Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super‐Resolution
IET Image Processing · 2026-01 · 20 (1)
DOI: 10.1049/ipr2.70438 ↗At a glance
Journal article in IET Image Processing, published online on 2026-07-28. Written by Ruoyi Zhang and 4 co-authors. Cited 1 times so far (Crossref); 30 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Shanghai Typhoon Institute, China Meteorological Administration.
Abstract (original language)
High‐resolution satellite imagery is indispensable for tracking the genesis, intensification, and trajectory of tropical cyclones (TCs). However, existing deep learning‐based super‐resolution (SR) methods often treat satellite image sequences as generic videos, neglecting the underlying atmospheric physical laws governing cloud motion. To address this, we propose a physics encoded spatial and temporal generative adversarial network (PESTGAN) for TC image super‐resolution. Specifically, we design a disentangled generator architecture incorporating a PhyCell module, which approximates the vorticity equation via constrained convolutional operators and encodes the resulting approximate physical dynamics as implicit latent representations to separate physical dynamics from visual textures. Furthermore, a dual‐discriminator framework is introduced, employing a temporal discriminator to enforce motion consistency alongside spatial realism. Experiments on the digital typhoon dataset for 4 upscaling demonstrate that PESTGAN establishes a better performance in structural fidelity and perceptual quality. While maintaining competitive pixel‐level accuracy compared to existing approaches, our method significantly excels in reconstructing meteorologically plausible cloud structures with superior physical fidelity.
Funding
- Shanghai Typhoon Institute
- China Meteorological Administration
Cite
APA
Zhang, R., Yuan, J., Ye, L., Yu, R., & Zhao, L. (2026). Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super‐Resolution. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.70438
Vancouver
Zhang R, Yuan J, Ye L, Yu R, Zhao L. Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super‐Resolution. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.70438
BibTeX
@article{Zhang2026,
author = {Zhang, Ruoyi and Yuan, Jiawei and Ye, Lujia and Yu, Runling and Zhao, Liling},
title = {Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super‐Resolution},
journal = {IET Image Processing},
year = {2026},
volume = {20},
number = {1},
doi = {10.1049/ipr2.70438}
}
EUVIMED