空间异质下地铁建成环境与站点覆盖客流吸引度关系研究

doi:10.16097/j.cnki.1009-6744.2024.04.024

交通运输系统工程与信息 ›› 2024, Vol. 24 ›› Issue (4): 253-262.DOI: 10.16097/j.cnki.1009-6744.2024.04.024

空间异质下地铁建成环境与站点覆盖客流吸引度关系研究

陈红，李晨光，王铎，段超杰，姚振兴^*

长安大学，运输工程学院，西安710064

收稿日期:2024-03-03 修回日期:2024-05-24 接受日期:2024-06-03 出版日期:2024-08-25 发布日期:2024-08-22
作者简介:陈红(1963- )，女，湖南湘潭人，教授，博士。
基金资助:
国家自然科学基金青年科学基金(52002030)。

Relationship Between Built Environment of Metro Station and Passenger Attraction Considering Spatial Heterogeneity

CHENHong,LI Chenguang,WANG Duo,DUAN Chaojie,YAO Zhenxing^*

School of Transportation Engineering, Chang'an University, Xi'an 710064, China

Received:2024-03-03 Revised:2024-05-24 Accepted:2024-06-03 Online:2024-08-25 Published:2024-08-22
Supported by:
YoungScientistsFundoftheNationalNaturalScienceFoundationofChina(52002030)。

摘要/Abstract

摘要： 机器学习模型广泛应用于探究建成环境与客流的交互关系。然而，机器学习考虑的是全局关系，无法捕捉空间变化，为解决这一问题，本文从密度、多样性、设计、目的地可达性、可获得性和网络连通性等方面构建了11种建成环境指标，提出一种轻量级梯度提升机(LightGBM)与地理加权回归(GWR)的集成综合分析模型(SLightGBM)，以探究建成环境对站点覆盖客流吸引度的空间异质性和非线性影响，并将该模型与LightGBM，普通最小二乘法(OLS)和GWR进行比较，以揭示SLightGBM模型在回归效果上的优势。针对西安市的研究结果表明：SLightGBM模型的R2、MAE与RMSE分别达到了0.68、8379.16和11797.19，显著优于对比模型；建成环境因素存在空间异质性，工作人口密度和公交站点密度在中心区域最为重要，而餐饮密度在南部区域更显著；工作人口密度和餐饮密度与客流吸引度呈正相关，而最小换乘次数与客流吸引度呈负相关关系，且具有明显的协同作用。研究表明，影响因子空间差异性和阈值分析结果对于指导城市建设和改善公共交通系统具有重要的启示意义。

关键词: 城市交通, 空间特性, SLightGBM, 地铁客流, 阈值分析

Abstract: Machine learning models have been extensively applied in exploring the interaction between the built environment and passenger flow. However, machine learning primarily considers global relationships and fails to capture spatial variations. To address this issue, this paper defined 11 built environment variables from the aspects of density, diversity, design, destination accessibility, availability, and network connectivity. The study proposed an integrated ensemble analysis model, SLightGBM, combining Light Gradient Boosting Machine (LightGBM) with Geographically Weighted Regression (GWR), to investigate the spatial heterogeneity and nonlinear impact of the built environment on the attractiveness of station coverage. The SLightGBM model was compared with the LightGBM, Ordinary Least Squares(OLS), and GWR to demonstrate its regression superiority. The results from Xi'an city indicate that: (1) The SLightGBM model showed better performance than other models, with R2 value of 0.68, MAE of 8379.16, and RMSE of 11797.19. (2) The factors of the built environment vary across spaces. The densities of the employment and bus stops are most important in central areas, whereas the density of restaurants is more prominent in the southern regions. (3) Higher employment and restaurants densities are positively correlated with the attractiveness of metro ridership, while the minimum transfer times are negatively correlated with the attractiveness of metro ridership, showing a strong combined effect. This study indicates the importance of understanding spatial differences and threshold effects of these factors in urban planning and public transport system improvement.

Key words: urban traffic, spatial characteristics, SLightGBM, metro ridership, threshold analysis

中图分类号:

U268.6

陈红, 李晨光, 王铎, 段超杰, 姚振兴. 空间异质下地铁建成环境与站点覆盖客流吸引度关系研究[J]. 交通运输系统工程与信息, 2024, 24(4): 253-262.

CHENHong, LI Chenguang, WANG Duo, DUAN Chaojie, YAO Zhenxing. Relationship Between Built Environment of Metro Station and Passenger Attraction Considering Spatial Heterogeneity[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(4): 253-262.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.04.024

http://www.tseit.org.cn/CN/Y2024/V24/I4/253

参考文献

[1]崔叙,喻冰洁,杨林川,等.城市轨道交通出行的时空特征及影响因素非线性机制:基于梯度提升决策树的成都实证[J]. 经济地理,2021,41(7): 61-72. [CUI S, YU B J, YANG L C, et al. Spatio-temporal characteristics and non-linear influencing factors of urban rail transit: The case of Chengdu using the gradient boosting decision tree[J]. Economic Geography, 2021, 41(7): 61 72.]

[2]INGVARDSON J B, NIELSEN O A. How urban density, network topology and socio-economy influence public transport ridership: Empirical evidence from 48 European metropolitan areas[J]. Journal of Transport Geography, 2018, 72: 50-63.

[3]LOO B P Y, CHEN C, CHAN E T H. Rail-based transit oriented development: lessons from New York City and Hong Kong[J]. Landscape and Urban Planning, 2010, 97 (3): 202-212.

[4] GAN Z, FENG T, YANG M, et al. Analysis of metro station ridership considering spatial heterogeneity[J]. Chinese Geographical Science, 2019, 29: 1065-1077.

[5]LI L, ZHONG L, RAN B, et al. Analysis of the relationship between metro ridership and built environment: A machine learning method considering combinational features[J]. Tunnelling and Underground Space Technology, 2024, 144: 105564.

[6]杨红,申犁帆,胡议文,等.老年人地铁出行时空特征及与建成环境非线性关系:以武汉市为例[J].地理科学进展, 2023, 42(3): 491-504. [YANG H, SHEN L F, HU Y W, et al. Spatial and temporal characteristics of elderly people's metro travel behavior and its non linear relationship with the built environment: A case study of Wuhan City[J]. Progress in Geography, 2023, 42 (3): 491-504.]

[7]PENG B, ZHANG Y, LI C, et al. Nonlinear, threshold and synergistic effects of first/last-mile facilities on metro ridership[J]. Transportation Research Part D: Transport and Environment, 2023, 121: 103856.

[8] XU T, YANG H, CHEN D, et al. Exploring spatial variation in relationship between station level metro ridership and influencing variables, 2019[C]. 5th International Conference on Transportation Information and Safety (ICTIS), IEEE, 2019.

[9] MUSELLA G, CASTELLANO R, BRUNO E. Evaluating the spatial heterogeneity of innovation drivers: A comparison between GWR and GWPR[J]. METRON, 2023, 81(3): 343- 365.

[10] TASYUREK M, CELIK M. 4D-GWR: Geographically, altitudinal, and temporally weighted regression[J]. Neural Computing and Applications, 2022, 34(17): 14777 14791.

[11] 李想, 晏启鹏,骆晨,等.空间异质性建成环境对地铁与公交换乘客流的影响[J].交通运输系统工程与信息, 2023, 23(2): 100-110. [LI X, YAN Q P, LUO C, et al. Impact of built environment on flow of transfer passengers between subway and bus considering spatial heterogeneity[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(2): 100-110.]

[12] 马健霄, 赵飞燕,尹超英,等. 建成环境和出租车需求对网约车出行需求影响的时空间分异模式[J]. 交通运输系统工程与信息,2023,23(5):136-145. [MA J X, ZHAO F Y, YIN C Y, et al. Spatial-temporal heterogeneity effects of built environment and taxi demand on ride-hailing demand[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(5): 136-145.]

[13] 西安市自然资源和规划局.2021年西安市交通发展年度报告[R/OL]. (2023-10-11) [2024-03-04]. http: //zygh.xa.gov.cn/zwgk/ghjh/ 64a3d59af8fd1c1a703495a5. html. [Xi'an Municipal Bureau of Natural Resources and Planning. 2021 Annual Report on Urban Transport Development in Xi'an[R/OL]. (2023-10- 11) [2024-03-04]. http://zygh.xa.gov.cn/zwgk/ghjh/ 64a3d59af8fd1c1a703495a5. html.]

[14] PANG L, JIANG Y, WANG J, et al. Research of metro stations with varying patterns of ridership and their relationship with built environment, on the example of Tian**, China[J]. Sustainability, 2023, 15(12): 9533.

[15] 贺鹏, 李雯茜,李妍,等.建成环境对轨道交通客流非线性影响的空间特征[J].交通运输系统工程与信息, 2023, 23(3): 187-194. [HE P, LI W X, LI Y, et al. Spatial patterns of nonlinear effects of built environment on Beijing subway ridership[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(3): 187-194.]

空间异质下地铁建成环境与站点覆盖客流吸引度关系研究

Relationship Between Built Environment of Metro Station and Passenger Attraction Considering Spatial Heterogeneity

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]	刘涛, 郭家新, 韩莹, 唐春艳. 氢燃料电池公交研究文献综述及展望[J]. 交通运输系统工程与信息, 2024, 24(5): 1-13.
[2]	张兰怡, 徐艺诺, 王硕, 谢郑一, 翁大维, 王振昊, 胡喜生, 郑娉婷. 碳达峰背景下沿海城市群道路交通节能减排潜力[J]. 交通运输系统工程与信息, 2024, 24(5): 45-55.
[3]	张雅丽, 付锐, 魏文辉, 袁伟, 郭应时. 考虑速度模式的纯电动公交进出站生态驾驶策略[J]. 交通运输系统工程与信息, 2024, 24(5): 103-115.
[4]	茧敏, 陈绍宽, 王卓, 李昊. 城市轨道交通网络跨线列车开行方案优化模型研究[J]. 交通运输系统工程与信息, 2024, 24(5): 116-127.
[5]	孙元广, 邓澄远, 彭磊, 陈虹兵, 李纵然, 柏赟. 潮汐客流需求驱动的地铁列车不成对运行图节能优化方法[J]. 交通运输系统工程与信息, 2024, 24(5): 128-139.
[6]	岳昊, 董显龙, 王力, 曲秋莳, 张旭. 模块化公交系统车辆单元动态编组方案优化[J]. 交通运输系统工程与信息, 2024, 24(5): 160-172.
[7]	户佐安, 曾添, 杜俊, 魏易东, 王士博, 马毅. 双足运动微观视角下单列行人流建模与仿真研究[J]. 交通运输系统工程与信息, 2024, 24(5): 185-196.
[8]	金溪, 穆延. 暴雨内涝下城市路网抗涝韧性评估[J]. 交通运输系统工程与信息, 2024, 24(5): 226-236.
[9]	陈坚, 陈嘉果, 陈琦, 刘柯良, 代雪杨. 山地城市道路交通碳排放影响因素非线性关系模型[J]. 交通运输系统工程与信息, 2024, 24(5): 237-245.
[10]	牛振宁, 安琨, 马万经. 车网互动场景下电动网约车运营与充放电动态调度策略[J]. 交通运输系统工程与信息, 2024, 24(4): 50-59.
[11]	邓明君, 李书行, 李响, 张兵, 薛运强. 基于主线密度预测的快速路入口匝道控制方法[J]. 交通运输系统工程与信息, 2024, 24(4): 94-104.
[12]	李铁柱, 谢炳言, 刘天昊, 陈海波, 王召. 基于规则的信号交叉口纯电动公交节能驾驶策略[J]. 交通运输系统工程与信息, 2024, 24(4): 139-150.
[13]	姚恩建, 王鑫, 刘莎莎, 杨扬, 李成. 考虑机会充电与行程时间可靠性的区域多车型电动公交调度优化[J]. 交通运输系统工程与信息, 2024, 24(4): 151-165.
[14]	熊杰, 梁晶晶, 李向楠, 窦雪萍, 李同飞. 考虑分时电价和多车型的电动公交行车计划优化[J]. 交通运输系统工程与信息, 2024, 24(4): 188-199.
[15]	李洪运, 江志彬, 谷金晶, 刘伟, 王炳勋. 轨道交通远郊区段计划性停运对常乘客的转移影响[J]. 交通运输系统工程与信息, 2024, 24(4): 212-222.