将深度光流立体方法蒸馏以获取稠密三维风场

中文摘要 AI 辅助

地球静止轨道大气运动矢量（AMV）提供稠密水平风矢量（u、v）和高度，被输入数据同化系统。传统AMV采用基于窗口的互相关跟踪特征，并结合数值天气预报（NWP）背景状态通过红外亮温估计高度，形成循环依赖，导致高度不准确、计算成本高且反演结果稀疏。来自GEO-GEO和GEO-LEO的立体风通过不同姿态的视差从几何上解析高度，消除了对NWP的依赖并提高了准确性，但仍计算量大且覆盖范围有限。本研究中，我们用深度光流替换立体匹配中的基于窗口的跟踪，以实现高效且改进的反演。微调过程平衡自监督几何残差损失与探空仪重建的监督损失。为消除对多卫星重叠的需求，我们将立体教师模型蒸馏为单卫星学生模型，学生模型模拟教师模型的卡方和高度不确定性以进行质量保证。学生模型可生成全球地球静止轨道（GEO）圆盘图像的风场。验证时将立体模型和学生模型与探空仪、业务AMV、ERA5再分析数据及EarthCARE云廓线进行对比。三重共定位结果显示，立体风在水汽波段（6.2、6.9和7.3μm）的性能优于业务AMV，在长波红外波段（11.2μm）则出现性能下降。

英文摘要

Geostationary atmospheric motion vectors (AMVs) provide the dense horizontal wind vectors (u,v) and heights ingested into data assimilation systems. Traditional AMVs track features using window-based cross-correlation and estimate heights via infrared brightness temperatures paired with numerical weather prediction (NWP) background states, creating a circular dependency that yields inaccurate heights, high computational cost, and sparse retrievals. Stereo winds from GEO-GEO and GEO-LEO geometrically resolve heights from parallax shifts across different poses, eliminating NWP dependence and improving accuracy, but they remain computationally heavy with limited coverage. In this work, we replace window-based tracking in stereo matching with deep optical flow for efficient, improved retrieval. Fine-tuning balances a self-supervised geometric residual loss with supervised radiosonde reconstruction. To eliminate multi-satellite overlap requirements, we distill the stereo teacher into a single-satellite student model. Chi-square and height uncertainties from the teacher are emulated by the student for quality assurance. The student generates winds across full-disk GEO imagery globally. Validation compares stereo and student models against radiosondes, operational AMVs, ERA5 reanalysis, and EarthCARE cloud profiles. Results through triple collocation show that stereo winds improve performance beyond operational AMVs for water vapor bands (6.2, 6.9, and 7.3 μm), wit degradation in the long-wave infrared (11.2 μm) band.

发表机构

• Zeus AI（宙斯人工智能）
• NASA Goddard Space Flight Center（美国国家航空航天局戈达德太空飞行中心）
• Carr Astronautics（卡尔宇航公司）
• Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）

机构由 AI 辅助整理，请以论文原文为准。