Restoration of Missing Patterns on Satellite Infrared Sea Surface Temperature Images Due to Cloud Coverage Using Deep Generative Inpainting Network
Restoration of Missing Patterns on Satellite Infrared Sea Surface Temperature Images Due to Cloud Coverage Using Deep Generative Inpainting Network
复制标题
DOI：
10.3390/jmse9030310
复制
发表时间：
2021-03-01
影响因子：
2.9
通讯作者：
Choi, Jae Young
中科院分区：
文献类型：
--
作者：
Kang, Song-Hee;Choi, Youngjin;Choi, Jae Young
在本文中，我们提出了一种新的深度生成修复网络（GIN），在生成对抗学习的框架下训练，该网络针对云干扰卫星海表温度（SST）图像的恢复进行了优化。所提出的GIN结构可以实现准确和快速的恢复结果。建议的GIN包括粗和细重建阶段，以促进SST图像中丢失（云）区域的细节和纹理。我们还提出了一种新的预处理策略，用每日海洋表面温度的平均值代替陆地面积，以提高恢复精度。为了学习所提出的GIN，我们开发了一种新的方法，该方法结合了多个损失函数，非常适合于提高缺失SST信息的恢复质量。我们的研究结果表明，恢复和实际卫星图像数据之间的温度差异不大于0.7摄氏度的月平均值，这表明对缺失的海表温度数据具有良好的弹性。建议GIN具有更快的恢复时间，是可行的实时海洋相关的应用。此外，SST图像恢复的计算成本远低于流行的插值方法。
In this paper, we propose a novel deep generative inpainting network (GIN) trained under the framework of generative adversarial learning, which is optimized for the restoration of cloud-disturbed satellite sea surface temperature (SST) imagery. The proposed GIN architecture can achieve accurate and fast restoration results. The proposed GIN consists of rough and fine reconstruction stages to promote the details and textures of missing (clouded) regions in SST images. We also propose a nov el preprocessing strategy that replaces the land areas with the average value of daily oceanic surface temperatures for improving restoration accuracy. To learn the proposed GIN, we developed a novel approach that combines multiple loss functions well suited for improving the restoration quality over missing SST information. Our results show that the difference in temperature between restored and actual satellite image data was no larger than 0.7 degrees C in monthly average values, which suggests excellent resilience against the missing sea surface temperature data. The proposed GIN has a faster restoration time and is feasible for real-time ocean-related applications. Furthermore, the computational cost of restoring SST images is much lower than the popular interpolation methods.