{"id":"W4322004835","doi":"10.5194/egusphere-egu23-8746","title":"A large sample study of the effects of upstream hydrometeorological input features for LSTM-based daily flow forecasting in Canadian catchments","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Hydrometeorology; Upstream (networking); Computer science; Surface runoff; Sample (material); Environmental science; Upstream and downstream (DNA); Hydrology (agriculture); Meteorology; Precipitation; Geography; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001882841,0.0006633226,0.0004547453,0.0004672766,0.001172694,0.0006123179,0.001093625,0.0005394609,0.001040847],"category_scores_gemma":[0.007861607,0.0002151815,0.0006546096,0.001097244,0.0007336718,0.0005892175,0.0005261879,0.0009061115,0.0001520091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007663865,"about_ca_system_score_gemma":0.005978097,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9228905,"about_ca_topic_score_gemma":0.9312963,"domain_scores_codex":[0.9994943,0.0001230945,0.00002205305,0.0001276601,0.0001263281,0.0001065761],"domain_scores_gemma":[0.997295,0.001293726,0.0001070368,0.000195568,0.0008911692,0.0002175157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00237904,0.0009337311,0.3298722,0.0003028358,0.0005634904,0.000528108,0.0009513078,0.4603549,0.00766333,0.002703187,0.01568291,0.1780649],"study_design_scores_gemma":[0.0001247244,0.0002164539,0.2568018,0.0000350837,0.00016617,0.00005255824,0.0008614102,0.7333757,0.003702629,0.0007250741,0.003857654,0.00008073211],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957417,0.0001739269,0.001742325,0.0003356205,0.00001607951,0.00003219384,0.001049478,0.00009594252,0.0008128971],"genre_scores_gemma":[0.9935862,0.0001109523,0.002584175,0.0000712094,0.00001087255,0.00001744737,0.002841481,0.00001972802,0.0007579478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07710946,"threshold_uncertainty_score":0.1551271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02253947094995154,"score_gpt":0.2512325113581749,"score_spread":0.2286930404082233,"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."}}