Abstract
Active travel is important to public health and the environment. Previous studies substantiate built environment influences active travel, but they seldom assess its overall contribution. Most of the studies assume that built environment characteristics have linear associations with active travel. This study uses Gradient Boosting Decision Trees to explore nonlinear relationships between the built environment and active travel in the Twin Cities. Collectively, the built environment has more predictive power for active travel than demographics, and parks, proximity to downtown, and transit access have important influences. The threshold effects of built environment variables help inform planning practice.
| Original language | English (US) |
|---|---|
| Journal | Journal of Planning Education and Research |
| DOIs | |
| State | Accepted/In press - 2020 |
Bibliographical note
Funding Information:The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This study was funded by the Sustainable Research Network project of the National Science Foundation of USA: Integrated Urban Infrastructure Solutions for Environmentally Sustainable, Healthy and Livable Cities (Award No. 1444745).
Publisher Copyright:
© The Author(s) 2020.
Keywords
- community design
- land use
- machine learning
- travel behavior
- walking
