发表机构
Technical University of Munich; Helmholtz Centre for Polar and Marine Research, Alfred Wegener Institute; Swiss Federal Institute of Technology Zurich (ETH Zurich)（慕尼黑工业大学; 亥姆霍兹极地与海洋研究中心阿尔弗雷德·韦格纳研究所; 瑞士联邦理工学院苏黎世分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对卫星LST数据因云层有间隙、重建难问题，提出多模态快速傅里叶卷积生成对抗网络，利用快速傅里叶卷积实现全局感受野，由卫星观测和SAR数据引导，能恢复大量缺失区域，重建效果好。
AI 中文摘要
卫星衍生的陆地表面温度（LST）提供了地面站无法比拟的空间综合数据。然而，由于云层的存在，其效用常常受到严重数据间隙的限制。由于LST对于理解陆气相互作用至关重要，已经提出了许多方法来应对这一挑战。但是，开发一个可扩展且适应性强的管道来生成无间隙的LST数据集并重建受云污染的像素仍然具有挑战性。此外，在高空间分辨率观测中重建广泛的缺失区域尤其困难。为了应对这一挑战，我们提出了一种多模态快速傅里叶卷积生成对抗网络，用于在高分辨率（30米）陆地卫星图像中重建受云污染的像素，以生成无间隙的晴空LST产品。该方法利用快速傅里叶卷积在整个图像上实现全局感受野，并由由卫星观测和合成孔径雷达（SAR）数据组成的一系列数据引导。在所有LST分位数上，场景平均均方根误差（在重建像素上计算）的四分位间距始终在0.8K和1.8K之间。所提出的方法能够恢复广泛的缺失区域，包括云引起的间隙超过70%的场景，同时依赖于在近全球范围内容易获得的辅助数据。
英文摘要
Satellite-derived Land Surface Temperature (LST) provides spatially comprehensive data that ground stations cannot match. However, its utility is frequently limited by severe data gaps due to the presence of clouds. As LST is essential for understanding land-atmosphere interactions, numerous methods have been proposed to address this challenge. Yet, the development of a scalable and adaptable pipeline for generating gap-free LST datasets and reconstructing cloud-contaminated pixels remains challenging. Moreover, the reconstruction of extensive missing regions in fine-spatial-resolution observations is particularly difficult. To address this challenge, we propose a Multimodal Fast Fourier Convolutional GAN for reconstructing cloud-contaminated pixels in fine-resolution (30 m) Landsat imagery to generate gap-free clear-sky LST products. The method leverages Fast Fourier Convolution to enable a global receptive field across the image, and is guided by a stack of data consisting of satellite observations and Synthetic Aperture Radar (SAR) data. Across all LST quantiles, the interquartile range of scene-averaged RMSE (computed over reconstructed pixels) is consistently between 0.8 K and 1.8 K. The proposed approach enables the recovery of extensive missing regions, including scenes with more than 70% cloud-induced gaps, while relying on auxiliary data that are readily available at a near-global scale.
Comments35 pages, 9 figures, Journal
