{"id":"W7093366044","doi":"10.1016/j.apr.2025.102784","title":"Machine learning-based estimation of vehicular emissions using on-board diagnostics data for intelligent fleet management","year":2025,"lang":"en","type":"article","venue":"Atmospheric Pollution Research","topic":"Vehicle emissions and performance","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Cistel Technology (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Powertrain; Cold start (automotive); Phase (matter); Fleet management; Driving cycle; NOx; Gasoline","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000280466,0.0007675948,0.000623815,0.001069003,0.0002296142,0.0005235763,0.0005314947,0.0006125949,0.0006090652],"category_scores_gemma":[0.001222889,0.0002417557,0.0003384845,0.0006402968,0.0001512105,0.0006439409,0.0003255302,0.000540557,0.0003034489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003548432,"about_ca_system_score_gemma":0.0003460121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008870055,"about_ca_topic_score_gemma":0.01048676,"domain_scores_codex":[0.999786,0.00004849475,0.00001519129,0.00005527057,0.00005848346,0.0000365963],"domain_scores_gemma":[0.9995012,0.0002106639,0.00008905477,0.00005861318,0.0001183588,0.00002215612],"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":[0.0004602207,0.000847661,0.05402391,0.0000894571,0.0001771033,0.0001458605,0.00005236951,0.759343,0.02538976,0.0005659314,0.001507778,0.1573969],"study_design_scores_gemma":[0.00000647073,0.00005216312,0.01031266,0.000004576771,0.00001298183,0.00001762431,0.00001671337,0.9859027,0.003159842,0.0003121476,0.000195297,0.000006851362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8632119,0.0002869612,0.1315639,0.0001619374,0.00009058572,0.00005040018,0.0007368968,0.0009837615,0.002913668],"genre_scores_gemma":[0.9942252,0.00003770854,0.004651217,0.00001235875,0.00001239061,0.000009239058,0.0004970831,0.00001058894,0.0005441266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008870055,"threshold_uncertainty_score":0.0176369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06134223780047844,"score_gpt":0.3637666848119601,"score_spread":0.3024244470114816,"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."}}