{"id":"W3167787884","doi":"10.5194/egusphere-egu21-13244","title":"Learning from one’s errors: A data-driven approach for mimicking an ensemble of hydrological model residuals","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Streamflow; Ensemble forecasting; Computer science; Gaussian; Calibration; Nonlinear system; Applied mathematics; Mathematics; Statistics; Artificial intelligence; Chemistry; Physics","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":[0.001795263,0.000466844,0.0004642663,0.0004466682,0.0002665079,0.001022924,0.001558438,0.001210516,0.0009170369],"category_scores_gemma":[0.005448719,0.0004022016,0.0008424741,0.0004562356,0.0008135786,0.001334571,0.001286264,0.001367343,0.0001428072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009479988,"about_ca_system_score_gemma":0.001016095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005229018,"about_ca_topic_score_gemma":0.005276759,"domain_scores_codex":[0.9995376,0.0001847369,0.00002947194,0.0001283343,0.0000878204,0.00003211074],"domain_scores_gemma":[0.9982672,0.0009460848,0.0002254298,0.0002457249,0.0002403499,0.00007523316],"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":[0.00001814255,0.00002433007,0.001452662,0.00001898467,0.00002531284,0.00004551034,0.00004976027,0.9677344,0.0008345903,0.01983621,0.0002112553,0.009748798],"study_design_scores_gemma":[0.000002048906,0.00000804087,0.0001019476,0.000002354348,0.000002805323,0.000004309134,0.000003300007,0.9960719,0.0002152182,0.003371779,0.0002128628,0.00000351297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04521305,0.00006546552,0.9523227,0.0003592196,0.00005174795,0.00003532277,0.000162431,0.0002260574,0.001563983],"genre_scores_gemma":[0.8342078,0.0001202889,0.1634769,0.0001511332,0.00005293032,0.0001317032,0.0002891484,0.00008280198,0.001487402],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005229018,"threshold_uncertainty_score":0.0103972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1175202524594818,"score_gpt":0.2912092209517997,"score_spread":0.1736889684923179,"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."}}