cs.AINov 17, 2026

DARWIN: a Geospatial Foundation Model for Marine Intelligence

Authors: Coen van den Elsen, Laurens Geffert

Organizations: Ocean OS

Abstract

We present DARWIN, a geospatial foundation model for marine intelligence. Recent Earth-observation foundation models have concentrated on terrestrial domains. The marine realm poses distinct challenges: missingness, multi-modal physical and biogeochemical variables, sparse labels, and dynamics that are transient, multi-scale, and non stationary over time. DARWIN adapts a masked-autoencoder backbone to these properties through missingness-aware encoding, expanded spatial and temporal masking, and Fourier-style positional embeddings, and is pretrained on 26 years of global Copernicus reanalysis together with GEBCO bathymetry. On predicting chlorophyll-a, the pretrained backbone attains the lowest monthly relative error in every month of 2022, outperforming both no-encoder baselines and an identically architected random-init encoder. At 10% of the supervised training data, DARWIN already surpasses the random-init model trained on 100% of the data. Embedding analysis and qualitative reconstructions show that DARWIN captures coherent oceanographic structure rather than memorising input statistics, providing a scalable backbone for downstream marine applications such as anomaly detection, species distribution modelling, and environmental monitoring.

Figures & tables

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. OceanMAE: A Foundation Model for Ocean Remote Sensing

    Apr 9, 2026Viola-Joanna Stamer, Panagiotis Agrafiotis, Behnood Rasti +1Remote SensingSelf-Supervised Visual Representation Learning

  2. YingLan: A Multimodal Ocean Foundation Model for Unified Representation Learning from Heterogeneous Observations

    Oct 21, 2026Sen Jia, Siqi Wei, Junyu Wang +8Multimodal Foundation ModelsSpatiotemporal Forecasting

  3. Self-Supervised Multi-Modal World Model with 4D Space-Time Embedding

    Mar 7, 2026Lance Legel, Qin Huang, Brandon Voelker +9World Model LearningGeospatial Representation Learning