MR-GNF:基于椭球网格的多分辨率图神经预测用于高效区域天气预测
MR-GNF: Multi-Resolution Graph Neural Forecasting on Ellipsoidal Meshes for Efficient Regional Weather Prediction
AI总结:
MR-GNF通过多尺度图神经网络实现高效区域天气预测,利用椭球网格结构在1.6M参数内捕捉三维结构,提供稳定6至24小时预报,成本低于传统数值天气预报。
摘要:
天气预测为人工智能(AI)学习复杂多尺度物理系统提供了理想测试平台。传统数值天气预测在频繁区域更新时计算成本高,因为高分辨率嵌套需要高强度的边界耦合。我们引入了多分辨率图神经预测(MR-GNF),这是一种轻量且物理感知的模型,它直接在地球的椭球多尺度图上进行短期区域预测。该框架将0.25°的目标区域与0.5°的上下文带和1.0°的外域相结合,使跨尺度信息传递连续进行而无需显式嵌套边界。其轴向图注意力网络在压力层之间交替进行垂直自注意力,在表面节点之间进行水平图注意力,仅用1.6M参数即可捕捉隐含的三维结构。在40年的ERA5再分析数据(1980-2024)上训练,MR-GNF在英国-爱尔兰区域提供稳定的+6小时至+24小时的近地层温度、风和降水预测。尽管总计算成本低于80个GPU小时(单个RTX 6000 Ada),该模型在重量级区域AI系统中表现相当或更优,同时在不同尺度上保持物理一致性。这些结果表明,基于图的神经运算符可以以低于NWP成本的分数实现可信的高分辨率天气预测,为AI驱动的预警和可再生能源预测系统开辟了实用路径。项目页面和代码:https://github.com/AndriiShchur/MR-GNF
英文摘要:
Weather forecasting offers an ideal testbed for artificial intelligence (AI) to learn complex, multi-scale physical systems. Traditional numerical weather prediction remains computationally costly for frequent regional updates, as high-resolution nests require intensive boundary coupling. We introduce Multi-Resolution Graph Neural Forecasting (MR-GNF), a lightweight, physics-aware model that performs short-term regional forecasts directly on an ellipsoidal, multi-scale graph of the Earth. The framework couples a 0.25° region of interest with a 0.5° context belt and 1.0° outer domain, enabling continuous cross-scale message passing without explicit nested boundaries. Its axial graph-attention network alternates vertical self-attention across pressure levels with horizontal graph attention across surface nodes, capturing implicit 3-D structure in just 1.6 M parameters. Trained on 40 years of ERA5 reanalysis (1980-2024), MR-GNF delivers stable +6 h to +24 h forecasts for near-surface temperature, wind, and precipitation over the UK-Ireland sector. Despite a total compute cost below 80 GPU-hours on a single RTX 6000 Ada, the model matches or exceeds heavier regional AI systems while preserving physical consistency across scales. These results demonstrate that graph-based neural operators can achieve trustworthy, high-resolution weather prediction at a fraction of NWP cost, opening a practical path toward AI-driven early-warning and renewable-energy forecasting systems. Project page and code: https://github.com/AndriiShchur/MR-GNF
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。