Vandal Thomas J, Nemani Ramakrishna R
IEEE Trans Neural Netw Learn Syst. 2023 Jul;34(7):3245-3254. doi: 10.1109/TNNLS.2021.3101742. Epub 2023 Jul 6.
Applications of satellite data in areas such as weather tracking and modeling, ecosystem monitoring, wildfire detection, and land-cover change are heavily dependent on the tradeoffs to spatial, spectral, and temporal resolutions of observations. In weather tracking, high-frequency temporal observations are critical and used to improve forecasts, study severe events, and extract atmospheric motion, among others. However, while the current generation of geostationary (GEO) satellites has hemispheric coverage at 10-15-min intervals, higher temporal frequency observations are ideal for studying mesoscale severe weather events. In this work, we present a novel application of deep learning-based optical flow to temporal upsampling of GEO satellite imagery. We apply this technique to 16 bands of the GOES-R/Advanced Baseline Imager mesoscale dataset to temporally enhance full-disk hemispheric snapshots of different spatial resolutions from 10 to 1 min. Experiments show the effectiveness of task-specific optical flow and multiscale blocks for interpolating high-frequency severe weather events relative to bilinear and global optical flow baselines. Finally, we demonstrate strong performance in capturing variability during convective precipitation events.
卫星数据在天气跟踪与建模、生态系统监测、野火探测以及土地覆盖变化等领域的应用，在很大程度上依赖于观测的空间、光谱和时间分辨率之间的权衡。在天气跟踪方面，高频时间观测至关重要，可用于改进天气预报、研究极端事件以及提取大气运动等。然而，尽管当前一代地球静止（GEO）卫星以10 - 15分钟的间隔进行半球覆盖，但更高的时间频率观测对于研究中尺度极端天气事件而言是理想的。在这项工作中，我们展示了基于深度学习的光流在GEO卫星图像时间上采样方面的一种新应用。我们将此技术应用于GOES - R/先进基线成像仪中尺度数据集的16个波段，以便在时间上增强不同空间分辨率（从10分钟到1分钟）的全圆盘半球快照。实验表明，相对于双线性和全局光流基线，特定任务的光流和多尺度块在插值高频极端天气事件方面是有效的。最后，我们展示了在捕捉对流降水事件期间的变异性方面的强大性能。
