenodo.18778730","title":"Machine Learning Models for Climate Prediction and Adaptation in Gabon","year":2003,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Climate change; Leverage (statistics); Random forest; Predictive modelling; Gradient boosting; Boosting (machine learning); Ensemble learning; Adaptation (eye)","score_opus":0.058168180684956376,"score_gpt":0.22770649985965408,"score_spread":0.1695383191746977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131656214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54198754,0.002813363,0.44587648,0.0020668558,0.00012817963,0.00007794755,0.0008547653,0.0017020717,0.004492769],"genre_scores_gemma":[0.940919,0.0006831198,0.054415114,0.00007774897,0.000049914284,0.00011985763,0.0005688676,0.000054608736,0.0031117362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99983287,0.00007699312,0.000010917936,0.000031210435,0.000023154218,0.000024799381],"domain_scores_gemma":[0.99943537,0.0003810602,0.000052184318,0.000023236511,0.000090782734,0.000017404007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010525892,0.00065001904,0.00068339234,0.00057219964,0.0005123238,0.000958684,0.0006935962,0.0007560073,0.0007773749],"category_scores_gemma":[0.0026300799,0.00031498942,0.00043916612,0.00072736834,0.0003373906,0.00059513014,0.00056091254,0.0008549682,0.00019906029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022937393,0.000007205398,0.0011460072,0.000009938359,0.00001705042,0.000012668778,0.000016801036,0.9892551,0.00016787431,0.0010453921,0.00018192716,0.008117124],"study_design_scores_gemma":[0.0000021337664,0.0000025606316,0.00023823733,0.0000018382045,0.0000026846863,0.000001330147,0.0000029503822,0.998722,0.00006869615,0.0008032892,0.00015245065,0.0000017803342],"about_ca_topic_score_codex":0.09018918,"about_ca_topic_score_gemma":0.08288451,"teacher_disagreement_score":0.09018918,"about_ca_system_score_codex":0.0015173184,"about_ca_system_score_gemma":0.0014864971,"threshold_uncertainty_score":0.17932844},"labels":[],"label_agreement":null},{"id":"W7132343873","doi":"","title":"Data driven study of estuary hypoxia","year":2021,"lang":"en","type":"article","venue":"NPARC","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hypoxia (environmental); Limiting; Estuary; Data-driven; Time series; Work (physics)","score_opus":0.060576763580498905,"score_gpt":0.28035660652712857,"score_spread":0.21977984294662967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132343873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9901029,0.00007717872,0.0029696978,0.00019104576,0.000016583146,0.000028152122,0.0055226367,0.00011985283,0.0009719445],"genre_scores_gemma":[0.9919457,0.00007101944,0.0030408944,0.000028474215,0.00000997035,0.000017015756,0.004392079,0.000015040689,0.00047979678],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978775,0.000040621562,0.000011517645,0.000041856267,0.00008606551,0.000032229473],"domain_scores_gemma":[0.9991025,0.00034182039,0.00007522147,0.00005886103,0.0003543926,0.0000671193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033957427,0.00029268587,0.00022889175,0.00075619394,0.00036122382,0.00047981605,0.00049787626,0.00037977882,0.00038932037],"category_scores_gemma":[0.0019137093,0.00013271655,0.00026798696,0.0014446169,0.00030852863,0.0002298102,0.00025075107,0.00046668656,0.00007626223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002894603,0.0005482027,0.44986045,0.00024839013,0.00030499784,0.0015479632,0.0007116883,0.46402383,0.022796473,0.003464969,0.0056289164,0.050574712],"study_design_scores_gemma":[0.000016278502,0.00006677095,0.37641838,0.000014171738,0.00003187632,0.00012599744,0.0005978324,0.6131515,0.005394871,0.00083420036,0.0033036005,0.000044552737],"about_ca_topic_score_codex":0.40711305,"about_ca_topic_score_gemma":0.41764745,"teacher_disagreement_score":0.40711305,"about_ca_system_score_codex":0.0019477514,"about_ca_system_score_gemma":0.001307317,"threshold_uncertainty_score":0.80948675},"labels":[],"label_agreement":null},{"id":"W7134062026","doi":"10.5281/zenodo.18894921","title":"Machine Learning Models for Climate Prediction and Adaptive Planning in Ghana: An Integrated Approach","year":2009,"lang":"en","type":"article","venue":"Open MIND","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Robustness (evolution); Climate change; Ensemble learning; Gradient boosting; Baseline (sea); Boosting (machine learning); Extreme learning machine","score_opus":0.08958371682290218,"score_gpt":0.29320643904836585,"score_spread":0.20362272222546368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134062026","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2758947,0.0027893994,0.7076979,0.0030183357,0.000108028304,0.000097305754,0.0006345063,0.00085689523,0.008902885],"genre_scores_gemma":[0.9057886,0.00083206705,0.09039094,0.000072517614,0.000054365733,0.0001252151,0.00024759254,0.000035235513,0.0024535963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985766,0.00007442536,0.00000745286,0.000020559077,0.00002229652,0.000017577882],"domain_scores_gemma":[0.9995561,0.00032501796,0.00003954966,0.000013712349,0.000051047937,0.000014539008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058398047,0.00044394808,0.00051566196,0.0004871536,0.00025197235,0.00071661366,0.0005115121,0.0006183709,0.0014499424],"category_scores_gemma":[0.0018662526,0.0002365155,0.00031943587,0.0006550246,0.00017438197,0.00076498534,0.00042961616,0.00068283046,0.00015902014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028789842,0.000021497404,0.002177984,0.00002775648,0.000034633053,0.000058915393,0.000035934456,0.9608934,0.000217964,0.0029813477,0.00056215504,0.03295956],"study_design_scores_gemma":[0.000003816735,0.0000070045085,0.0003101395,0.0000052049118,0.0000064742203,0.00000629308,0.000016494045,0.9965167,0.000080364895,0.0026147757,0.00043015697,0.0000025123359],"about_ca_topic_score_codex":0.025488866,"about_ca_topic_score_gemma":0.028126888,"teacher_disagreement_score":0.025488866,"about_ca_system_score_codex":0.0008939889,"about_ca_system_score_gemma":0.0010815983,"threshold_uncertainty_score":0.050680995},"labels":[],"label_agreement":null},{"id":"W7134067883","doi":"10.5281/zenodo.18894920","title":"Machine Learning Models for Climate Prediction and Adaptive Planning in Ghana: An Integrated Approach","year":2009,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Robustness (evolution); Climate change; Ensemble learning; Gradient boosting; Baseline (sea); Boosting (machine learning); Extreme learning machine","score_opus":0.06422603121641468,"score_gpt":0.2455761004581572,"score_spread":0.18135006924174252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134067883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23141001,0.003170045,0.7530405,0.0028796308,0.00010792988,0.00009923055,0.000827184,0.00092628365,0.007539242],"genre_scores_gemma":[0.890075,0.0010947267,0.10538749,0.00008470327,0.00006611769,0.00016055549,0.00038244625,0.000050901777,0.0026980005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998522,0.0000778439,0.000007621652,0.000022223458,0.000022484692,0.000017599426],"domain_scores_gemma":[0.9995771,0.00030698947,0.00003924836,0.000013709447,0.000049083148,0.000013942161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054351264,0.0004997808,0.0005810742,0.0004824295,0.00024537533,0.0006845209,0.00052625453,0.0007276249,0.0013746736],"category_scores_gemma":[0.0017099573,0.00026440315,0.00034051944,0.00070797116,0.00017278297,0.0007180643,0.00044166576,0.00070929853,0.00017538216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002472323,0.000016748048,0.0016797686,0.000025578916,0.000031936743,0.00004761262,0.000025834419,0.9702097,0.00019896588,0.0021891529,0.00051641796,0.02503358],"study_design_scores_gemma":[0.00000392051,0.000006490544,0.00028711747,0.0000048809165,0.000006507886,0.000006219375,0.000012580124,0.99701715,0.00007986388,0.0021265333,0.00044626644,0.0000025463528],"about_ca_topic_score_codex":0.025897428,"about_ca_topic_score_gemma":0.025737366,"teacher_disagreement_score":0.025897428,"about_ca_system_score_codex":0.0008636996,"about_ca_system_score_gemma":0.001076756,"threshold_uncertainty_score":0.051493406},"labels":[],"label_agreement":null},{"id":"W7134988802","doi":"10.1007/s13131-025-2569-y","title":"Forecasting of water temperature and salinity in a coastal strait region using machine learning techniques","year":2025,"lang":"en","type":"article","venue":"Acta Oceanologica Sinica","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ocean Networks Canada Society","funders":"","keywords":"Salinity; Temperature salinity diagrams; Artificial neural network; Sea surface temperature; Hydrology (agriculture); Air temperature","score_opus":0.0327423736796189,"score_gpt":0.25913884754150573,"score_spread":0.22639647386188683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134988802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9913994,0.00014247124,0.006764093,0.00017787059,0.000035175028,0.000011060432,0.0003413411,0.00012829427,0.0010002346],"genre_scores_gemma":[0.996314,0.00007265812,0.0029319269,0.0000061330875,0.000013580273,0.0000057926695,0.00029294292,0.0000036541853,0.00035940757],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99992967,0.000014598108,0.000007215755,0.000019517704,0.000016012595,0.000012950585],"domain_scores_gemma":[0.999571,0.00014603014,0.000074496464,0.000030014793,0.00013054154,0.000047906404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026152897,0.00039728335,0.00029474657,0.0006479788,0.00027301093,0.000539438,0.00043373115,0.00040069758,0.00031944807],"category_scores_gemma":[0.0009883633,0.00014222976,0.00040884773,0.0010208917,0.0002513013,0.00039377468,0.00020670294,0.00039116113,0.00009701859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000156696,0.00012781851,0.096284784,0.000045260073,0.00012183134,0.00026593774,0.00007928405,0.872104,0.0028452359,0.00050863496,0.00077945855,0.02668099],"study_design_scores_gemma":[0.0000074717636,0.000015906187,0.016537083,0.0000029388405,0.000011643665,0.00000896103,0.000028860317,0.9828248,0.00028376014,0.00015017562,0.0001224103,0.000005966271],"about_ca_topic_score_codex":0.13990134,"about_ca_topic_score_gemma":0.12356892,"teacher_disagreement_score":0.13990134,"about_ca_system_score_codex":0.0010206739,"about_ca_system_score_gemma":0.0009999983,"threshold_uncertainty_score":0.27817404},"labels":[],"label_agreement":null},{"id":"W73408484","doi":"","title":"Fuzzy Model: Time Dependent Dispersion in Rivers.","year":2009,"lang":"en","type":"article","venue":"Indian International Conference on Artificial Intelligence","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Dispersion (optics); Fuzzy logic; Computer science; Artificial intelligence; Physics; Optics","score_opus":0.06283129012735406,"score_gpt":0.3021028151528228,"score_spread":0.23927152502546872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W73408484","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13695963,0.001374344,0.839803,0.0021120827,0.00043611275,0.000064245396,0.0010116146,0.00041119507,0.017827831],"genre_scores_gemma":[0.94745517,0.000661351,0.0332175,0.00011078794,0.0001523895,0.000080096965,0.00046011194,0.000050617455,0.01781197],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980336,0.000054004508,0.000011032875,0.000048258044,0.000050278726,0.00003295976],"domain_scores_gemma":[0.9993254,0.0003687921,0.00005612184,0.000043179207,0.0001565936,0.000049988543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070610543,0.0004509806,0.00077756343,0.0005891198,0.0005780088,0.001313839,0.0018267201,0.0018511668,0.004248789],"category_scores_gemma":[0.0027407804,0.00028554516,0.0006705617,0.00078007,0.0004099952,0.0014373098,0.0005487838,0.0013904864,0.0005172195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006866823,0.00004415928,0.0012737269,0.000028783537,0.00004233667,0.00010570374,0.00006377733,0.9494155,0.00056560466,0.0318883,0.0018206848,0.0146826785],"study_design_scores_gemma":[0.0000033817576,0.00000699444,0.00011387356,0.0000027972753,0.0000048746424,0.000009276109,0.000006998376,0.99594057,0.000048112142,0.0036145328,0.00024547856,0.0000031294019],"about_ca_topic_score_codex":0.027970348,"about_ca_topic_score_gemma":0.017867139,"teacher_disagreement_score":0.027970348,"about_ca_system_score_codex":0.0009181796,"about_ca_system_score_gemma":0.00087839307,"threshold_uncertainty_score":0.055615067},"labels":[],"label_agreement":null},{"id":"W936250512","doi":"10.2166/wqrj.2009.024","title":"Temperature Impact of the Industrial Cooling Water Discharges in a Long Boat Slip of Hamilton Harbour","year":2009,"lang":"en","type":"article","venue":"Water Quality Research Journal","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada","funders":"National Water Research Institute","keywords":"Slip (aerodynamics); Environmental science; Water cooling; Air temperature; Water level; Thermal; Harbour; Heat transfer; Hydrology (agriculture); Atmospheric sciences; Meteorology; Geology; Mechanics; Geotechnical engineering; Thermodynamics; Geography","score_opus":0.12839478249272232,"score_gpt":0.4020742882508854,"score_spread":0.27367950575816313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W936250512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9995665,0.000006936929,0.000057176316,0.0000045695247,0.0000010862748,0.00000426372,0.00010257089,0.0000049300556,0.00025184487],"genre_scores_gemma":[0.99946326,0.000008639949,0.00011078515,0.0000043549007,0.0000010812657,0.0000046670407,0.000120784156,0.0000015891895,0.00028478133],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998938,0.0000069989896,0.0000040314967,0.000030457333,0.000036822392,0.00002785497],"domain_scores_gemma":[0.9998677,0.0000134238435,0.00003488328,0.000005719695,0.000044397675,0.000033843517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000075148244,0.00021798834,0.00023720381,0.00039514928,0.00068255654,0.00037600615,0.00024677458,0.00022469876,0.00074115023],"category_scores_gemma":[0.00015608263,0.00016553103,0.00020059293,0.000446589,0.00044140985,0.0001611879,0.00028887813,0.000234176,0.00011700366],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045645813,0.00011795764,0.87057686,0.000063333086,0.00006930669,0.0010446223,0.0018340101,0.0022574302,0.11325818,0.00006234994,0.00043133777,0.009828131],"study_design_scores_gemma":[0.0000035379305,0.00007294189,0.9956987,0.0000027438132,0.0000065820655,0.000024568764,0.00049927825,0.0011637266,0.0022974105,0.0000061779147,0.0002197323,0.0000046354976],"about_ca_topic_score_codex":0.19326389,"about_ca_topic_score_gemma":0.39281964,"teacher_disagreement_score":0.8067361,"about_ca_system_score_codex":0.0015850668,"about_ca_system_score_gemma":0.0007856221,"threshold_uncertainty_score":0.38427794},"labels":[],"label_agreement":null}]}