{"id":"W2897506718","doi":"10.1021/acs.est.8b03395","title":"Mapping Air Pollution with Google Street View Cars: Efficient Approaches with Mobile Monitoring and Land Use Regression","year":2018,"lang":"en","type":"article","venue":"Environmental Science & Technology","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":204,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Google; Health Effects Institute; Environmental Defense Fund; U.S. Environmental Protection Agency","keywords":"Kriging; Environmental science; Air quality index; Air pollution; Covariate; Regression analysis; Spatial analysis; Pollution; Computer science; Statistics; Meteorology; Remote sensing; Geography; Mathematics; Machine learning","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.000430579,0.0002155916,0.0001890786,0.0001806718,0.0008650193,0.0000382547,0.0003162244,0.0001234906,0.00007507718],"category_scores_gemma":[0.00001673665,0.0001472822,0.00001292346,0.0008800411,0.005382372,0.0004865658,0.0004458086,0.0002102356,0.00006426062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005209299,"about_ca_system_score_gemma":0.0000265521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002360573,"about_ca_topic_score_gemma":0.00009868874,"domain_scores_codex":[0.9978906,0.00003619427,0.0001897206,0.0006988117,0.0005326737,0.0006520373],"domain_scores_gemma":[0.9992088,0.00001856687,0.0001384091,0.0004097621,0.000002942654,0.0002215099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004201166,0.0001687402,0.9465289,0.00001171353,0.000005142159,0.00001003578,0.001397878,0.002958111,0.01187495,0.00004321474,0.00002500286,0.03693436],"study_design_scores_gemma":[0.000636958,0.001635423,0.9458337,0.0001874254,0.00001330304,0.0001106078,0.004699852,0.001705282,0.03736525,0.00005723674,0.007347091,0.0004078686],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974586,0.0001357515,0.0008448376,0.0006975046,0.00004615371,0.0004549343,0.000006952666,0.0001019918,0.0002532275],"genre_scores_gemma":[0.9926283,0.00005881201,0.007028752,0.0001321531,0.00003117765,0.00004642133,0.000001806641,0.00001394579,0.00005866696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0365265,"threshold_uncertainty_score":0.9973244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03244978402797934,"score_gpt":0.2589235277295356,"score_spread":0.2264737437015563,"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."}}