Weather Radar Nowcasting for Extreme Precipitation Prediction Based on the Temporal and Spatial Generative Adversarial Network

被引:11
|
作者
Chen, Xunlai [1 ,2 ]
Wang, Mingjie [1 ,2 ]
Wang, Shuxin [1 ,2 ]
Chen, Yuanzhao [1 ,2 ]
Wang, Rui [1 ,2 ]
Zhao, Chunyang [1 ,2 ]
Hu, Xiao [1 ,2 ]
机构
[1] Shenzhen Meteorol Bur, Qixiang Rd, Shenzhen 518040, Peoples R China
[2] Shenzhen Key Lab Severe Weather South China, Shenzhen 518040, Peoples R China
关键词
weather radar nowcasting; generative adversarial network (GAN); Temporal and Spatial GAN (TSGAN); heavy precipitation;
D O I
10.3390/atmos13081291
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Since strong convective weather is closely related to heavy precipitation, the nowcasting of convective weather, especially the nowcasting based on weather radar data, plays an essential role in meteorological operations for disaster prevention and mitigation. The traditional optical flow method and cross-correlation method have a low forecast accuracy and a short forecast leading time, while deep learning methods show remarkable advantages in nowcasting. However, most of the current forecasting methods based on deep learning suffer from the drawback that the forecast results become increasingly blurred as the forecast time increases. In this study, a weather radar nowcasting method based on the Temporal and Spatial Generative Adversarial Network (TSGAN) is proposed, which can obtain accurate forecast results, especially in terms of spatial details, by extracting spatial-temporal features, combining attention mechanisms and using a dual-scale generator and a multi-scale discriminator. The case studies on the forecast results of strong convective weather demonstrate that the GAN method performs well in terms of forecast accuracy and spatial detail representation compared with traditional optical flow methods and popular deep learning methods. Therefore, the GAN method proposed in this study can provide strong decision support for forecasting heavy precipitation processes. At present, the proposed method has been successfully applied to the actual weather forecasting business system.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] CLGAN: a generative adversarial network (GAN)-based video prediction model for precipitation nowcasting
    Ji, Yan
    Gong, Bing
    Langguth, Michael
    Mozaffari, Amirpasha
    Zhi, Xiefei
    GEOSCIENTIFIC MODEL DEVELOPMENT, 2023, 16 (10) : 2737 - 2752
  • [2] A spatiotemporal mixed-enhanced generative adversarial network for radar-based precipitation nowcasting
    He, Long
    Zheng, Kun
    Ruan, Huihua
    Yang, Shuo
    Zhang, Jinbiao
    Luo, Cong
    Tang, Siyu
    Yi, Yunlei
    Tian, Yugang
    Cheng, Jianmei
    COMPUTERS & GEOSCIENCES, 2025, 200
  • [3] Experimental Study on Generative Adversarial Network for Precipitation Nowcasting
    Luo, Chuyao
    Li, Xutao
    Ye, Yunming
    Feng, Shanshan
    Ng, Michael K.
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [4] Enhancing Spatial Variability Representation of Radar Nowcasting with Generative Adversarial Networks
    Gong, Aofan
    Li, Ruidong
    Pan, Baoxiang
    Chen, Haonan
    Ni, Guangheng
    Chen, Mingxuan
    REMOTE SENSING, 2023, 15 (13)
  • [5] A generative adversarial network approach to (ensemble) weather prediction
    Bihlo, Alex
    NEURAL NETWORKS, 2021, 139 : 1 - 16
  • [6] FsrGAN: A Satellite and Radar-Based Fusion Prediction Network for Precipitation Nowcasting
    Niu, Dan
    Li, Yinghao
    Wang, Hongbin
    Zang, Zengliang
    Jiang, Mingbo
    Chen, Xunlai
    Huang, Qunbo
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024, 17 : 7002 - 7013
  • [7] Weather Radar Data Compression Based on Spatial and Temporal Prediction
    Zeng, Qiangyu
    He, Jianxin
    Shi, Zhao
    Li, Xuehua
    ATMOSPHERE, 2018, 9 (03):
  • [8] AutoNowP: An Approach Using Deep Autoencoders for Precipitation Nowcasting Based on Weather Radar Reflectivity Prediction
    Czibula, Gabriela
    Mihai, Andrei
    Albu, Alexandra-Ioana
    Czibula, Istvan-Gergely
    Burcea, Sorin
    Mezghani, Abdelkader
    MATHEMATICS, 2021, 9 (14)
  • [9] GA-SmaAt-GNet: Generative adversarial small attention GNet for extreme precipitation nowcasting
    Reulen, Eloy
    Shi, Jie
    Mehrkanoon, Siamak
    KNOWLEDGE-BASED SYSTEMS, 2024, 305
  • [10] A Conditional Generative Adversarial Network for Weather Radar Beam Blockage Correction
    Tan, Songjian
    Chen, Haonan
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61