{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002876041,0.0003542749,0.0002987882,0.0005134536,0.0001945534,0.0004332429,0.0002136711,0.0005793229,0.0003211817],"category_scores_gemma":[0.0007483089,0.000118475,0.0003350753,0.0003895732,0.0001354313,0.0002930958,0.0001307366,0.0004149001,0.0001564179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003859742,"about_ca_system_score_gemma":0.0003518758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008744149,"about_ca_topic_score_gemma":0.01190741,"domain_scores_codex":[0.9998106,0.00002932563,0.00001167174,0.00006217616,0.00005850922,0.00002768441],"domain_scores_gemma":[0.9996672,0.0001437474,0.00007038286,0.00001588569,0.00008779494,0.0000149177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001470818,0.0007473103,0.2727133,0.0002307171,0.0002998514,0.0002338202,0.00009679971,0.115634,0.4832554,0.0002088109,0.000751201,0.1243581],"study_design_scores_gemma":[0.00001955115,0.0004156582,0.1180568,0.000007424463,0.00009516762,0.00012157,0.00008939335,0.7072515,0.1730866,0.0002108947,0.0006121938,0.00003322264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9965985,0.0000862669,0.002871602,0.00001742371,0.000007132859,0.000004484857,0.0001488531,0.00005572089,0.0002098793],"genre_scores_gemma":[0.9966312,0.00006517293,0.002452935,0.00001088214,0.000003662953,0.000003575208,0.0003130703,0.000005484132,0.0005141237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008744149,"threshold_uncertainty_score":0.0173865,"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."}}