A Physics-Enhanced Network for Predicting Sequential Satellite Images of Typhoon Clouds

Typhoons are extreme weather events that pose significant threats to human life and property. Sequential satellite imagery of typhoon clouds, which is rich in spatio-temporal information, plays a critical role in understanding their formation, development, and evolutionary dynamics. Recently, the rapid advancement of deep learning that combines physical insights with data-driven has opened new avenues for research in Earth science. In this study, for high-quality prediction of sequential typhoon cloud images, we propose a physics-enhanced deep learning model termed C<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>PhyNet. Specifically, we introduce a novel disentangling spatio-temporal block integrated with a criss-cross physics-enhanced unit. To further improve the fine structural details in the predicted typhoon cloud images, a concurrent spatial and channel squeeze-and-excitation attention mechanism is incorporated into both the encoder and decoder modules. Our quantitative analysis demonstrates the superiority of the proposed approach over existing sequential image prediction models on the publicly available Digital Typhoon dataset. The experimental results show that our method achieves superior performance, with a Structural Similarity Index Measure (SSIM) of 0.8200 and a Peak Signal-to-Noise Ratio (PSNR) of 23.26. C<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>PhyNet is capable of generating high-quality sequential typhoon cloud images, which can significantly enhance the ability of meteorologists to forecast typhoon-related details with greater accuracy. Furthermore, our research contributes to improved risk mitigation and more effective disaster warning and management strategies.