{"id":"W4415819655","doi":"10.3390/ijgi14110434","title":"Multimodal Spatiotemporal Deep Fusion for Highway Traffic Accident Prediction in Toronto: A Case Study and Roadmap","year":2025,"lang":"en","type":"article","venue":"ISPRS International Journal of Geo-Information","topic":"Traffic and Road Safety","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sensor fusion; Intelligent transportation system; Fusion; Crash; Feature (linguistics); Road traffic; Hotspot (geology); Road surface","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.0003756661,0.0008052004,0.0002440417,0.0007936833,0.0004237779,0.0004590643,0.0006225319,0.0004333647,0.0008321964],"category_scores_gemma":[0.0009311833,0.0001653105,0.0004227756,0.001144818,0.0003317461,0.0003772613,0.000488806,0.0004155011,0.0001278519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004455777,"about_ca_system_score_gemma":0.003698761,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7494568,"about_ca_topic_score_gemma":0.7438804,"domain_scores_codex":[0.9998243,0.00002734076,0.000008037226,0.00004165916,0.00004076373,0.00005792214],"domain_scores_gemma":[0.9997501,0.00007008901,0.00002248214,0.00002340465,0.0001052732,0.00002864301],"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":[0.0002827099,0.0001211604,0.06621507,0.00009385077,0.0001249758,0.0009017246,0.0002561985,0.8574836,0.00318822,0.00152078,0.006839617,0.06297211],"study_design_scores_gemma":[0.000006491918,0.0000249768,0.01962194,0.000008851365,0.00002381446,0.00003467542,0.000218605,0.9778141,0.001158407,0.0004313743,0.0006413905,0.00001535391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9650636,0.0004990059,0.02382205,0.0007267215,0.0000415915,0.00006080128,0.006057587,0.0007092337,0.003019366],"genre_scores_gemma":[0.9926383,0.0001081258,0.004517311,0.00001614859,0.000005308091,0.000009954665,0.00206044,0.0000108473,0.0006335798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2505432,"threshold_uncertainty_score":0.5040374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004112016674653563,"score_gpt":0.2545576688261713,"score_spread":0.2504456521515178,"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."}}