Holiday metro travel for people with disabilities: exploring spatiotemporal patterns and nonlinear built environment impacts

Abstract

The unique physical characteristics and travel preferences of disabled individuals may lead to specific spatiotemporal characteristics of subway travel. This difference may also be temporally heterogeneous on holidays versus every day, and its association with the built environment may be significantly different. However, few studies have investigated such differences in depth. This study explores the differences in the spatiotemporal characteristics of subway travel for people with disabilities using subway swipe data from Wuhan, China, on the May 1 holiday and every day, and analyzes the effects of the built environment on holiday and everyday travel for people with disabilities compared to non-disabled people using XGBoost and SHAP models. The results show that compared with non-disabled people, the spatial and temporal changes of passenger flow of disabled people are less affected by holidays, and the spatial distribution of passenger flow and traveling time is reduced and contracted, respectively, based on weekdays. Second, the relative importance of each element of the built environment on metro passenger flows for the disabled and the non-disabled differed significantly, with medical facilities and network density being the most important variables for the disabled, both on holidays and weekdays. Comparatively, non-disabled people are more affected by holidays, with the highest contribution to disabled metro patronage on weekdays being made by food and beverage facilities, which changes to attractions on holidays. In addition, all built environment elements show nonlinear and significant threshold effects on disabled and non-disabled metro ridership. Finally, the built environment has an interaction effect on disabled subway passenger flow, for example, the closer to the sub-center, the higher the number of firms, the more inhibitory effect on disabled weekday and holiday subway passenger flow. The results of the study will contribute to an in-depth understanding of the spatial and temporal characteristics of metro travel for among disabled individuals, thereby developing disability-friendly measures for rail transit systems.

Keywords

People with disabilities / Urban rail transit / Built environment / XGBoost-SHAP / Nonlinear relationship / Synergies

References

[1] World Health Organization. (2022). Global report on health equity for persons with disabilities: executive summary. https://www.who.int/publications-detail-redirect/9789240063624. Accessed 7 Jun 2024

[2] BascomGW, ChristensenKM. The impacts of limited transportation access on persons with disabilities’ social participation. J Transp Health, 2017, 7: 227-234.

[3] HenlyM, BruckerDL. Transportation patterns demonstrate inequalities in community participation for working-age Americans with disabilities. Transp Res A Policy Pract, 2019, 130: 93-106.

[4] WongS. Traveling with blindness: a qualitative space-time approach to understanding visual impairment and urban mobility. Health Place, 2018, 49: 85-92.

[5] LindsayS. Accessible and inclusive transportation for youth with disabilities: exploring innovative solutions. Disabil Rehabil, 2020, 42: 1131-1140.

[6] Brumbaugh S (2018) Travel patterns of American adults with disabilities [issue brief]. https://doi.org/10.21949/1524180

[7] ChenK, ZhaoP, QinK, et al.. Towards healthcare access equality: understanding spatial accessibility to healthcare services for wheelchair users. Comput Environ Urban Syst, 2024, 108. 102069

[8] ZhaoY, WuY, ZhangX, et al.. Analysis and prediction of dockless shared bike demand evolving around urban rail transit stations: case study in Shenzhen, China. Urban Rail Transit, 2023, 9: 368-382.

[9] LiuJ, ShiW. A cross-boundary travel tale: unraveling Hong Kong residents’ mobility pattern in Shenzhen by using metro smart card data. Appl Geogr, 2021, 130. 102416

[10] LiuZ, ZhangA, YaoY, et al.. Analysis of the performance and robustness of methods to detect base locations of individuals with geo-tagged social media data. Int J Geogr Inf Sci, 2021, 35: 609-627.

[11] (2023) Calendar events’ influence on the relationship between metro ridership and the built environment: A heterogeneous effect analysis in Shenzhen, China. Tunnell Undergr Space Technol 141:105388. https://doi.org/10.1016/j.tust.2023.105388

[12] KepaptsoglouK, StathopoulosA, KarlaftisMG. Ridership estimation of a new LRT system: direct demand model approach. J Transp Geogr, 2017, 58: 146-156.

[13] LiuS, YaoE, LiB. Exploring urban rail transit station-level ridership growth with network expansion. Transp Res Part D Transp Environ, 2019, 73: 391-402.

[14] Vergel-TovarCE, RodriguezDA. The ridership performance of the built environment for BRT systems: evidence from Latin America. J Transp Geogr, 2018, 73: 172-184.

[15] GanZ, YangM, FengT, TimmermansHJP. Examining the relationship between built environment and metro ridership at station-to-station level. Transp Res Part D Transp Environ, 2020, 82. 102332

[16] WongS, McLaffertySL, PlaneyAM, PrestonVA. Disability, wages, and commuting in New York. J Transp Geogr, 2020, 87. 102818

[17] ZhangS, YangY, ZhenF, et al.. Understanding the travel behaviors and activity patterns of the vulnerable population using smart card data: an activity space-based approach. J Transp Geogr, 2021, 90. 102938

[18] Van WeeB, HandyS. Key research themes on urban space, scale, and sustainable urban mobility. Int J Sustain Transp, 2016, 10: 18-24.

[19] DingC, CaoX, LiuC. How does the station-area built environment influence Metrorail ridership? Using gradient boosting decision trees to identify non-linear thresholds. J Transp Geogr, 2019, 77: 70-78.

[20] YangH, ZhangQ, WenJ, et al.. Multi-group exploration of the built environment and metro ridership: comparison of commuters, seniors and students. Transp Policy, 2024, 155: 189-207.

[21] LiL, ZhongL, RanB, DuB. Analysis of the relationship between metro ridership and built environment: a machine learning method considering combinational features. Tunnell Undergr Space Technol, 2024, 144. 105564

[22] MogajiE, NguyenNP. Transportation satisfaction of disabled passengers: evidence from a developing country. Transp Res Part D Transp Environ, 2021, 98. 102982

[23] BezyakJL, SabellaSA, GattisRH. Public transportation: an investigation of barriers for people with disabilities. J Disabil Policy Stud, 2017, 28: 52-60.

[24] KwonK, AkarG. People with disabilities and use of public transit: the role of neighborhood walkability. J Transp Geogr, 2022, 100. 103319

[25] LiuJ, ShiW, ChenP. Exploring travel patterns during the holiday season—a case study of Shenzhen Metro system during the Chinese Spring Festival. ISPRS Int J Geo-Inf, 2020, 9651.

[26] ChenE, YeZ, WangC, ZhangW. Discovering the spatio-temporal impacts of built environment on metro ridership using smart card data. Cities, 2019, 95. 102359

[27] QinT, DongW, HuangH. Perceptions of space and time of public transport travel associated with human brain activities: a case study of bus travel in Beijing. Comput Environ Urban Syst, 2023, 99. 101919

[28] EwingR, CerveroR. Travel and the built environment: a meta-analysis. J Am Plann Assoc, 2010, 76: 265-294.

[29] YangL, YuB, LiangY, et al.. Time-varying and non-linear associations between metro ridership and the built environment. Tunnell Undergr Space Technol, 2023, 132. 104931

[30] BotticelloAL, RohrbachT, CobboldN. Disability and the built environment: an investigation of community and neighborhood land uses and participation for physically impaired adults. Ann Epidemiol, 2014, 24: 545-550.

[31] KerrJ, RosenbergD, FrankL. The role of the built environment in healthy aging: community design, physical activity, and health among older adults. J Plann Lit, 2012, 27: 43-60.

[32] ZhengJ, HouY, HuM, et al.. Spatiotemporal patterns and factors influencing metro ridership of people with disabilities. Transp Res Part D Transp Environ, 2024, 136. 104478

[33] AnD, TongX, LiuK, ChanEHW. Understanding the impact of built environment on metro ridership using open source in Shanghai. Cities, 2019, 93: 177-187.

[34] SchreuerN, PlautP, GolanL, SachsD. The relations between walkable neighbourhoods and active participation in daily activities of people with disabilities. J Transp Health, 2019, 15. 100630

[35] SuS, WangZ, LiB, KangM. Deciphering the influence of TOD on metro ridership: an integrated approach of extended node-place model and interpretable machine learning with planning implications. J Transp Geogr, 2022, 104. 103455

[36] ValeDS, VianaCM, PereiraM. The extended node-place model at the local scale: evaluating the integration of land use and transport for Lisbon’s subway network. J Transp Geogr, 2018, 69: 282-293.

[37] (2023) Multiscale spatial analysis of metro usage and its determinants for sustainable urban development in Shenzhen, China. Tunnell Undergr Space Technol 133:104912. https://doi.org/10.1016/j.tust.2022.104912

[38] CardozoOD, García-PalomaresJC, GutiérrezJ. Application of geographically weighted regression to the direct forecasting of transit ridership at station-level. Appl Geogr, 2012, 34: 548-558.

[39] DingC, CaoX, YuB, JuY. Non-linear associations between zonal built environment attributes and transit commuting mode choice accounting for spatial heterogeneity. Transp Res Part A Policy Pract, 2021, 148: 22-35.

[40] DongX. Investigating changes in longitudinal associations between declining bus ridership, bus service, and neighborhood characteristics. J Public Transp, 2022, 24. 100011

[41] IngvardsonJB, NielsenOA. How urban density, network topology and socio-economy influence public transport ridership: empirical evidence from 48 European metropolitan areas. J Transp Geogr, 2018, 72: 50-63.

[42] ZhangM, WangL. The impacts of mass transit on land development in China: the case of Beijing. Res Transp Econ, 2013, 40: 124-133.

[43] YangH, PengJ, LuY, et al.. Nonlinear impact of built environment on people with disabilities’ metro use behavior. Appl Geogr, 2024, 169. 103323

[44] ShaoQ, ZhangW, CaoX, et al.. Threshold and moderating effects of land use on metro ridership in Shenzhen: implications for TOD planning. J Transp Geogr, 2020, 89. 102878

[45] ZhouX, ZhaoZ, FuW, et al.. The impact of heterogeneous accessibility to metro stations on land use changes in a bike-sharing context. J Transp Geogr, 2024, 121. 104019

[46] GuoL, YangS, ZhangQ, et al.. Examining the nonlinear and synergistic effects of multidimensional elements on commuting carbon emissions: a case study in Wuhan, China. Int J Environ Res Public Health, 2023, 201616.

[47] Pan B (2018) Application of XGBoost algorithm in hourly PM2.5 concentration prediction. IOP Conf Ser: Earth Environ Sci 113:012127. https://doi.org/10.1088/1755-1315/113/1/012127

[48] Zamani JoharestaniM, CaoC, NiX, et al.. PM2.5 prediction based on random forest, XGBoost, and deep learning using multisource remote sensing data. Atmosphere, 2019, 10. 373

[49] Shwartz-ZivR, ArmonA. Tabular data: Deep learning is not all you need. Inf Fusion, 2022, 81: 84-90.

[50] HuS, XiongC, ChenP, SchonfeldP. Examining nonlinearity in population inflow estimation using big data: an empirical comparison of explainable machine learning models. Transp Res Part A Policy Pract, 2023, 174. 103743

[51] YangH, LuY, WangJ, et al.. Understanding post-pandemic metro commuting ridership by considering the built environment: a quasi-natural experiment in Wuhan, China. Sustain Cities Soc, 2023, 96. 104626

[52] Chen T, Guestrin C (2016) XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York, NY, USA, pp 785–794

[53] GaoW, WangW, DimitrovD, WangY. Nano properties analysis via fourth multiplicative ABC indicator calculating. Arab J Chem, 2018, 11: 793-801.

[54] KlingwortJ, BurgerJ. A framework for population inference: combining machine learning, network analysis, and non-probability road sensor data. Comput Environ Urban Syst, 2023, 103. 101976

[55] LiZ. Extracting spatial effects from machine learning model using local interpretation method: an example of SHAP and XGBoost. Comput Environ Urban Syst, 2022, 96. 101845

[56] Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems. Curran Associates, Inc.

[57] LiuJ, JiangR, ZhuD, ZhaoJ. Short-term subway inbound passenger flow prediction based on AFC data and PSO-LSTM optimized model. Urban Rail Transit, 2022, 8: 56-66.

[58] PengJ, LuoX, GuoS, et al.. Understanding post-pandemic spatiotemporal differences in the recovery of metro travel behavior among different groups by considering the built environment. J Eng Appl Sci, 2024, 71: 1-22.

[59] (2020) The COVID-19 response must be disability inclusive. The Lancet Public Health 5:e257. https://doi.org/10.1016/S2468-2667(20)30076-1

[60] ErmagunA, HajivosoughS, SamimiA, RashidiTH. A joint model for trip purpose and escorting patterns of the disabled. Travel Behav Soc, 2016, 3: 51-58.

[61] KrahnGL, WalkerDK, Correa-De-AraujoR. Persons with disabilities as an unrecognized health disparity population. Am J Public Health, 2015, 105: S198-S206.

[62] StaffordL, BaldwinC. Planning walkable neighborhoods: are we overlooking diversity in abilities and ages?. J Plann Lit, 2018, 33: 17-30.

[63] WengM, DingN, LiJ, et al.. The 15-minute walkable neighborhoods: measurement, social inequalities and implications for building healthy communities in urban China. J Transp Health, 2019, 13: 259-273.

[64] WangZ, SongJ, ZhangY, et al.. Spatial heterogeneity analysis for influencing factors of outbound ridership of subway stations considering the optimal scale range of “7D” built environments. Sustainability, 2022, 1416314.

[65] HeY, ZhaoY, TsuiKL. An adapted geographically weighted LASSO (Ada-GWL) model for predicting subway ridership. Transportation, 2021, 48: 1185-1216.

Funding

The National Natural Science Foundation of China(52108056)

The Fundamental Research Funds for the Central Universities, China(2024RC14)

RIGHTS & PERMISSIONS

The Author(s)

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.