{"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,"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","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001681919,0.0003528213,0.0003126485,0.00004061927,0.0002120275,0.0001143913,0.0002738225,0.0001478691,0.001084852],"category_scores_gemma":[0.0000138355,0.0003064698,0.0000816663,0.0002906804,0.0001014862,0.0002003087,0.0001752191,0.0003560682,0.0000417461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001271322,"about_ca_system_score_gemma":0.000005488857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001473867,"about_ca_topic_score_gemma":0.000005410731,"domain_scores_codex":[0.9982296,0.00003735295,0.0003336592,0.0005045567,0.0002410167,0.0006537836],"domain_scores_gemma":[0.9993318,0.00008045938,0.00006987132,0.0002740364,0.000007080545,0.000236768],"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":[0.000009925431,0.00000668317,0.009526055,0.00004626169,0.000009857833,0.00005902936,0.0000479939,0.9483323,0.0001791396,0.00001411577,0.0005005634,0.04126808],"study_design_scores_gemma":[0.0003074022,0.0001054557,0.0674798,0.0001317032,0.00001487594,0.0002118136,5.747997e-7,0.9298908,0.0000359531,0.00002723166,0.001475852,0.0003185558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9436392,0.00007198062,0.05344856,0.00003806113,0.0004668268,0.0001522827,0.00000284669,0.000419545,0.00176071],"genre_scores_gemma":[0.9873807,0.000002356377,0.01174904,0.0002716829,0.0005030861,0.000006531272,0.00001021187,0.00004025583,0.00003606725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05795375,"threshold_uncertainty_score":0.9999387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006439691324542921,"score_gpt":0.1745177948863353,"score_spread":0.1680781035617924,"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."}}