{"id":"W4409202904","doi":"10.1016/j.scitotenv.2025.179286","title":"Traffic-related air pollution backcasting using convolutional neural network and long short-term memory approach","year":2025,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; McGill University; Hudbay Minerals (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Health Effects Institute","keywords":"Backcasting; Term (time); Convolutional neural network; Environmental science; Computer science; Air pollution; Artificial intelligence; Ecology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002973551,0.0005490386,0.0004645995,0.0005088018,0.0002404332,0.000445436,0.0008317675,0.0006165527,0.0008497743],"category_scores_gemma":[0.0007291683,0.0002424473,0.0005962455,0.0005350334,0.0001840936,0.0006251312,0.0004163186,0.0009432579,0.0002456822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004267394,"about_ca_system_score_gemma":0.0007171743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.031587,"about_ca_topic_score_gemma":0.02644121,"domain_scores_codex":[0.9999077,0.000008260212,0.000005608446,0.00002716894,0.00002590773,0.00002538154],"domain_scores_gemma":[0.9998148,0.00004670029,0.00001933193,0.00002235535,0.00008141453,0.00001544575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002936039,0.0002086339,0.004301029,0.00006496211,0.000136562,0.0001222374,0.00003289948,0.8087876,0.012008,0.002064658,0.00216434,0.1698155],"study_design_scores_gemma":[0.000002546068,0.000004035453,0.0003272622,9.935757e-7,0.000007074367,0.000003054859,0.000001703223,0.9986916,0.000686385,0.0001887888,0.00008438819,0.000002240972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3259696,0.001499581,0.6641604,0.0005295854,0.0007600121,0.00004130997,0.0006432398,0.00174517,0.004651234],"genre_scores_gemma":[0.9623626,0.0004018605,0.03252881,0.00006647311,0.0001275658,0.00001843086,0.0006665355,0.00004229771,0.003785358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.031587,"threshold_uncertainty_score":0.06280631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02304868306335488,"score_gpt":0.2361420183585752,"score_spread":0.2130933352952203,"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."}}