{"id":"W4407138366","doi":"10.22541/essoar.173867517.78974393/v1","title":"Evaluating the Functional Realism of Deep Learning Rainfall-Runoff Models Using Catchment Hydrology Principles","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":"Global Institute for Water Security; University of Saskatchewan; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Surface runoff; Hydrology (agriculture); Catchment hydrology; Drainage basin; Environmental science; Geology; Geography; Geotechnical engineering; Cartography; Ecology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002331091,0.0005186188,0.0002654851,0.000405795,0.0001975916,0.000732533,0.00069264,0.0006328467,0.0007036217],"category_scores_gemma":[0.004618768,0.0002549974,0.0005067137,0.0002252677,0.0006251631,0.001054263,0.0007785892,0.0007424898,0.00005966362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001150724,"about_ca_system_score_gemma":0.0006728701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009747425,"about_ca_topic_score_gemma":0.006669101,"domain_scores_codex":[0.9997662,0.00009307039,0.0000167121,0.00004786337,0.00004359264,0.00003257316],"domain_scores_gemma":[0.9985175,0.00105549,0.0001276132,0.0001053961,0.0001263788,0.00006759631],"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":[0.00003307121,0.00001964608,0.003655137,0.00001432678,0.00002723888,0.00001849068,0.00002420344,0.989592,0.0007802668,0.001847301,0.00006894011,0.003919333],"study_design_scores_gemma":[0.000002226214,0.00001199725,0.0004728223,0.000001754331,0.000002742966,0.000002374108,0.000005062615,0.998204,0.0001856134,0.001078031,0.00003190609,0.000001453556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8364661,0.0001834667,0.1589933,0.0007447863,0.00002419931,0.00005047453,0.0003604572,0.0004805676,0.002696617],"genre_scores_gemma":[0.9931994,0.00003085308,0.00641569,0.0000358302,0.000006382622,0.00001347242,0.0001216623,0.00001267888,0.0001639848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009747425,"threshold_uncertainty_score":0.01938134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09730085765135571,"score_gpt":0.3239499740431266,"score_spread":0.2266491163917709,"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."}}