Contribution to a conference proceedings

FZJ-2025-03964

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Terramesh: A Planetary Mosaic of Multimodal Earth Observation Data

Blumenstiel, B. (Corresponding author) ; Fraccaro, P. ; Marsocci, V. ; Jakubik, J. ; Maurogiovanni, S.FZJ* ; Czerkawski, M. ; Sedona, R.FZJ* ; Cavallaro, G.FZJ* ; Brunschwiler, T. ; Bernabe-Moreno, J. ; Longépé, N.

2025
IEEE

This record in other databases:  

Please use a persistent id in citations: doi:10.1109/CVPRW67362.2025.00225

Abstract: 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.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)
2. AI Foundation - AI Foundation Models for EO (AIFM4EO, FAST-EO) (D/564/67338791) (D/564/67338791)
3. Simulation and Data Lab AI and ML for Remote Sensing (SDLRS)

Appears in the scientific report 2025

---