Identifying urban functional regions: A multi-dimensional framework approach integrating metro smart card data and car-hailing data

Abstract

Urban functions often diverge from initial planning due to changes driven by residents’ behaviors. Effective urban planning and renewal require accurately identifying urban functional regions based on residents’ behavior data (including activity and travel data). However, previous methods have primarily relied on either point of interest (POI) data or a single source of traffic data, and often ignore the combined influence of residents’ activities and travel behaviors. In this study, we introduce a novel framework that integrates multiple sources of traffic data (such as metro smart card data and car-hailing data) with POI data to identify urban functional regions. This approach is unique because it simultaneously considers two critical dimensions of residents’ behavior: travel and activity behaviors. By combining these dimensions, we extract a comprehensive set of characteristics, including travel time, travel flow, origin-destination patterns, activity types, and activity time, which are then aggregated at the regional level (i.e., traffic analysis zone). To process these characteristics, we use latent Dirichlet allocation (LDA) to extract high-level semantic features from each data type. Additionally, to handle the sparse data from metro smart cards, we employ a specialized clustering technique. The integration of diverse and complementary information from multiple data sources enables more accurate and nuanced identification of urban functional regions than single data source and k-means clustering algorithm, providing valuable insights for urban planners.