Convective Precipitation Nowcasting Using U-Net Model

• Published in: IEEE transactions on geoscience and remote sensing 2022, Vol.60, p.1-8
• Main Authors: Han, Lei, Liang, He, Chen, Haonan, Zhang, Wei, Ge, Yurong
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Convective precipitation; Correlation; Deep learning; Meteorological radar; Methods; Neural networks; Nowcasting; Precipitation; precipitation nowcasting; Predictive models; Radar; Radar data; Radar imaging; Recurrent neural networks; Reflectance; Storms; Training; U-Net; weather radar
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2021.3100847

Convective precipitation nowcasting remains challenging due to the fast change in convective weather. Radar images are the most important data source in nowcasting research area. This study proposes a radar data-based U-Net model for precipitation nowcasting. The nowcasting problem is first transformed into an image-to-image translation problem in deep learning under the U-Net architecture, which is based on convolutional neural networks (CNNs). The input of the model is five consecutive radar images; the output is the predicted radar reflectivity image. The model consists of three operations: upsampling, downsampling, and skip connection. Three methods, U-Net, TREC, and TrajGRU, are used for comparison in the experiments. The experimental results show that both deep learning methods outperform the TREC method, and the CNN-based U-Net can achieve almost the same performance as TrajGRU which is a recurrent neural network (RNN)-based model. With the advantages that U-Net is simple, efficient, easy to understand, and customize, this result shows the great potential of CNN-based models in addressing time-series applications.