Urban delineation through the lens of commute networks: Leveraging graph embeddings to distinguish socioeconomic groups in cities

2025-07-15

AI Summary

This study addresses the limitation of administrative boundaries in delineating socially and economically heterogeneous urban functional communities, leveraging commuting networks instead. We propose an end-to-end framework integrating Graph Neural Networks (GNNs) with unsupervised clustering: first, constructing a weighted directed graph where nodes represent fine-grained geographic units (e.g., census tracts) and edges encode census-based commuting flows; second, employing GNNs to learn low-dimensional node embeddings that capture latent socioeconomic associations; and third, applying clustering to partition communities. Empirical evaluation across multiple U.S. cities yields spatially coherent communities exhibiting statistically significant disparities in median income and other socioeconomic indicators, confirming the strong representational power of commuting patterns for urban socioeconomic structure. Our key contribution is the first systematic application of GNNs to commuting network modeling for socioeconomic-aware urban partitioning—establishing a novel, data-driven paradigm for urban governance and planning.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Combinatorial Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Computational social science
• Economics, Online Markets and Human Computation: Social networks and social learning

Abstract

Delineating areas within metropolitan regions stands as an important focus among urban researchers, shedding light on the urban perimeters shaped by evolving population dynamics. Applications to urban science are numerous, from facilitating comparisons between delineated districts and administrative divisions to informing policymakers of the shifting economic and labor landscapes. In this study, we propose using commute networks sourced from the census for the purpose of urban delineation, by modeling them with a Graph Neural Network (GNN) architecture. We derive low-dimensional representations of granular urban areas (nodes) using GNNs. Subsequently, nodes' embeddings are clustered to identify spatially cohesive communities in urban areas. Our experiments across the U.S. demonstrate the effectiveness of network embeddings in capturing significant socioeconomic disparities between communities in various cities, particularly in factors such as median household income. The role of census mobility data in regional delineation is also noted, and we establish the utility of GNNs in urban community detection, as a powerful alternative to existing methods in this domain. The results offer insights into the wider effects of commute networks and their use in building meaningful representations of urban regions.

Problem

• Using commute networks to delineate urban socioeconomic groups
• Applying GNNs to cluster urban areas by mobility data
• Identifying income disparities via network embeddings in cities

Innovation

• Using GNNs for urban commute network analysis
• Clustering node embeddings to detect communities
• Leveraging census data for socioeconomic delineation