{"id":"W2901899013","doi":"10.1016/j.envpol.2018.11.034","title":"Evaluation of random forest regression and multiple linear regression for predicting indoor fine particulate matter concentrations in a highly polluted city","year":2018,"lang":"en","type":"article","venue":"Environmental Pollution","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":158,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; BC Centre for Disease Control; Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Particulates; Linear regression; Environmental science; Regression analysis; Regression dilution; Regression; Random forest; Statistics; Bayesian multivariate linear regression; Mathematics; Ecology; Computer science; Machine learning; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001209419,0.000144554,0.0001658954,0.00004225528,0.000238447,0.00001035132,0.00006303952,0.00009926849,0.0001756491],"category_scores_gemma":[0.0001815686,0.0001215643,0.00004402132,0.0001033745,0.0003237943,0.0002549044,0.000095772,0.00008975006,0.00002007808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002942694,"about_ca_system_score_gemma":0.000008257239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000177323,"about_ca_topic_score_gemma":0.0001699344,"domain_scores_codex":[0.9984027,0.0001970421,0.0003879928,0.0003067848,0.0004628815,0.0002426173],"domain_scores_gemma":[0.9994524,0.00008198809,0.0002306014,0.0001565764,0.000008175173,0.00007025166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002280416,0.0001118076,0.9032769,0.000008315955,0.00000871027,2.613143e-7,0.0009373011,0.003107801,0.08488151,0.000001936209,0.00007992432,0.007357487],"study_design_scores_gemma":[0.003080136,0.0001262176,0.7096655,0.000114653,0.00004778798,0.00000246063,0.0001413276,0.2501671,0.03633781,0.0001333933,0.00007028801,0.0001133278],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974078,0.00005358646,0.001323782,0.0002113752,0.0001462963,0.0007029262,0.00005091441,0.00001783936,0.0000855082],"genre_scores_gemma":[0.9984491,0.000005649992,0.001221202,0.00002262249,0.0001291911,0.0000413384,0.00004565523,0.00001331215,0.0000718902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2470593,"threshold_uncertainty_score":0.495725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03490814752223052,"score_gpt":0.2868460557212793,"score_spread":0.2519379081990488,"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."}}