Revealing implicit associations between urban form and socioeconomic indices
Bibliographic Data
| ID | 21246986 |
|---|---|
| Authors | Jinmo Rhee (0000-0003-4710-7385, University of Calgary, corresponding author), Kiarash Kiany (0009-0006-3309-3903, University of Calgary), Alberto de Salvatierra (0000-0002-3931-0132, University of Calgary) |
| Year | 2026 |
| Publication date | 2026-01-28 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Environment and Planning B Urban Analytics and City Science (JOURNAL) |
| Journal identifiers | ISSN: 2399-8083 • E-ISSN: 2399-8091 |
| Publisher | SAGE Publications (PUBLISHER • US) |
| DOI | 10.1177/23998083261420450 |
| OpenAlex | W7125977055 |
| Language | EN |
| References cited | 27 |
This study provides empirical evidence that parcel-level socioeconomic indices can be reliably inferred from urban form using deep learning. Building on a representation that links cadastral parcels with digital surface models, we train EfficientNet variants to predict return on investment (ROI)—used here as a representative parcel-level economic indicator—directly from volumetric form. Across more than 24,000 parcels in a North American city, the models exhibit stable convergence and consistent generalization, capturing systematic variations across residential, commercial, and industrial morphologies. Although errors increase in dense commercial cores—where financial volatility and vertical complexity are highest—predictions remain bounded and preserve spatial gradients of ROI. The learned embeddings further reveal coherent manifolds structured by building massing, footprint geometry, and block configuration, indicating that the model extracts underlying spatial principles that correlate with economic outcomes. These findings demonstrate that urban form encodes measurable signals of economic performance and establish morphological learning as a viable pathway for integrating financial, environmental, and socio-cultural indices into form-based urban analysis and design
Bounded function · Cadastre · Footprint · Socioeconomic status · Human Mobility and Location-Based Analysis · Land Use and Ecosystem Services · Urban Design and Spatial Analysis
Linking objectively measured physical activity with objectively measured urban form
Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States
Energy consumption and urban texture
Classification of urban morphology with deep learning
Street Network Models and Indicators for Every Urban Area in the World
Comparative analysis of urban structures in three American Rust Belt cities
Crime Prevention through Housing Design
Measuring Urban Compactness in UK Towns and Cities
Urban form and livability
New urbanism and housing values
Urban spatial order
Travel and the Built Environment
| Citation velocity | historical |
|---|---|
| Highly cited | No |