{"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,"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","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.002253814,0.0001106448,0.0001617839,0.00004450454,0.0001006266,0.00003987399,0.0002056972,0.00005765181,0.0003263511],"category_scores_gemma":[0.00003090577,0.00009010884,0.00001231812,0.00009851411,0.0006489859,0.0006685839,0.0002405083,0.00005243788,0.00001960088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003711182,"about_ca_system_score_gemma":0.00001194511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004344083,"about_ca_topic_score_gemma":0.0001271764,"domain_scores_codex":[0.9982707,0.0001106913,0.000247741,0.0005228307,0.0006431843,0.000204866],"domain_scores_gemma":[0.9995746,0.0000669605,0.0001065019,0.0001931486,0.000003108185,0.00005569297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000388592,0.000142165,0.1961463,0.0000265002,0.00001188862,5.354881e-7,0.0006564473,0.74791,0.03712065,0.000118146,0.00002824345,0.01780026],"study_design_scores_gemma":[0.0006324446,0.0003450285,0.1163428,0.00002030002,0.00001881237,0.000005935493,0.000116274,0.8815522,0.0002018871,0.000553425,0.0001203547,0.00009052304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975123,0.0000881403,0.000401485,0.00005132668,0.00009351387,0.0007338002,0.0001050562,0.00001045798,0.001003919],"genre_scores_gemma":[0.9981596,0.00001370684,0.001573492,0.00002048926,0.00001071327,0.00001837139,0.00003442314,0.00000504565,0.0001641432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1336422,"threshold_uncertainty_score":0.3674532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1220507468108173,"score_gpt":0.2800154020876894,"score_spread":0.1579646552768721,"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."}}