{"id":"W4406580365","doi":"10.1016/j.watres.2025.123156","title":"Establishing performance criteria for evaluating watershed-scale sediment and nutrient models at fine temporal scales","year":2025,"lang":"en","type":"review","venue":"Water Research","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Watershed; Environmental science; Sediment; Scale (ratio); Nutrient; Temporal scales; Hydrology (agriculture); Geology; Computer science; Geomorphology; Ecology; Geotechnical engineering; Geography; Cartography; Machine learning","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":[0.06255727,0.001774167,0.001941165,0.006282095,0.000833382,0.004155103,0.002732423,0.002141565,0.001413751],"category_scores_gemma":[0.132266,0.0006166103,0.004787909,0.004649102,0.001361341,0.003828388,0.002843227,0.00193724,0.0003151171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002586549,"about_ca_system_score_gemma":0.002893228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01217994,"about_ca_topic_score_gemma":0.009335635,"domain_scores_codex":[0.977191,0.01350173,0.002964288,0.00209829,0.003780695,0.0004640222],"domain_scores_gemma":[0.8556774,0.1191039,0.008141063,0.008498034,0.007833756,0.000745817],"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":[0.001000983,0.000333141,0.09959792,0.003227266,0.006136494,0.0001441053,0.000248097,0.8124955,0.001411174,0.01044235,0.007621667,0.0573413],"study_design_scores_gemma":[0.0003574627,0.001130324,0.04994231,0.001239239,0.001918032,0.0001254012,0.0006180718,0.8994523,0.00589167,0.02809332,0.0109972,0.0002346063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"review","genre_scores_codex":[0.5791294,0.0169644,0.3440532,0.003725598,0.0004798079,0.001632606,0.03658361,0.002234935,0.01519633],"genre_scores_gemma":[0.8567166,0.002176219,0.1116481,0.0005287768,0.0001418695,0.001239674,0.02652005,0.0004107383,0.0006178476],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.06255727,"threshold_uncertainty_score":0.3308384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1515011388516302,"score_gpt":0.4111818766521916,"score_spread":0.2596807378005614,"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."}}