Abstract
Machine learning-based weather forecasting models now surpass state-of-the-art numerical weather prediction systems, but training and operating these models at high spatial resolution remains computationally expensive. We present a modular framework that decouples forecasting from spatial resolution by applying learned generative super-resolution as a post-processing step to coarse-resolution forecast trajectories. We formulate super-resolution as a stochastic inverse problem, using a residual formulation to preserve large-scale structure while reconstructing unresolved variability. The model is trained with flow matching exclusively on reanalysis data and is applied to global medium-range forecasts. We evaluate (i) design consistency by re-coarsening super-resolved forecasts and comparing them to the original coarse trajectories, and (ii) high-resolution forecast quality using standard ensemble verification metrics and spectral diagnostics. Results show that super-resolution preserves large-scale structure and variance after re-coarsening, introduces physically consistent small-scale variability, and achieves competitive probabilistic forecast skill at 0.25° resolution relative to an operational ensemble baseline, while requiring only a modest additional training cost compared with end-to-end high-resolution forecasting.
Abstract (translated)
基于机器学习的天气预报模型现已超越最先进的数值天气预报系统，但以高空间分辨率训练和运行这些模型仍具有较高的计算成本。我们提出了一种模块化框架，通过将学习到的生成式超分辨率作为粗分辨率预报轨迹的后处理步骤，将预报与空间分辨率解耦。我们将超分辨率公式化为随机逆问题，采用残差公式在重建未解析变化的同时保持大尺度结构。该模型仅使用再分析数据通过流匹配进行训练，并应用于全球中期预报。我们通过以下方式评估：(i) 通过将超分辨率预报重新粗化并与原始粗轨迹比较，检验设计一致性；(ii) 使用标准集合预报检验指标和谱诊断评估高分辨率预报质量。结果表明，超分辨率在重新粗化后保持了大尺度结构和方差，引入了物理一致的小尺度变化，并在0.25°分辨率下相对于业务集合预报基线实现了具有竞争力的概率预报技巧，而训练成本仅比端到端高分辨率预报略有增加。
URL
https://arxiv.org/abs/2604.00897
