Super-resolution of satellite-derived SST data via Generative Adversarial Networks Article Swipe

MAKE IMPACT

Fanelli, Claudia , LI Tiany , Biferale, Luca , Nardelli, Bruno Buongiorno , Ciani, Daniele , Pisano Andrea , Buzzicotti, Michele · YOU? · · 2025 · Open Access ·

In this work, we address the super-resolution problem of satellite-derived sea surface temperature (SST) using deep generative models. Although standard gap-filling techniques are effective in producing spatially complete datasets, they inherently smooth out fine-scale features that may be critical for a better understanding of the ocean dynamics. We investigate the use of deep learning models as Autoencoders (AEs) and generative models as Conditional-Generative Adversarial Networks (C-GANs), to reconstruct small-scale structures lost during interpolation. Our supervised -- model free -- training is based on SST observations of the Mediterranean Sea, with a focus on learning the conditional distribution of high-resolution fields given their low-resolution counterparts. We apply a tiling and merging strategy to deal with limited observational coverage and to ensure spatial continuity. Quantitative evaluations based on mean squared error metrics, spectral analysis, and gradient statistics show that while the AE reduces reconstruction error, it fails to recover high-frequency variability. In contrast, the C-GAN effectively restores the statistical properties of the true SST field at the cost of increasing the pointwise discrepancy with the ground truth observation. Our results highlight the potential of deep generative models to enhance the physical and statistical realism of gap-filled satellite data in oceanographic applications.

Type

article

Landing Page

http://arxiv.org/abs/2511.22610

PDF

https://arxiv.org/pdf/2511.22610

OA Status

green

OpenAlex ID

https://openalex.org/W7108248320

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W7108248320

Canonical identifier for this work in OpenAlex

Title

Super-resolution of satellite-derived SST data via Generative Adversarial Networks

Work title

Type

article

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-11-27

Full publication date if available

Authors

Fanelli, Claudia, LI Tiany, Biferale, Luca, Nardelli, Bruno Buongiorno, Ciani, Daniele, Pisano Andrea, Buzzicotti, Michele

List of authors in order

Landing page

https://arxiv.org/abs/2511.22610

Publisher landing page

PDF URL

https://arxiv.org/pdf/2511.22610

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2511.22610

Direct OA link when available

Concepts

Pointwise, Generative grammar, Computer science, Artificial intelligence, Deep learning, Ground truth, Focus (optics), Statistical model, Machine learning, Adversarial system, Field (mathematics), Probability distribution, Generative model, Data-driven, Mean squared error, Pattern recognition (psychology), Deep belief network, Missing data, Benchmark (surveying), Conditional probability distribution, Data point, Algorithm, Data mining, Data modeling

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

Full payload