吉林大学学报(工学版) ›› 2025, Vol. 55 ›› Issue (1): 141-149.doi: 10.13229/j.cnki.jdxbgxb.20230337

• 交通运输工程·土木工程 • 上一篇    下一篇

城市建成环境与道路交通运行关系

年光跃1(),潘海啸1(),孙健2   

  1. 1.同济大学 建筑与城市规划学院,上海 200092
    2.长安大学 未来交通学院,西安 710021
  • 收稿日期:2023-04-10 出版日期:2025-01-01 发布日期:2025-03-29
  • 通讯作者: 潘海啸 E-mail:ngyown@tongji.edu.cn;hxpank@online.sh.cn
  • 作者简介:年光跃(1986-),男,在站博士后.研究方向:城市与交通规划.E-mail: ngyown@tongji.edu.cn
  • 基金资助:
    国家自然科学基金区域创新发展联合基金项目(U20A20330);上海同济城市规划设计研究院有限公司项目(KY-2016-ZD2-B01)

Exploring relationship between urban built environment and road traffic performance

Guang-yue NIAN1(),Hai-xiao PAN1(),Jian SUN2   

  1. 1.College of Architecture and Urban Planning,Tongji University,Shanghai 200092,China
    2.School of Future Transportation,Chang'an University,Xi'an 710021,China
  • Received:2023-04-10 Online:2025-01-01 Published:2025-03-29
  • Contact: Hai-xiao PAN E-mail:ngyown@tongji.edu.cn;hxpank@online.sh.cn

摘要:

为解决建成环境与道路交通运行之间的量化描述和解释问题,本文以路段平均行程速度表征交通运行状况,基于面板数据构建随机森林预测模型,以建成环境预测路段车速。结果表明:构建的随机森林预测模型表现出优秀的性能,道路交通运行与建成环境显著相关,并呈现多样化的非线性关系。本文研究弥补了先前相关研究中交通运行动态特性考虑不足、小范围片区研究偶然性偏差、非线性关系缺乏等问题,同时本文研究结果可为城市与交通规划、管理决策等提供支持。

关键词: 城市交通, 关联机理, 随机森林, 建成环境, 行程速度, 非线性关系

Abstract:

This study provides a quantitative analysis of the relationship between the built environment and road traffic performance. We define traffic performance by measuring average travel speeds on road segments and develop a random forest model using multi-source panel data to predict speeds based on built environment variables. The results demonstrate high predictive accuracy, revealing a significant correlation between road traffic performance and the built environment, characterized by complex non-linear relationships. Our work addresses three limitations in prior research: overlooking dynamic traffic performance characteristics; potential chance bias in small-area studies; and insufficient exploration of non-linear relationships. These findings provide actionable insights for urban planners and policymakers to optimize transport infrastructure and management strategies.

Key words: urban traffic, correlation mechanism, random forest, built environment, travel speed, non-linear relationship

中图分类号: 

  • U121

图1

选取研究路段空间分布"

表1

路段指标汇总统计表"

变量名称符号最小值中值平均值最大值标准差
路段长度l250.288602.351665.7392 202.920300.180
POI混合度m00.8640.78510.255
是否有地铁站s000.16710.373
车辆服务密度d100.0210.0614.7440.164
住宅小区密度d200.0470.0920.6670.111
医疗卫生服务密度d300.0340.1271.8020.213
停车场出入口密度d4000.0580.9550.114
公交站密度d500.0330.0400.2300.035
科技文化服务密度d600.0360.1142.6950.205
生活服务密度d700.0840.2999.0170.593
体育休闲服务密度d800.0270.1093.7730.220
政府机构密度d900.0390.1271.9630.224
购物服务密度d1000.1220.63022.8731.434
餐饮服务密度d1100.0650.2857.5120.566
公司企业密度d1200.0520.1173.0790.213
金融保险密度d13000.0601.3080.126
住宿服务密度d14000.0763.2820.215
商住楼密度d15000.0210.5320.057
景点密度d16000.0190.8630.052

图2

16个建成环境密度变量之间的相关系数矩阵图"

表2

因子载荷值及其代表性变量"

建成环境

密度变量

符号因子变量
f1f2f3f4f5
车辆服务密度d10.1950.7460.1950.2700.040
住宅小区密度d20.2440.3410.794-0.0210.110
医疗卫生服务密度d30.8610.2990.2060.2080.064
停车场出入口密度d40.6670.2260.4870.1530.087
公交站密度d50.7460.3020.3680.1970.037
科技文化服务密度d60.5400.5440.3020.1890.024
生活服务密度d70.7090.1300.3560.3930.036
体育休闲服务密度d80.8870.3230.1850.0440.071
政府机构密度d90.6450.6430.1160.0080.061
购物服务密度d100.5340.0670.6210.317-0.003
餐饮服务密度d110.1010.1030.077-0.0160.984
公司企业密度d120.4680.7250.190-0.0640.162
金融保险密度d130.7860.3810.1110.0620.063
住宿服务密度d140.8420.2500.1860.1220.042
商住楼密度d150.8640.2100.2270.0490.106
景点密度d160.1640.1350.0720.927-0.021

图3

随机森林预测模型性能评估和变量重要性排序及显著性"

表3

多元线性回归模型结果"

变 量Estimate

Std.

Error

t valuePr(>|t|)
模型评价R20.011p-value3.6×10-9
截距23.9580.94325.409<2.0×10-16***
是否有地铁站s-4.1570.655-6.3472.4×10-10***
POI混合度m1.3600.9601.4160.157
路段长度l0.0030.0013.8190.000 1***
因子f10.2210.2370.9340.350
因子f20.2130.2410.8840.377
因子f30.2410.2420.9980.318
因子f40.1570.2530.6220.534
因子f50.0330.3390.0970.923

图4

预测变量部分依赖图"

1 住房和城乡建设部城市交通基础设施监测与治理实验室. 2022年度中国主要城市道路网密度与运行状态监测报告[R]. 北京:住房和城乡建设部, 2022.
2 陆化普. 城市交通拥堵机理分析与对策体系[J]. 综合运输, 2014, 392(3): 10-19.
Lu Hua-pu. Analysis of urban traffic congestion mechanism and countermeasure system[J]. China Transportation Review, 2014, 392(3): 10-19.
3 袁浩, 任杰, 杨睿, 等. 考虑空间异质性的城市建成环境对交通拥堵状态的影响[J]. 武汉理工大学学报:交通科学与工程版, 2021, 45(5): 840-845.
Yuan Hao, Ren Jie, Yang Rui, et al. Influence of urban building environment on traffic congestion considering spatial heterogeneity[J]. Journal of Wuhan University of Technology(Transportation Science & Engineering), 2021, 45(5): 840-845.
4 李佳敏, 张彪, 郭亮. 大城市交通与建成环境综合规划的范式扩展与深化——中美案例的比较与启示[J]. 西部人居环境学刊, 2021, 36(4): 36-44.
Li Jia-min, Zhang Biao, Guo Liang. The paradigm expansion and deepening of the comprehensive planning of transportation & built environment in metropolis: comparison and enlightenment of the Sino-American case[J]. Journal of Human Settlements in West China, 2021, 36(4): 36-44.
5 Wang M, Debbage N. Urban morphology and traffic congestion: longitudinal evidence from US cities[J]. Computers, Environment and Urban Systems, 2021, 89: No.101676.
6 Handy S L, Boarnet M G, Ewing R, et al. How the built environment affects physical activity: views from urban planning[J]. American Journal of Preventive Medicine, 2002, 23(Sup.2): 64-73.
7 韩会然, 杨成凤. 建成环境对出行行为的影响研究进展与展望[J]. 安徽师范大学学报:自然科学版, 2019, 42(2): 166-173.
Han Hui-ran, Yang Cheng-feng. Progress and prospects of the research on built environment and residents´travel behavior[J]. Journal of Anhui Normal University(Natural Science), 2019, 42(2): 166-173.
8 Ewing R, Cervero R. Travel and the built environment—a meta-analysis[J]. Journal of the American Planning Association, 2010, 76(3): 265-294.
9 Handy S, Cao X, Mokhtarian P. Correlation or causality between the built environment and travel behavior? Evidence from northern California[J]. Transportation Research Part D: Transport and Environment, 2005, 10(6): 427-444.
10 Cao J. Heterogeneous effects of neighborhood type on commute mode choice: an exploration of residential dissonance in the twin cities[J]. Journal of Transport Geography, 2015, 48(C): 188-196.
11 Zhang Q, Clifton K J, Moeckel R, et al. Household trip generation and the built environment: does more density mean more trips?[J]. Transportation Research Record, 2019, 2673(5): 596-606.
12 尹超英, 邵春福, 黄兆国, 等. 基于梯度提升决策树的多尺度建成环境对小汽车拥有的影响[J]. 吉林大学学报:工学版, 2022, 52(3): 572-577.
Yin Chao-ying, Shao Chun-fu, Huang Zhao-guo, et al. Investigating influences of multi⁃scale built environment on car ownership behavior based on gradient boosting decision trees[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 572-577.
13 颜冉, 杨新刚, 杨婷. 城市建成环境对道路服务水平的影响研究[J]. 安徽建筑大学学报, 2020, 28(5): 70-75.
Yan Ran, Yang Xin-gang, Yang Ting. Research on road service level influenced by urban built environment[J]. Journal of Anhui Jianzhu University, 2020, 28(5): 70-75.
14 钟绍鹏, 何璟, 朱康丽, 等. 基于建成环境和低频浮动车数据的路段行程时间估计[J]. 交通运输系统工程与信息, 2021, 21(4): 125-131,147.
Zhong Shao-peng, He Jing, Zhu Kang-li, et al. Travel time estimation based on built environment and low frequency floating car data[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(4): 125-131,147.
15 Pan Y, Chen S, Niu S, et al. Investigating the impacts of built environment on traffic states incorporating spatial heterogeneity[J]. Journal of Transport Geography, 2020, 83: No.102663.
16 Zhang K S, Sun D, Shen S W, et al. Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data[J]. Journal of Transport and Land Use, 2017, 10(1): 675-694.
17 Zhong S, Wang Z, Wang Q, et al. Exploring the spatially heterogeneous effects of urban built environment on road travel time variability[J]. Journal of Transportation Engineering, Part A: Systems, 2021, 147(1): No.4020142.
18 王东炜, 李辉, 李岩, 等. 城市道路网络路段状态相关性与道路间距分析[J]. 交通运输工程学报, 2017, 17(1): 101-108.
Wang Dong-wei, Li Hui, Li Yan, et al. Analysis of road section state correlation and road distance in urban road network[J]. Journal of Traffic and Transportation Engineering, 2017, 17(1): 101-108.
19 Cervero R. Mixed land-uses and commuting: evidence from the American housing survey[J]. Transportation Research Part A: Policy and Practice, 1996, 30(5): 361-377.
20 Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
[1] 董春娇,陆育霄,马社强,李鹏辉. 考虑等待忍耐时间的电动自行车违规行为研判[J]. 吉林大学学报(工学版), 2024, 54(9): 2540-2546.
[2] 马书红,廖国美,黄岩,张俊杰. 建成环境对交通小区地铁通勤客流的异质性影响[J]. 吉林大学学报(工学版), 2024, 54(7): 1913-1922.
[3] 熊志华,董黛悦,董春娇,郑炎,解超. 考虑个人偏好的观赛人群组合决策选择行为[J]. 吉林大学学报(工学版), 2024, 54(4): 979-986.
[4] 吴娇蓉,林清凯,邓泳淇. 基于公交线路运行稳定性的潜在公交专用道需求识别方法[J]. 吉林大学学报(工学版), 2024, 54(3): 692-699.
[5] 庄焱,董春娇,米雪玉,张小雨,王菁. 基于随机参数Logit的中小城市居民出行方式选择建模[J]. 吉林大学学报(工学版), 2024, 54(2): 461-468.
[6] 张文会,伊静. 考虑通行能力和排队延误的公交停靠系统优化[J]. 吉林大学学报(工学版), 2024, 54(1): 146-154.
[7] 宋世军,樊敏. 基于随机森林算法的大数据异常检测模型设计[J]. 吉林大学学报(工学版), 2023, 53(9): 2659-2665.
[8] 尹超英,陆颖,邵春福,马健霄,许得杰. 考虑空间自相关的建成环境对通勤方式选择的影响[J]. 吉林大学学报(工学版), 2023, 53(7): 1994-2000.
[9] 杨亚让,吴云虎. 基于随机森林的无线传感器通信网络阻塞故障检测[J]. 吉林大学学报(工学版), 2023, 53(5): 1490-1495.
[10] 王斌,何丙辉,林娜,王伟,李天阳. 基于随机森林特征选择的茶园遥感提取[J]. 吉林大学学报(工学版), 2022, 52(7): 1719-1732.
[11] 邝先验,陈自如. 基于CA的无信号灯控制路段行人过街横道处动态博弈礼让行为[J]. 吉林大学学报(工学版), 2022, 52(4): 837-846.
[12] 贾洪飞,邵子函,杨丽丽. 终点不确定条件下网约车合乘匹配模型及算法[J]. 吉林大学学报(工学版), 2022, 52(3): 564-571.
[13] 尹超英,邵春福,黄兆国,王晓全,王晟由. 基于梯度提升决策树的多尺度建成环境对小汽车拥有的影响[J]. 吉林大学学报(工学版), 2022, 52(3): 572-577.
[14] 董春娇,董黛悦,诸葛承祥,甄理. 电动自行车出行特性及骑行决策行为建模[J]. 吉林大学学报(工学版), 2022, 52(11): 2618-2625.
[15] 吴静娴,申华鹏,韩印,杨敏. 考虑城市建成环境非线性作用的通勤时间模型[J]. 吉林大学学报(工学版), 2022, 52(11): 2568-2573.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!