Data driven assessment of built environment impacts on urban health across United States cities

Abstract

The built environment plays a crucial role in urban health through its constant interaction with residents. Yet, a comprehensive analysis across multiple U.S. cities covering different geographical conditions has been missing. This study examines the impact of the built environment on mental, physical, and overall health in 19 major U.S. cities across diverse climate zones, aiming to discover the influential factors and create a predictive health model for the entire nation. Utilizing a convolutional neural network, this research extracted building characteristics from google street view and employed a multiple regression model, XGBoost, support vector regression (SVR), decision tree, and random forest, achieving R-squared values of 0.75, 0.76, and 0.82 for mental, physical, and general health, respectively. The findings revealed certain building features profoundly influence urban health, including lead paint as a persistent health hazard, while air conditioning boosts health outcomes. Traditional materials like wood and masonry, common in older buildings, are linked to better health compared to modern materials. The study also reveals significant geographic variations, underscoring the intricate relationship between architecture and public health. By highlighting the vital role of building features in shaping urban health, this research provides a foundation for policymakers to inform building regulations, prioritize vulnerable areas, and support health-oriented urban design, ultimately contributing to healthier, more livable urban environments.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 11 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.