Examining the relationship between built environment and metro ridership at station-to-station level

Abstract Very few studies have examined the impact of built environment on urban rail transit ridership at the station-to-station (origin-destination) level. Moreover, most direct ridership models (DRMs) tend to involve simple a prior assumed linear or log-linear relationship in which the estimated parameters are assumed to hold across the entire data space of the explanatory variables. These models cannot detect any changes in the linear (or non-linear) effects across different values of the features of built environment on urban rail transit ridership, which possibly induces biased results and hides some non-negligible and detailed information. Based on these research gaps, this study develops a time-of-day origin-destination DRM that uses smart card data pertaining to the Nanjing metro system, China. It applies a gradient boosting regression trees model to provide a more refined data mining approach to investigate the non-linear associations between features of the built environment and station-to-station ridership. Data related to the built environment, station type, demographics, and travel impedance including a less used variable – detour, were collected and used in the analysis. The empirical results show that most independent variables are associated with station-to-station ridership in a discontinuous non-linear way, regardless of the time period. The built environment on the origin side has a larger effect on station-to-station ridership than the built environment on the destination side for the morning peak hours, while the opposite holds for the afternoon peak hours and night. The results also indicate that transfer times is more important variables than detour and route distance.

[1]  Chuan Ding,et al.  How does the station-area built environment influence Metrorail ridership? Using gradient boosting decision trees to identify non-linear thresholds , 2019, Journal of Transport Geography.

[2]  Soora Rasouli,et al.  Activity-based models of travel demand: promises, progress and prospects , 2014 .

[3]  Juhwan Oh,et al.  Transit-oriented development in a high-density city: Identifying its association with transit ridership in Seoul, Korea , 2011 .

[4]  Matthew E. Kahn,et al.  The effects of new public projects to expand urban rail transit , 2000 .

[5]  Sherry Ryan,et al.  Pedestrian Environments and Transit Ridership , 2009 .

[6]  J. Gutiérrez,et al.  Application of geographically weighted regression to the direct forecasting of transit ridership at station-level , 2012 .

[7]  M. Kuby,et al.  Factors influencing light-rail station boardings in the United States , 2004 .

[8]  Michael G. McNally,et al.  The Four Step Model , 2007 .

[9]  Hjp Harry Timmermans,et al.  Using ensembles of decision trees to predict transport mode choice decisions: effects on predictive success and uncertainty estimates , 2014 .

[10]  Yingling Fan,et al.  Examining threshold effects of built environment elements on travel-related carbon-dioxide emissions , 2019, Transportation Research Part D: Transport and Environment.

[11]  Harry Timmermans,et al.  Station-based average travel distance and its relationship with urban form and land use: An analysis of smart card data in Nanjing City, China , 2019, Transport Policy.

[12]  Javier Gutiérrez,et al.  Transit ridership forecasting at station level: an approach based on distance-decay weighted regression , 2011 .

[13]  Joan L. Walker,et al.  Modeling Private Car Ownership in China , 2010 .

[14]  Reid Ewing,et al.  Travel and the Built Environment , 2010 .

[15]  Yanru Zhang,et al.  A gradient boosting method to improve travel time prediction , 2015 .

[16]  Davy Janssens,et al.  Improving Performance of Multiagent Rule-Based Model for Activity Pattern Decisions with Bayesian Networks , 2004 .

[17]  Qingquan Li,et al.  Spatial variations in urban public ridership derived from GPS trajectories and smart card data , 2018 .

[18]  Yan Song,et al.  Analysis of Metro ridership at station level and station-to-station level in Nanjing: an approach based on direct demand models , 2014 .

[19]  Junyi Zhang,et al.  Use of smartphone applications and its impacts on urban life: A survey and random forest analysis in Japan , 2019, Sustainable Cities and Society.

[20]  Enjian Yao,et al.  Exploring urban rail transit station-level ridership growth with network expansion , 2019 .

[21]  Dujuan Yang,et al.  Effects of rural built environment on travel-related CO2 emissions considering travel attitudes , 2019, Transportation Research Part D: Transport and Environment.

[22]  Chuan Ding,et al.  A gradient boosting logit model to investigate driver’s stop-or-run behavior at signalized intersections using high-resolution traffic data , 2016 .

[23]  Keemin Sohn,et al.  An analysis of Metro ridership at the station-to-station level in Seoul , 2012 .

[24]  Petter Næss,et al.  Applying gradient boosting decision trees to examine non-linear effects of the built environment on driving distance in Oslo , 2018 .

[25]  Dennis Y N Li,et al.  Developing Metro Systems in the People’s Republic of China: Policy and Gaps , 2006 .

[26]  Matthew G. Karlaftis,et al.  Ridership Estimation of New LRT System: A Direct Demand Model Approach , 2015 .

[27]  D. Rodriguez,et al.  The relationship between urban form and station boardings for Bogotá's BRT , 2008 .

[28]  Harry Timmermans,et al.  Analysis of Metro Station Ridership Considering Spatial Heterogeneity , 2019, Chinese Geographical Science.

[29]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[30]  Keechoo Choi,et al.  Land use characteristics of subway catchment areas and their influence on subway ridership in Seoul , 2015 .

[31]  Harry Timmermans,et al.  Estimating panel effects in probabilistic representations of dynamic decision trees using Bayesian generalized linear mixture models , 2018 .

[32]  Christopher E. Ferrell,et al.  TRANSIT-ORIENTED DEVELOPMENT IN THE UNITED STATES: EXPERIENCES, CHALLENGES, AND PROSPECTS , 2004 .

[33]  Hjp Harry Timmermans,et al.  A learning-based transportation oriented simulation system , 2004 .

[34]  Craig Townsend,et al.  Direct Ridership Model of Rail Rapid Transit Systems in Canada , 2015 .

[35]  Orlando Strambi,et al.  Trip Generation Modeling Using CHAID, a Criterion-Based Segmentation Modeling Tool , 1998 .

[36]  Keemin Sohn,et al.  Factors generating boardings at Metro stations in the Seoul metropolitan area , 2010 .

[37]  Michael Duncan,et al.  To Park or To Develop: Trade-Off in Rail Transit Passenger Demand , 2010 .

[38]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[39]  Ta Theo Arentze,et al.  Parametric Action Decision Trees: Incorporating Continuous Attribute Variables Into Rule-Based Models of Discrete Choice , 2007 .

[40]  Xuehao Chu,et al.  RIDERSHIP MODELS AT THE STOP LEVEL , 2004 .

[41]  Sevgi Erdogan,et al.  How to Increase Rail Ridership in Maryland: Direct Ridership Models for Policy Guidance , 2016 .

[42]  Dujuan Yang,et al.  Analysis of the impact of street-scale built environment design near metro stations on pedestrian and cyclist road segment choice: A stated choice experiment , 2020, Journal of Transport Geography.