Impact of spatiotemporal heterogeneity in built environment on taxi travel demand
MA Jianxiao
YIN Jiexiang
SHAO Chunfu
YIN Chaoying
Abstract：This study investigates the spatiotemporal heterogeneity in the impact of the built environ-ment on taxi travel demand using taxi order data from Nanjing.By integrating multiple data sources,the built environment is characterized across five dimensions:density,diversity,design,destination accessibility,and public transport proximity.Considering both weekdays and weekends,a Multi-scale Geographically Weighted Regression(MGWR)model is developed to account for the scale differences among feature variables and to explore the interactive relationship between the built environment and taxi travel demand.The research data is visualized using ArcGIS to provide an intuitive representation of model results and spatial distribution characteristics.The findings show that,compared to the Ordi-nary Least Squares(OLS)and the Geographically Weighted Regression(GWR)models,the MGWR model exhibits superior performance,with the adjusted R2adj improving by 52.42%and 4.62%on week-days,and by 51.98%and 0.97%on weekends.Additionally,the AICc values decrease by 19.66%and 10.93%on weekdays,and by 21.37%and 8.35%on weekends,confirming the MGWR model's better fitting performance.The regression coefficients reveal spatiotemporal heterogeneity in the im-pact of different built environment characteristics.Based on the average regression coefficients of sig-nificant spatial unit variables,population density,road density,slow road density,metro accessibil-ity,and bus stop density positively influence taxi travel demand on both weekdays and weekends,while bus accessibility exerts a negative impact.On weekends,land use mix and distance to the city center negatively affect taxi travel demand,with a greater proportion of significant spatial units ob-served.The research findings provide valuable insights for optimizing urban functional structures and improving taxi operation policies.
Keywords：urban transportationbuilt environmenttaxi travel demandMulti-scale Geographical Weighted Regression(MGWR)spatiotemporal heterogeneity
Publication Date：2025-02-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：9( 119-127 )