{"id":"W4414679246","doi":"10.1016/j.scitotenv.2025.180593","title":"Machine learning for air quality prediction and data analysis: Review on recent advancements, challenges, and outlooks","year":2025,"lang":"en","type":"review","venue":"The Science of The Total Environment","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario","funders":"International Development Research Centre; National Research Foundation; University of the Witwatersrand, Johannesburg","keywords":"Air quality index; Anomaly detection; Cluster analysis; Gradient boosting; Random forest; Reinforcement learning; Interpretability; Convolutional neural network","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":[0.001861742,0.001039904,0.001719099,0.002484252,0.0002831462,0.001484651,0.001163595,0.001395664,0.003663134],"category_scores_gemma":[0.003574009,0.0004532806,0.001227798,0.004007816,0.0005611454,0.002028847,0.0008683164,0.002054732,0.001757492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007055145,"about_ca_system_score_gemma":0.001970646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001875874,"about_ca_topic_score_gemma":0.002323911,"domain_scores_codex":[0.9994509,0.0001413033,0.00009045332,0.0001012612,0.0001797665,0.00003632247],"domain_scores_gemma":[0.9972185,0.002064245,0.0001908227,0.00006090765,0.0003993205,0.00006618118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005679017,0.00008291369,0.0003465838,0.03350921,0.000230894,0.00009715954,0.00008306849,0.001364185,0.0006712657,0.007731507,0.02334296,0.9324836],"study_design_scores_gemma":[0.00002241461,0.0001716571,0.001339697,0.01666558,0.0004577526,0.000519899,0.00009571273,0.0009552858,0.0004729494,0.007532799,0.9717106,0.00005566945],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000930179,0.998246,0.0004993409,0.000434136,0.0001664869,0.000005913561,0.00002517878,0.000009897667,0.0005201007],"genre_scores_gemma":[0.0006555322,0.9982674,0.0004809482,0.0001710994,0.0002185058,0.000007804387,0.00003608079,0.000002617744,0.0001599382],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.003663134,"threshold_uncertainty_score":0.01225436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1174184163994693,"score_gpt":0.3567292268380523,"score_spread":0.239310810438583,"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."}}