Skip to content
#diffusion models Open access

DIRECT 1.0: a diffusion-based generative model for dense sea surface temperature reconstructions from sparse satellite observations

Sep 2026 · Geoscientific Model Development · 0 citations · 43 references
Oceanographic and Atmospheric Processes

TL;DR

DI, a conditional generative framework for dense SST reconstruction that models the full distribution of plausible solutions rather than a single deterministic estimate, is introduced, enabling reliable SST reconstruction from sparse satellite observations.

Abstract

Satellite sea surface temperature (SST) observations are frequently obscured by cloud cover, creating large gaps that must be reconstructed for many oceanographic and climate applications. Because multiple high-resolution SST fields may be consistent with the same sparse observations, this reconstruction problem is inherently ambiguous. Nevertheless, most existing approaches remain deterministic, producing a single estimate that is often overly smooth, may contain unrealistic artifacts, and provides limited or unreliable uncertainty estimates. To address these limitations, we introduce DIRECT, a conditional generative framework for dense SST reconstruction that models the full distribution of plausible solutions rather than a single deterministic estimate. DIRECT is based on a rectified flow-matching formulation, conditioned on temporal context and day-of-year seasonality, and trained on sparse Level-3 observations. It presents an observation-guided rectification that anchors the generative trajectory to measured pixels at every integration step. By sampling multiple reconstructions, DIRECT produces an ensemble of physically plausible SST fields, enabling both an accurate mean reconstruction and spatially resolved uncertainty estimates. The latter is adjusted with a simple post-hoc variance term to avoid under-dispersed uncertainty estimates. Experiments on three Level-3 SST datasets (Mediterranean, Adriatic, and Atlantic) show that DIRECT sets a new state-of-the-art, reducing Root Mean Square Error by 6 %–14 % compared with the strongest published method, while better preserving mesoscale structure. Further analysis of spatial scale correlations indicates that DIRECT maintains physically consistent textures even when reconstructing large, completely unobserved regions. Performance improvements remain robust across a wide range of cloud-coverage conditions, enabling reliable SST reconstruction from sparse satellite observations.

Read PDF

Similar papers

#machine learning Preprint Sep 2026

Steering Diffusion Priors with Sparse Observations for High-Resolution Temperature Downscaling

Local heatwave hazard depends on fine-scale air temperature, but ground stations are sparse and reanalysis products such as ERA5 cannot resolve the terrain and land-surface contrasts that shape real heat exposure. We present a conditional diffusion emulator for high-resolution 2-m temperature downscaling, conditioned o...

Anirudh Avireddy, Manmeet Singh, Shivanshi Singh et al. · 0 citations
Open access Sep 2026

A Generative AI Framework for Inferring Consistent Ocean Statistics at Depth Using Sea Surface Data

Understanding subsurface ocean dynamics is essential for quantifying oceanic heat and mass transport, but direct observations at depth remain sparse due to logistical and technological constraints. In contrast, satellite missions provide rich surface datasets—such as sea surface height, temperature, and salinity—that...

A. Souza, Simone Silvestri, Katherine E. V. Deck et al. · 0 citations

Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces

This work forms this reconstruction problem as generative atmospheric super-resolution and introduces composable observation interfaces for conditioning a single pretrained 13-variable atmospheric diffusion model without retraining the underlying model.

Yang Xu, Dibyajyoti Chakraborty, Hai-Wen Guan et al. · 0 citations
Preprint Sep 2026

Physical-Field Reconstruction from Sparse Observations: When Are Diffusion Models Preferable to Deterministic Regression?

Reconstructing physical fields from sparse observations is central to system identification, forecasting, and control, yet sparse measurements generally underdetermine the full field. This makes reconstruction an ill-posed inverse problem rather than simple interpolation. Although many deterministic and generative meth...

Hao Zhou, Rui Zhang, Qi Wang et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.