{"id":"W4312971753","doi":"10.1039/d2ea00084a","title":"Application of machine learning and statistical modeling to identify sources of air pollutant levels in Kitchener, Ontario, Canada","year":2022,"lang":"en","type":"article","venue":"Environmental Science Atmospheres","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Continental (Canada); Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Pollutant; Environmental science; Air pollutants; Meteorology; Air pollution; Geography; Ecology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007267693,0.0001021105,0.0001684273,0.00001193755,0.0003255252,0.000006675336,0.0002646283,0.00001802242,0.002443851],"category_scores_gemma":[0.0000357452,0.0001042766,0.00001255511,0.0002736765,0.0003694902,0.0001559811,0.0005726887,0.0001829749,0.000003993179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269443,"about_ca_system_score_gemma":0.0001499887,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9242432,"about_ca_topic_score_gemma":0.7995625,"domain_scores_codex":[0.9981027,0.000072741,0.0003417542,0.000342456,0.0008180177,0.0003223523],"domain_scores_gemma":[0.9994989,0.00005264345,0.0001187694,0.0001316624,0.000001224551,0.0001968115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003249293,0.00008922523,0.6424339,0.000009396163,0.000001770609,0.000003306749,0.002795288,0.3137916,0.02711175,0.00008566221,0.00002147387,0.0136241],"study_design_scores_gemma":[0.0002172014,0.0001630055,0.8669699,0.000006405739,0.000004370366,0.000005960711,0.002569749,0.1262887,0.002005826,0.0002857562,0.00133335,0.0001497313],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943486,0.00006237073,0.004881249,0.0002487482,0.00002882401,0.0002076324,0.00005661618,0.000004314391,0.0001615914],"genre_scores_gemma":[0.9944192,0.000005144179,0.00514165,0.0003018737,0.000003151938,0.00001551944,0.000003432365,0.000006556851,0.00010349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.224536,"threshold_uncertainty_score":0.998468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647046729034847,"score_gpt":0.274190913781408,"score_spread":0.2577204464910596,"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."}}