用扩散模型控制集合方差，实现高分辨率气象再分析降尺度。
Controlling Ensemble Variance in Diffusion Models: An Application for Reanalyses Downscaling
- 通过调整扩散步数调控反向过程方差，建立理论框架。
- 生成与参考数据一致的风速集合成员，空间方差分布匹配真实气象变率。
- 解决CARRA数据缺集合信息问题，适合高分辨率气象模拟需求。
近年来，扩散模型已成为气象学中生成集合成员的强大工具。本文展示如何通过改变扩散步数，有效控制去噪扩散隐式模型（DDIM）的集合方差。我们提出一个理论框架，将扩散步数与反向扩散过程表达的方差关联起来。聚焦再分析降尺度任务，我们构建了一个覆盖ERA5到CERRA区域的集合扩散模型，生成具有方差校准特征的全时空分辨率风速集合成员。该方法使全球平均方差与参考集合数据一致，并确保空间方差分布符合实际气象变率。此外，我们解决了CARRA数据缺乏集合信息的问题，展示了该方法在高效、高分辨率集合生成中的实用性。
原文摘要 · Abstract (English)
In recent years, diffusion models have emerged as powerful tools for generating ensemble members in meteorology. In this work, we demonstrate how a Denoising Diffusion Implicit Model (DDIM) can effectively control ensemble variance by varying the number of diffusion steps. Introducing a theoretical framework, we relate diffusion steps to the variance expressed by the reverse diffusion process. Focusing on reanalysis downscaling, we propose an ensemble diffusion model for the full ERA5-to-CERRA domain, generating variance-calibrated ensemble members for wind speed at full spatial and temporal resolution. Our method aligns global mean variance with a reference ensemble dataset and ensures spatial variance is distributed in accordance with observed meteorological variability. Additionally, we address the lack of ensemble information in the CARRA dataset, showcasing the utility of our approach for efficient, high-resolution ensemble generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。