Revealing Spatial Patterns and Environmental Influences on Jogging Volume and Speed: Insights from Crowd-Sourced GPS Trajectory Data and Random Forest

Outdoor jogging plays a critical role in active mobility and transport-related physical activity (TPA), contributing to both urban health and sustainability. While existing studies have primarily focused on jogging participation volumes through survey data, they often overlook the real-time dynamics that shape jogging experiences. This study seeks to provide a data-driven analysis of both jogging volume and speed, exploring how environmental factors influence these behaviors. Utilizing a dataset of over 1000 crowd-sourced jogging trajectories in Shenzhen, we spatially linked these trajectories to road-section-level units to map the distribution of jogging volume and average speed. By depicting a bivariate map of both behavioral characteristics, we identified spatial patterns in jogging behavior, elucidating variations in the distribution of volume and speed. A random forest regression model was validated and employed to capture nonlinear relationships and assess the differential impacts of various environmental factors on jogging volume and speed. The results reveal distinct jogging patterns across the city, where jogging volume is shaped by the mixed interplay of natural, visual, and built environment factors, while jogging speed is primarily influenced by visual factors. Additionally, the analysis highlights nonlinear effects, particularly identifying a threshold beyond which incremental environmental improvements provide diminishing returns in jogging speed. These findings clarify the distinct roles of environmental factors in influencing jogging volume and speed, offering insights into the dynamics of active mobility. Ultimately, this study provides data-informed implications for urban planners seeking to create environments that support TPA and promote active lifestyles.