{"id":"W4319319781","doi":"10.1016/j.envpol.2023.121222","title":"Proposal for a new customization process for a data-based water quality index using a random forest approach","year":2023,"lang":"en","type":"article","venue":"Environmental Pollution","topic":"Water Quality and Pollution Assessment","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"National Research Foundation of Korea; Ministry of Education","keywords":"Water quality; Random forest; Watershed; Environmental science; Index (typography); Hydrology (agriculture); Computer science; Statistics; Mathematics; Machine learning; Ecology; Engineering","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":[0.003410863,0.0009443284,0.001127873,0.002727385,0.0008972634,0.001995165,0.001691127,0.0009954723,0.00313358],"category_scores_gemma":[0.007770077,0.0006091258,0.001647332,0.001688887,0.0006247108,0.002096349,0.001737046,0.001628809,0.002063176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004661726,"about_ca_system_score_gemma":0.001500094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005634749,"about_ca_topic_score_gemma":0.005058957,"domain_scores_codex":[0.9970064,0.0003848278,0.0002923692,0.0009802255,0.001108635,0.0002276153],"domain_scores_gemma":[0.9954921,0.0010321,0.000269118,0.0008215351,0.002201995,0.0001831179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002892854,0.0004697336,0.006119365,0.0002322473,0.0002685991,0.0003155784,0.0002483768,0.04512688,0.09865436,0.01097294,0.005933632,0.8313691],"study_design_scores_gemma":[0.0001054145,0.0001736964,0.00695808,0.00004517879,0.0001686204,0.0004096595,0.0001040667,0.9041988,0.05905522,0.01150867,0.01710871,0.0001639539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002452997,0.00001959425,0.9946474,0.00003072658,0.00001978193,0.0001020001,0.00007922868,0.002405425,0.000242901],"genre_scores_gemma":[0.05011222,0.00003439123,0.9476258,0.00004770417,0.00004526569,0.0002227297,0.0005930123,0.0004322326,0.000886669],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005634749,"threshold_uncertainty_score":0.01803857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09393405478191114,"score_gpt":0.3445857654593867,"score_spread":0.2506517106774756,"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."}}