OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations

Abstract:Despite comprising over 70\% of its surface, the world's oceans are critically underobserved compared to the land surface or the this http URL the global ocean requires jointly observing its surface and subsurface structure, yet no standardized, high-resolution dataset couples satellite surface fields to co-located \emph{in situ} depth profiles in an AI-ready this http URL resources either consist of model-reconstructed gridded products rather than observations, cover only a single variable or basin, or operate at resolutions too coarse for mesoscale this http URL introduce \textsc{OceanDepths}, the first open, global, regridded AI-ready dataset that pairs satellite-derived sea surface temperature (SST), sea surface salinity (SSS), and sea surface height (SSH) L4 products with co-located EN4 subsurface temperature and salinity profiles, complemented by matched GLORYS12 ocean reanalysis data to support comparisons or multi-stage this http URL dataset spans 2000--2024 at \SI{0.1}{\degree}$\times$\SI{0.1}{\degree} spatial resolution and at weekly temporal resolution, covering the entire globe's sea surface and with over 9.5 million paired profiles interpolated to 50 standardized depth this http URL provide a configurable system to split the globe in equally sized spatial this http URL 4D multivariate structure, high resolution, long temporal extent, and extreme sparsity of subsurface observations (${\sim}$0.01\% per depth level) make \textsc{OceanDepths}a challenging testbed for novel AI this http URL demonstrate subsurface state reconstruction as an example task with simple baseline models, but also envision \textsc{OceanDepths}to support the development of observation-based forecast methods and other related tasks.\added{Available at: this https URL.}

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)

arXiv:2608.16373 [cs.LG]

(or arXiv:2608.16373v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2608.16373 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.