考虑建成环境的交通事故严重程度致因交互效应研究

doi:10.16097/j.cnki.1009-6744.2024.02.027

交通运输系统工程与信息 ›› 2024, Vol. 24 ›› Issue (2): 272-280.DOI: 10.16097/j.cnki.1009-6744.2024.02.027

考虑建成环境的交通事故严重程度致因交互效应研究

王健宇^*，陈献天，焦朋朋，覃楚亮，王泽昊

北京建筑大学，通用航空技术北京实验室，北京100044

收稿日期:2023-12-21 修回日期:2024-02-02 接受日期:2024-02-06 出版日期:2024-04-25 发布日期:2024-04-25
作者简介:王健宇(1991- )，男，辽宁沈阳人，讲师，博士。
基金资助:
北京市自然科学基金 (9234025)；国家自然科学基金 (52172301)；北京市社会科学基金 (21GLA010)。

Interactive Effect on Traffic Accident Severity Considering Built Environment

WANGJianyu^*,CHEN Xiantian,JIAO Pengpeng,QIN Chuliang,WANG Zehao

Beijing Key Laboratory of General Aviation Technology, Beijing University of Civil Engineering and Architecture, Beijing 100044, China

Received:2023-12-21 Revised:2024-02-02 Accepted:2024-02-06 Online:2024-04-25 Published:2024-04-25
Supported by:
BeijingNaturalScienceFoundation (9234025)；National Natural Science Foundation of China (52172301)；Beijing Social Science Foundation (21GLA010)。

摘要/Abstract

摘要： 为探究考虑建成环境影响下各类因素对交通事故的作用机理，本文提出一种融合ADASYN(Adaptive Synthetic Sampling)平衡算法与CatBoost模型的方法，对沈阳市2015—2020年的道路交通事故进行研究，并解析事故致因的交互效应。首先，通过地理信息匹配的方法补充事故地点周围14项建成环境因子，构建多源数据集。其次，通过比较4种经典的机器学习模型，即CatBoost，Random Forest，XGBoost，LightGBM，并筛选出泛化能力最强的模型。随后，利用SHAP (Shapley Additive Explanation)归因方法对最优模型进行解释以揭示单个风险因素效应以及影响重要度排序。最后，基于单因素分析，探究建成环境与事故特征之间的交互效应。研究表明：相同的特征在单因素以及双因素交互分析中对事故影响机制存在差异。在单因素分析中，季节、交通方式这2项因素对致命事故具有显著的正向影响；而主干路密度、快速路密度、工业用地比例、现场形态、道路物理隔离这5项因素对致命事故有着显著的负向影响。在双因素交互分析中，高主路密度与秋冬季节交互以及低工业用地比例与春季交互等对致命事故具有正向影响；而高工业用地比例与行人交互则产生了负向影响。本文成果可为相关人员提供准确的影响交通事故严重程度的相关因素，为优化和建设城市交通系统提供一定的理论支撑。

关键词: 交通工程, 事故严重程度分析, CatBoost模型, 城市道路交通事故, 建成环境, 交互效应

Abstract: To explore the mechanism of various factors influencing traffic accidents under the impact of the built environment, this paper proposes a method that integrates the ADASYN (Adaptive Synthetic Sampling) balancing algorithm with the CatBoost model to study road traffic accidents in Shenyang from 2015 to 2020, and to analyze the interactive effects of accident causation. Firstly, by employing geographic information matching, the study supplemented 14 built environment factors around the accident locations with to construct a multi-source dataset. Secondly, by comparing four classic machine learning models—namely, CatBoost, Random Forest, XGBoost, and LightGBM—the study selected the model with the strongest generalization ability. Subsequently, the SHAP (Shapley Additive Explanation) attribution method was used to interpret the optimal model to reveal the effect of individual risk factors and their importance ranking. Finally, based on single-factor analysis, the study explored the interactive effects between the built environment and accident characteristics. The research indicates that the same features have different impacts on the mechanism of accidents in both single-factor and dual-factor interaction analyses. In single-factor analysis, two factors, season and mode of transportation, have a significant positive impact on fatal accidents; whereas five factors, including trunk road density, expressway density, industrial land proportion, site morphology, and physical road separation, have a significant negative impact on fatal accidents. In dual-factor interaction analysis, high trunk road density interacting with autumn and winter seasons, and low industrial land proportion interacting with spring, have a positive impact on fatal accidents; while a high industrial land proportion interacting with pedestrian traffic has a negative impact. The findings of this study offer precise insights into the factors influencing the severity of traffic accidents, providing a theoretical foundation for optimizing and developing urban transportation systems.

Key words: traffic engineering, accident severity analysis, CatBoost model, urban road traffic accidents, built environment, interaction effect

中图分类号:

U491.31

王健宇, 陈献天, 焦朋朋, 覃楚亮, 王泽昊. 考虑建成环境的交通事故严重程度致因交互效应研究[J]. 交通运输系统工程与信息, 2024, 24(2): 272-280.

WANGJianyu, CHEN Xiantian, JIAO Pengpeng, QIN Chuliang, WANG Zehao. Interactive Effect on Traffic Accident Severity Considering Built Environment[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(2): 272-280.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.02.027

http://www.tseit.org.cn/CN/Y2024/V24/I2/272

参考文献

[1]中华人民共和国交通运输部.2022年交通运输行业发展统计公报[EB/OL]. 中华人民共和国交通运输部, (2023-06-16) [2023-11-05]. https://xxgk.mot.gov. cn/2020/ jigou/zhghs/ 202306/ t20230615_3847023. html [Ministry of Transport of the People's Republic of China. Statistical bulletin on development of transport industry in 2022 [EB/OL]. The Ministry of Transport of the People's Republic of China, (2023-06-16)[2023-11 05].https://xxgk.mot.gov.cn/ 2020/ jigou/ zhghs/ 202306/ t20230615_3847023.html]

[2]国家统计局.中国统计年鉴[M].北京:中国统计出版社, 2023. [National Bureau of Statistics. China statistical yearbook[M]. Beijing: China Statistics Press, 2023.]

[3]胡立伟,吕一帆,赵雪亭,等.基于数据驱动的交通事故伤害程度影响因素及其耦合关系研究[J].交通运输系统工程与信息,2022,22(5): 117-124, 134. [HU L W, LU Y F, ZHAO X T, et al. Research on the influencing factors and coupling relationship of traffic accident injury degree based on data driven[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(5): 117-124, 134.]

[4]杨洋,贺昆,王云鹏,等.面向动态交通流的高速公路事故风险模型空间移植研究[J].交通运输系统工程与信息,2023, 23(3): 174-186. [YANG Y, HE K, WANG Y P, et al. A highway accident risk model in the dynamic traffic flow space transplantation research[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(3): 174-186.]

[5]PARSA A B, MOVAHEDI A, TAGHIPOUR H, et al. Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis[J]. Accident Analysis & Prevention, 2020, 136: 105405

[6]AHMAD N, AHMED A, WALI B, et al. Exploring factors associated with crash severity on motorways in pakistan[J]. Proceedings of the Institution of Civil Engineers-Transport 2019, 175(4): 189-198.

[7] MEHRNAZ A, MEHMET B U, KARST T G, et al. A comprehensive analysis of the relationships between the built environment and traffic safety in the Dutch urban areas[J]. Accident Analysis & Prevention, 2022, 172(7): 1-17.

[8]陈坚,邱智宣,彭涛,等.建成环境对城市交通事故严重程度影响研究[J].重庆交通大学学报(自然科学版), 2023, 42(3): 105-111, 150. [CHEN J, QIU Z X, PENG T, et al. Study on the impact of built environment on the severity of urban traffic accidents[J]. Journal of Chongqing Jiaotong University (Natural Science Edition), 2023, 42(3): 105-111, 150.]

[9] 谢波,凌昌隆,王兰.城市街道模式对交通安全的影响研究:以武汉市主城区为例[J]. 城市规划,2022,46 (8): 75-83. [XIE B, LING C L, WANG L. Study on the impact of urban street patterns on traffic safety: A case study of Wuhan City[J]. City Planning Journal, 2002, 46 (8): 75-83.]

[10] 戢晓峰, 乔新.建成环境对行人交通事故严重程度的非线性影响[J]. 交通运输系统工程与信息,2023,23 (1): 314-323. [JI X F, QIAO X. Nonlinear effects of built environment on pedestrian traffic accident severity[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(1): 314-323.]

[11] LUO P Y, YU B J, LI P F, et al. How 2D and 3D built environments impact urban surface temperature under extreme heat: A study in Chengdu, China[J]. Building and Environment, 2023(231): 110035.

[12] EWING R, CERVERO R. Travel and the built environment: A meta-analysis[J]. Journal of the American Planning Association, 2010, 76(3): 265-294.

[13] 陈俊宇, 李金龙, 许伦辉,等.基于ADASYN-XGBoost 的交通事故自动检测方法[J].交通信息与安全,2023, 41(3): 12-22. [CHEN J Y, LI J L, XU L H, et al. An automatic detection method for traffic accidents based on ADASYN-XGBoost[J]. Journal of Transport Information and Safety, 2023, 41(3): 12-22.]

[14] 龙科军,邹道兴,何石坚.基于多源数据融合的高速公路交通事故黑点判别[J].长沙理工大学学报(自然科学版), 2022, 19(1): 89-95. [LONG K J, ZOU D X, HE S J. Based on multi-source data fusion of highway traffic accident black spots discriminant[J]. Journal of Changsha University of Science and Technology (Natural Science Edition), 2022,19(1): 89-95.]

[15] DEMIR S, SAHIN E K. Predicting occurrence of liquefaction-induced lateral spreading using gradient boosting algorithms integrated with particle swarm optimization: PSO-XGBoost, PSO-LightGBM, and PSO CatBoost[J]. Acta Geotech, 2023(18): 3403-3419.

[16] KJERSTI A, MARTIN J, ANDERS L. Explaining individual predictions when features are dependent: More accurate approximations to Shapley values[J]. Artificial Intelligence, 2021, 298(9): 1-23.

考虑建成环境的交通事故严重程度致因交互效应研究

Interactive Effect on Traffic Accident Severity Considering Built Environment

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	马书红, 陈西芳, 杨磊, 赵玉哲, 曾玉. 可达性对城市群多模式交通碳排放的空间异质性影响[J]. 交通运输系统工程与信息, 2024, 24(3): 64-74.
[2]	吴场建, 曹奇, 任刚. 考虑路径关系的干线多路径绿波优化模型[J]. 交通运输系统工程与信息, 2024, 24(3): 103-113.
[3]	杨亚璪, 宾涛. 电动汽车集中型充电站选址定容模型[J]. 交通运输系统工程与信息, 2024, 24(3): 204-212.
[4]	胡立伟, 陈琛, 赵雪亭, 刘冰, 侯智, 张瑞杰, 贺雨. 基于行车风险场的快速路短交织区车辆交互风险识别[J]. 交通运输系统工程与信息, 2024, 24(3): 221-231.
[5]	陈永恒, 李世豪, 杨绥程, 刘博, 湛天舒. 平行式快速路出口交通组织方法研究[J]. 交通运输系统工程与信息, 2024, 24(3): 232-239.
[6]	吴建清, 张子毅, 王钰博, 张昱, 田源. 考虑多模态数据的重载货车危险驾驶行为识别方法[J]. 交通运输系统工程与信息, 2024, 24(2): 63-75.
[7]	杨达, 刘家威, 郑斌, 孙峰. 基于时域卷积网络与注意力机制的车辆换道轨迹预测模型[J]. 交通运输系统工程与信息, 2024, 24(2): 114-126.
[8]	彭金栓, 成家佳, 赵刘昌, 罗霜, 袁浩, 徐磊. 无信控交叉口驾驶人潜在危险感知能力评估[J]. 交通运输系统工程与信息, 2024, 24(2): 127-135.
[9]	穆雨薇, 袁伟, 张会明, 郝帅洁. 典型事故形态下驾驶人工作记忆与应激反应研究[J]. 交通运输系统工程与信息, 2024, 24(2): 179-187.
[10]	邓亚娟, 刘霜, 白钰, 刘文凤, 崔亮斌. 共享单车与公共交通多元关系分类及阈值研究[J]. 交通运输系统工程与信息, 2024, 24(2): 208-216.
[11]	陈奕璠, 张步镐, 党振, 郭唐仪, 顾子渊, 张玉梁. 建成环境对共享单车使用特征的非线性影响研究[J]. 交通运输系统工程与信息, 2024, 24(2): 217-224.
[12]	漆巍巍, 覃铄磊, 朱淑芳, 刘岩. 考虑空间溢出效应的高速公路交通事故随机参数频次模型[J]. 交通运输系统工程与信息, 2024, 24(2): 263-271.
[13]	韩磊, 杜志刚, 马傲君, 焦方通. 公路隧道入口区域驾驶人吸睛效应综合评价[J]. 交通运输系统工程与信息, 2024, 24(2): 313-322.
[14]	李坤宸, 袁伟, 李舒欣, 张会明. 听觉-言语认知负荷下工作记忆容量对跟车行驶影响[J]. 交通运输系统工程与信息, 2024, 24(1): 93-105.
[15]	崔洪军, 周启航, 朱敏清. 信号交叉口直行非机动车膨胀特性分析与风险评估[J]. 交通运输系统工程与信息, 2024, 24(1): 138-148.