{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001236861,0.0002340556,0.0002370271,0.00007488891,0.0004088038,0.00005595054,0.0003303593,0.0001365893,0.0001775289],"category_scores_gemma":[0.00003642149,0.0001913745,0.0001088549,0.0001688646,0.0001792432,0.0005652933,0.0001906399,0.00008616582,0.0001302271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005966866,"about_ca_system_score_gemma":0.00006325783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004141966,"about_ca_topic_score_gemma":0.00009961426,"domain_scores_codex":[0.9977894,0.0001464085,0.0004476455,0.000654179,0.0004463355,0.0005160394],"domain_scores_gemma":[0.9992052,0.00004270312,0.0001539949,0.0004449727,0.000002876661,0.0001502122],"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":[0.002969679,0.001029436,0.03628417,0.0003246208,0.00009508731,0.000001276987,0.002115923,0.8753262,0.06537347,0.0002717707,0.01047511,0.005733212],"study_design_scores_gemma":[0.006649506,0.0001135669,0.01398447,0.00001303506,0.00007168811,0.000002833101,0.0003985433,0.9592301,0.00885826,0.002071819,0.00817393,0.0004322218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3396519,0.000006446104,0.6552398,0.001445056,0.0001660059,0.002726204,0.0005367788,0.0001381429,0.0000896092],"genre_scores_gemma":[0.9852985,0.000001795405,0.009447674,0.0003080607,0.0001620001,0.0002660292,0.003796689,0.00003842478,0.0006808134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6457921,"threshold_uncertainty_score":0.7804025,"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."}}