TriPhysGAN-Attn: a physics-informed generative model for radar echo forecasting via triple mechanism decomposition and attention fusion

Zhang, Y. ORCID: https://orcid.org/0000-0003-3011-3113, Yuan, Z. ORCID: https://orcid.org/0009-0009-4323-7458, Badii, A., Wang, J. ORCID: https://orcid.org/0009-0005-0390-3859 and Li, P. (2026) TriPhysGAN-Attn: a physics-informed generative model for radar echo forecasting via triple mechanism decomposition and attention fusion. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 19. pp. 1-20. ISSN 2151-1535 doi: 10.1109/jstars.2026.3658947

Abstract/Summary

Nowcasting of precipitation plays a critical role in meteorological operations and disaster prevention. However, existing deep learning-based radar echo prediction models often suffer from unclear physical mechanisms and insufficient capability to represent the multiscale dynamic processes of precipitation systems, making them less effective in handling severe convective weather. In this study, we propose TriPhysGAN-Attn, a novel radar echo prediction model guided by meteorological physical mechanisms. We divide the evolution of precipitation into three fundamental processes: Advection, initiation and dissipation, and deformation. Accordingly, we design an advection branch to model multiscale motion fields, an initiation and dissipation branch driven by state differences, and a deformation branch guided by motion field gradients. To enhance physical consistency, we incorporate a physically informed loss function along with meteorological priors and supervision signals. A multihead cross-attention mechanism is employed to dynamically fuse information across the three processes, facilitating collaborative modeling. In addition, a generative adversarial framework and a coordinate attention module are integrated to better capture local discontinuities and spatial structures. Experimental results show that TriPhysGAN-Attn outperforms existing methods on real radar datasets, achieving superior performance in structural preservation, prediction accuracy, and robustness under extreme weather conditions.

Item Type	Article
URI	https://centaur.reading.ac.uk/id/eprint/128416
Identification Number/DOI	10.1109/jstars.2026.3658947
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
Publisher	IEEE
Download/View statistics	View download statistics for this item