{"id":"W4392450360","doi":"10.1016/j.aap.2024.107528","title":"Geographically weighted machine learning for modeling spatial heterogeneity in traffic crash frequency and determinants in US","year":2024,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Traffic and Road Safety","field":"Engineering","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"China Scholarship Council; Chalmers Tekniska Högskola; VINNOVA","keywords":"Crash; Intersection (aeronautics); Spatial heterogeneity; Econometrics; Random forest; Geography; Poison control; Socioeconomic status; Computer science; Transport engineering; Statistics; Cartography; Mathematics; Machine learning; Engineering; Demography; Population; Ecology; Environmental health","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":[0.0004142353,0.0001652288,0.0003018259,0.0007892136,0.00007254942,0.00005700247,0.00008728012,0.0001200761,0.00002402617],"category_scores_gemma":[0.00001327384,0.0001640568,0.0002514194,0.0008120348,0.000009874975,0.0002159984,0.00003139376,0.000220512,0.000001889114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006066995,"about_ca_system_score_gemma":0.00001060919,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003047818,"about_ca_topic_score_gemma":0.08609069,"domain_scores_codex":[0.9987631,0.00006570951,0.0004815647,0.0003168615,0.0001311518,0.0002415391],"domain_scores_gemma":[0.9997554,0.00004147605,0.00003034276,0.0001083394,0.00001778135,0.00004666121],"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":[0.000007184323,0.00002033928,0.5190158,0.00001888459,0.000168208,0.000009494785,0.0001098807,0.4492742,0.0001200713,0.000006385909,3.324292e-7,0.03124924],"study_design_scores_gemma":[0.0002609236,0.00002148322,0.2492038,0.00007188991,0.0002972863,0.000001612782,0.00000896553,0.7497823,0.00003476202,0.000178943,0.000006470908,0.000131526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9052957,0.002147791,0.09209771,0.00001420413,0.00008439074,0.0002049427,7.527153e-7,0.0001481641,0.000006393936],"genre_scores_gemma":[0.9984562,0.0007539662,0.0005970086,0.000002432666,0.00003562736,0.0000455409,0.00007295818,0.00002349318,0.00001280254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3005081,"threshold_uncertainty_score":0.9305857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009305087185470212,"score_gpt":0.2522256619824602,"score_spread":0.24292057479699,"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."}}