PRACTICAL EMBEDDING WORKFLOWS WITH TERRATORCH, THE GEOSPATIAL FINE-TUNING TOOLKIT

Geospatial foundation models pretrained on large-scale Earth observation archives offer strong transfer capabilities across remote sensing tasks, but practical adoption remains challenging due to heterogeneous data formats, complex fine-tuning pipelines, and inconsistent evaluation protocols. We present TerraTorch, a configuration-driven toolkit for reproducible adaptation and benchmarking of geospatial foundation models. This workshop contribution complements earlier TerraTorch system work by focusing specifically on embedding-centric workflows: (i) generic embedding generation from pretrained encoders and (ii) downstream learning on top of frozen embeddings for semantic segmentation. All demonstrations are linked to executable repository examples, lowering the barrier for ML4RS researchers and practitioners to apply foundation models in real-world Earth observation settings.