{"id":"W4408428122","doi":"10.5194/egusphere-egu25-13060","title":"Comparing deep-learning and semi-distributed models for flow forecasting at fine spatial and temporal resolutions: a case study of 40 urbanized catchments in Toronto, Canada.","year":2025,"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":"Deep learning; Flow (mathematics); Computer science; Environmental science; Geography; Artificial intelligence; Mathematics","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":[0.0004873043,0.0007912095,0.000269809,0.0005715297,0.0007978551,0.0009186661,0.0009818167,0.0006616728,0.001169673],"category_scores_gemma":[0.001507188,0.0002236288,0.0004205782,0.00122529,0.0006514274,0.0005901479,0.0004654106,0.0006926909,0.0001614586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01488167,"about_ca_system_score_gemma":0.007068904,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9742673,"about_ca_topic_score_gemma":0.9738339,"domain_scores_codex":[0.9998017,0.00002952196,0.00001114353,0.000058204,0.00004018354,0.00005929975],"domain_scores_gemma":[0.9994849,0.0001978138,0.00003629732,0.00003335394,0.0001673771,0.00008016852],"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":[0.0003831153,0.0002348696,0.08592595,0.0002069144,0.0001621925,0.0006696759,0.0007111056,0.8477536,0.002410203,0.001882216,0.007958365,0.05170188],"study_design_scores_gemma":[0.00004820752,0.00003875375,0.06558913,0.00002956967,0.0000421389,0.00003484916,0.0009724121,0.9293919,0.001149302,0.0005514041,0.002115816,0.00003662383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886388,0.0005679319,0.003933907,0.0007112361,0.00003049771,0.00006142497,0.002664231,0.000397318,0.002994683],"genre_scores_gemma":[0.9943722,0.0001895805,0.002233417,0.00004139503,0.000007021678,0.00001077839,0.001914014,0.00002429543,0.00120736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0257327,"threshold_uncertainty_score":0.1079746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02955662325242684,"score_gpt":0.2571719295472747,"score_spread":0.2276153062948479,"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."}}