发表机构
The Pennsylvania State University; Purdue University（宾夕法尼亚州立大学; 普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出基于潜在流匹配的多模态时空大气数据同化方法，利用ERA5再分析数据训练先验，结合后验采样同化真实观测，可完成多种DA任务，从稀疏观测生成的集合预报性能达先进水平。
AI 中文摘要
数据同化（DA）利用贝叶斯推理，通过观测数据更新数值预报模型的状态。本研究提出一种根本不同的统一大气数据同化方法：采用潜在视频流匹配，从使用ERA5再分析数据（8天窗口内的69个变量）训练的先验中采样时间一致的轨迹；同时利用后验采样同化真实观测源，如美国国家海洋和大气管理局（NOAA）的全球无线电探空仪综合档案（IGRA）和综合地面数据库（ISD）。由于先验生成连续轨迹，可自然地在观测帧与未观测帧间传播信息，因此仅通过改变观测帧即可执行滤波、平滑等各类DA任务；此外，能直接从稀疏观测生成全集合预报，性能可与最先进的观测到预报模型相媲美。
英文摘要
Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data. In this study, we propose a fundamentally different, unified approach to atmospheric data assimilation. We use latent video flow-matching to sample temporally consistent trajectories from a prior trained using ERA5 reanalysis (69 variables over an 8-day window). We also use posterior sampling to assimilate real observation sources, such as those from the NOAA Integrated Global Radiosonde Archive and the Integrated Surface Database. Because the prior generates a continuous trajectory, it naturally propagates information between observed and unobserved frames. Therefore, we can perform various DA tasks, such as filtering and smoothing, simply by changing the observed frames. Moreover, we generate full-state ensemble forecasts directly from sparse observations, achieving performance competitive with state-of-the-art observation-to-forecast models.
