On the Nonlinear Relationship Between Land Use and Urban Rail Transit Passenger Flow

doi:10.12141/j.issn.1000-565X.230125

Abstract

Abstract:

The impact of land use on passenger flow within the influence scope of urban rail transit stations has different spatiotemporal differentiation characteristics. To explore the complex nonlinear relationship between land use and passenger flow at different stations, this paper proposed a differentiation identification method based on the spatial distribution of land use variables, and through time-phased multiscale geographic weighted regression, station clustering indicators that can characterize the spatiotemporal changing characteristics of land use impact on passenger flow were obtained. K-means++ algorithm was used to divide the stations into four categories, and the complex nonlinear relationship between land use and railway passenger flow under different categories was explored based on the improved gradient boosting decision tree model. Research shows that the accuracy of nonlinear model can be effectively improved by capturing the spatiotemporal heterogeneity of the relationship between the land use and passenger flow and classifying the stations properly. According to the output results, the key factors are different for each category. For the first category, the bus station number and sidewalk density have top relative importance value of 61.35% and 30.08% respectively; the key factors are the same for the fourth, but with an importance value decreasing from 61.35% to 30.31% for the bus station number. For the second category, the building densityhas the greatest impact with a relative ratio of 66.57%, and on the contrary, which only accounts for 5.59% for the third one. Meanwhile, there are significant and varying threshold effects on the relationship between land use and rail transit passenger flow. The result shows that different types of stations should put different emphasis on land use development, and land use design indicators should be controlled within a reasonable range. This research will provide theoretical support and quantitative guidance for the formulation of differentiated land use development strategies around stations.

Key words: multiscale geographic weighted regression, land use, spatial differentiation, threshold effect, gradient boosting decision tree, rail transit passenger flow

CLC Number:

U491.1

WEI Liying, SHI Jingjing. On the Nonlinear Relationship Between Land Use and Urban Rail Transit Passenger Flow[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(5): 43-51.

Figures/Tables 11

Fig.1

Fig.2

Table 1

Fig.3

Fig.4

Fig.5

Fig.6

Table 2

Table 3

Relative importance of independent variables"

变量	聚类1		聚类2		聚类3		聚类4
变量	重要性/%	排序	重要性/%	排序	重要性/%	排序	重要性/%	排序
$X b$	6.88	3	66.57	1	5.59	5	0.49	5
$X m$	3.09	5	6.37	5	11.55	4	16.68	4
$X p$	61.35	1	7.19	4	54.75	1	30.31	2
$X w$	30.08	2	58.59	2	14.04	3	34.43	1
$X a$	5.48	4	27.85	3	19.67	2	18.58	3

Table 3

Fig.7

Fig.8

References 19

1	SUNG H， CHOI K， LEE S，et al ．Exploring the impacts of land use by service coverage and station-level accessibility on rail transit ridership［J］．Journal of Transport Geography，2014，36：134-140．
2	王淑伟，孙立山，郝思源，等．基于精细化用地的轨道客流直接估计模型［J］．交通运输系统工程与信息，2015，15（3）：37-43．
	WANG Shu-wei， SUN Li-shan， HAO Si-yuan，et al ．Station level transit ridership direct estimation model based on precise land use［J］．Journal of Transportation Systems Engineering and Information Technology，2015，15（3）：37-43．
3	ZHAO J， DENG W， SONG Y，et al ．What influences metro station ridership in China？ insights from Nanjing［J］．Cities，2013，35：114-124．
4	孔祥夫，杨家文．土地利用视角下的轨道站点客流预测——以深圳市为例［J］．地理科学，2018，38（12）：2074-2083．
	KONG Xiangfu， YANG Jiawen ．A new method for forecasting station-level transit ridership from land-use perspective： the case of Shenzhen City［J］．Geographical Science，2018，38（12）：2074-2083．
5	崔叙，喻冰洁，梁朋朋，等．基于“客流-用地”的城市轨道交通站点类型识别与空间再平衡研究——以成都市为例［J］．现代城市研究，2021（7）：68-79．
	CUI Xu， YU Bingjie， LIANG Pengpeng，et al ．Urban rail transit station type identification and job-housing spatial rebalancing based on passenger flow and land use： taking Chengdu as an example［J］．Modern Urban Research，2021（7）：68-79．
6	RODRIGUEZ D A， KANG C D ．A typology of the built environment around rail stops in the global transit-oriented city of Seoul，Korea［J］．Cities，2020，100：102663/1-12．
7	YU Z， ZHU X， LIU X ．Characterizing metro stations via urban function：thematic evidence from transit-oriented development （TOD） in Hong Kong［J］．Journal of Transport Geography，2022，99：103299/1-11．
8	岂常禄，胡昊．基于混合地理加权回归的城市轨道交通站点客流预测研究［J］．铁道科学与工程学报，2021，18（7）：1903-1909．
	QI Changlu， HU Hao ．Research on ridership forecast of urban rail transit station based on mixed geographic weighted regression［J］．Journal of Railway Science and Engineering，2021，18（7）：1903-1909．
9	DING C， CAO X， LIU C ．How does the station-area built environment influence metrorail ridership？ using gradient boosting decision trees to identify non-linear thresholds［J］．Journal of Transport Geography，2019，77：70-78．
10	DU Q， ZHOU Y， HUANG Y，et al ．Spatiotemporal exploration of the non-linear impacts of accessibility on metro ridership［J］．Journal of Transport Geography，2022，102：103380/1-17．
11	IBRAEVA A， CORREIA G， SILVA C，et al ．Transit-oriented development：a review of research achievements and challenges［J］．Transportation Research Part A：Policy and Practice，2020，132：110-130．
12	谭佩珊，麦可，张亚涛，等．利用多源城市数据划定地铁站点吸引范围［J］．地球信息科学学报，2021，23（4）：593-603．
	TAN Peishan， Ke MAI， ZHANG Yatao，et al ．Identifying the catchment area of metro stations using multi-source urban data［J］．Journal of Geo-Information Science，2021，23（4）：593-603．
13	姜莉，温惠英．空间耦合连接性的TOD测度模型构建及应用研究［J］．交通运输系统工程与信息，2021，21（4）：239-247．
	JIANG Li， WEN Hui-ying ．TOD Measurement model with spatial coupling connectivity［J］．Journal of Transportation Systems Engineering and Information Technology，2021，21（4）：239-247．
14	高德辉，许奇，陈培文，等．城市轨道交通客流与精细尺度建成环境的空间特征分析［J］．交通运输系统工程与信息，2021，21（6）：25-32．
	GAO De-hui， XU Qi， CHEN Pei-wen，et al ．Spatial characteristics of urban rail transit passenger flows and fine-scale built environment［J］．Journal of Transportation Systems Engineering and Information Technology，2021，21（6）：25-32．
15	LIU J， WANG B， XIAO L ．Non-linear associations between built environment and active travel for working and shopping：an extreme gradient boosting approach［J］．Journal of Transport Geography，2021，92：103034/1-12．
16	DING C， CAO X， NAESS P ．Applying gradient boosting decision trees to examine non-linear effects of the built environment on driving distance in Oslo［J］．Transportation Research，Part A：Policy and Practice，2018，110：107-117．
17	李亮，赵星，张海燕，等．基于时空维度变量的杭州市轨道交通站点聚类研究［J］．北京交通大学学报，2022，46（4）：31-42．
	LI Liang， ZHAO Xing， ZHANG Haiyan，et al ．Clustering research on Hangzhou metro station based on spatio-temporal variables［J］．Journal of Beijing Jiaotong University，2022，46（4）：31-42．
18	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 Xiao-feng， QIAO Xin ．Nonlinear influence of built environment on pedestrian traffic accident severity［J］．Journal of Transportation Systems Engineering and Information Technology，2023，23（1）：314-323．
19	SHAO Q F， ZHANG W J， CAO X Y，et al ．Threshold and moderating effects of land use on metro ridership in Shenzhen：implications for TOD planning［J］．Journal of Transport Geography，2020，89：102878/1-12．

变量	最大值	最小值	均值	标准差
建筑密度/（km²·km^-2）	0.759	0.002	0.456	0.215
用地混合熵	0.957	0.378	0.883	0.068
公交站点数量/座	30	2	20.17	15.14
慢行密度/（km·km^-2）	0.015	0.003	0.000 95	0.001 83
可达性/km	1.263	0.491	0.700	0.402

聚类	r²	MAE	MSE		r²	MAE	MSE
1	0.634	0.13	0.04	4	0.634	0.12	0.05
2	0.591	0.15	0.09	未分类	0.567	0.19	0.13
3	0.645	0.11	0.05

[1]	ZHU Caihua, LI Yan, SUN Xiaoli, et al. Traffic Demand Prediction of Urban Public Bicycles with the Consideration of Land Use [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(3): 9-20,37.
[2]	XU Jianmin, WEI Xin, LIN Yongjie, et al. Urban Vehicle Trip Chain Ｒeconstruction Based on Gradient Boosting Decision Tree [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(7): 55-64.
[3]	Hu Yu-cong Chen Hai-wei Ouyang Jian Piao Lian-hua Liang Feng-ming. Land-Use Spatial Distribution Simulation and Traffic Demand Forecasting in New Town [J]. Journal of South China University of Technology (Natural Science Edition), 2014, 42(12): 26-34.
[4]	Ding Chuan Xie Bing-lei Wang Yao-wu. Interactive Relationship Between Urban Arterial Transit Route and Land Use in TOD Mode [J]. Journal of South China University of Technology (Natural Science Edition), 2013, 41(2): 66-73.
[5]	Chen Da-wei Xiao Wei-zhou Li Xu-hong He Liu. Forecast and Analysis of Passenger Flow of Urban Rail Transit Under Iterative Feedback Constraints [J]. Journal of South China University of Technology (Natural Science Edition), 2011, 39(8): 99-103.