Spatiotemporal analysis for travel patterns of the personal mobility using an explainable machine learning approach: A case of Seoul, South Korea

Shared bicycles are becoming increasingly popular as a primary mode of micro-mobility due to easy accessibility in urban areas and ability to integrate with other public transportation systems. Understanding the travel patterns and modal characteristics of shared bicycles is essential for developing sustainable and eco-friendly urban transportation systems. Although the recent advance of GeoAIs has enabled the exploration of complex, nonlinear relationships in shared mobility patterns, these studies often provide a temporally aggregated view. Consequently, they tend to overlook the dynamics of these nonlinear effects, specifically how the influence of built environment, demographic, and public transit factors shifts across different times of day and seasons. This study addresses this gap by emphasizing a LightGBM model enhanced with a robust SHapley Additive Explanation (SHAP) framework, explicitly capturing these nonlinear effects and distinguishing spatiotemporal dynamics. As an empirical case study, we examine the shared bicycle system in Seoul. The findings reveal distinct differences in travel patterns and influencing factors between weekdays and weekends. Also, it is empirically shown that shared bicycles can be served mainly as an alternative means of connecting the first- and last-mile gaps, effectively integrating with the public transportation network. This study contributes to clarify personal mobility patterns and inform sustainable transport policy by demonstrating shared bicycles’ urban potential.