{"id":"W4394681151","doi":"10.1007/s00704-024-04932-8","title":"Hydrologic interpretation of machine learning models for 10-daily streamflow simulation in climate sensitive upper Indus catchments","year":2024,"lang":"en","type":"article","venue":"Theoretical and Applied Climatology","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"European Commission","keywords":"Indus; Streamflow; Environmental science; Drainage basin; Hydrology (agriculture); Interpretability; Hydrological modelling; Ecohydrology; Precipitation; Elevation (ballistics); Catchment hydrology; Climate change; Machine learning; Computer science; Climatology; Geology; Meteorology; Structural basin; Ecosystem; Geography; Cartography; Geomorphology; Mathematics","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":[0.0009755149,0.0003542544,0.0002705883,0.0005307457,0.0003339161,0.0008085096,0.0005507528,0.0005454269,0.001033954],"category_scores_gemma":[0.002366628,0.0001443325,0.0004826587,0.0003976583,0.0004210705,0.0005749193,0.0003198594,0.0005704337,0.00009294497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001243318,"about_ca_system_score_gemma":0.0006229601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03294347,"about_ca_topic_score_gemma":0.02052166,"domain_scores_codex":[0.9997748,0.0001248053,0.00001088894,0.00003291151,0.00002855984,0.00002808552],"domain_scores_gemma":[0.9985889,0.001001514,0.0001267751,0.00006696909,0.0001648361,0.0000509786],"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":[0.00002156452,0.00002145062,0.005102484,0.000005856985,0.000009511015,0.00003128733,0.00001509291,0.9923078,0.0001935255,0.0006394797,0.0001067749,0.00154516],"study_design_scores_gemma":[0.000001258316,0.000004700562,0.0007061102,8.828246e-7,9.669716e-7,0.000001836236,0.000005412347,0.9989663,0.0001025164,0.0001881164,0.0000204086,0.000001369461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829275,0.00003695365,0.01424683,0.0001852525,0.00001113539,0.00001500449,0.0001949579,0.0001924675,0.002189825],"genre_scores_gemma":[0.9980715,0.00001132346,0.001616613,0.000008257672,0.00000274115,0.00000594927,0.0000877422,0.000006157468,0.0001897702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03294347,"threshold_uncertainty_score":0.06550342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00895614136215751,"score_gpt":0.2443350653031113,"score_spread":0.2353789239409538,"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."}}