{"id":"W3047727732","doi":"10.1021/acs.est.0c00412","title":"Predicting Traffic-Related Air Pollution Using Feature Extraction from Built Environment Images","year":2020,"lang":"en","type":"article","venue":"Environmental Science & Technology","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Mean squared error; Artificial neural network; Air quality index; Air pollution; Environmental science; Geographic information system; Interpolation (computer graphics); Feature extraction; Computer science; Remote sensing; Meteorology; Geography; Artificial intelligence; Statistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003579823,0.0003088765,0.000239151,0.0001402351,0.000893226,0.00004060095,0.000684965,0.0003004519,0.000866093],"category_scores_gemma":[0.00008779285,0.0003138245,0.00008082017,0.0008773244,0.002369622,0.0007644282,0.0007473859,0.0006257971,0.0005641801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113587,"about_ca_system_score_gemma":0.00001607551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001524353,"about_ca_topic_score_gemma":0.000003559727,"domain_scores_codex":[0.9970078,0.00005595564,0.0003717373,0.001079641,0.0007807788,0.0007040737],"domain_scores_gemma":[0.999041,0.00002790283,0.0002686092,0.0003931997,0.000001659203,0.0002676109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001530254,0.00009689998,0.07190952,0.000001924113,0.00001014414,0.00001800578,0.0007762868,0.08460509,0.8109846,0.000006208472,0.00007466749,0.03150142],"study_design_scores_gemma":[0.001347867,0.000684651,0.3263267,0.00006817244,0.0001369268,0.0001684664,0.007386297,0.1586447,0.4903245,0.0006036324,0.01278853,0.001519607],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925432,0.000153456,0.001949921,0.004075439,0.0002454018,0.0002725527,0.00003617357,0.0003782752,0.0003455357],"genre_scores_gemma":[0.9925008,0.00003493787,0.006981116,0.0002140771,0.0001169594,0.00001251831,0.00001256011,0.00002952758,0.00009743765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.32066,"threshold_uncertainty_score":0.9999314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0151348073747949,"score_gpt":0.2399868108004676,"score_spread":0.2248520034256727,"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."}}