Typhoons, a kind of devastating natural disaster, have caused incalculable damages worldwide. The meteorological radar image is essential for weather forecasting, especially typhoons. The weather nowcasting (future 0–6 h) can be implemented via extrapolating radar images without using the primary weather forecasting method—the numerical weather prediction model. However, the existing related techniques based on statistics or artificial intelligence were not efficient enough. In this article, a novel radar image extrapolation algorithm named dynamic multiscale fusion-generative adversarial network (DMSF-GAN) was proposed. DMSF-GAN captures the future radar image distribution based on current radar images through modifying the GAN. In the generative module of GAN, an auto-encoder consisting of dynamic inception-3-D and feature connection blocks extracts significant features from current radar images. The feasibility of the proposed model was verified on a real radar image dataset, and the experimental results proved that the proposed algorithm could effectively capture the location and pattern of the future radar echo, especially for typhoon weather systems. Compared with the mainstream methods of radar image extrapolation such as optical-flow and recurrent neural network (RNN)-based models, DMSF-GAN has a more superior and robust performance, which is also suitable for running on low-configuration machines.

中文翻译：

---

用于雷达图像外推的动态多尺度融合生成对抗网络

台风是一种毁灭性的自然灾害，在世界范围内造成了无法估量的损失。气象雷达图像对于天气预报，尤其是台风预报至关重要。天气临近预报（未来 0-6 小时）可以通过外推雷达图像来实现，而无需使用主要的天气预报方法——数值天气预报模型。然而，现有的基于统计或人工智能的相关技术不够高效。在本文中，提出了一种新的雷达图像外推算法，称为动态多尺度融合生成对抗网络（DMSF-GAN）。DMSF-GAN 通过修改 GAN，基于当前雷达图像捕捉未来雷达图像分布。在 GAN 的生成模块中，由动态 inception-3-D 和特征连接块组成的自动编码器从当前雷达图像中提取重要特征。在真实的雷达图像数据集上验证了所提模型的可行性，实验结果证明所提算法能够有效捕捉未来雷达回波的位置和模式，尤其是对于台风天气系统。与基于光流和循环神经网络（RNN）模型等雷达图像外推的主流方法相比，DMSF-GAN 具有更优越和鲁棒的性能，也适合在低配置机器上运行。实验结果证明，该算法能够有效捕捉未来雷达回波的位置和模式，尤其是台风天气系统。与基于光流和循环神经网络（RNN）模型等雷达图像外推的主流方法相比，DMSF-GAN 具有更优越和鲁棒的性能，也适合在低配置机器上运行。实验结果证明，该算法能够有效捕捉未来雷达回波的位置和模式，尤其是台风天气系统。与基于光流和循环神经网络（RNN）模型等雷达图像外推的主流方法相比，DMSF-GAN 具有更优越和鲁棒的性能，也适合在低配置机器上运行。