{"id":"W4399082594","doi":"10.1016/j.chemosphere.2024.142476","title":"Predicting the Occurrence of Substituted and Unsubstituted, Polycyclic Aromatic Compounds in Coking Wastewater Treatment Plant Effluent using Machine Learning Regression","year":2024,"lang":"en","type":"article","venue":"Chemosphere","topic":"Water Quality Monitoring and Analysis","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Muscular Dystrophy Canada; University of Toronto","funders":"","keywords":"Effluent; Wastewater; Sewage treatment; Dissolved organic carbon; Support vector machine; Predictability; Environmental science; Environmental chemistry; Chemistry; Environmental engineering; Machine learning; Mathematics; Computer science; Statistics","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":[0.0002423104,0.0001585475,0.000202242,0.00001854755,0.0001515812,0.00006528833,0.0001129753,0.00004615759,0.00002776002],"category_scores_gemma":[0.00001839454,0.00009336968,0.00004995261,0.0002771745,0.0001442136,0.0001174626,0.00009260868,0.0001604508,0.000007328043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001770523,"about_ca_system_score_gemma":0.000009250092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003373791,"about_ca_topic_score_gemma":0.00007724494,"domain_scores_codex":[0.998963,0.00007847933,0.0002792274,0.0002749254,0.0002027624,0.0002016107],"domain_scores_gemma":[0.9996181,0.00009687857,0.00007449357,0.0001619324,0.000001165538,0.00004747292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000244054,0.00007904113,0.8022463,0.0001207396,0.00006474978,0.00004546731,0.005359533,0.009308794,0.1796429,0.000002753016,0.000011786,0.00309351],"study_design_scores_gemma":[0.0008407093,0.00008543686,0.02715954,0.002414812,0.0002456254,0.00008644345,0.001717531,0.595642,0.370144,0.0001069745,0.001126731,0.0004301462],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985521,0.001020907,0.0000190601,0.00007569951,0.0001208367,0.00009536591,0.000007933209,0.00004408231,0.00006405418],"genre_scores_gemma":[0.9995347,0.00006514287,0.0002575888,0.000002733621,0.0000268668,0.000005607137,0.00002305817,0.000008129221,0.00007617601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7750868,"threshold_uncertainty_score":0.5100185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02624612579743293,"score_gpt":0.259496122574252,"score_spread":0.2332499967768191,"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."}}