用图神经网络在地球椭球网格上实现高效区域天气预测
MR-GNF: Multi-Resolution Graph Neural Forecasting on Ellipsoidal Meshes for Efficient Regional Weather Prediction
- 构建多分辨率图结构，跨尺度传递信息无需显式边界
- 仅160万参数，在英国爱尔兰区6~24小时预报精度媲美主流模型
- 适合需要快速更新的气象预警与可再生能源预测场景
天气预报是人工智能学习复杂多尺度物理系统的理想试验场。传统数值天气预报因高分辨率嵌套需大量边界耦合，计算成本高昂。本文提出多分辨率图神经预报（MR-GNF），一种轻量级、物理感知模型，直接在地球椭球多尺度图上进行短时区域预报。该框架将0.25°兴趣区与0.5°上下文带及1.0°外域耦合，实现无显式嵌套边界的连续跨尺度消息传递。其轴向图注意力网络交替使用垂直自注意力（跨气压层）与水平图注意力（地表节点），仅用160万参数即可捕捉隐含三维结构。模型基于1980–2024年40年ERA5再分析数据训练，对英国-爱尔兰区域近地面温度、风速和降水实现稳定+6至+24小时预报。尽管总计算成本低于80 GPU小时（单块RTX 6000 Ada），性能仍可比肩或超越更复杂的区域AI系统，并保持跨尺度物理一致性。结果表明，基于图的神经算子可在远低于传统数值模式的成本下实现可信高分辨率天气预测，为人工智能驱动的早期预警与可再生能源预测提供可行路径。
原文摘要 · Abstract (English)
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
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。