Cryo-Bench: Benchmarking Foundation Models for Cryosphere Applications
Researchers have introduced Cryo-Bench, a new benchmark designed to evaluate the performance of Geo-Foundation Models (GFMs) specifically for cryosphere applications. The benchmark covers key components like glaciers, glacial lakes, sea ice, and calving fronts across various sensors and regions. In evaluations, UNet achieved the highest average mIoU with a frozen encoder, while certain GFMs like DOFA and TerraMind showed promise in few-shot learning scenarios. AI
IMPACT Establishes a new evaluation standard for AI models in cryosphere research, potentially guiding future development and application in climate science.