OceanSAR-1-wave is a linear probing head for significant wave height (SWH) prediction built on top of the OceanSAR-1 foundation model. It leverages the powerful features extracted by OceanSAR-1 to accurately predict ocean wave heights from Synthetic Aperture Radar (SAR) imagery.
This model is designed for significant wave height prediction from SAR imagery over ocean surfaces. It can be used for:
The model achieves state-of-the-art performance in linear probing on significant wave height prediction, with performance varying by backbone architecture:
1import torch
2from transformers import AutoModelForImageClassification
3
4# Load the foundation model and the linear probing head
5oceansar = AutoModelForImageClassification.from_pretrained("galeio-research/OceanSAR-1")
6
7# Prepare your SAR image (should be single-channel VV polarization)
8# Here using random data as example
9dummy_image = torch.randn(1, 1, 256, 256) # (C, H, W)
10
11# Extract features
12with torch.no_grad():
13 outputs = oceansar(dummy_image)
14 # For regression, use the single output value as the wave height prediction
15 wave_height = outputs.logits.item() # Output in meters
Significant wave height prediction performance is evaluated using Root Mean Square Error (RMSE), achieving:
1@article{kerdreux2025efficientselfsupervisedlearningearth,
2 title={Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation},
3 author={Kerdreux, Thomas and Tuel, Alexandre and Febvre, Quentin and Mouche, Alexis and Chapron, Bertrand},
4 journal={arXiv preprint arXiv:2504.06962},
5 year={2025},
6 eprint={2504.06962},
7 archivePrefix={arXiv},
8 primaryClass={cs.CV},
9 url={https://arxiv.org/abs/2504.06962},
10}
This work was granted access to the HPC resources of IDRIS and TGCC under the allocation 2025-[A0171015666] made by GENCI.
