Detecting Urban Mobility Structure and Learning Functional Distribution with Multi-Scale Features

Urban mobility structure detection and functional distribution learning are significant for urban planning and management. However, existing methods have limitations in handling complex urban data and capturing global spatial structure features. To deal with these challenges, we proposed a multi-scale feature-aware urban mobility structure embedding method based on contrastive learning. First, we designed a multi-scale contrastive learning strategy to effectively learn local human activity features and global spatial structure features, determine the community affiliation of regions, and generate regional embedding vectors. Next, we introduced a correlation matrix to encode the functional synergy and competition of Point of Interests (POIs) and construct the complex correlation between urban mobility structure and urban functional distribution to evaluate the quality of regional embedding vectors. Experiments in Haikou City show that the proposed method can accurately detect the urban mobility structure and functional distribution. The analysis reveals that the central urban area of Haikou exhibits concentrated functions and significant traffic tidal effects, while the suburban areas have relatively weaker functions, with residents displaying a high level of dependence on the central area. Therefore, urban planning needs to optimize the functional layout, improve the functions of the suburbs, and promote the balance of urban space.