A typhoon is a destructive weather system that can cause severe casualties and economic losses. Typhoon intensity (TI) is a measurement to evaluate its ruinous degree. Hence, typhoon intensity prediction is an important research problem and many methods have been proposed. However, most of the existing approaches have very limited capability to combine the 2D Typhoon Structure Domain-expert Knowledge (2D-TSDK) and the 3D Typhoon Structure Data-driven Knowledge (3D-TSDK) for the TI prediction. To address this issue, this paper proposes a spatio-temporal deep learning method named Spatial Attention Fusing Network (SAF-Net). The designed model aims to fuse 2D-TSDK and 3D-TSDK by developing a specific Wide & Deep framework. In the data-driven component, a special Spatial Attention (SA) module is designed to automatically select high-response wind speed areas and embedded into a three-branch CNN to exploit 3D-TSDK. Then, the Wide & Deep framework integrates the 2D-TSDK and 3D-TSDK for the TI prediction. Comprehensive experiments have been conducted on a real-world dataset, and the result shows that the proposed method outperforms state-of-the-art typhoon intensity prediction methods. The code is available in GitHub: https://github.com/xuguangning1218/TI_Prediction

台风是一种破坏性的天气系统，会造成严重的人员伤亡和经济损失。台风强度（TI）是衡量其破坏程度的度量。因此，台风强度预测是一个重要的研究问题，并且已经提出了许多方法。然而，大多数现有方法将 2D 台风结构领域专家知识 (2D-TSDK) 和 3D 台风结构数据驱动知识 (3D-TSDK) 结合用于 TI 预测的能力非常有限。为了解决这个问题，本文提出了一种名为Spatial Attention Fusing Network (SAF-Net)的时空深度学习方法。设计的模型旨在通过开发特定的 Wide & Deep 框架来融合 2D-TSDK 和 3D-TSDK。在数据驱动组件中，一个特殊的空间注意力 (SA) 模块旨在自动选择高响应风速区域并嵌入到三分支 CNN 中以利用 3D-TSDK。然后，Wide & Deep 框架集成了 2D-TSDK 和 3D-TSDK 用于 TI 预测。在真实世界的数据集上进行了综合实验，结果表明所提出的方法优于最先进的台风强度预测方法。代码在 GitHub：https://github.com/xuguangning1218/TI_Prediction 结果表明，所提出的方法优于最先进的台风强度预测方法。代码在 GitHub：https://github.com/xuguangning1218/TI_Prediction 结果表明，所提出的方法优于最先进的台风强度预测方法。代码在 GitHub：https://github.com/xuguangning1218/TI_Prediction