{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005262509,0.0002864078,0.00078188,0.00005529022,0.0005553517,0.00001736534,0.001104727,0.00006226254,0.00002737471],"category_scores_gemma":[0.0004876908,0.0001563403,0.000155048,0.0003669428,0.001022294,0.0001395246,0.00244618,0.0003114007,0.000004299209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002441054,"about_ca_system_score_gemma":0.00002867593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003870449,"about_ca_topic_score_gemma":0.000001611542,"domain_scores_codex":[0.997089,0.0003971604,0.000613116,0.0008789381,0.0007327545,0.0002890232],"domain_scores_gemma":[0.9975443,0.000323847,0.000629333,0.001420087,0.000004686812,0.0000777707],"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":[0.000004953553,0.00003986417,0.000007208571,0.003663973,0.00009330816,5.691392e-8,0.00008137448,0.001735096,0.000002386251,0.00005167654,0.00001903273,0.9943011],"study_design_scores_gemma":[0.0003840247,0.0003811246,0.003014677,0.02745558,0.007408341,0.00001151666,0.0002589061,0.005912555,0.00001679913,0.0003437696,0.9540676,0.000745051],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00006028899,0.9973138,0.00007865833,0.0005845017,0.0001468241,0.001151848,0.0001350582,0.00001256243,0.0005164875],"genre_scores_gemma":[0.0002258672,0.9983895,0.0002625755,0.00002301308,0.0000303194,0.00007307555,0.00003649102,0.00001020054,0.0009489859],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.993556,"threshold_uncertainty_score":0.6375372,"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."}}