{"id":"W7082998206","doi":"10.1016/j.aeaoa.2025.100372","title":"Prediction of ambient PM2.5 chemical components in Southern California using machine learning","year":2025,"lang":"en","type":"article","venue":"Atmospheric Environment X","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Aeronautics and Space Administration","keywords":"Particulates; Aerodynamic diameter; Generalizability theory; Air quality index; Satellite; Gradient boosting; Environmental monitoring; Predictive modelling","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":[0.0001680116,0.0001112226,0.0001531124,0.0000047673,0.00004757308,0.00001029485,0.0002721665,0.00006742766,0.00007310838],"category_scores_gemma":[0.00002377236,0.0001096973,0.00004256272,0.0001757983,0.00005306476,0.00004540506,0.0002855558,0.0001597533,0.00002054411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009041728,"about_ca_system_score_gemma":0.00001135232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000187092,"about_ca_topic_score_gemma":8.958694e-7,"domain_scores_codex":[0.9990543,0.00004930554,0.0002662827,0.0002802414,0.0001609387,0.0001888922],"domain_scores_gemma":[0.9995915,0.00002921418,0.0000957361,0.0002442454,0.000006274752,0.00003305966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001728894,0.0003016804,0.4520044,0.00006916378,0.00003349745,0.0000111555,0.0005600576,0.1869793,0.3571448,0.0001643241,0.00002384268,0.002690551],"study_design_scores_gemma":[0.0005495254,0.00002562339,0.01279451,0.00007214062,0.0000111257,0.000004210436,0.000105048,0.961673,0.01586247,0.0004863053,0.008287053,0.0001290416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8903934,0.0001440741,0.1083583,0.0002326411,0.00005635722,0.00009710267,0.00000515603,0.00003654346,0.0006763855],"genre_scores_gemma":[0.9798158,0.00001623664,0.01941705,0.00004676616,0.000008672867,0.000006375403,0.00001165094,0.000002268949,0.0006751212],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7746937,"threshold_uncertainty_score":0.4473326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0147150430105994,"score_gpt":0.1873254275410174,"score_spread":0.172610384530418,"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."}}