Developing Nationwide Estimates of Built Environment Quality Characteristics Using Street-View Imagery and Computer Vision
Open Access
- 3 July 2025
- journal article
- Published by American Chemical Society (ACS) in Environmental Science & Technology
- Vol. 59 (27) , 13638-13646
Abstract
Environmental health studies commonly rely on urban composition measures for built environment exposure assessment. However, quality measures are equally important, as they directly influence health behaviors. We leveraged computer vision and street-view imagery to estimate five components of built environment quality (perceived beauty, relaxation potential, nature quality, safe for walking, and safety from crime) across all U.S. cities, explicitly addressing socio-demographic and temporal biases. We collected 72 516 surveys via Amazon Mechanical Turk, where participants ranked street-view images and provided socio-demographic data. Deep learning models predicted quality metrics at 120 million street locations for 2008, 2012, 2016, and 2020. Cross-validation accuracy ranged from 73% (nature quality) to 59% (safety from crime) compared to 50% expected by random chance. Adjusting sampling weights based on demographics reduced but did not eliminate biases for Hispanic/Latino and Native Hawaiian or Pacific Islander groups (3.5 and 4% lower accuracy, respectively). We also adjusted model predictions for seasonal biases, correcting higher scores from late spring and early summer imagery (p < 0.001). The resulting nationwide estimates of street-level beauty, relaxation, nature quality, and safety for walking (but not safety from crime) can inform epidemiological research, urban planning strategies, and public health interventions.Keywords
Funding Information
- U.S. Department of Health and Human Services (P30 ES000002, R01HL150119, R21ES029722)
This publication has 36 references indexed in Scilit:
- Greenspace and depression incidence in the US-based nationwide Nurses' Health Study II: A deep learning analysis of street-view imageryEnvironment International, 2025
- Understanding urban perception with visual data: A systematic reviewCities, 2024
- Clarity or confusion: A review of computer vision street attributes in urban studies and planningCities, 2024
- Predicting outdoor ultrafine particle number concentrations, particle size, and noise using street-level images and audio dataEnvironment International, 2020
- What determines how we see nature? Perceptions of naturalness in designed urban green spacesPeople and Nature, 2019
- A picture tells a thousand…exposures: Opportunities and challenges of deep learning image analyses in exposure science and environmental epidemiologyEnvironment International, 2019
- Noise in Cities: Urban and Transport Planning Determinants and Health in Cities2018
- Exploring pathways linking greenspace to health: Theoretical and methodological guidanceEnvironmental Research, 2017
- A machine learning-based method for the large-scale evaluation of the qualities of the urban environmentComputers, Environment and Urban Systems, 2017
- Deep Learning the City: Quantifying Urban Perception at a Global Scale2016