🤖 AI Summary
Cloud contamination severely compromises the reliability of optical remote sensing imagery for near-real-time land use and land cover (LULC) mapping. To address this challenge, this work proposes CloudLULC-Net, an end-to-end heterogeneous SAR-optical fusion framework that directly predicts LULC maps from cloud-contaminated Sentinel-2 images together with temporally adjacent Sentinel-1 SAR data, accompanied by the introduction of a large-scale benchmark dataset, CloudLULC-Set. The method innovatively integrates optical reliability modulation, adaptive heterogeneous information aggregation, a unified semantic mapping Transformer, and semantic anchor-guided optimization to effectively mitigate semantic uncertainty under cloud occlusion. Experimental results demonstrate that the model achieves 86.60% overall accuracy, 83.29% F1 score, and 73.51% mIoU on CloudLULC-Set, significantly outperforming both reconstruction-first and existing end-to-end approaches while maintaining robust performance across varying cloud coverage levels.
📝 Abstract
Optical remote sensing imagery is frequently degraded by cloud and cloud-shadow contamination, which limits its reliability for near-real-time land use and land cover (LULC) mapping. Although synthetic aperture radar (SAR) can provide cloud-penetrating structural information, existing SAR-optical fusion methods often assume reliable optical observations and insufficiently address the semantic uncertainty introduced by cloud contamination. To address this issue, we propose CloudLULC-Net, an end-to-end heterogeneous SAR-optical fusion framework that directly predicts LULC maps from cloud-contaminated Sentinel-2 imagery and temporally adjacent Sentinel-1 SAR observations. The proposed network incorporates optical reliability modulation to suppress unreliable optical responses, heterogeneous information adaptive aggregation to model high-order spatial-channel interactions between optical and SAR representations, and a unified semantic mapping transformer to organize fused features in a LULC-oriented latent space. A semantic anchor-guided optimization strategy is further introduced to improve the consistency of intermediate semantic representations. To support this task, we construct CloudLULC-Set, a large-scale benchmark dataset containing 40,223 curated SAR-optical-label triplets with pixel-level LULC annotations across diverse geographic regions and cloud conditions. Experimental results show that CloudLULC-Net achieves an OA of 86.60%, an F1-score of 83.29%, and an mIoU of 73.51%, outperforming representative heterogeneous reconstruction-first and end-to-end SAR-optical mapping methods. Comparisons with existing global LULC products and analyses under different cloud-cover levels further demonstrate the robustness and practical value of CloudLULC-Net for target-date LULC mapping in cloud-prone regions.The project is publicly available at: https://github.com/RSIIPAC/CloudLULC