{"id":"W1982717852","doi":"10.5194/hess-8-940-2004","title":"Generalisation for neural networks through data sampling and training procedures, with applications to streamflow predictions","year":2004,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"Golder Associates (Canada); Université Laval","funders":"","keywords":"Boosting (machine learning); Artificial neural network; Computer science; Machine learning; Artificial intelligence; Streamflow; Training (meteorology); Bayesian probability; Perceptron; Stacking; Data mining; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007563513,0.001149129,0.0008265171,0.001109107,0.0005471746,0.0007573734,0.001142483,0.001246397,0.001488202],"category_scores_gemma":[0.01985909,0.0005860944,0.001090879,0.001059826,0.0006843155,0.001422512,0.001296407,0.002175184,0.0004776605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009911271,"about_ca_system_score_gemma":0.0007996808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009756588,"about_ca_topic_score_gemma":0.009915466,"domain_scores_codex":[0.998722,0.0007413077,0.00008267007,0.0001782431,0.0002118579,0.00006399798],"domain_scores_gemma":[0.9912189,0.006447723,0.0004246548,0.0005868798,0.001234321,0.00008756305],"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":[0.0001372143,0.0001024377,0.002716706,0.0001337415,0.0001045782,0.00006705408,0.0001368423,0.8263714,0.002009926,0.002821757,0.0008242709,0.164574],"study_design_scores_gemma":[0.000008153845,0.00003508629,0.000554287,0.00001532823,0.000009441545,0.00000945848,0.00001243035,0.9961879,0.001006441,0.001790463,0.0003647928,0.000006300665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0809893,0.001065682,0.9134061,0.0003692536,0.00006987761,0.0002509062,0.0001712649,0.00230581,0.001371731],"genre_scores_gemma":[0.499499,0.000582688,0.4970179,0.0001510978,0.00006152332,0.0004635115,0.0006345809,0.0002553492,0.001334416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009756588,"threshold_uncertainty_score":0.0400002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1000607176050327,"score_gpt":0.2941618640285655,"score_spread":0.1941011464235328,"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."}}