用物理定律指导深度学习，实现高效精准的气象预报与降尺度。
Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting
- 将物理方程融入数据驱动模型，通过自动微分计算物理项
- 推理速度提升170倍，仅需5.5万参数，且保持高精度
- 适合需要快速、可解释气象预测的研究与应用
传统数值天气预报（NWP）计算成本高且物理描述不完整。深度学习虽高效准确，但常忽略物理规律，影响可解释性与泛化能力。本文提出PhyDL-NWP，一种融合物理方程与隐式力参数化的物理引导深度学习框架。该方法可从任意时空坐标预测气象变量，利用自动微分计算物理项，并通过物理信息损失约束预测结果符合控制动力学。该框架实现无分辨率限制的降尺度，将天气建模为连续函数，能以极小开销微调预训练模型，推理速度最高达170倍提升，仅使用55,000个参数。实验表明，PhyDL-NWP在预测性能和物理一致性上均显著优于基线。
原文摘要 · Abstract (English)
Weather forecasting is essential but remains computationally intensive and physically incomplete in traditional numerical weather prediction (NWP) methods. Deep learning (DL) models offer efficiency and accuracy but often ignore physical laws, limiting interpretability and generalization. We propose PhyDL-NWP, a physics-guided deep learning framework that integrates physical equations with latent force parameterization into data-driven models. It predicts weather variables from arbitrary spatiotemporal coordinates, computes physical terms via automatic differentiation, and uses a physics-informed loss to align predictions with governing dynamics. PhyDL-NWP enables resolution-free downscaling by modeling weather as a continuous function and fine-tunes pre-trained models with minimal overhead, achieving up to 170x faster inference with only 55K parameters. Experiments show that PhyDL-NWP improves both forecasting performance and physical consistency.
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。