{"id":"W4396780695","doi":"10.1016/j.uclim.2024.101950","title":"An ensemble deep learning approach to spatiotemporal tropospheric ozone forecasting: A case study of Tehran, Iran","year":2024,"lang":"en","type":"article","venue":"Urban Climate","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Environmental science; Tropospheric ozone; Troposphere; Meteorology; Ozone; Climatology; Ensemble learning; Atmospheric sciences; Geography; Computer science; Artificial intelligence; Geology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007695797,0.0004997436,0.0003823029,0.00048908,0.0004512412,0.0004594806,0.0007560015,0.0005022479,0.0004781616],"category_scores_gemma":[0.0009917686,0.0001625532,0.000476231,0.0008136806,0.0001899554,0.0005701396,0.0004157527,0.0004978155,0.00007325882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001242568,"about_ca_system_score_gemma":0.001178667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1167192,"about_ca_topic_score_gemma":0.1092092,"domain_scores_codex":[0.9998234,0.00004192288,0.00000952532,0.00003563783,0.00003672627,0.00005283643],"domain_scores_gemma":[0.9996917,0.0001233386,0.00002454161,0.00002743055,0.000113104,0.00001985561],"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":[0.00020665,0.0003751249,0.06070969,0.00005731096,0.0001925666,0.000904297,0.0001970325,0.833927,0.001763837,0.001585799,0.004652473,0.09542812],"study_design_scores_gemma":[0.00001047329,0.00003066172,0.009985442,0.000002585668,0.00003764944,0.00003177178,0.0001814798,0.9879035,0.0007195603,0.000537639,0.0005514487,0.000007835477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837415,0.0001882889,0.01301045,0.0004444014,0.00004435626,0.000022002,0.0003775589,0.0002003501,0.001971049],"genre_scores_gemma":[0.9939486,0.00008288198,0.005024789,0.00001246364,0.000009563708,0.000008013054,0.0002924454,0.000007503442,0.0006136397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1167192,"threshold_uncertainty_score":0.2320797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05894756765021599,"score_gpt":0.2918799390767126,"score_spread":0.2329323714264966,"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."}}