High-resolution probabilistic estimation of three-dimensional regional ocean dynamics from sparse surface observations

2026-04-03

AI Summary

This study addresses the challenge of reconstructing three-dimensional ocean states, which is hindered by the sparsity of in situ observations and the surface-only limitation of satellite measurements. To overcome this, the authors propose a depth-aware generative framework based on a conditional denoising diffusion probabilistic model (DDPM) that reconstructs high-resolution 3D temperature, salinity, and velocity fields using only sea surface height and temperature data with up to 99.9% missing entries—without relying on dynamical background fields. The method innovatively incorporates a continuous depth embedding, enabling the model to learn a unified vertical representation and generalize to unseen depths. Experiments in the Gulf of Mexico demonstrate the approach’s ability to accurately reproduce large-scale circulation and multiscale variability, with heat transport estimates, spectral analyses, and statistical metrics collectively confirming its superior performance.

Abstract

The ocean interior regulates Earth's climate but remains sparsely observed due to limited in situ measurements, while satellite observations are restricted to the surface. We present a depth-aware generative framework for reconstructing high-resolution three-dimensional ocean states from extremely sparse surface data. Our approach employs a conditional denoising diffusion probabilistic model (DDPM) trained on sea surface height and temperature observations with up to 99.9 percent sparsity, without reliance on a background dynamical model. By incorporating continuous depth embeddings, the model learns a unified vertical representation of the ocean states and generalizes to previously unseen depths. Applied to the Gulf of Mexico, the framework accurately reconstructs subsurface temperature, salinity, and velocity fields across multiple depths. Evaluations using statistical metrics, spectral analysis, and heat transport diagnostics demonstrate recovery of both large-scale circulation and multiscale variability. These results establish generative diffusion models as a scalable approach for probabilistic ocean reconstruction in data-limited regimes, with implications for climate monitoring and forecasting.

Problem

• ocean reconstruction
• sparse observations
• three-dimensional ocean dynamics
• probabilistic estimation
• data-limited regimes

Innovation

• diffusion probabilistic model
• 3D ocean reconstruction
• sparse surface observations
• depth-aware generative modeling
• data-limited oceanography