用3D Swin Transformer和扩散模型提升5公里级小时降雨预报精度
CNCast: Leveraging 3D Swin Transformer and DiT for Enhanced Regional Weather Forecasting
- 基于3D Swin Transformer架构，融合传统数值预报边界条件
- 在1-5天小时级预报中优于全球模型Pangu，尤其在降水预测上表现突出
- 采用潜空间扩散模型实现5公里分辨率小时降雨诊断，适合高精度区域预报
本研究提出一种基于3D Swin Transformer的区域天气预报模型，可实现1小时至5天的精确小时级天气预测，显著提升短期预报的可靠性与实用性。相较于成熟的全球模型Pangu，该模型在多数气象变量预测上表现更优，展现出有限区域建模中的更强潜力。其关键创新在于融合了受传统数值天气预报（NWP）启发的增强边界条件，大幅提高预测准确性。此外，模型通过潜空间扩散模型（DiT），实现了约5公里空间分辨率的小时级总降水量诊断，提供了一种生成高分辨率降水数据的新方法。
原文摘要 · Abstract (English)
This study introduces a cutting-edge regional weather forecasting model based on the SwinTransformer 3D architecture. This model is specifically designed to deliver precise hourly weather predictions ranging from 1 hour to 5 days, significantly improving the reliability and practicality of short-term weather forecasts. Our model has demonstrated generally superior performance when compared to Pangu, a well-established global model. The evaluation indicates that our model excels in predicting most weather variables, highlighting its potential as a more effective alternative in the field of limited area modeling. A noteworthy feature of this model is the integration of enhanced boundary conditions, inspired by traditional numerical weather prediction (NWP) techniques. This integration has substantially improved the model's predictive accuracy. Additionally, the model includes an innovative approach for diagnosing hourly total precipitation at a high spatial resolution of approximately 5 kilometers. This is achieved through a latent diffusion model, offering an alternative method for generating high-resolution precipitation data.
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。