Subsurface Property Mapping using Google AlphaEarth Foundations

TL;DR

This study investigates the use of AlphaEarth embeddings for subsurface property estimation from surface data, demonstrating their potential to produce coherent, plausible models in geophysical applications.

Contribution

It introduces a novel application of foundation-model surface representations for regional surface-to-subsurface inference, showing promising results in seismic and temperature mapping.

Findings

Embedding-informed models outperform simpler baselines.

Domain covariates stabilize seismic property estimation.

Embedding features are crucial for temperature reconstruction.

Abstract

Subsurface properties are essential for hazard assessment, energy and environmental management, and infrastructure resilience, but direct observations are sparse and uneven, motivating the use of surface observations as indirect constraints. Here we explore whether AlphaEarth embeddings can be applied to subsurface estimation despite indirect and non-unique physical links between surface and depth. We test this idea in two conterminous U.S. applications: shallow seismic site characterization using $V_S 30$ with embedding features alone and with conventional covariates (topographic slope and a tectonic-status indicator), and subsurface temperature reconstruction using embedding-based nonlinear regression. Across both applications, embedding-informed models recover spatially coherent, physically plausible patterns and outperform simpler baselines. The comparison also highlights a key difference: domain covariates materially stabilize $V_S 30$ regression, whereas temperature mapping relies primarily on embedding features. Overall, the results support the feasibility of foundation-model surface representations for regional surface-to-subsurface inference, while emphasizing the need for robust spatial validation under heterogeneous labels and uneven data coverage.