发表机构
Nanyang Technological University; Tsinghua University; Peking University; Tongji University（南洋理工大学; 清华大学; 北京大学; 同济大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出VeinCast框架，通过物理引导动态场图与图条件融合，在1.5° ERA5基准上，于14天提前期的69个气象场预报任务中取得与主流模型相当的竞争力，证实关系级物理引导的有效性。
AI 中文摘要
全球中期天气预报需要对异构大气场之间结构化且依赖状态的交互进行建模。现有数据驱动模型大多隐式学习这些交互，而方程级物理约束可能继承近似和模型形式偏差。本文提出VeinCast，这是一个物理引导动态场图与图条件融合框架，可联合预测69个地表及高空场。在每个局部窗口内，其物理引导动态场图结合预定义大气关系与依赖状态的Top-K残差边，并利用所得图上下文适配地球窗口注意力。图条件潜在融合进一步利用图上下文与源节点中心性引导场到潜在空间的聚合，同时有界反馈保留场特定信息。在1.5° ERA5基准上，VeinCast在长达14天的提前期内，在全部69个气象场上展现出与FuXi、Pangu-Weather、GraphCast、FengWu、ARROW等代表性全球天气预报模型相当的竞争力。 ablation实验证实两个模块提供互补增益，证明关系级物理引导对数据驱动天气预报的有效性。
英文摘要
Global medium-range weather forecasting requires modeling structured yet state-dependent interactions among heterogeneous atmospheric fields. Existing data-driven models largely learn these interactions implicitly, whereas equation-level physical constraints may inherit approximation and model-form biases. We present VeinCast, a physics-guided dynamic field graph and graph-conditioned fusion framework that jointly forecasts 69 surface and upper-air fields. Within each local window, its Physics-Guided Dynamic Field Graph combines predefined atmospheric relations with state-dependent Top-K residual edges and adapts Earth-window attention using the resulting graph context. Graph-Conditioned Latent Fusion further employs graph context and source-node centrality to guide field-to-latent aggregation, while bounded feedback preserves field-specific information. On the $1.5^\circ$ ERA5 benchmark, VeinCast demonstrates competitive forecasting performance across all 69 meteorological fields at lead times of up to 14 days, compared with representative global weather forecasting models including FuXi, Pangu-Weather, GraphCast, FengWu, and ARROW. Ablations confirm that the two modules provide complementary gains, demonstrating the effectiveness of relational-level physical guidance for data-driven weather forecasting.
