{"id":"W4408195755","doi":"10.1016/j.trd.2025.104688","title":"Real-time air quality prediction using traffic videos and machine learning","year":2025,"lang":"en","type":"article","venue":"Transportation Research Part D Transport and Environment","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; University of Victoria","keywords":"Air quality index; Computer science; Quality (philosophy); Artificial intelligence; Machine learning; Real-time computing; Meteorology; Geography; Physics","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":[0.001611937,0.0001943483,0.0002377195,0.00009393301,0.0006502684,0.00001838923,0.00008926343,0.0001196607,0.0004831205],"category_scores_gemma":[0.000009997509,0.0001955701,0.00005507073,0.0002214536,0.0004881455,0.0002209213,0.00001396013,0.0003983673,0.00002553229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001327506,"about_ca_system_score_gemma":0.00001475915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00168955,"about_ca_topic_score_gemma":0.0001616351,"domain_scores_codex":[0.997699,0.0001958425,0.0004965789,0.0005603342,0.0006165659,0.0004316762],"domain_scores_gemma":[0.9994366,0.0001260366,0.00006743984,0.00017527,0.000008355359,0.0001862522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000164888,0.000157428,0.9027658,0.0001429663,0.00004640389,0.00001506926,0.002315914,0.06605348,0.01316683,0.00009956427,0.00004591975,0.01502577],"study_design_scores_gemma":[0.0006393342,0.0001156955,0.9762296,0.00007952083,0.00005159005,0.000001000456,0.0003642412,0.01223935,0.0005891599,0.0001271069,0.009357976,0.0002054509],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972171,0.0001013563,0.001163126,0.0002808174,0.00004483875,0.0003573442,0.00005328682,0.00008637176,0.0006957755],"genre_scores_gemma":[0.9960208,0.001157462,0.0009310445,0.00001497524,0.00003461634,0.00004009832,0.000152027,0.00001886499,0.001630121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07346381,"threshold_uncertainty_score":0.7975116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06993699846159576,"score_gpt":0.3295432473948642,"score_spread":0.2596062489332684,"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."}}