Filling Cloud Gaps in Satellite AOD Retrievals Using an LSTM CNN-Autoencoder Model
Filling Cloud Gaps in Satellite AOD Retrievals Using an LSTM CNN-Autoencoder Model
复制标题
DOI：
10.1109/igarss46834.2022.9884482
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Jacob Daniels;Colleen P. Bailey;Lu Liang
中科院分区：
文献类型：
--
作者：
Jacob Daniels;Colleen P. Bailey;Lu Liang
卫星图像能够在一系列应用中对全球环境因素进行时空连续监测和了解。然而，这些数据往往受到传感器故障或大气干扰的影响，特别是遮挡部分或全部区域的密集云层。对于诸如MCD19A2气溶胶光学厚度（AOD）数据集的动态数据集，间隙填充尤其具有挑战性。困难在于往往是大的，连续块的云像素与丢失的数据，限制了空间填充的能力和每日波动的功能，如AOD，招致高难度的间隙填充从时间趋势。在这项研究中，我们提出了一种时空长短期记忆（LSTM）卷积自动编码器方法，该方法有效地重建了MODIS AOD数据厚云干扰造成的缺失数据。所提出的方法优于以前的方法重建数据丢失厚云干扰AOD检索与广义网络实现加权平均PSNR，SSIM和R2分别为47.2，0.992和0.941，原始，无云的日子和那些相同的日子与模拟厚云干扰掩蔽，而不需要额外的协变量。
Satellite imagery enables spatially-temporally continuous monitoring and understanding of global environmental factors for a range of applications. This data, however, often suffers from gaps in retrieval from sensor malfunction or atmospheric interference, particularly dense clouds that obscure parts or all of an area. For dynamic datasets such as the MCD19A2 Aerosol Optical Depth (AOD) dataset, gap filling is especially challenging. The difficulty lies in the often large, continuous blocks of cloudy pixels with missing data that limit the ability of spatial filling and the daily fluctuation in features such as AOD that incur high difficulty in gap filling from temporal trends. In this study, we propose a spatiotemporal long short-term memory (LSTM) convolutional autoencoder method that effectively reconstructs missing data resulting from thick cloud interference for MODIS AOD data. The proposed method outperforms previous methods of reconstructing data lost to thick cloud interference in AOD retrievals with a generalized network achieving a weighted average PSNR, SSIM, and R2 of 47.2, 0.992, and 0.941, respectively, between original, cloud-free days and those same days masked with simulated thick cloud interference without the need for additional covariates.