{"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,"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","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001089949,0.0002300709,0.0004610103,0.00008282351,0.0002879472,0.00004919733,0.0004083365,0.0001939446,0.001084593],"category_scores_gemma":[0.0001210899,0.0001680636,0.0001191111,0.0003928794,0.0004402684,0.0003230765,0.00008683301,0.0008143366,0.00001331448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001202655,"about_ca_system_score_gemma":0.00002697931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006460836,"about_ca_topic_score_gemma":0.00003663661,"domain_scores_codex":[0.9976645,0.0002688222,0.0006744216,0.0003048657,0.0004038681,0.0006835757],"domain_scores_gemma":[0.9989755,0.0001460473,0.0004465732,0.0001977127,0.00002247277,0.0002116543],"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":[0.000483169,0.0000725645,0.00625881,0.000002281167,0.00002479121,0.0002268665,0.0004500777,0.9715375,0.0007621635,0.000005680143,0.00004556752,0.02013058],"study_design_scores_gemma":[0.0005101276,0.0009433444,0.001150095,0.00001691938,0.00005231939,0.00379647,0.00003449682,0.9923068,0.00002613469,0.0004481162,0.0005259478,0.0001892556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990133,0.00003378479,0.005700041,0.0003085783,0.0001420033,0.00009905145,7.627143e-7,0.00002903568,0.003553706],"genre_scores_gemma":[0.9803312,0.000002269927,0.01870173,0.0004705826,0.0004098017,0.000001530486,0.000001595495,0.00003000177,0.0000512251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02076933,"threshold_uncertainty_score":0.9998286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07284336732487058,"score_gpt":0.2531215800790667,"score_spread":0.1802782127541961,"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."}}