TY - CONF
AU - Blumenstiel, Benedikt
AU - Fraccaro, Paolo
AU - Marsocci, Valerio
AU - Jakubik, Johannes
AU - Maurogiovanni, Stefano
AU - Czerkawski, Mikolaj
AU - Sedona, Rocco
AU - Cavallaro, Gabriele
AU - Brunschwiler, Thomas
AU - Bernabe-Moreno, Juan
AU - Longépé, Nicolas
TI - Terramesh: A Planetary Mosaic of Multimodal Earth Observation Data
PB - IEEE
M1 - FZJ-2025-03964
SP - n/a
PY - 2025
AB - 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.
T2 - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
CY - 11 Jun 2025 - 12 Jun 2025, Nashville (TN)
Y2 - 11 Jun 2025 - 12 Jun 2025
M2 - Nashville, TN
LB - PUB:(DE-HGF)8
DO - DOI:10.1109/CVPRW67362.2025.00225
UR - https://juser.fz-juelich.de/record/1046797
ER -