改进物理约束神经网络，提升南太平洋短期天气预报精度与稳定性。
Physics-Constrained Neural Networks for Improved Short-Term Weather Forecasting: A Case Study over the South Pacific
- 用高阶数值求解器提速4倍，时间步达1200秒
- 融合先进神经网络，1-12小时预报误差降低8%-22%
- 适合需要物理一致性与高效预测的气象建模者
本研究在WeatherGFT架构基础上，提出三项改进以提升混合短期天气预报模型的准确性与稳定性。首先，采用五阶加权非振荡格式（WENO-5）、β平面近似和亚网格粘性，使积分时间步长提升至1200秒，日均均方误差降低26%。其次，用统一自回归混合模块替代原有24个专用模块，避免对特定预报时长过拟合。第三，将物理核心与两种前沿神经网络结合，构建PI-PredFormer与PI-IAM4VP模型。在2000–2004年南太平洋子集上的评估显示，该混合模型在1–12小时预报时长下，根均方误差较纯神经模型降低8%–22%，同时更好保持物理一致性。结果表明，对混合组件的渐进优化是实现更精准、高效短时预报的可行路径。
原文摘要 · Abstract (English)
This study introduces enhancements to physics-constrained neural networks (PCNNs) that improve the accuracy and stability of hybrid short-term weather forecasting models. Building on the WeatherGFT architecture, three innovations are proposed. First, an upgraded numerical solver, combining a fifth-order weighted essentially non-oscillatory scheme (WENO-5), a beta-plane approximation, and subgrid-scale viscosity, permits a fourfold increase in the integration time step to 1200 s while reducing the daily mean squared error by up to 26%. Second, a unified autoregressive hybrid block replaces the original chain of 24 specialised modules, eliminating overfitting to specific lead times. Third, the physical core is integrated with two state-of-the-art neural backbones, resulting in PI-PredFormer and PI-IAM4VP. Evaluation on the WeatherBench South Pacific subset from 2000 to 2004 shows that these hybrids reduce root mean squared error at 1-12 h lead times by 8-22% compared to purely neural counterparts, while better preserving physical consistency. These results demonstrate that incremental refinement of hybrid components offers a practical route toward more accurate and efficient short-range weather forecasting.
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。