用流匹配生成高精度、空间连贯的气象预报集合，低成本且可多时效使用。
Generating ensembles of spatially-coherent in-situ forecasts using flow matching
- 基于流匹配与空间注意力变换器，生成空间连贯的多变量预报集合。
- 在欧洲西部站点上，5天预报的温度与阵风表现优于现有方法。
- 单次训练即可支持多时效后处理，大幅降低计算成本，适合实际部署。
我们提出一种基于机器学习的在位气象预报后处理方法，兼具空间连贯性与多变量特性。相比先前工作，流匹配后处理（FMAP）更好地捕捉了观测分布的相关结构，同时提升了站点边际性能。FMAP生成的预报不局限于原始格点预测的内容，能从数据中推断新的相关结构。该模型仅需少量数值模拟即可生成任意数量的预报，实现低成本预报系统。一次训练即可完成多时效后处理，无需生成时多次训练模型。本文详述方法，包括在流匹配生成建模框架中训练的空间注意力变压器骨干网络。在EUPPBench数据集上的实验表明，FMAP在西欧站点上对表面温度和阵风值进行长达五天的预报，表现优异。
原文摘要 · Abstract (English)
We propose a machine-learning-based methodology for in-situ weather forecast postprocessing that is both spatially coherent and multivariate. Compared to previous work, our Flow MAtching Postprocessing (FMAP) better represents the correlation structures of the observations distribution, while also improving marginal performance at the stations. FMAP generates forecasts that are not bound to what is already modeled by the underlying gridded prediction and can infer new correlation structures from data. The resulting model can generate an arbitrary number of forecasts from a limited number of numerical simulations, allowing for low-cost forecasting systems. A single training is sufficient to perform postprocessing at multiple lead times, in contrast with other methods which use multiple trained networks at generation time. This work details our methodology, including a spatial attention transformer backbone trained within a flow matching generative modeling framework. FMAP shows promising performance in experiments on the EUPPBench dataset, forecasting surface temperature and wind gust values at station locations in western Europe up to five-day lead times.
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。