Preprints
https://doi.org/10.5194/egusphere-2022-859
https://doi.org/10.5194/egusphere-2022-859
14 Nov 2022
 | 14 Nov 2022

CLGAN: A GAN-based video prediction model for precipitation nowcasting

Yan Ji, Bing Gong, Michael Langguth, Amirpasha Mozaffari, and Xiefei Zhi

Abstract. The prediction of precipitation patterns at high spatio-temporal resolution up to two hours ahead, also known as precipitation nowcasting, is of great relevance in weather-dependant decision-making and early warning systems. In this study, we are aiming to provide an efficient and easy-to-understand model - CLGAN, to improve the nowcasting skills of heavy precipitation events with deep neural networks for video prediction. The model constitutes a Generative Adversarial Network (GAN) architecture whose generator is built upon an u-shaped encoder-decoder network (U-Net) equipped with recurrent LSTM cells to capture spatio-temporal features. A comprehensive comparison among CLGAN, and baseline models optical flow model DenseRotation as well as the advanced video prediction model PredRNN-v2 is performed. We show that CLGAN outperforms in terms of scores for dichotomous events and object-based diagnostics. The ablation study indicates that the GAN-based architecture helps to capture heavy precipitation events. The results encourage future work based on the proposed CLGAN architecture to improve the precipitation nowcasting and early-warning systems.

Yan Ji et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CEC1: 'Comment on egusphere-2022-859', Juan Antonio Añel, 12 Dec 2022
    • AC1: 'Reply on CEC1', Yan Ji, 12 Dec 2022
  • RC1: 'Comment on egusphere-2022-859', Anonymous Referee #1, 13 Dec 2022
    • AC2: 'Reply on RC1', Yan Ji, 17 Jan 2023
  • RC2: 'Comment on egusphere-2022-859', Anonymous Referee #2, 16 Dec 2022
    • AC3: 'Reply on RC2', Yan Ji, 17 Jan 2023
  • CC1: 'Comment on egusphere-2022-859', Qiuming Kuang, 20 Dec 2022
    • AC4: 'Reply on CC1', Yan Ji, 17 Jan 2023

Yan Ji et al.

Yan Ji et al.

Viewed

Total article views: 907 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
652 228 27 907 14 12
  • HTML: 652
  • PDF: 228
  • XML: 27
  • Total: 907
  • BibTeX: 14
  • EndNote: 12
Views and downloads (calculated since 14 Nov 2022)
Cumulative views and downloads (calculated since 14 Nov 2022)

Viewed (geographical distribution)

Total article views: 872 (including HTML, PDF, and XML) Thereof 872 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 21 Mar 2023
Download
Short summary
Formulating the short-term precipitation forecasting as a video prediction task, a novel deep learning architecture CLGAN is proposed in this work. A benchmark data set is newly built for the task, on minute-level precipitation measurements. Our results show that the GAN-component of CLGAN encourages the model to generate predictions sharing statistical properties of observed precipitation, which makes it outperform the baseline in dichotomous and spatial scores for heavy precipitation events.