Artificial Intelligence #earth observation#satellite imagery
TerraMind: First Any-to-Any Generative Multimodal Foundation Model for Earth Observation
Researchers have introduced TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO). Pretrained on dual-scale representations across nine geospatial modalities, it achieves beyond state-of-the-art performance on the PANGAEA benchmark and introduces a novel 'Thinking-in-Modalities' capability.
Jun 21, 2026 1 source