Identifying urban functional areas and their dynamic changes in Beijing: using multiyear transit smart card data

A growing number of megacities have been experiencing changes to their landscape due to rapid urbanization trajectories and travel behavior dynamics. Therefore, it is of great significance to investigate the distribution and evolution of a city's urban functional areas over different periods of time. Although the smart card automated fare collection system is already widely used, few studies have used smart card data to infer information about changes in urban functional areas, particularly in developing countries. Thus, this research aims to delineate the dynamic changes that have occurred in urban functional areas based on passengers' travel patterns, using Beijing as a case study. We established a Bayesian framework and applied a Gaussian mixture model derived from transit smart card data in order to gain insight into passengers' travel patterns at station level and then identify the dynamic changes in their corresponding urban functional areas. Our results show that Beijing can be clustered into five different functional areas based on the analysis of corresponding transit station functions: multimodal interchange hub and leisure area; residential area; employment area; mixed but mainly residential area; and mixed residential and employment area. In addition, we found that urban functional areas have experienced slight changes between 2014 and 2017. The findings can be used to inform urban planning strategies designed to tackle urban spatial structure issues, as well as guiding future policy evaluation of urban landscape pattern use