用扩散模型将气象预报从100km分辨率提升到30km，生成更精准的高分辨率预测。
Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models
- 基于扩散模型学习细尺度残差，从低分辨率输入重建高分辨率气象场。
- 在30km分辨率下准确还原小尺度结构，提升表面变量的概率预报能力。
- 适合需要高精度气象预测的气候研究与灾害预警领域使用。
我们提出一种基于概率扩散模型的全球大气降尺度方法，集成于Anemoi框架中。该方法通过学习细尺度残差的条件分布（即高分辨率场与插值后低分辨率输入的差异），将低分辨率集合预报转化为高分辨率集合。模型在欧洲中期天气预报中心IFS再分析数据对上训练，以100 km分辨率粗场重建30 km分辨率的细尺度变化。训练主要聚焦于恢复小尺度结构，而高噪声区域的微调使模型能生成极端事件。评估显示，该模型在中长期IFS集合目标上的概率技能（FCRPS）提升，重现了目标功率谱的小尺度特征，捕捉到风压耦合等物理一致的多变量关系，并在热带气旋中生成与目标集合一致的极端值。
原文摘要 · Abstract (English)
We introduce a probabilistic diffusion-based method for global atmospheric downscaling implemented within the Anemoi framework. The approach transforms low-resolution ensemble forecasts into high-resolution ensembles by learning the conditional distribution of finer-scale residuals, defined as the difference between the high-resolution fields and the interpolated low-resolution inputs. The system is trained on reforecast pairs from ECMWF IFS, using coarse fields at 100 km to reconstruct fine-scale variability at 30 km resolution. The bulk of the training focuses on recovering small-scale structures, while fine-tuning in high-noise regimes enables the generation of extremes. Evaluation against the medium-range IFS ensemble target shows that the model increases probabilistic skill (FCRPS) for surface variables, reproduces target power spectra at small scales, captures physically consistent multivariate relationships such as wind-pressure coupling, and generates extreme values consistent with those of the target ensemble in tropical cyclones.
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。