{"id":"W3096533615","doi":"10.1016/j.trd.2020.102599","title":"Potential of machine learning for prediction of traffic related air pollution","year":2020,"lang":"en","type":"article","venue":"Transportation Research Part D Transport and Environment","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":98,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Machine learning; Artificial neural network; Context (archaeology); Air quality index; Artificial intelligence; Computer science; Air pollution; Particulates; Black box; Particulate pollution; Meteorology; Geography","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":[0.0007396038,0.0001147142,0.0002232979,0.00004638027,0.0001722841,0.000001821713,0.00008021662,0.0001072277,0.0008619628],"category_scores_gemma":[0.00001060259,0.0001137019,0.00008117069,0.0001735785,0.0003683459,0.0001535658,0.000004002283,0.0002364749,0.00001060234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003739436,"about_ca_system_score_gemma":0.00001839495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001594062,"about_ca_topic_score_gemma":0.00006547497,"domain_scores_codex":[0.9981533,0.00008435247,0.0005846928,0.0002955885,0.000587159,0.0002949161],"domain_scores_gemma":[0.999489,0.00003887769,0.0001274938,0.00009055432,0.00001111337,0.0002429268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.001297645,0.0004136671,0.1448189,0.0007851776,0.00006906127,0.000007225027,0.01012975,0.8193706,0.01135729,0.0002616325,0.0004819409,0.01100707],"study_design_scores_gemma":[0.001546129,0.001210689,0.9524231,0.00003315278,0.000060548,4.79857e-7,0.0003871797,0.02193494,0.001612211,0.0001221958,0.02055253,0.0001168223],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885398,0.0001152766,0.005684272,0.004427668,0.00002440846,0.0007049239,0.0003973546,0.00002738554,0.00007893283],"genre_scores_gemma":[0.9978539,0.0007720861,0.0005900441,0.00009844147,0.00001887639,0.00003547016,0.0005247964,0.00001516911,0.00009121727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8076042,"threshold_uncertainty_score":0.9437888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06156756906355659,"score_gpt":0.3065006866479429,"score_spread":0.2449331175843864,"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."}}