Exploring the non-linear associations between spatial attributes and walking distance to transit

Authors

Tao Tao
Jueyu Wang
Jason (Xinyu) Cao

Document Type

Journal Article

Publication Date

2020

Subject Area

infrastructure - station, land use - impacts, land use - planning, place - north america, planning - surveys, ridership - behaviour

Keywords

Machine learning, Walking behavior, Station area planning, Built environment, Land use

Abstract

When examining environmental correlates of walking distance to transit stops, few studies report the importance of spatial attributes relative to other factors. Furthermore, previous studies often assume that they have linear relationships with walking distance. Using the 2016 Transit On Board Survey in the Minneapolis and St. Paul Metropolitan Area, this study adopted the gradient boosting decision trees method to examine the relationships between walking distance and spatial attributes. Results showed that spatial attributes collectively have larger predictive power than other factors. Moreover, they tend to have non-linear associations with walking distance. We further identified the most effective ranges of spatial attributes to guide stop area planning and stop location choice in the region.

Rights

Permission to publish the abstract has been given by Elsevier, copyright remains with them.

Comments

Journal of Transport Geography home Page:

http://www.sciencedirect.com/science/journal/09666923

Recommended Citation

Tao, T., Wang, J., & Cao, X. (2020). Exploring the non-linear associations between spatial attributes and walking distance to transit. Journal of Transport Geography, Volume 82, 102560.