Investigating the Nonlinear Effect of Built Environment Factors on Metro Station-Level Ridership under Optimal Pedestrian Catchment Areas via the Machine Learning Method
Source abstract
Abstract
Exploring the built environment factor’s impact on metro ridership can help develop metro station area planning strategies. This is in order to compensate for the shortcomings of previous studies, which mostly used all uniform pedestrian catchment areas (PCA) around metro stations. Beijing was divided into two zones and 12 built environment explanatory variables were selected as independent variables based on the “7D” dimension of the built environment. The boarding ridership during the morning peak hours was used as the dependent variable. Nineteen PCA radii from 200 to 2000 m were assumed. The optimal PCA of metro stations for each zone was determined by using the eXtreme Gradient Boosting (XGBoost) model with the objective of minimizing the Mean Absolute Percentage Error (MAPE). The nonlinear impact of the built environment factor of each zone on metro ridership is analyzed under the optimal PCA of metro stations. The study results show that (1) the optimal PCAs of metro stations inside the 4th Ring Road and outside the 4th Ring Road are the circular buffer zones with a radius of 800 m and 1300 m, respectively. (2) There is a nonlinear influence of the built environment factor on metro ridership, with strong threshold effects and spatial heterogeneity. The PCA results can be used for the built environment’s zoning of metro stations. The XGBoost model and the nonlinear impact results provide significant implications for the practice of station-level ridership forecasting and integrating TOD development and built environment renewal.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Urban Transport and Accessibility · Transportation Planning and Optimization · Noise Effects and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Architecture and Art, Hebei University of Engineering, Handan 056038, China
Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing 100124, China
Funding
Hebei Social Science Development Research Project
References (66)
Show source-provided references
1. Exploring the impacts of land use by service coverage and station-level accessibility on rail transit ridership10.1016/j.jtrangeo.2014.03.013 ↗
2. Factors affecting public transportation usage rate: Geographically weighted regression10.1016/j.tra.2015.05.016 ↗
3. Examining the relationship between built environment and metro ridership at station-to-station level10.1016/j.trd.2020.102332 ↗
4. What influences Metro station ridership in China? Insights from Nanjing10.1016/j.cities.2013.07.002 ↗
5. Li, S., Liu, X., Li, Z., Wu, Z., Yan, Z., Chen, Y., and Gao, F. (2018). Spatial and Temporal Dynamics of Urban Expansion along the Guangzhou–Foshan Inter-City Rail Transit Corridor, China. Sustainability, 10.10.3390/su10030593 ↗
6. Factors affecting car ownership and mode choice in rail transit-supported suburbs of a large Chinese city10.1016/j.tra.2016.08.027 ↗
7. The relationship between car ownership and public transport provision: A case study of Hong Kong10.1016/S0967-070X(01)00028-2 ↗
8. Car ownership and public transport use: Revisiting the interaction10.1007/BF01099974 ↗
9. Congestion relief and public transport: An enhanced method using disaggregate mode shift evidence10.1016/j.cstp.2018.06.012 ↗
10. Creating and applying public transport indicators to test pathways of behaviours and health through an urban transport framework10.1016/j.jth.2017.01.007 ↗
11. Quantifying spatial gaps in public transport supply based on social needs10.1016/j.jtrangeo.2008.12.002 ↗
12. Suburbanization and transit-oriented development in China10.1016/j.tranpol.2008.12.011 ↗
13. How does the propensity of living near rail transit moderate the influence of rail transit on transit trip frequency in Xi’an?10.1016/j.jtrangeo.2016.05.016 ↗
14. Central People’s Government of the People’s Republic of China (2023, April 12). Modern Comprehensive Transport System Development Plan for the Fourteenth Five-Year Plan, Available online: http://www.gov.cn/zhengce/content/2022-01/18/content_5669049.htm.
15. Gazette, P. (2023, May 23). Beijing Underground’s Daily Passenger Volume Breaks 11 Million, Some Stations Will Start to Take Temporary Flow Restriction Measures in the Morning Rush Hour. Available online: https://baijiahao.baidu.com/s?id=1758039502843960181&wfr=spider&for=pc.
16. Analysis of Metro ridership at station level and station-to-station level in Nanjing: An approach based on direct demand models10.1007/s11116-013-9492-3 ↗
17. Wang, Z., Song, J., Zhang, Y., Li, S., Jia, J., and Song, C. (2022). Spatial Heterogeneity Analysis for Influencing Factors of Outbound Ridership of Subway Stations Considering the Optimal Scale Range of “7D” Built Environments. Sustainability, 14.10.3390/su142316314 ↗
18. Spatiotemporal exploration of the non-linear impacts of accessibility on metro ridership10.1016/j.jtrangeo.2022.103380 ↗
19. Understanding cycling distance according to the prediction of the XGBoost and the interpretation of SHAP: A non-linear and interaction effect analysis10.1016/j.jtrangeo.2022.103414 ↗
20. Nonlinear and threshold effects of traffic condition and built environment on dockless bike sharing at street level10.1016/j.jtrangeo.2022.103375 ↗
21. How does the station-area built environment influence Metrorail ridership? Using gradient boosting decision trees to identify non-linear thresholds10.1016/j.jtrangeo.2019.04.011 ↗
22. Land use characteristics of subway catchment areas and their influence on subway ridership in Seoul10.1016/j.jtrangeo.2015.08.002 ↗
23. Spatially varying impacts of built environment factors on rail transit ridership at station level: A case study in Guangzhou, China10.1016/j.jtrangeo.2019.102631 ↗
24. The varying patterns of rail transit ridership and their relationships with fine-scale built environment factors: Big data analytics from Guangzhou10.1016/j.cities.2019.102580 ↗
25. Threshold and moderating effects of land use on metro ridership in Shenzhen: Implications for TOD planning10.1016/j.jtrangeo.2020.102878 ↗
26. Travel Demand and the 3Ds: Density, Diversity, and Design10.1016/S1361-9209(97)00009-6 ↗
27. Impacts of Mixed Use and Density on Utilization of Three Modes of Travel: Single-Occupant Vehicle, Transit, and Walking
28. Transit-Oriented Development in the Sun Belt10.1177/0361198196155200120 ↗
29. Correlates of Walking for Transportation or Recreation Purposes10.1123/jpah.3.s1.s77 ↗
30. Factors influencing light-rail station boardings in the United States10.1016/j.tra.2003.10.006 ↗
31. Factors generating boardings at Metro stations in the Seoul metropolitan area10.1016/j.cities.2010.05.001 ↗
32. Relationship of Walk Access Distance to Rapid Rail Transit Stations with Personal Characteristics and Station Context10.1061/(ASCE)UP.1943-5444.0000155 ↗
33. Transit ridership forecasting at station level: An approach based on distance-decay weighted regression10.1016/j.jtrangeo.2011.05.004 ↗
34. Transit-oriented development in a high-density city: Identifying its association with transit ridership in Seoul, Korea10.1016/j.cities.2010.09.004 ↗
35. Rail-based transit-oriented development: Lessons from New York City and Hong Kong10.1016/j.landurbplan.2010.06.002 ↗
36. Application of geographically weighted regression to the direct forecasting of transit ridership at station-level10.1016/j.apgeog.2012.01.005 ↗
37. Factors influencing trip generation on metro system in Madrid (Spain)10.1016/j.trd.2018.11.021 ↗
38. Improvements to the calibration of a geographically weighted regression with parameter-specific distance metrics and bandwidths10.1016/j.compenvurbsys.2018.03.012 ↗
39. Neighbourhood effects on station-level transit use: Evidence from the Taipei metro10.1016/j.jtrangeo.2021.103127 ↗
40. Yu, L., Cong, Y., and Chen, K. (2020). Determination of the Peak Hour Ridership of Metro Stations in Xi’an, China Using Geographically-Weighted Regression. Sustainability, 12.10.3390/su12062255 ↗
41. Applying a random forest method approach to model travel mode choice behavior10.1016/j.tbs.2018.09.002 ↗
42. A comparative study of machine learning classifiers for modeling travel mode choice10.1016/j.eswa.2017.01.057 ↗
43. Prediction and behavioral analysis of travel mode choice: A comparison of machine learning and logit models10.1016/j.tbs.2020.02.003 ↗
44. Nonlinear effects of built environment features on metro ridership: An integrated exploration with machine learning considering spatial heterogeneity10.1016/j.scs.2023.104613 ↗
45. Liang, W., Luo, S., Zhao, G., and Wu, H. (2020). Predicting Hard Rock Pillar Stability Using GBDT, XGBoost, and LightGBM Algorithms. Mathematics, 8.10.3390/math8050765 ↗
46. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
47. Nonlinear relationships and interaction effects of an urban environment on crime incidence: Application of urban big data and an interpretable machine learning method10.1016/j.scs.2023.104419 ↗
48. Spatio-Temporal Segmented Traffic Flow Prediction with ANPRS Data Based on Improved XGBoost10.1155/2021/5559562 ↗
49. Ran, D., Jiaxin, H., and Yuzhe, H. (2020, January 13–14). Application of a Combined Model based on K-means++ and XGBoost in Traffic Congestion Prediction. Proceedings of the 2020 5th International Conference on Smart Grid and Electrical Automation (ICSGEA), Zhangjiajie, China.10.1109/ICSGEA51094.2020.00095 ↗
50. Lv, C.X., An, S.Y., Qiao, B.J., and Wu, W. (2021). Time series analysis of hemorrhagic fever with renal syndrome in mainland China by using an XGBoost forecasting model. BMC Infect. Dis., 21.10.1186/s12879-021-06503-y ↗
51. Traffic Incident Clearance Time Prediction and Influencing Factor Analysis Using Extreme Gradient Boosting Model10.1155/2020/6401082 ↗
52. Non-linear associations between built environment and active travel for working and shopping: An extreme gradient boosting approach10.1016/j.jtrangeo.2021.103034 ↗
53. To walk or not to walk? Examining non-linear effects of streetscape greenery on walking propensity of older adults10.1016/j.jtrangeo.2021.103099 ↗
54. The application of XGBoost and SHAP to examining the factors in freight truck-related crashes: An exploratory analysis10.1016/j.aap.2021.106153 ↗
55. Impacts of building configurations on urban stormwater management at a block scale using XGBoost10.1016/j.scs.2022.104235 ↗
56. The relationship between urban form and station boardings for Bogotá’s BRT10.1016/j.tra.2007.10.006 ↗
57. Estimation of transit ridership based on spatial analysis and precise land use data
58. What Really Matters for Increasing Transit Ridership: Understanding the Determinants of Transit Ridership Demand in Broward County, Florida10.1177/0042098012443864 ↗
59. Travel and the Built Environment10.1080/01944361003766766 ↗
60. How does the built environment affect transit use by train, tram and bus?10.5198/jtlu.2020.1739 ↗
61. Understanding the impact of built environment on metro ridership using open source in Shanghai10.1016/j.cities.2019.05.013 ↗
62. Discovering the spatio-temporal impacts of built environment on metro ridership using smart card data10.1016/j.cities.2019.05.028 ↗
63. Walk the line: Station context, corridor type and bus rapid transit walk access in Jinan, China10.1016/j.jtrangeo.2011.09.007 ↗
64. Nano properties analysis via fourth multiplicative ABC indicator calculating10.1016/j.arabjc.2017.12.024 ↗
65. Lundberg, S.M., and Su-In, L. (2017, January 4–9). A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
66. Mean Absolute Percentage Error for regression models10.1016/j.neucom.2015.12.114 ↗