{"id":"W4387047581","doi":"10.1016/j.atmosenv.2023.120111","title":"Estimation of daily NO2 with explainable machine learning model in China, 2007–2020","year":2023,"lang":"en","type":"article","venue":"Atmospheric Environment","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mean squared error; Context (archaeology); Ordinary least squares; Extrapolation; Environmental science; Satellite; Statistics; Meteorology; Atmospheric sciences; Mathematics; Geography; Engineering","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002895921,0.0003145672,0.0003164549,0.000003459282,0.0001282666,0.00001192019,0.0002702638,0.0001012503,0.001796613],"category_scores_gemma":[0.00001202934,0.0002840951,0.00006282086,0.0004740318,0.0002926584,0.0002838469,0.0003522763,0.0002643429,0.0006012717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000489696,"about_ca_system_score_gemma":0.000009150931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007637189,"about_ca_topic_score_gemma":0.00001915785,"domain_scores_codex":[0.9978563,0.00005761986,0.000410128,0.0005500931,0.0005900181,0.0005359037],"domain_scores_gemma":[0.9992574,0.00003238977,0.0001932016,0.0003825871,8.340035e-7,0.0001335546],"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":[0.00004258417,0.0001280903,0.1657141,0.00001504349,0.00001131752,0.00003080192,0.0005406955,0.8256127,0.0002691746,0.00001242251,0.0001340841,0.007488986],"study_design_scores_gemma":[0.000579145,0.0001927695,0.1663381,0.00001724857,0.00001729516,0.00000689833,0.0002466871,0.8313853,0.0000500374,0.0001749139,0.0007220649,0.0002695718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9160226,0.00007465894,0.08079466,0.0001302077,0.00003165462,0.0003441367,0.000002557145,0.00008318088,0.002516354],"genre_scores_gemma":[0.893839,0.0005931756,0.09902877,0.00005325696,0.000008726063,0.0000765649,0.00003511657,0.00006044374,0.006304927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02218356,"threshold_uncertainty_score":0.9999611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003993632093894314,"score_gpt":0.1802442628267737,"score_spread":0.1762506307328794,"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."}}