Geospatial Foundation Models Capture Health-Relevant Dimensions of Place Beyond Conventional Social Risk Indices
Abstract
Area-based social risk indices summarize residents' socioeconomic conditions but incompletely capture physical features of place that may affect health. We evaluated whether numerical representations of physical place produced by four geospatial foundation model families from 2022 satellite data explained residual variance in tract-level associations between the Area Deprivation Index, Social Deprivation Index, and Social Vulnerability Index with health outcomes. We used LightGBM to predict variables from the American Community Survey and 40 chronic disease and health-behavior outcomes from CDC PLACES across 82,646 census tracts in the contiguous United States, evaluating performance across 10 held-out states. Among survey variables, models were moderately predictive of some variables including housing type (R-squared up to 0.54) but weak for disability, unemployment, and income disparity. For health outcomes, models explained up to 54% of variance left unexplained by social risk indices, with the largest gains for annual checkups, arthritis, and high blood pressure. Mean total variance explained by geospatial foundation models across the 40 health-related outcomes increased from 0.31 in the smallest tract-size decile to 0.39 in the largest. Geospatial foundation models capture health-relevant features of place not represented by conventional social risk indices and may usefully augment them in epidemiological analyses.
Related
- Multisource Remote Sensing and Geospatial Analysis of Vineyard Wildfire Impacts and Exposure: The 2019 Kincade Fire
- Training strategy over architecture: A systematic ablation study for Spartina detection from aerial imagery with small geospatial datasets
- An upper bound on the number of relevant variables in a bounded degree Boolean function on the Hamming graph
- Quasicircularity of the Zakeri Curve and Capture Component Boundaries
- Topologically Relevant Landmark Selection on Point Clouds
BibTeX
@misc{hendrix2026geospatial,
title = {{Geospatial Foundation Models Capture Health-Relevant Dimensions of Place Beyond Conventional Social Risk Indices}},
author = {Nathaniel Hendrix and Carl Y. Zhang and Chris Heitzig and Andrew Bazemore and David H. Rehkopf},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.11689},
eprint = {2609.11689},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.11689},
note = {CC BY-SA 4.0},
}
RIS
TY - UNPB
TI - Geospatial Foundation Models Capture Health-Relevant Dimensions of Place Beyond Conventional Social Risk Indices
AU - Nathaniel Hendrix
AU - Carl Y. Zhang
AU - Chris Heitzig
AU - Andrew Bazemore
AU - David H. Rehkopf
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.11689
UR - https://arxiv.org/abs/2609.11689
AB - Area-based social risk indices summarize residents' socioeconomic conditions but incompletely capture physical features of place that may affect health. We evaluated whether numerical representations of physical place produced by four geospatial foundation model families from 2022 satellite data explained residual variance in tract-level associations between the Area Deprivation Index, Social Deprivation Index, and Social Vulnerability Index with health outcomes. We used LightGBM to predict variables from the American Community Survey and 40 chronic disease and health-behavior outcomes from CDC PLACES across 82,646 census tracts in the contiguous United States, evaluating performance across 10 held-out states. Among survey variables, models were moderately predictive of some variables including housing type (R-squared up to 0.54) but weak for disability, unemployment, and income disparity. For health outcomes, models explained up to 54% of variance left unexplained by social risk indices, with the largest gains for annual checkups, arthritis, and high blood pressure. Mean total variance explained by geospatial foundation models across the 40 health-related outcomes increased from 0.31 in the smallest tract-size decile to 0.39 in the largest. Geospatial foundation models capture health-relevant features of place not represented by conventional social risk indices and may usefully augment them in epidemiological analyses.
ER -