Key points are not available for this paper at this time.
Exploring the mechanisms between the built environment influences active travel is crucial for promoting green transportation and fostering the sustainable development of cities. Existing literature focus on the correlation between the built environment and active travel in urban centers, with limited studies on suburban environments, ignoring the implications of spatial heterogeneity. This paper conducts a comprehensive spatio-temporal analysis of suburban residents' active travel behavior and explores the nonlinear relationship between suburban built environment and active travel. A novel hybrid modeling framework that combines eXtreme Gradient Boosting and Multi-scale Geographic Weighted Regression is introduced to forecast suburban active travel demand with the consideration of the nonlinearity and spatial heterogeneity in parameter estimates. Shapley additive explanations is used to elucidate the non-linear relationship between built environment variables and active travel. The results indicate that the proposed hybrid model performs the best with high predictive power and interpretability. The density of tourist attractions, transportation facilities, and household properties emerges as the three most influential factors affecting residents' active travel behavior. Social-economic attributes contribute 15.70% to the prediction, while three categories of built environment variables (accessibility, transportation facilities, and land use) contribute 7.31%, 5.13%, and 71.87%, respectively. The hybrid model appears to be effective to identify the nonlinear relationship and threshold effects between built environment variables and active travel. Besides, the model provides actionable insights for designing sustainable and efficient suburban environments, supporting targeted planning and policy-making efforts.
Liu et al. (Sun,) studied this question.