GeoViSTA: Geospatial Vision-Tabular Transformer for Multimodal Environment Representation

TL;DR

GeoViSTA introduces a novel vision-tabular transformer that unifies geospatial imagery and socioeconomic data, enhancing environmental and social outcome predictions through self-supervised learning.

Contribution

It proposes a bilateral cross-attention architecture with geography-aware alignment for joint geospatial embedding of imagery and tabular data.

Findings

Improves linear probing performance on downstream geospatial tasks.

Outperforms baselines in predicting disease mortality and fire hazard.

Demonstrates the benefit of joint physical and socioeconomic environment modeling.

Abstract

Large-scale pretraining on Earth observation imagery has yielded powerful representations of the natural and built environment. However, most existing geospatial foundation models do not directly model the structured socioeconomic covariates typically stored in tabular form. This modality gap limits their ability to capture the complete total environment, which is critical for reasoning about complex environmental, social, and health-related outcomes. In this work, we propose GeoViSTA (Geospatial Vision-Tabular Transformer), a vision-tabular architecture that learns unified geospatial embeddings from co-registered gridded imagery and tabular data. GeoViSTA utilizes bilateral cross-attention to exchange spatial and semantic information across modalities, guided by a geography-aware attention mechanism that aligns continuous image patches with irregular census-tract tokens. We train GeoViSTA with a self-supervised joint masked-autoencoding objective, forcing it to recover missing image patches and tabular rows using local spatial context and cross-modal cues. Empirically, GeoViSTA's unified embeddings improve linear probing performance on high-impact downstream tasks, outperforming baselines in predicting disease-specific mortality and fire hazard frequency across held-out regions. These results demonstrate that jointly modeling the physical environment alongside structured socioeconomic context yields highly transferable representations for holistic geospatial inference.