{"id":"W2973317664","doi":"10.1080/10962247.2019.1668872","title":"Improving the accuracy of emission inventories with a machine-learning approach and investigating transferability across cities","year":2019,"lang":"en","type":"article","venue":"Journal of the Air & Waste Management Association","topic":"Vehicle emissions and performance","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Greenhouse gas; Transferability; Environmental science; Metropolitan area; Transport engineering; Aggregate (composite); Computer science; Meteorology; Engineering; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.001162323,0.0000926912,0.0001587626,0.00002926897,0.000169621,0.00005007862,0.000175025,0.00003734992,0.00000242701],"category_scores_gemma":[0.00009050379,0.00004955692,0.00005762919,0.0001700523,0.00002271623,0.000293818,0.00006553439,0.0003177596,1.677209e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001126713,"about_ca_system_score_gemma":0.0000105911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001343369,"about_ca_topic_score_gemma":0.000003145637,"domain_scores_codex":[0.9990919,0.00007970738,0.0002995283,0.00006416666,0.0003283446,0.0001363369],"domain_scores_gemma":[0.999321,0.0001026261,0.0003624902,0.0001187397,0.00006788378,0.00002724979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000383627,0.00001934916,0.7486398,0.0009524482,0.0002363009,3.235309e-7,0.009690449,0.2201744,0.006962024,0.00008272254,0.0001189974,0.01308475],"study_design_scores_gemma":[0.002205644,0.0002494171,0.2075489,0.00106118,0.0002363896,0.00001435686,0.02260899,0.7497706,0.01400325,0.00029641,0.001656049,0.0003487889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9982328,0.0001575314,0.000490638,0.0002753341,0.0001251855,0.0001720413,0.000001836186,0.00001364014,0.0005309809],"genre_scores_gemma":[0.9989674,0.00007665266,0.0004476834,0.000023294,0.00005146511,0.000002361584,7.884588e-7,0.00001103771,0.0004193248],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5410909,"threshold_uncertainty_score":0.2020872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006894321044755305,"score_gpt":0.2010436503640984,"score_spread":0.1941493293193431,"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."}}