{"id":"W4293238417","doi":"10.3390/atmos13050696","title":"A Deep Learning Approach for Meter-Scale Air Quality Estimation in Urban Environments Using Very High-Spatial-Resolution Satellite Imagery","year":2022,"lang":"en","type":"article","venue":"Atmosphere","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Medical Research Council; Wellcome Trust","keywords":"Remote sensing; Satellite; Satellite imagery; Scale (ratio); Environmental science; Air quality index; Deep learning; Computer science; Meteorology; Geography; Cartography; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0003330301,0.0006332847,0.000335411,0.0004760977,0.0001972362,0.0004938822,0.0009992822,0.0005850013,0.0008023909],"category_scores_gemma":[0.000715073,0.0003918118,0.0004512788,0.000738933,0.0003076683,0.0006419928,0.0006628367,0.0008809432,0.0002337312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007781112,"about_ca_system_score_gemma":0.0006570297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02571624,"about_ca_topic_score_gemma":0.03034009,"domain_scores_codex":[0.9998854,0.00001819222,0.00000612272,0.00004166123,0.00002735876,0.00002120043],"domain_scores_gemma":[0.9998434,0.00005646431,0.00002366638,0.0000166319,0.00004866753,0.00001113142],"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":[0.00003450135,0.00006257579,0.002093239,0.00003473046,0.00005787838,0.00005092079,0.00003382146,0.8838035,0.003244575,0.001182668,0.001086465,0.108315],"study_design_scores_gemma":[9.653503e-7,0.000004338398,0.0001979656,0.000001510925,0.000001938598,0.000002457747,0.000003276782,0.9990792,0.0002764777,0.0003394402,0.00009095365,0.00000143214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08530111,0.0003647748,0.9104356,0.0002782404,0.00004752094,0.00004256143,0.0003002943,0.001324603,0.001905356],"genre_scores_gemma":[0.7873514,0.000260894,0.2077797,0.000160463,0.00004134467,0.00008716647,0.0007670163,0.00005488154,0.003497177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02571624,"threshold_uncertainty_score":0.0511331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03402103100573157,"score_gpt":0.2869922196982387,"score_spread":0.2529711886925071,"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."}}