利用流匹配生成空间相干的原位天气预报集合
Generating ensembles of spatially-coherent in-situ forecasts using flow matching
AI总结：
提出基于流匹配的后处理方法FMAP，生成空间相干且多变量的原位天气预报集合，在EUPPBench上预测西欧站点温度与阵风，性能优于现有方法。
摘要：
我们提出了一种基于机器学习的方法，用于原位天气预报的后处理，该方法既具有空间相干性又具有多变量特性。与以往工作相比，我们的流匹配后处理（FMAP）更好地表示了观测分布的相关系结构，同时提高了站点处的边缘性能。FMAP生成的预报不受底层网格化预测已建模内容的限制，并能从数据中推断出新的相关结构。所得到的模型能够从有限数量的数值模拟中生成任意数量的预报，从而实现低成本的预报系统。与在生成时使用多个训练网络的其他方法不同，单一训练足以在多个预测时效进行后处理。本文详细介绍了我们的方法，包括在流匹配生成建模框架内训练的空间注意力变换器主干。FMAP在EUPPBench数据集上的实验中显示出有前景的性能，预测了西欧站点位置的地表温度和阵风值，预测时效长达五天。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
