% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Blumenstiel:1046797,
      author       = {Blumenstiel, Benedikt and Fraccaro, Paolo and Marsocci,
                      Valerio and Jakubik, Johannes and Maurogiovanni, Stefano and
                      Czerkawski, Mikolaj and Sedona, Rocco and Cavallaro,
                      Gabriele and Brunschwiler, Thomas and Bernabe-Moreno, Juan
                      and Longépé, Nicolas},
      title        = {{T}erramesh: {A} {P}lanetary {M}osaic of {M}ultimodal
                      {E}arth {O}bservation {D}ata},
      publisher    = {IEEE},
      reportid     = {FZJ-2025-03964},
      pages        = {n/a},
      year         = {2025},
      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.},
      month         = {Jun},
      date          = {2025-06-11},
      organization  = {2025 IEEE/CVF Conference on Computer
                       Vision and Pattern Recognition
                       Workshops (CVPRW), Nashville (TN), 11
                       Jun 2025 - 12 Jun 2025},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / AI Foundation - AI
                      Foundation Models for EO (AIFM4EO, FAST-EO)
                      (D/564/67338791)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(ESA-Grant)D/564/67338791},
      typ          = {PUB:(DE-HGF)8},
      doi          = {10.1109/CVPRW67362.2025.00225},
      url          = {https://juser.fz-juelich.de/record/1046797},
}