{"id":"W4375953138","doi":"10.1016/j.ssci.2023.106180","title":"A machine learning and data analytics approach for predicting evacuation and identifying contributing factors during hazardous materials incidents on railways","year":2023,"lang":"en","type":"article","venue":"Safety Science","topic":"Traffic and Road Safety","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Transport engineering; Hazardous waste; Emergency evacuation; Poison control; Derailment; SAFER; Computer science; Engineering; Risk analysis (engineering); Computer security; Track (disk drive); Medical emergency","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001102135,0.000915759,0.0007084591,0.002495913,0.0007721312,0.001347299,0.0008957044,0.001141384,0.001217009],"category_scores_gemma":[0.003550066,0.0002636397,0.001042135,0.001539982,0.0003397002,0.001152228,0.0008744477,0.001293921,0.0004029734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009247524,"about_ca_system_score_gemma":0.001845807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02055389,"about_ca_topic_score_gemma":0.01711739,"domain_scores_codex":[0.9994173,0.0001447357,0.00007052516,0.0001513521,0.0001391807,0.00007699174],"domain_scores_gemma":[0.998053,0.001237472,0.0001389041,0.00009376186,0.0003581517,0.0001188276],"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":[0.0007924958,0.003555716,0.09591559,0.0002085878,0.0003955926,0.0006137351,0.0003293265,0.4565809,0.005574536,0.004208531,0.006654171,0.4251708],"study_design_scores_gemma":[0.000008430375,0.00008296306,0.003600511,0.00000780659,0.00002148555,0.00002255021,0.00008102145,0.993986,0.0005564443,0.00130187,0.0003229174,0.000008070353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5768079,0.0007248927,0.4098754,0.002413102,0.0002551215,0.0004779071,0.003066566,0.002419071,0.0039601],"genre_scores_gemma":[0.8916805,0.0002128848,0.1041175,0.000149805,0.0001057891,0.000156286,0.00217032,0.00002132637,0.001385551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02055389,"threshold_uncertainty_score":0.04086852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0426287966896905,"score_gpt":0.2880794701268235,"score_spread":0.245450673437133,"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."}}