THOR-1.0

Key features:

• Multi-sensor support: Sentinel-1 (SAR), Sentinel-2 (MSI), Sentinel-3 OLCI & SLSTR
• Flexible resolution: 10 m to 1000 m native resolutions
• Compute-adaptive: Flexible patch sizes and ground covers (1000 m to +100,000 m)
• Data-efficient: State-of-the-art performance in data-limited regimes
• Model type: Vision Transformer (FlexiViT)

Usage

THOR is designed for fine-tuning on downstream tasks such as land cover classification, crop mapping, flood detection, and more. Its flexible architecture allows users to adapt the model to various geospatial applications while leveraging its multi-sensor capabilities.

For downstream applications, we recommend using the terratorch framework with our THOR terratorch extension.

Terratorch backbone loading example

# Example usage of THOR ViT backbone with terratorch

# Import our custom thor_terratorch_ext module to register THOR backbones
import thor_terratorch_ext  # noqa: F401

# Load the backbone registry
from terratorch import BACKBONE_REGISTRY

# List available THOR backbones
print([b for b in list(BACKBONE_REGISTRY) if "thor" in b])

# Build a THOR ViT model with specific bands
model = BACKBONE_REGISTRY.build(
    "thor_v1_base",
    pretrained=True,
    model_bands=["BLUE", "GREEN", "RED", "VV", "VH"],
    input_params=dict(  # Optional input parameters to customize
        ground_covers=[
            2880
        ],  # Ground cover in meters (typically input image size [px] * input image resolution)
        flexivit_patch_size_seqs=[8],  # Patch size in pixels
    ),
)

Training Details

Training Data

THOR is pre-trained on THOR-Pretrain, a large-scale multi-sensor dataset containing paired observations from Sentinel-1, Sentinel-2, and Sentinel-3 satellites, as well as auxiliary land cover and elevation data and meteorological variables.

Training Procedure

For training configuration, see the config file: thor-base.yaml

Compute Infrastructure

The model was trained on the LUMI supercomputer in Finland using 4 nodes, each equipped with 4 AMD MI250X GPUs, totaling 32 GCDs.

Evaluation

Results

THOR demonstrates highly competitive performance on the PANGAEA benchmark, particularly in data-limited regimes. With only 10% training data, THOR-Base achieves the best average rank across all datasets.

Results in mIoU on PANGAEA benchmark with 10% training data. Bold = best, italic = second-best.

Attribution

The development of THOR was funded and supported by European Space Agency (ESA) Φ-lab (FM4CS project, contract no. 4000143489/24/I-DT), and the Research Council of Norway (KnowEarth project no. 337481).

Citation

If you use THOR in your research, please cite the paper:

BibTeX:

@article{forgaard2026thor,
      title={THOR: A Versatile Foundation Model for Earth Observation Climate and Society Applications},
      author={Theodor Forgaard and Jarle H. Reksten and Anders U. Waldeland and Valerio Marsocci and Nicolas Longépé and Michael Kampffmeyer and Arnt-Børre Salberg},
      year={2026},
      eprint={2601.16011},
      archivePrefix={arXiv},
      primaryClass={eess.IV},
      url={https://arxiv.org/abs/2601.16011},
}

Contact

Arnt Salberg - Norwegian Computing Center (NR) salberg@nr.no