TerraMesh: A Planetary Mosaic of Multimodal Earth Observation Data

Benedikt Blumenstiel, Paolo Fraccaro, Valerio Marsocci, Johannes Jakubik, Stefano Maurogiovanni, Mikolaj Czerkawski, Rocco Sedona, Gabriele Cavallaro, Thomas Brunschwiler, Juan Bernabe Moreno, Nicolas Longepe; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2025, pp. 2394-2402

Large-scale foundation models in Earth Observation can learn versatile, label-efficient representations by leveraging massive amounts of unlabeled data. However, existing public datasets are often limited in scale, geographic coverage, or sensor variety. We introduce TerraMesh, a new globally diverse, multimodal dataset combining optical, synthetic aperture radar, elevation, and land-cover modalities in an Analysis-Ready Data format. TerraMesh includes over 9 million samples with eight spatiotemporal aligned modalities, enabling large-scale pre-training and fostering robust cross-modal correlation learning. The dataset spans nearly all terrestrial ecosystems and is stored with Zarr to facilitate efficient, HPC-friendly loading at scale. We provide detailed data processing steps, comprehensive statistics, and empirical evidence demonstrating improved model performance when pre-trained on TerraMesh. The dataset will be made publicly available with a permissive license.