{"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,"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","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.005427252,0.0002522048,0.0003364556,0.0001465113,0.006109369,0.0001545028,0.001032433,0.0001646666,0.0004239134],"category_scores_gemma":[0.0008922081,0.0001905767,0.00004406585,0.001273154,0.01405221,0.0007260326,0.0008424158,0.0005271017,0.0008310581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000536777,"about_ca_system_score_gemma":0.00004398563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006825066,"about_ca_topic_score_gemma":0.0002199481,"domain_scores_codex":[0.9964966,0.0008565007,0.0003952692,0.0007704764,0.0005720055,0.0009091159],"domain_scores_gemma":[0.9986449,0.0004573278,0.0002707107,0.0003379289,0.00003504846,0.0002541165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003470684,0.0005489152,0.7529472,0.0002285102,0.00005567029,0.000112834,0.01716647,0.06384521,0.02532442,0.01828222,0.00009767598,0.1210438],"study_design_scores_gemma":[0.001520424,0.01463244,0.06194995,0.0003438625,0.00006303605,0.002351339,0.004732832,0.8640342,0.004424503,0.01298219,0.03115099,0.00181418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9140055,0.0002373775,0.0001110947,0.0002534708,0.0004023289,0.0001899661,0.000001285439,0.0002368939,0.08456203],"genre_scores_gemma":[0.9979796,0.0000188299,0.001341127,0.0004534749,0.00008170353,0.00001763752,0.00000189077,0.000007925409,0.00009774345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.800189,"threshold_uncertainty_score":0.9999469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02148488182457135,"score_gpt":0.2763075689827972,"score_spread":0.2548226871582259,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}