高效模拟初始化的潜空间传输：从全球到公里尺度的空间相干概率降尺度

中文摘要 AI 辅助

概率降尺度必须表示确定性区域预测未解决的公里尺度结构。我们提出了一种模拟初始化的潜空间传输方法，利用历史区域残差作为气象学上合理的经验来源。一个冻结的图神经网络从综合预报系统（IFS）预测确定性状态。对于每个输入，从20个具有相似IFS条件的训练日期中提取残差来初始化集合。一个条件流匹配模型在精心设计的65因子、100,000节点潜空间中传输这些场，网格解码器重建81个大气通道，包括2.5公里间距的降水。在季节和循环平衡的2025年测试中，集合CRPS在所有81个变量上优于确定性平均绝对误差。匹配的模拟在点和空间误差上优于高斯初始化，并相比协方差匹配减少了谱误差。与发布的CorrDiff、本地CorrDiff-mini模型和全网格EDM的比较提供了2023年验证样本的上下文。降尺度模型的总训练时间约为一台NVIDIA H200上的12小时，每个81场成员的推理时间约为12秒。冻结网络在提供本地静态数据和高分辨率IFS衍生模拟库时，也能生成法国上空的场。该方法将经验初始化与全域潜空间传输相结合，为计算上可行的区域集合提供支持。

英文摘要

Probabilistic downscaling must represent kilometer-scale structure left unresolved by a deterministic regional prediction. We introduce an analog-initialized latent transport method that uses historical regional residuals as a meteorologically informed empirical source. A frozen graph neural network predicts the deterministic state from the Integrated Forecasting System (IFS). For each input, residuals from 20 training dates with similar IFS conditions initialize the ensemble. A conditional flow-matching model transports these fields in a carefully designed 65-factor, 100,000-node latent space, and a grid decoder reconstructs 81 atmospheric channels including precipitation at 2.5km spacing. On a season- and cycle-balanced 2025 test, ensemble CRPS improves over deterministic mean absolute error for all 81 variables. Matched analogs improve point and spatial errors over Gaussian initialization and reduce spectral error compared with covariance matching. Comparisons with released CorrDiff, a local CorrDiff-mini model and full grid EDM provide context on the 2023 validation sample. Total training of the downscaling model takes approximately 12h on one NVIDIA H200, and inference takes about 12s per 81-field member. The frozen networks also generate fields over France when supplied with local static data and a high-resolution IFS-derived analog bank. The method combines empirical initialization with whole-domain latent transport for computationally practical regional ensembles.

发表机构

• Norwegian Meteorological Institute（挪威气象研究所）

机构由 AI 辅助整理，请以论文原文为准。