MRDAM: Satellite Cloud Image Super-Resolution via Multi-Scale Residual Deformable Attention Mechanism

Abstract

Highlights: What are the main findings? The proposed model effectively integrates progressive multi-scale feature extraction with deformable attention mechanisms, achieving comprehensive representation of cloud systems, spanning from macroscopic cloud organizations down to local textures and irregular morphological patterns. A composite loss function is introduced, which significantly enhances the reconstruction of high-frequency details while preserving meteorological physical consistency in the super-resolved cloud image. What is the implication of the main finding? The framework offers a viable approach for high-resolution cloud analysis, showing potential value in nowcasting and climatological applications. The methodology demonstrates how meteorological physical constraints can be incorporated into deep-learning-based image reconstruction, providing a reference for domain-aware super-resolution tasks in remote sensing and atmospheric sciences. High-resolution meteorological satellite cloud imagery plays a crucial role in diagnosing and forecasting severe convective weather phenomena characterized by suddenness and locality, such as tropical cyclones. However, constrained by imaging principles and various internal/external interferences during satellite data acquisition, current satellite imagery often fails to meet the spatiotemporal resolution requirements for fine-scale monitoring of these weather systems. Particularly for real-time tracking of tropical cyclone genesis-evolution dynamics and capturing detailed cloud structure variations within cyclone cores, existing spatial resolutions remain insufficient. Therefore, developing super-resolution techniques for meteorological satellite cloud imagery through software-based approaches holds significant application potential. This paper proposes a Multi-scale Residual Deformable Attention Model (MRDAM) based on Generative Adversarial Networks (GANs), specifically designed for satellite cloud image super-resolution tasks considering their morphological diversity and non-rigid deformation characteristics. The generator architecture incorporates two key components: a Multi-scale Feature Progressive Fusion Module (MFPFM), which enhances texture detail preservation and spectral consistency in reconstructed images, and a Deformable Attention Additive Fusion Module (DAAFM), which captures irregular cloud pattern features through adaptive spatial-attention mechanisms. Comparative experiments against multiple GAN-based super-resolution baselines demonstrate that MRDAM achieves superior performance in both objective evaluation metrics (PSNR/SSIM) and subjective visual quality, proving its superior performance for satellite cloud image super-resolution tasks.