Nonlinear effects of bike-sharing demands considering spatial heterogeneity

doi:10.3785/j.issn.1008-973X.2025.12.012

Journal of ZheJiang University (Engineering Science)

2025, Vol. 59

Issue (12): 2576-2584 DOI: 10.3785/j.issn.1008-973X.2025.12.012

Nonlinear effects of bike-sharing demands considering spatial heterogeneity

Qingchang LU(

),Kangjie YUAN

School of Electronics and Control Engineering, Chang’an University, Xi’an 710064, China

Download:

HTML

PDF(1820KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A GW-XGBoost model considering spatial heterogeneity was constructed, and the SHAP model was used to explain the extent and spatial differences in the role of built environment factors, in order to explore the influence of spatial heterogeneity on the nonlinear relationship between the built environment and bike-sharing trips. Compared with the geographically weighted regression and extreme gradient boosting tree models, the GW-XGBoost model significantly improved the explanatory and predictive power of the model by introducing geospatial weighting and adaptive bandwidth, with the overall goodness-of-fit increased by 15.59% on average, and it could reveal the intensity, direction and local differences of the built environment on the nonlinear impact of bike-sharing trips. The results showed that the built environment factors had a nonlinear impact on bike-sharing trips. When the population density reached 20000 persons per km², the impact turned from negative to positive. When the distance from CBD factor was between 15 and 20 km, its effect shifted from positive to negative, and then became stabilized when moving outward from the city center. When the floor area ratio reached 1.8, the impact effect turned from negative to positive. The research results provide a scientific basis and methodological support for the resource optimization of the urban bike-sharing system.

Key words： bike-sharing built environment machine learning spatial heterogeneity nonlinear effect

Received: 27 December 2024 Published: 25 November 2025

CLC:

U 491.1

Fund: 国家自然科学基金资助项目（72471035）.

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Qingchang LU
	Kangjie YUAN

Cite this article:

Qingchang LU,Kangjie YUAN. Nonlinear effects of bike-sharing demands considering spatial heterogeneity. Journal of ZheJiang University (Engineering Science), 2025, 59(12): 2576-2584.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2025.12.012 OR https://www.zjujournals.com/eng/Y2025/V59/I12/2576

空间异质性下共享单车出行量的非线性影响

为了探究空间异质性对建成环境与共享单车出行量之间非线性关系的影响，构建考虑空间异质性的GW-XGBoost模型，采用SHAP模型解释建成环境因素的作用程度和空间差异. 相较于地理加权回归和极端梯度提升树模型，模型GW-XGBoost通过引入地理空间加权和自适应带宽显著提升了模型解释力和预测力，整体拟合优度平均提高15.59%，同时能够揭示建成环境对单车出行量非线性影响的强度方向和局部差异. 结果显示，建成环境因素对单车出行量呈现非线性影响. 在人口密度增加到20 000 人/km²后，影响由负转正；离CBD的距离位于15~20 km时，由中心向外围影响效应由正转负随后趋于平稳；在容积率增加到1.8后，影响效应由负转正. 研究结果为城市共享单车系统的资源优化提供科学依据和方法支撑.

关键词： 共享单车, 建成环境, 机器学习, 空间异质性, 非线性影响

Fig.1 Study area and distribution of bike-sharing trips

Tab.1 Descriptive statistics and test results of variables

Tab.2 Model performance comparison

Fig.2 Distribution of R² in GW-XGBoost model

Fig.3 Relative importance of influencing variables

Tab.3 Local SHAP values for GW-XGBoost model

Fig.4 SHAP value distribution of population density

Fig.5 SHAP value distribution of distance to CBD

Fig.6 SHAP value distribution of floor area ratio

Fig.7 Impact of population density on bike-sharing trips

Fig.8 Impact of distance to CBD on bike-sharing trips

Fig.9 Impact of floor area ratio on bike-sharing trips


[1]	EREN E, UZ V E A review on bike-sharing: the factors affecting bike-sharing demand[J]. Sustainable Cities and Society, 2020, 54: 101882 doi: 10.1016/j.scs.2019.101882

[2]	CHEN Z, VAN LIEROP D, ETTEMA D Dockless bike-sharing systems: what are the implications?[J]. Transport Reviews, 2020, 40 (3): 333- 353 doi: 10.1080/01441647.2019.1710306

[3]	WANG X, LINDSEY G, SCHONER J E, et al Modeling bike share station activity: effects of nearby businesses and jobs on trips to and from stations[J]. Journal of Urban Planning and Development, 2016, 142: 04015001 doi: 10.1061/(ASCE)UP.1943-5444.0000273

[4]	ALCORN L G, JIAO J Bike-sharing station usage and the surrounding built environments in major Texas Cities[J]. Journal of Planning Education and Research, 2023, 43 (1): 122- 135 doi: 10.1177/0739456X19862854

[5]	WU C, KIM I, CHUNG H The effects of built environment spatial variation on bike-sharing usage: a case study of Suzhou, China[J]. Cities, 2021, 110: 103063 doi: 10.1016/j.cities.2020.103063

[6]	SUN Y, WANG Y, WU H How does the urban built environment affect dockless bikesharing-metro integration cycling? Analysis from a nonlinear comprehensive perspective[J]. Journal of Cleaner Production, 2024, 449: 141770 doi: 10.1016/j.jclepro.2024.141770

[7]	徐标, 路庆昌共享单车停车需求的多尺度时空影响因素[J]. 浙江大学学报: 工学版, 2023, 57 (2): 380- 391 XU Biao, LU Qingchang Multi-scale spatiotemporal influencing factors of bike-sharing parking demand[J]. Journal of Zhejiang University: Engineering Science, 2023, 57 (2): 380- 391

[8]	YANG L, YU B, LIANG Y, et al Time-varying and non-linear associations between metro ridership and the built environment[J]. Tunnelling and Underground Space Technology, 2023, 132: 104931 doi: 10.1016/j.tust.2022.104931

[9]	DING C, CAO X, WANG Y Synergistic effects of the built environment and commuting programs on commute mode choice[J]. Transportation Research Part A: Policy and Practice, 2018, 118: 104- 118 doi: 10.1016/j.tra.2018.08.041

[10]	HATAMI F, RAHMAN M M, NIKPARVAR B, et al Non-linear associations between the urban built environment and commuting modal split: a random forest approach and SHAP evaluation[J]. IEEE Access, 2023, 11: 12649- 12662 doi: 10.1109/ACCESS.2023.3241627

[11]	WANG S, GAO K, ZHANG L, et al Geographically weighted machine learning for modeling spatial heterogeneity in traffic crash frequency and determinants in US[J]. Accident Analysis and Prevention, 2024, 199: 107528 doi: 10.1016/j.aap.2024.107528

[12]	LV H, LI H, CHEN Y, et al An origin-destination level analysis on the competitiveness of bike-sharing to underground using explainable machine learning[J]. Journal of Transport Geography, 2023, 113: 103716 doi: 10.1016/j.jtrangeo.2023.103716

[13]	WANG Y, ZHAN Z, MI Y, et al Nonlinear effects of factors on dockless bike-sharing usage considering grid-based spatiotemporal heterogeneity[J]. Transportation Research Part D: Transport and Environment, 2022, 104: 103194 doi: 10.1016/j.trd.2022.103194

[14]	ZHOU T, FENG T, KEMPERMAN A Assessing the effects of the built environment and microclimate on cycling volume[J]. Transportation Research Part D: Transport and Environment, 2023, 124: 103936 doi: 10.1016/j.trd.2023.103936

[15]	ZHU B, HU S, KAPARIAS I, et al Revealing the driving factors and mobility patterns of bike-sharing commuting demands for integrated public transport systems[J]. Sustainable Cities and Society, 2024, 104: 105323 doi: 10.1016/j.scs.2024.105323

[16]	深圳市人大常委会. 深圳经济特区互联网租赁自行车管理若干规定[EB/OL]. (2021−07−06) [2024−12−20]. https://www.szrd.gov.cn/v2/zx/szfg/content/post_966176.html.

[17]	WU J, TA N, SONG Y, et al Urban form breeds neighborhood vibrancy: a case study using a GPS-based activity survey in suburban Beijing[J]. Cities, 2018, 74: 100- 108 doi: 10.1016/j.cities.2017.11.008

[18]	仝德, 高静, 龚咏喜城中村对深圳市职住空间融合的影响: 基于手机信令数据的研究[J]. 北京大学学报: 自然科学版, 2020, 56 (6): 1091- 1101 TONG De, GAO Jing, GONG Yongxi Impact of urban village on job-housing balance in Shenzhen: a study using mobile phone signaling data[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020, 56 (6): 1091- 1101

[19]	LI M, TU W, TONG H, et al Quantifying the nighttime economy–housing separation from a human activity standpoint: a case study in Shenzhen, China[J]. Cities, 2024, 148: 104894 doi: 10.1016/j.cities.2024.104894

[20]	朱岑远, 郑乐, 张毅萌基于MGWR的共享单车空间异质性分析[J]. 物流科技, 2024, 47 (24): 72- 77 ZHU Cenyuan, ZHENG Yue, ZHANG Yimeng Spatial heterogeneity analysis of bikesharing based on MGWR[J]. Logistics Sci-Tech, 2024, 47 (24): 72- 77

[21]	YAO Y, LIU X, LI X, et al Simulating urban land-use changes at a large scale by integrating dynamic land parcel subdivision and vector-based cellular automata[J]. International Journal of Geographical Information Science, 2017, 31 (12): 2452- 2479 doi: 10.1080/13658816.2017.1360494

[22]	GUO Y, YANG L, CHEN Y Bike share usage and the built environment: a review[J]. Frontiers in Public Health, 2022, 10: 848169 doi: 10.3389/fpubh.2022.848169

[23]	孙艺玲, 仝德, 曹超城市建成环境对公共自行车使用的影响机制研究: 以深圳市南山区为例[J]. 北京大学学报: 自然科学版, 2018, 54 (6): 1325- 1331 SUN Yiling, TONG De, CAO Chao How urban built environment affects the use of public bicycles: a case study of Nanshan District of Shenzhen[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54 (6): 1325- 1331

[24]	关昊天, 戢晓峰, 李武, 等建成环境对共享单车与地铁组合出行的影响关系[J]. 交通运输系统工程与信息, 2024, 24 (4): 200- 211 GUAN Haotian, JI Xiaofeng, LI Wu, et al Influence of built environment on integrated use of bike sharing and metro[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24 (4): 200- 211

[25]	EWING R, CERVERO R Travel and the built environment: a synthesis[J]. Transportation Research Record: Journal of the Transportation Research Board, 2001, 1780 (1): 87- 114 doi: 10.3141/1780-10

[26]	CHEN T, GUESTRIN C. XGBoost: a scalable tree boosting system [C]// 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016: 785−794.

[27]	XIAO L, LO S, LIU J, et al Nonlinear and synergistic effects of TOD on urban vibrancy: applying local explanations for gradient boosting decision tree[J]. Sustainable Cities and Society, 2021, 72: 103063 doi: 10.1016/j.scs.2021.103063

[28]	YANG W, LI Y, LIU Y, et al Environmental factors for outdoor jogging in Beijing: insights from using explainable spatial machine learning and massive trajectory data[J]. Landscape and Urban Planning, 2024, 243: 104969 doi: 10.1016/j.landurbplan.2023.104969

[29]	成骋, 陈文栋, 马洪生, 等基于Leiden算法的共享单车活动社区识别方法: 南京案例分析[J]. 交通信息与安全, 2023, 41 (2): 103- 111,156 CHENG Cheng, CHEN Wendong, MA Hongsheng, et al A method for identifying operation zones of free-floating shared bikes based on leiden algorithm: a case study of the city of Nanjing[J]. Journal of Transport Information and Safety, 2023, 41 (2): 103- 111,156

[30]	WANG J, WANG Z, WANG Z, et al Exploring the effect of neighbouring built and demographic environment on station-level bike-sharing trips under COVID-19[J]. Journal of Transport and Health, 2024, 36: 101818

[31]	BI H, LI A, HUA M, et al Examining the varying influences of built environment on bike-sharing commuting: empirical evidence from Shanghai[J]. Transport Policy, 2022, 129: 51- 65 doi: 10.1016/j.tranpol.2022.10.004

[32]	严亚磊, 于涛, 沈丽珍共享单车出行的建成环境影响机制: 以上海市为例[J]. 上海城市规划, 2020, (6): 85- 91 YAN Yalei, YU Tao, SHEN Lizhen The impact mechanism of built environment on shared bikes travel: a case study of Shanghai[J]. Shanghai Urban Planning Review, 2020, (6): 85- 91

[1]	Chong WANG,Lizhao DAI,Bin CHEN. Probabilistic model for shear capacity of corroded RC beams based on Gaussian process regression[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(11): 2352-2360.

[2]	Xinyang LI,Weifeng LIU,Xuning GUO,Yunling LI,Feilin ZHU,Ping’an ZHONG. Complementary characteristics of wind-photovoltaic-hydropower output in basin[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1505-1515.

[3]	Pan LI,Bing ZHOU,Tian CHAI,Yuan DENG,Qianxi PAN,Xiaojian WU. Vehicle obstacle avoidance control system considering driving style[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1377-1386.

[4]	Yufu HUO,Beihong JIN,Zhaoyi LIAO. Multi-modal information augmented model for micro-video recommendation[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(6): 1142-1152.

[5]	Su LI,Ze CHEN,Baoyan SONG,Haolin ZHANG. Enterprise composite blockchain construction method for business environment evaluation[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(5): 891-899.

[6]	Longsen HUANG,Jun FANG,Yunliang ZHOU,Zhicheng GUO. Optimization method of approximate aggregate query based on variational auto-encoder[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(5): 931-940.

[7]	Biao XU,Qing-chang LU. Multi-scale spatiotemporal influencing factors of bike-sharing parking demand[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(2): 380-391.

[8]	Yi-cong GAO,Yan-kun WANG,Shao-mei FEI,Qiong LIN. Intelligent proofreading method of engineering drawing based on transfer learning[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(5): 856-863, 889.

[9]	Peng ZHANG,Zi-du TIAN,Hao WANG. Flight parameter data anomaly detection method based on improved generative adversarial network[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(10): 1967-1976.

[10]	Fa-ming HUANG,Li-han PAN,Chi YAO,Chuang-bing ZHOU,Qing-hui JIANG,Zhi-lu CHANG. Landslide susceptibility prediction modelling based on semi-supervised machine learning[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(9): 1705-1713.

[11]	Jia-hao REN,Hai-ou WANG,Jiang-kuan XING,Kun LUO,Jian-ren FAN. Lower-dimensional approximation models of tangential strain rate of turbulent flames[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(6): 1128-1134.

[12]	You ZHAN,Qiang LI,Xiao-tian MA,Chen-ping WANG,Yan-jun QIU. Macro and micro texture based prediction of pavement surface friction[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(4): 684-694.

[13]	Yong YU,Jing-yuan XUE,Sheng DAI,Qiang-wei BAO,Gang ZHAO. Quality prediction and process parameter optimization method for machining parts[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(3): 441-447.

[14]	Qiao-hong CHEN,YI CHEN,Wen-shu Li,Yu-bo JIA. Clothing image classification based on multi-scale SE-Xception[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(9): 1727-1735.

[15]	Xin-wei MA,Yan-jie JI,Xue JIN,Yang XU,Rui-ming CAO. Analysis on travel characteristics of bike-sharing users and influence factors on way to travel[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(6): 1202-1209.

Viewed

Full text

Abstract

Cited

Shared

Discussed