{"id":"W2080093988","doi":"10.1007/s40534-015-0068-0","title":"Identification of crash hotspots using kernel density estimation and kriging methods: a comparison","year":2015,"lang":"en","type":"article","venue":"Journal of Modern Transportation","topic":"Traffic and Road Safety","field":"Engineering","cited_by":158,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Minnesota Department of Transportation; U.S. Department of Transportation","keywords":"Hotspot (geology); Kernel density estimation; Kriging; Crash; Computer science; Statistics; Data mining; Geography; Mathematics; Geology","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":[0.005369239,0.0007392851,0.001258684,0.003445924,0.0002675201,0.0009242205,0.0009071757,0.0007501314,0.0004162637],"category_scores_gemma":[0.01931125,0.0003575064,0.0009159938,0.001902277,0.0003147508,0.00145713,0.0006303167,0.0005951081,0.0001586096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007208009,"about_ca_system_score_gemma":0.001001004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01062336,"about_ca_topic_score_gemma":0.008866925,"domain_scores_codex":[0.9971411,0.001487655,0.0002114324,0.0003329428,0.0007104744,0.0001163235],"domain_scores_gemma":[0.9867507,0.009991012,0.0007198455,0.0007283822,0.00166565,0.0001444812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00166854,0.0003740822,0.1738958,0.00112536,0.001245389,0.0001711905,0.001326292,0.3419358,0.004215503,0.005324439,0.0006202954,0.4680974],"study_design_scores_gemma":[0.00006333192,0.0006957061,0.08973781,0.0001121395,0.0002820652,0.0002612062,0.000903182,0.9000132,0.004214127,0.001948469,0.001647854,0.0001209114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6517041,0.003435243,0.340327,0.00022786,0.00005877164,0.0001985956,0.0003207227,0.0005779044,0.003149803],"genre_scores_gemma":[0.9248142,0.0009926572,0.07361638,0.00001449012,0.00001170812,0.00004504846,0.0002138176,0.00003516303,0.0002565378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01062336,"threshold_uncertainty_score":0.02839565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03982573114077832,"score_gpt":0.3218337965003856,"score_spread":0.2820080653596073,"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."}}