PhyOceanCast：基于物理信息扩散模型的全球海洋预报
PhyOceanCast: Global Ocean Forecasting with Physics-Informed Diffusion
将扩散模型与球面图注意力、小波时序模块结合，用于全球海洋多变量时空预测，其物理约束和球面拓扑保持思路可迁移到其他地球科学或视频预测任务。
原文依据 We introduce PhyOceanCast, a physics-informed diffusion model that overcomes these limitations through two key innovations.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论海洋动力学驱动全球气候模式与极端天气事件，因此准确的时空预报对气候监测和海洋作业至关重要。传统的全球海洋预报系统（GOFSs）能提供高精度预测，但计算成本高昂且未能充分利用不断增长的历史数据。近期深度学习模型取得了显著成功，但仍面临三个根本性挑战：（1）尽管海洋变量通过状态方程关系存在强物理耦合，它们却将变量同质化处理；（2）忽略球面几何，导致高纬度地区严重失真；（3）难以建模多尺度时序动态。我们提出PhyOceanCast，一种物理信息扩散模型，通过两项关键创新克服上述局限。第一，多尺度海洋耦合球面图注意力网络（SGAN-MOC）在保持球面拓扑的同时，通过异质编码和k跳约束注意力实现跨变量交互。第二，物理信息小波时序相干（PWTC）模块利用平流-扩散约束将海洋动力学分解到多个尺度。PhyOceanCast预报145个海洋变量，包括温度、盐度和速度场，覆盖36个深度层及海面高度。大量实验表明其性能优于扩散模型、Transformer及混合基线，为全球海洋规范变量预报开辟了新范式。
英文原文摘要 1537 字符
Ocean dynamics drive global climate patterns and extreme weather events, making accurate spatiotemporal forecasting essential for climate monitoring and marine operations. Traditional Global Ocean Forecasting Systems (GOFSs) offer high accuracy predictions, yet remain computationally expensive and fail to fully leverage growing historical data. Recent deep learning models have achieved notable success, but still face three fundamental challenges: (1) they homogenize ocean variables despite strong physical coupling via equation-of-state relationships; (2) they neglect spherical geometry, resulting in severe distortions at high latitudes; and (3) they struggle to model multi-scale temporal dynamics. We introduce PhyOceanCast, a physics-informed diffusion model that overcomes these limitations through two key innovations. First, the Spherical Graph Attention Network for Multi-scale Ocean Coupling (SGAN-MOC) preserves spherical topology while enabling cross-variable interactions via heterogeneous encoding and k-hop-constrained attention. Second, the Physics-Informed Wavelet Temporal Coherence (PWTC) module that decomposes ocean dynamics across multiple scales with advection-diffusion constraints. PhyOceanCast forecasts 145 ocean variables, including temperature, salinity, and velocity fields, across 36 depth levels plus sea surface height. Extensive experiments demonstrate superior performance over diffusion, transformer, and hybrid baselines, promising a new paradigm for global ocean canonical variable forecasting.