{"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,"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","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001164903,0.0001600156,0.0002252049,0.0002031262,0.0005974969,0.0002307789,0.0003171995,0.0001397138,0.0005255104],"category_scores_gemma":[0.00006926988,0.000112381,0.00009318634,0.0009497142,0.0005984826,0.0001433351,0.0002805103,0.0004612048,0.0001036509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001468551,"about_ca_system_score_gemma":0.000002695374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000573729,"about_ca_topic_score_gemma":0.0001095703,"domain_scores_codex":[0.9970285,0.0003875478,0.0002643247,0.0005820582,0.0008056887,0.0009318878],"domain_scores_gemma":[0.9993007,0.00009216007,0.00003380172,0.0003145978,0.00002589508,0.0002328565],"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":[0.00009390434,0.0001804545,0.01177574,0.000003803208,0.00004178,0.0001101877,0.001757752,0.8291157,0.138747,0.00001003443,0.0002404853,0.0179232],"study_design_scores_gemma":[0.0001031587,0.0002728853,0.005539407,0.000009393908,0.0000351795,0.00002304834,0.00002308486,0.9883823,0.002489844,0.002248482,0.0006749001,0.0001983526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968954,0.00005623511,0.0008608644,0.0008401747,0.00002321782,0.0001300522,0.000001231405,0.00007348336,0.001119315],"genre_scores_gemma":[0.9978792,0.00000266835,0.001504968,0.0002121821,0.0001537501,0.000002753743,0.000009860659,0.00001654644,0.0002180557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1592666,"threshold_uncertainty_score":0.575397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09425411509377377,"score_gpt":0.3154021896202334,"score_spread":0.2211480745264596,"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."}}