Tag
The world's oceans have reached their highest recorded average surface temperature, surpassing previous records due to human-caused climate change and the growing El Niño phenomenon, raising concerns about extreme weather and marine life impacts.
This paper introduces EddyFlow, a deep learning framework for kilometer-scale sea surface temperature downscaling that balances predictive accuracy, scale-dependent structure, and regional generalization. It achieves strong zero-shot performance and near-ideal spectral fidelity across multiple ocean regions.