Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings

TL;DR

This paper demonstrates that AlphaEarth Foundation embeddings derived from satellite imagery improve hydrological model predictions in ungauged basins by capturing complex environmental features more effectively than traditional attributes.

Contribution

It introduces the use of satellite-based AlphaEarth embeddings to enhance hydrological modeling and demonstrates their effectiveness in predicting river flows in ungauged basins.

Findings

Embeddings improve prediction accuracy in unseen basins.

Similarity based on embeddings aids in selecting comparable basins.

Adding dissimilar basins can decrease model performance.

Abstract

Predicting river flow in places without streamflow records is challenging because basins respond differently to climate, terrain, vegetation, and soils. Traditional basin attributes describe some of these differences, but they cannot fully represent the complexity of natural environments. This study examines whether AlphaEarth Foundation embeddings, which are learned from large collections of satellite images rather than designed by experts, offer a more informative way to describe basin characteristics. These embeddings summarize patterns in vegetation, land surface properties, and long-term environmental dynamics. We find that models using them achieve higher accuracy when predicting flows in basins not used for training, suggesting that they capture key physical differences more effectively than traditional attributes. We further investigate how selecting appropriate donor basins influences prediction in ungauged regions. Similarity based on the embeddings helps identify basins with comparable environmental and hydrological behavior, improving performance, whereas adding many dissimilar basins can reduce accuracy. The results show that satellite-informed environmental representations can strengthen hydrological forecasting and support the development of models that adapt more easily to different landscapes.