# OceanMAE: A Foundation Model for Ocean Remote Sensing Source: [OceanMAE: A Foundation Model for Ocean Remote Sensing]() Collection index: [llms.txt]() Data updated: 2026-04-11T05:00:04.811Z Authors: Viola-Joanna Stamer, Panagiotis Agrafiotis, Behnood Rasti, Beg\\"um Demir Published: 2026-04-09T12:29:41.000Z ## Abstract Accurate ocean mapping is essential for applications such as bathymetry estimation, seabed characterization, marine litter detection, and ecosystem monitoring. However, ocean remote sensing (RS) remains constrained by limited labeled data and by the reduced transferability of models pre-trained mainly on land-dominated Earth observation imagery. In this paper, we propose OceanMAE, an ocean-specific masked autoencoder that extends standard MAE pre-training by integrating multispectral Sentinel-2 observations with physically meaningful ocean descriptors during self-supervised learning. By incorporating these auxiliary ocean features, OceanMAE is designed to learn more informative and ocean-aware latent representations from large- scale unlabeled data. To transfer these representations to downstream applications, we further employ a modified UNet-based framework for marine segmentation and bathymetry estimation. Pre-trained on the Hydro dataset, OceanMAE is evaluated on MADOS and MARIDA for marine pollutant and debris segmentation, and on MagicBathyNet for bathymetry regression. The experiments show that OceanMAE yields the strongest gains on marine segmentation, while bathymetry benefits are competitive and task-dependent. In addition, an ablation against a standard MAE on MARIDA indicates that incorporating auxiliary ocean descriptors during pre-training improves downstream segmentation quality. These findings highlight the value of physically informed and domain-aligned self-supervised pre- training for ocean RS. Code and weights are publicly available at https://git.tu-berlin.de/joanna.stamer/SSLORS2. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Marine Debris Segmentation on MARIDA (test)](): Marine Debris Segmentation; MARIDA (test); Pixel Accuracy: 77. - [Pollutants and Sea-Surface Segmentation on MADOS](): Pollutants and Sea-Surface Segmentation; MADOS; PA: 87.4. ## Original sources and implementation [Original paper]() [PDF]()