Effects of meteorology on bike-sharing: Cases of 13 cities using non-linear analyses

Abstract

Bike-sharing system (BSS) provides bicycle rental services for short-term use. The association of BSS with meteorological factors has not been studied sufficiently using nonlinear analysis. To bridge these gaps, this study explored the impact of meteorological conditions on bike-sharing system (BSS) usage in 13 cities in Europe and North America, using a combination of nonlinear analyses to avoid the limitations of linear analyses used traditionally. Specifically, self-organizing map (SOM) and decision tree analyses were used. The SOM results revealed six meteorological profiles (clusters). Kruskal–Wallis test was applied to determine the main effect of the cluster on the input variables. The decision tree indicated temperature (34.4 %), followed by clusters (23.3 %), and cities (17.5 %) as the most influential factors on BSS usage. These findings demonstrated the need to generate nonlinear analyses to understand the dynamic interaction of meteorological variables and BSS usage, providing insights for developing sustainable urban transportation policies.