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

Tao Tao, Jueyu Wang, Xinyu Cao

Research output: Contribution to journalArticle

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.

Original languageEnglish (US)
Article number102560
JournalJournal of Transport Geography
Volume82
DOIs
StatePublished - Jan 2020

Fingerprint

Decision trees
walking
agglomeration area
Planning
planning
metropolitan area
attribute

Keywords

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

Cite this

Exploring the non-linear associations between spatial attributes and walking distance to transit. / Tao, Tao; Wang, Jueyu; Cao, Xinyu.

In: Journal of Transport Geography, Vol. 82, 102560, 01.2020.

Research output: Contribution to journalArticle

@article{040529c314f040e189a3b07b9ca65adb,
title = "Exploring the non-linear associations between spatial attributes and walking distance to transit",
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.",
keywords = "Built environment, Land use, Machine learning, Station area planning, Walking behavior",
author = "Tao Tao and Jueyu Wang and Xinyu Cao",
year = "2020",
month = "1",
doi = "10.1016/j.jtrangeo.2019.102560",
language = "English (US)",
volume = "82",
journal = "Journal of Transport Geography",
issn = "0966-6923",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Exploring the non-linear associations between spatial attributes and walking distance to transit

AU - Tao, Tao

AU - Wang, Jueyu

AU - Cao, Xinyu

PY - 2020/1

Y1 - 2020/1

N2 - 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.

AB - 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.

KW - Built environment

KW - Land use

KW - Machine learning

KW - Station area planning

KW - Walking behavior

UR - http://www.scopus.com/inward/record.url?scp=85073537919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073537919&partnerID=8YFLogxK

U2 - 10.1016/j.jtrangeo.2019.102560

DO - 10.1016/j.jtrangeo.2019.102560

M3 - Article

AN - SCOPUS:85073537919

VL - 82

JO - Journal of Transport Geography

JF - Journal of Transport Geography

SN - 0966-6923

M1 - 102560

ER -