{"id":"W2157041867","doi":"10.5194/hess-14-603-2010","title":"An experiment on the evolution of an ensemble of neural networks for streamflow forecasting","year":2010,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Ensemble learning; Artificial neural network; Confidence interval; Ensemble forecasting; Reliability (semiconductor); Computer science; Streamflow; Perceptron; Neural ensemble; Statistics; Artificial intelligence; Mathematics; Drainage basin","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":[0.001383458,0.00009259154,0.000156314,0.00002875087,0.000386159,0.00001525272,0.0002545107,0.00009266159,0.00003994142],"category_scores_gemma":[0.000058682,0.0000555688,0.00003062993,0.0001453276,0.001014154,0.0001328271,0.00004437677,0.0001001919,0.000001399156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009056524,"about_ca_system_score_gemma":0.000008193616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003753819,"about_ca_topic_score_gemma":0.0002763411,"domain_scores_codex":[0.9989377,0.0001368987,0.0002170489,0.0002920592,0.0001621289,0.0002541457],"domain_scores_gemma":[0.9993437,0.0002321063,0.000163673,0.0001851077,0.00000980179,0.00006561166],"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":[0.00011704,0.0001331239,0.02821855,0.00002074425,0.000006973089,0.000001900424,0.0008195222,0.8817197,0.07245456,0.006771252,0.0000125593,0.009724095],"study_design_scores_gemma":[0.0001063181,0.001539642,0.003193793,0.00001059189,0.000005783524,0.00002796197,0.0002554349,0.9912755,0.003231708,0.0002826932,0.0000104779,0.00006004418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975549,0.00001848551,0.0009078034,0.00006988912,0.0002163385,0.0002159453,0.000002577012,0.00002021514,0.0009938639],"genre_scores_gemma":[0.9983656,2.501827e-7,0.001535563,0.0000357762,0.00003888283,0.00001414005,9.539989e-7,0.000003445502,0.00000542328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1095559,"threshold_uncertainty_score":0.3736691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02715553531984586,"score_gpt":0.2480457906401564,"score_spread":0.2208902553203105,"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."}}