Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super-resolution

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Ruoyi, Yuan, Jiawei, Ye, Lujia, Yu, Runling, Zhao, Liling
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910026913808384
author Zhang, Ruoyi
Yuan, Jiawei
Ye, Lujia
Yu, Runling
Zhao, Liling
author_facet Zhang, Ruoyi
Yuan, Jiawei
Ye, Lujia
Yu, Runling
Zhao, Liling
contents 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 convolutions 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$\times$ upscaling demonstrate that PESTGAN establishes a better performance in structural fidelity and perceptual quality. While maintaining competitive pixel-wise accuracy compared to existing approaches, our method significantly excels in reconstructing meteorologically plausible cloud structures with superior physical fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2602_17277
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super-resolution
Zhang, Ruoyi
Yuan, Jiawei
Ye, Lujia
Yu, Runling
Zhao, Liling
Computer Vision and Pattern Recognition
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 convolutions 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$\times$ upscaling demonstrate that PESTGAN establishes a better performance in structural fidelity and perceptual quality. While maintaining competitive pixel-wise accuracy compared to existing approaches, our method significantly excels in reconstructing meteorologically plausible cloud structures with superior physical fidelity.
title Physics Encoded Spatial and Temporal Generative Adversarial Network for Tropical Cyclone Image Super-resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.17277