Submitted as: model description paper 06 Jul 2021

Submitted as: model description paper | 06 Jul 2021

Review status: this preprint is currently under review for the journal GMD.

A Generative Adversarial Model for Radar Echo Extrapolation Based on Convolutional Recurrent Units

Kun Zheng1, Yan Liu1, Jinbiao Zhang2, Cong Luo3, Siyu Tang3, Huihua Ruan2, Qiya Tan1, Yunlei Yi4, and Xiutao Ran4 Kun Zheng et al.
  • 1School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, China
  • 2Guangdong Meteorological Observation Data center, Guangzhou 510080, China
  • 3GuangDong Meteorological Observatory, GuangDong, 510080, China
  • 4Wuhan Zhaotu Technology Co. Ltd., Wuhan 430074, China

Abstract. Precipitation nowcasting play a vital role in preventing meteorological disasters and doppler radar data acts as an important input for nowcasting models. The traditional extrapolation method is difficult to model highly nonlinear echo movements. The key challenge of the nowcasting mission lies in achieving high-precision radar echo extrapolation. In recent years, machine learning has made a great progress in the extrapolation of weather radar echoes. However, most of models neglect the multi-modal characteristics of radar echo data, resulting in blurred and unrealistic prediction images. This paper aims to solve this problem by utilizing the feature of the GAN that can enhance the multi-modal distribution modelling, and design the radar echo extrapolation model of GAN-argcPredNet. The model composed of argcPredNet generator and a convolutional neural network discriminator. In generator, a gate control data memory and output are designed in the rgcLSTM prediction unit of the generator, thereby reducing the loss of spatiotemporal information. In discriminator, model uses a dual-channel input method, which enables it to strictly score according to the true echo distribution, and has a more powerful discrimination ability. Through experiments on the radar data set of Shenzhen, China, the results show that the radar echo hit rate (POD) and critical success index (CSI) increased by 5.5 % and %10.4 % compared with rgcPredNet, the false alarm rate (FAR) is reduced by 15 %~20 %. From the comparison of the result graph and the evaluation index, we also found a problem. The recursive prediction method will produce the phenomenon that the prediction result will gradually deviate from the true value over time. In addition, the accuracy of high-intensity echo extrapolation is relatively low. This is a question worthy of further investigation. In the future, we will continue to conduct research from these two directions.

Kun Zheng et al.

Status: open (until 31 Aug 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CEC1: 'Comment on gmd-2021-165', Astrid Kerkweg, 14 Jul 2021 reply
    • AC1: 'Reply on CEC1', Yan Liu, 15 Jul 2021 reply

Kun Zheng et al.

Model code and software

GAN-argcPredNet and argcPredNet models Kun Zheng

GAN-argcPredNet and argcPredNet models Kun Zheng

pretrained weights of GAN-argcPredNet and argcPredNet Kun Zheng

Kun Zheng et al.


Total article views: 220 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
178 35 7 220 3 2
  • HTML: 178
  • PDF: 35
  • XML: 7
  • Total: 220
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 06 Jul 2021)
Cumulative views and downloads (calculated since 06 Jul 2021)

Viewed (geographical distribution)

Total article views: 157 (including HTML, PDF, and XML) Thereof 157 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 30 Jul 2021
Short summary
In the extrapolation work, there is a phenomenon that the extrapolated image is blurred and unreal. The paper proposes a GAN-argcPredNet network model, which aims to solve this problem through GAN’s ability to strengthen the characteristics of multi-modal data modelling. GAN-ArgcPredNet has achieved excellent results. Our model can reduce the prediction loss in a small-scale space, so that the prediction results have more detailed features.