{"id":"W2111960238","doi":"10.5194/hess-10-485-2006","title":"Clustering of heterogeneous precipitation fields for the assessment and possible improvement of lumped neural network models for streamflow forecasts","year":2006,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Coquitlam College; Université Laval; Golder Associates (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Precipitation; Cluster analysis; Orography; Artificial neural network; Streamflow; Environmental science; Surface runoff; Self-organizing map; Watershed; Computer science; Rain gauge; Perceptron; Multilayer perceptron; Meteorology; Machine learning; Geography; Drainage basin","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":[0.0007810486,0.00008724914,0.0001716828,0.00001839839,0.0003170758,0.00001953716,0.0001183358,0.00006574502,0.000005987214],"category_scores_gemma":[0.00000915606,0.00005604312,0.00003795707,0.00008144061,0.0004160113,0.00009143929,0.00007856719,0.00003416235,1.152509e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009060605,"about_ca_system_score_gemma":0.000008214694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000251397,"about_ca_topic_score_gemma":0.000408364,"domain_scores_codex":[0.9990885,0.00003933621,0.0002665086,0.0002421092,0.0001228964,0.0002406804],"domain_scores_gemma":[0.9994033,0.000334066,0.0001374768,0.00008670551,0.00001174615,0.00002669278],"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":[0.00003067905,0.00001216667,0.005685914,0.00005200236,0.000006610754,1.807564e-7,0.00008065774,0.98423,0.0007815519,0.0001979764,0.0000138904,0.008908345],"study_design_scores_gemma":[0.0002486795,0.00103457,0.003259581,0.0000189784,0.00001993142,0.00001246946,0.00003080884,0.9932233,0.0003900479,0.001694944,0.00001070214,0.00005599554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9586573,0.0001008027,0.04010764,0.0001423483,0.0001541061,0.0005510894,0.000008871917,0.0000109757,0.0002668825],"genre_scores_gemma":[0.9931833,0.000004101993,0.006659597,0.00003469876,0.00003534749,0.00005536655,0.000001930879,0.000003291432,0.00002236078],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03452602,"threshold_uncertainty_score":0.2438722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0255196953726457,"score_gpt":0.2580244808052393,"score_spread":0.2325047854325936,"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."}}