作者：
Wang, Shuli;Gao, Kun*;Zhang, Lanfang*;Yu, Bo;Easa, Said M
通讯作者：
Gao, Kun;Zhang, Lanfang
作者机构：
Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, CN-201804, China
Department of Architecture and Civil Engineering, Chalmers University of Technology, Goteburg SE-412 96, Sweden
Department of Architecture and Civil Engineering, Chalmers University of Technology, Goteburg SE-412 96, Sweden. Electronic address: gkun@chalmers.se
Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, CN-201804, China. Electronic address: zlf2276@tongji.edu.cn
Department of Civil Engineering, Toronto Metropolitan University, Toronto M5B 2K3, Canada
通讯机构：
Department of Architecture and Civil Engineering, Chalmers University of Technology, Goteburg SE-412 96, Sweden. Electronic address:
Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, CN-201804, China. Electronic address
语种：
英文
关键词：
Interpretability,Spatial heterogeneity,Spatial machine learning,Traffic crash frequency
期刊：
Accident analysis and prevention
ISSN：
0001-4575
年：
2024
卷：
199
页码：
107528
摘要：
Spatial analyses of traffic crashes have drawn much interest due to the nature of the spatial dependence and spatial heterogeneity in the crash data. This study makes the best of Geographically Weighted Random Forest (GW-RF) model to explore the local associations between crash frequency and various influencing factors in the US, including road network attributes, socio-economic characteristics, and land use factors collected from multiple data sources. Special emphasis is put on modeling the spatial heterogeneity in the effects of a factor on crash frequency in different geographical areas in a data-driven way. The GW-RF model outperforms global models (e.g. Random Fores...
