Effects of Multidimensional Factors on the Distance Decay of Bike-Sharing Access to Metro Stations
Year: 2025
Type: article
Abstract: The last kilometer connection problem of metro transit stations is the core factor to measure the connection efficiency and service quality. Establishing the spatiotemporal distribution pattern of the connection distance is conducive to clarifying the interaction mechanism between bike-sharing connections and urban space. This study focuses on the travel behavior of shared bicycle users accessing metro stations, aiming to reveal the access distance decay patterns and their relationship with influence factors. Finally, the random forest algorithm was used to explore the nonlinear relationship between the influencing factors and the connection decay distance, and to clarify the importance of the factors. Multiple linear regression was applied to examine the linear correlation between the distance decay coefficient and the factors influence. The geographically weighted regression was further employed to explore spatial variations in their effects. Finally, the random forest algorithm was used to rank the importance of the impact factors. The results indicate that proximity distance to metro stations, proximity distance to bus stops, and the number of bus routes serving the station area have significant negative correlations with the distance decay coefficient. Significant spatial heterogeneity was observed in the influence of each factor on the distance decay coefficient, based on the geographically weighted regression analysis. With a high goodness-of-fit (R2 = 0.8032), the Random Forest regression model furthermore quantified the relative importance of each factor influencing the distance decay coefficient. The findings can be directly applied to optimize the layout of shared bicycle parking, metro access facilities planning, and multi-modal transportation system design.
Source: Applied Sciences
DOI: 10.3390/app152413228
Institutions: Shandong Jianzhu University, Beijing University of Technology
Language: English
Subfield: Transportation
Field: Social Sciences
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $2,896
Awards: G5864029068, G6586265318
OpenAlex ID: W4417436157
