EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

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

Zhigang Ou, Yi Zheng

Geophysical Research Letters · 16.04.2026 · 53 (7)

DOI: 10.1029/2025gl121604 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Geophysical Research Letters, online erschienen am 03.04.2026. Verfasst von Zhigang Ou und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ou, Z., & Zheng, Y. (2026). Foundation‐Scale Satellite Embeddings Reframe Hydrological Generalization as a Representation Problem. Geophysical Research Letters, 53(7). https://doi.org/10.1029/2025gl121604

Vancouver

Ou Z, Zheng Y. Foundation‐Scale Satellite Embeddings Reframe Hydrological Generalization as a Representation Problem. Geophysical Research Letters. 2026;53(7). doi:10.1029/2025gl121604

BibTeX
@article{Ou2026,
  author = {Ou, Zhigang and Zheng, Yi},
  title = {Foundation‐Scale Satellite Embeddings Reframe Hydrological Generalization as a Representation Problem},
  journal = {Geophysical Research Letters},
  year = {2026},
  volume = {53},
  number = {7},
  doi = {10.1029/2025gl121604}
}
Kostenlos starten →