TerraMind: Large-Scale Generative Multimodality for Earth Observation

Understand

We present TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO).

• Unlike other multimodal models, TerraMind is pretrained on dual-scale representations combining both token-level and pixel-level data across modalities.
• On a token level, TerraMind encodes high-level contextual information to learn cross-modal relationships, while on a pixel level, TerraMind leverages fine-grained representations to capture critical spatial nuances.
• We pretrained TerraMind on nine geospatial modalities of a global, large-scale dataset.