Citation

Tao T, Cao J. Transp. Res. A Policy Pract. 2024; 179: e103924.

Copyright

(Copyright © 2024, Elsevier Publishing)

DOI

10.1016/j.tra.2023.103924

PMID

unavailable

Abstract

Designing effective built environment policies to reduce auto use is key to promoting sustainable transportation in suburban areas. However, most studies on the association between the built environment and auto use focus on the entire region rather than suburban areas. In addition, previous studies often ignore the possible nonlinear association between them. Applying Gradient Boosting Decision Trees to the data in the Twin Cities, USA, this study explores the nonlinear relationships between built environment attributes and driving distance in suburban areas and illustrates how the relationships differ from those in urban areas. The results show that suburban residents are less sensitive to the built environment than urban residents. More importantly, built environment policies that work in urban areas might be infertile in suburban areas. Although many studies have advocated population densification and mixed-use development for driving mitigation, this study suggests that these policies are ineffective in suburban areas. Instead, promoting job accessibility and densifying intersection density are promising to reduce auto use in suburban areas. Densifying transit stops has a small but nontrivial contribution to mitigating auto use.

Language: en

Keywords

Land use; Machine learning; Nonlinear relationships; Sprawl; VMT