Cloud-Aware SAR Fusion for Enhanced Optical Sensing in Space Missions

2025-06-21

AI Summary

Cloud contamination severely limits the utility of optical satellite imagery for environmental monitoring and disaster response. To address this, we propose a SAR-optical multimodal deep learning reconstruction framework. Our method introduces two key innovations: (1) an SAR-guided attention-based feature alignment module that explicitly models cloud structure, and (2) a cloud-aware adaptive weighting loss function that enforces spectral consistency. Evaluated on both synthetic and real-world datasets, our approach achieves state-of-the-art performance: PSNR = 31.01 dB, SSIM = 0.918, and MAE = 0.017. The reconstructed cloud-free optical images exhibit sharp spatial detail and high spectral fidelity, enabling robust and reliable sub-cloud surface observation.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Cloud contamination significantly impairs the usability of optical satellite imagery, affecting critical applications such as environmental monitoring, disaster response, and land-use analysis. This research presents a Cloud-Attentive Reconstruction Framework that integrates SAR-optical feature fusion with deep learning-based image reconstruction to generate cloud-free optical imagery. The proposed framework employs an attention-driven feature fusion mechanism to align complementary structural information from Synthetic Aperture Radar (SAR) with spectral characteristics from optical data. Furthermore, a cloud-aware model update strategy introduces adaptive loss weighting to prioritize cloud-occluded regions, enhancing reconstruction accuracy. Experimental results demonstrate that the proposed method outperforms existing approaches, achieving a PSNR of 31.01 dB, SSIM of 0.918, and MAE of 0.017. These outcomes highlight the framework's effectiveness in producing high-fidelity, spatially and spectrally consistent cloud-free optical images.

Problem

• Eliminating cloud contamination in optical satellite imagery
• Fusing SAR and optical data for cloud-free reconstruction
• Improving accuracy in environmental and disaster monitoring

Innovation

• SAR-optical feature fusion with deep learning
• Attention-driven feature fusion mechanism
• Cloud-aware adaptive loss weighting strategy