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.

Storm identification, tracking, and forecasting make up an essential part of weather radar and severe weather surveillance operations. Existing nowcasting algorithms using radar data can be generally classified into two categories: centroid and cross-correlation tracking. Thunderstorm Identification, Tracking, and Nowcasting (TITAN) is a widely used centroid-type nowcasting algorithm based on this paradigm. The TITAN algorithm can effectively identify, track, and forecast individual convective storm cells, but TITAN tends to provide incorrect identification, tracking, and forecasting in cases where there are dense cells whose shape changes rapidly or where clusters of storm cells occur frequently. Aiming to improve the performance of TITAN in such scenarios, an enhanced TITAN (ETITAN) algorithm is presented. The ETITAN algorithm provides enhancements to the original TITAN algorithm in three aspects. First, in order to handle the false merger problem when two storm cells are adjacent, and to isolate individual storm cells from a cluster of storms, ETITAN uses a multithreshold identification method based on mathematical morphology. Second, in the tracking phase, ETITAN proposes a dynamic constraint-based combinatorial optimization method to track storms. Finally, ETITAN uses the motion vector field calculated by the cross-correlation method to forecast the position of the individual isolated storm cells. Thus, ETITAN combines aspects of the two general classes of nowcasting algorithms, that is, cross-correlation and centroid-type methods, to improve nowcasting performance. Results of experiments presented in this paper show the performance improvements of the ETITAN algorithm.

Deep learning is emerging as a powerful tool in scientific applications, such as radar-based convective storm nowcasting. However, it is still a challenge to extend the application of a well-trained deep learning nowcasting model, which demands to incorporate the learned knowledge at a certain location to other locations characterized by different precipitation features. This article designs a transfer learning framework to tackle this problem. A convolutional neural network (CNN)-based nowcasting method is utilized as the benchmark, based on which two transfer learning models are constructed through fine-tune and maximum mean discrepancy (MMD) minimization. The base CNN model is trained using radar data in the source study domain near Beijing, China, whereas the transferred models are applied to the target domain near Guangzhou, China, with only a small amount of data in the target area. The influence of a varying number of target data samples on the nowcasting performance is quantified. The experimental results demonstrate that the deep transfer learning models can improve the nowcasting skills.

Radar reflectivity (RR) greater than 35 dBZ usually indicates the presence of severe convective weather, which affects a variety of human activities, including aviation. However, RR data are scarce, especially in regions with poor radar coverage or substantial terrain obstructions. Fortunately, the radiance data of space-based satellites with universal coverage can be converted into a proxy field of RR. In this study, a convolutional neural network-based data-driven model is developed to convert the radiance data (infrared bands 07, 09, 13, 16, and 16–13) of Himawari-8 into the radar combined reflectivity factor (CREF). A weighted loss function is designed to solve the data imbalance problem due to the sparse convective pixels in the sample. The developed model demonstrates an overall reconstruction capability and performs well in terms of classification scores with 35 dBZ as the threshold. A five-channel input is more efficient in reconstructing the CREF than the commonly used one-channel input. In a case study of a convective event over North China in the summer using the test dataset, U-Net reproduces the location, shape and strength of the convective storm well. The present RR reconstruction technology based on deep learning and Himawari-8 radiance data is shown to be an efficient tool for producing high-resolution RR products, which are especially needed for regions without or with poor radar coverage.