Air pollution, an unexpected event, poses a significant threat to public health and affects human mobility. Ride-hailing provides an effective way to understand how human mobility adapts to air pollution. This study examines a week-long ride-hailing demand dataset from Chengdu, China, to evaluate the resilience of ride-hailing services (or ride-hailing resilience) in the face of poor air quality. A gradient boosting decision tree model is developed to explore the non-linear and interaction effects of air pollution, the built environment, and socioeconomic characteristics on ride-hailing demand and resilience. The results show that the relative importance and impact of independent factors on ride-hailing demand and resilience vary. Specifically, the density of residence facilities and air pollution are the most important predictors of ride-hailing demand and resilience, respectively. The non-linear and interaction effects of air pollution and selected built-environment and socioeconomic characteristics on ride-hailing resilience are presented. We recommend that urban planners and policymakers address the vulnerability of regions to air pollution, optimize the allocation of ride-hailing resources, and develop strategies to improve regional resilience.
No takes yet. Share an insight, caveat, or question.
Peng et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: