{"id":"W1776911451","doi":"10.1029/2003wr002816","title":"Artificial neural network ensembles and their application in pooled flood frequency analysis","year":2004,"lang":"en","type":"article","venue":"Water Resources Research","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":205,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Computer science; Artificial intelligence; Generalization; Ensemble learning; Boosting (machine learning); Ensemble forecasting; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.001285795,0.0001140976,0.0002078148,0.0002395586,0.0003131372,0.00005933049,0.0002656271,0.0001103914,0.0002730322],"category_scores_gemma":[0.00001868877,0.00007487839,0.00007346772,0.001381589,0.0003701479,0.0001101264,0.0002482054,0.0003084134,0.0003049482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008089988,"about_ca_system_score_gemma":0.000003424347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005978371,"about_ca_topic_score_gemma":0.01595454,"domain_scores_codex":[0.9981064,0.0003158649,0.0002345082,0.0004414385,0.0003082592,0.0005935053],"domain_scores_gemma":[0.999498,0.00006165246,0.00002198962,0.0003064199,0.00001033741,0.0001015775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009069403,0.0001443224,0.6627213,0.000005805948,0.0001892486,0.00003303439,0.008884547,0.2795206,0.03997362,0.0001159957,0.00003091577,0.008289875],"study_design_scores_gemma":[0.001265248,0.0004322829,0.6087644,0.00002032447,0.0003984423,0.00002160078,0.001432669,0.1465902,0.0510767,0.1817396,0.007248901,0.001009583],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967672,0.0001247931,0.0003739752,0.001237546,0.000006870318,0.0001564447,0.000001593892,0.0000283022,0.001303324],"genre_scores_gemma":[0.9995549,0.00001507558,0.0001180099,0.00006926578,0.0000738328,0.00004439924,0.00001776768,0.00001074173,0.00009600135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1816236,"threshold_uncertainty_score":0.9037549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02093775302569431,"score_gpt":0.2774856757709578,"score_spread":0.2565479227452635,"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."}}