Work

Foundation‐Scale Satellite Embeddings Reframe Hydrological Generalization as a Representation Problem

Year: 2026

Type: article

Abstract: A persistent challenge in hydrological modeling is reliably transferring predictive skill across time and among basins that appear distinct based on conventional static attributes. Here we address this challenge by leveraging Google's newly released data set generated from the AlphaEarth Foundations model, providing 64‐dimensional satellite embeddings (SE) that encode dynamic surface characteristics. Evaluated over 455 Australian catchments (2017–2022), SE‐enhanced models consistently outperform static‐attribute baselines. Temporal gains are most pronounced in regions under intense human disturbance, where median relative error reduction (RER) reaches 11.5%, reflecting reduced mismatch between static representations and evolving land‐surface states. Overcoming the fragmentation caused by discrete static attributes, SE reshapes the feature space into a continuous, globally connected representation, yielding a median RER of 32.1% for the most isolated basins. These results indicate that foundation‐scale embeddings fundamentally shift hydrological generalization from parameter transfer toward representation learning, offering a new pathway for robust prediction under nonstationary conditions.

Source: Geophysical Research Letters

DOI: 10.1029/2025gl121604

Authors: Zhigang Ou, Yi Zheng

Institution: Southern University of Science and Technology

Language: English

Topic: Hydrological Forecasting Using AI

Subfield: Environmental Engineering

Field: Environmental Science

Domain: Physical Sciences

SDGs: Climate action, Clean water and sanitation

Open Access status: gold

Estimated APC paid: $3,190