Spatial Super-Resolution of Satellite-Derived SST Data via Generative Adversarial Networks in the Mediterranean Sea
Remote Sensing · 19.10.2026 · 18 (20) · 3593
DOI: 10.3390/rs18203593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.10.2026. Verfasst von Claudia Fanelli und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Italian national project ITINERIS, Italian Integrated Environmental Research Infrastructures System, EU—Next Generation.
Abstract (Originalsprache)
In this work, we compare deep convolutional and generative models to improve the reconstruction of sea surface temperature (SST) gradients and effective resolution from cloud-contaminated satellite infrared data. Standard gap-filling techniques produce spatially complete datasets, but they inherently smooth out fine-scale features and gradients that may be critical for a better understanding of the ocean dynamics. Here, we investigate how the use of deep learning models as Autoencoders (AEs) and generative models as Conditional Generative Adversarial Networks (C-GANs) differently contribute to recovering the small-scale structures lost during interpolation. Our supervised, observation-based training relies on satellite-derived SST data from the Mediterranean Sea, with a focus on learning the statistical relationship between high-resolution fields and their low-resolution counterparts. We apply a tiling and merging strategy to deal with limited observational coverage and to ensure spatial continuity. Quantitative validation based on mean squared error metrics, spectral analysis, and gradient statistics shows that the AE reduces the reconstruction error, but 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 observations. Our results highlight the potential of deep models to enhance the physical and statistical realism of gap-filled satellite data in oceanographic applications.
Förderung
- Italian national project ITINERIS
- Italian Integrated Environmental Research Infrastructures System
- EU—Next Generation
- Copernicus Marine Service
- European Research Council
- Italian Ministry of University and Research
Zitieren
APA
Fanelli, C., Li, T., Biferale, L., Nardelli, B. B., Ciani, D., Pisano, A., & Buzzicotti, M. (2026). Spatial Super-Resolution of Satellite-Derived SST Data via Generative Adversarial Networks in the Mediterranean Sea. Remote Sensing, 18(20), 3593. https://doi.org/10.3390/rs18203593
Vancouver
Fanelli C, Li T, Biferale L, Nardelli BB, Ciani D, Pisano A, et al. Spatial Super-Resolution of Satellite-Derived SST Data via Generative Adversarial Networks in the Mediterranean Sea. Remote Sensing. 2026;18(20):3593. doi:10.3390/rs18203593
BibTeX
@article{Fanelli2026,
author = {Fanelli, Claudia and Li, Tianyi and Biferale, Luca and Nardelli, Bruno Buongiorno and Ciani, Daniele and Pisano, Andrea and Buzzicotti, Michele},
title = {Spatial Super-Resolution of Satellite-Derived SST Data via Generative Adversarial Networks in the Mediterranean Sea},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {20},
pages = {3593},
doi = {10.3390/rs18203593}
}
EUVIMED