Deep neural network based on adversarial training for short-term high-resolution precipitation nowcasting from radar echo images

Ruikai YANG; Shuangjian JIAO; Nan YANG

doi:10.1007/s00343-025-4354-3

Your Location：

Home >

Browse articles >

Deep neural network based on adversarial training for short-term high-resolution precipitation nowcasting from radar echo images

Physics | Updated：2026-03-26

- Deep neural network based on adversarial training for short-term high-resolution precipitation nowcasting from radar echo images
- Journal of Oceanology and Limnology Vol. 44, Issue 1, Pages: 85-98(2026)
- Affiliations：
  
  1.College of Engineering, Ocean University of China, Qingdao 266100, China
  2.Key Laboratory of Ocean Observation and Forecasting, Chinese Academy of Sciences, Qingdao 266000, China
  3.Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266000, China
- Author bio：
  
  hnbc_7@163.com
  yangnan@qdio.ac.cn
- Funds：
- DOI：10.1007/s00343-025-4354-3
  CLC：
- Received：24 December 2024，
  
  Accepted：04 February 2025，
  
  Online First：17 March 2025，
  
  Published：01 January 2026
- Accepted：
Scan QR Code
YANG Ruikai,JIAO Shuangjian,YANG Nan.Deep neural network based on adversarial training for short-term high-resolution precipitation nowcasting from radar echo images[J].Journal of Oceanology and Limnology,2026,44(01):85-98.
DOI：

YANG Ruikai,JIAO Shuangjian,YANG Nan.Deep neural network based on adversarial training for short-term high-resolution precipitation nowcasting from radar echo images[J].Journal of Oceanology and Limnology,2026,44(01):85-98. DOI： 10.1007/s00343-025-4354-3.

摘要

Abstract

Precipitation nowcasting is of great importance for disaster prevention and mitigation. However

precipitation is a complex spatio-temporal phenomenon influenced by various underlying physical factors. Even slight changes in the initial precipitation field can have a significant impact on the future precipitation patterns

making the nowcasting of short-term high-resolution precipitation a major challenge. Traditional deep learning methods often have difficulty capturing the long-term spatial dependence of precipitation and are usually at a low resolution. To address these issues

based upon the Simpler yet Better Video Prediction (SimVP) framework

we proposed a deep generative neural network that incorporates the Simple Parameter-Free Attention Module (SimAM) and Generative Adversarial Networks (GANs) for short-term high-resolution precipitation event forecasting. Through an adversarial training strategy

critical precipitation features were extracted from complex radar echo images. During the adversarial learning process

the dynamic competition between the generator and the discriminator could continuously enhance the model in prediction accuracy and resolution for short-term precipitation. Experimental results demonstrate that the proposed method could effectively forecast short-term precipitation events on various scales and showed the best overall performance among existing methods.

关键词

Keywords

references

Bauer P , Thorpe A , Brunet G . 2015 . The quiet revolution of numerical weather prediction . Nature , 525 ( 7567 ): 47 - 55 , https://doi.org/10.1038/nature14956 https://doi.org/10.1038/nature14956 .

Chang Z , Zhang X F , Wang S S et al . 2022 . STRPM: a spatiotemporal residual predictive model for high-resolution video prediction . In: Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . IEEE , New Orleans, USA . p. 13926 - 13935 , https://doi.org/10.1109/CVPR52688.2022.01356 https://doi.org/10.1109/CVPR52688.2022.01356 .

Fang J , Yang W T , Luan Y B et al . 2019 . Evaluation of the TRMM 3B42 and GPM IMERG products for extreme precipitation analysis over China . Atmospheric Research , 223 : 24 - 38 , https://doi.org/10.1016/j.atmosres.2019.03.001 https://doi.org/10.1016/j.atmosres.2019.03.001 .

Gao Z Y , Tan C , Wu L R et al . 2022 . SimVP: simpler yet better video prediction . In: Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . IEEE , New Orleans, USA . p. 3160 - 3170 , https://doi.org/10.1109/CVPR52688.2022.00317 https://doi.org/10.1109/CVPR52688.2022.00317 .

Jin Q Z , Zhang X B , Xiao X Y et al . 2024 . Preformer: simple and efficient design for precipitation nowcasting with transformers. IEEE Geoscience and Remote Sensing Letters , 21 : 1000205 , https://doi.org/10.1109/LGRS.2023.325628 https://doi.org/10.1109/LGRS.2023.325628 .

Ledig C , Theis L , Huszár F et al . 2017 . Photo-realistic single image super-resolution using a generative adversarial network . In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . IEEE , Honolulu, USA . p. 105 - 114 , https://doi.org/10.1109/CVPR.2017.19 https://doi.org/10.1109/CVPR.2017.19 .

Li X F , Liu B , Zheng G et al . 2020a . Deep-learning-based information mining from ocean remote-sensing imagery . National Science Review , 7 ( 10 ): 1584 - 1605 , https://doi.org/10.1093/nsr/nwaa047 https://doi.org/10.1093/nsr/nwaa047 .

Li X , Zhang L F , Wang J N . 2020b . The sensitivity of the prediction of Meiyu torrential rainfall to model resolution and cumulus parameterization . Torrential Rain and Disasters , 39 ( 6 ): 637 - 646 , https://doi.org/10.3969/j.issn.1004-9045.2020.06.012. https://doi.org/10.3969/j.issn.1004-9045.2020.06.012. (in Chinese with English abstract)

Liu J , Xu L , Chen N C . 2022 . A spatiotemporal deep learning model ST-LSTM-SA for hourly rainfall forecasting using radar echo images. Journal of Hydrology , 609 : 127748 , https://doi.org/10.1016/j.jhydrol.2022.127748 https://doi.org/10.1016/j.jhydrol.2022.127748 .

Min S K , Zhang X B , Zwiers F W et al . 2011 . Human contribution to more-intense precipitation extremes . Nature , 470 ( 7334 ): 378 - 381 , https://doi.org/10.1038/nature09763 https://doi.org/10.1038/nature09763 .

Ning W X , Liu X Y , Wang Z T . 2021 . Temperature and precipitation characteristics and spatial stratified heterogeneity in Badain Jaran Desert . Journal of University of Chinese Academy of Sciences , 38 ( 1 ): 103 - 113 , https://doi.org/10.7523/j.issn.2095-6134.2021.01.013. https://doi.org/10.7523/j.issn.2095-6134.2021.01.013. (in Chinese with English abstract)

Ravuri S , Lenc K , Willson M et al . 2021 . Skilful precipitation nowcasting using deep generative models of radar . Nature , 597 ( 7878 ): 672 - 677 , https://doi.org/10.1038/s41586-021-03854-z https://doi.org/10.1038/s41586-021-03854-z .

Schultz M G , Betancourt C , Gong B et al . 2021 . Can deep learning beat numerical weather prediction? Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences , 379 ( 2194 ): 20200097 , https://doi.org/10.1098/rsta.2020.0097 https://doi.org/10.1098/rsta.2020.0097 .

Shi X J , Chen Z R , Wang H et al . 2015 . Convolutional LSTM Network: a machine learning approach for precipitation nowcasting . In: Proceedings of the 29th International Conference on Neural Information Processing Systems . MIT Press , Montreal, Canada . p. 802 - 810 .

Szegedy C , Liu W , Jia Y Q et al . 2015 . Going deeper with convolutions . In: Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition . IEEE , Boston, USA . p. 1 - 9 , https://doi.org/10.1109/CVPR.2015.7298594 https://doi.org/10.1109/CVPR.2015.7298594 .

Veillette M S , Samsi S , Mattioli C J . 2020 . SEVIR: a storm event imagery dataset for deep learning applications in radar and satellite meteorology . In: Proceedings of the 34th International Conference on Neural Information Processing Systems . Curran Associates Inc. , Vancouver, Canada . p. 1846 .

Wang J N , Wang X D , Guan J P et al . 2023 . TAFFNet: time-aware adaptive feature fusion network for very short-term precipitation forecasts . Geophysical Research Letters , 50 ( 15 ): e2023 GL 104370 , https://doi.org/10.1029/2023GL104370 https://doi.org/10.1029/2023GL104370 .

Wang Y B , Long M S , Wang J M et al . 2017 . PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs . In: Proceedings of the 31st International Conference on Neural Information Processing Systems . Curran Associates Inc. , Long Beach, USA . p. 879 - 888 .

Wen G H , Huang G , Hu K M et al . 2015 . Changes in the characteristics of precipitation over northern Eurasia . Theoretical and Applied Climatology , 119 ( 3 ): 653 - 665 , https://doi.org/10.1007/s00704-014-1137-8 https://doi.org/10.1007/s00704-014-1137-8 .

Xu Z , Du J , Wang J J et al . 2019 . Satellite image prediction relying on GAN and LSTM neural networks . In: Proceedings of 2019 IEEE International Conference on Communications . IEEE , Shanghai, China . p. 1 - 6 , https://doi.org/10.1109/ICC.2019.8761462 https://doi.org/10.1109/ICC.2019.8761462 .

Yan Q , Ji F X , Miao K C et al . 2020 . Convolutional residual-attention: a deep learning approach for precipitation nowcasting . Advances in Meteorology , 2020 ( 1 ): 6484812 , https://doi.org/10.1155/2020/6484812 https://doi.org/10.1155/2020/6484812 .

Yang L X , Zhang R Y , Li L D et al . 2021 . SimAM: a simple, parameter-free attention module for convolutional neural networks . In: Proceedings of the 38th International Conference on Machine Learning . PMLR , p. 11863 - 11874 . https://do 10.1007/978-3-030-86362-3_14 http://dx.doi.org/10.1007/978-3-030-86362-3_14

Yang N , Li X F . 2024a . An individual motion-driven artificial intelligence method for precipitation forecasting using radar image sequencing. IEEE Transactions on Geoscience and Remote Sensing , 62 : 4208516 , https://doi.org/10.1109/TGRS.2024.3439871 https://doi.org/10.1109/TGRS.2024.3439871 .

Yang N , Li X F . 2024b . Lightweight AI-powered precipitation nowcasting . The Innovation Geoscience , 2 ( 2 ): 100066 , https://doi.org/10.59717/j.xinn-geo.2024.100066 https://doi.org/10.59717/j.xinn-geo.2024.100066 .

Yang W S , Chen H N , Han L et al . 2023 . Multitask learning for precipitation estimation using satellite observations from the GOES-R series. IEEE Geoscience and Remote Sensing Letters , 20 : 1002205 , https://doi.org/10.1109/LGRS.2023.3313150 https://doi.org/10.1109/LGRS.2023.3313150 .

Zhang A , Zhao X Y . 2022 . Changes of precipitation pattern in China: 1961-2010 . Theoretical and Applied Climatology , 148 ( 3 ): 1005 - 1019 , https://doi.org/10.1007/s00704-022-03986-w https://doi.org/10.1007/s00704-022-03986-w .

Zhang L , Zhou Z M , Guan J P et al . 2024 . AttUnet_R_SFT: a novel network to explore the application of complex terrain information in satellite precipitation estimating . Earth and Space Science , 11 ( 6 ): e2023 EA 003444 , https://doi.org/10.1029/2023EA003444 https://doi.org/10.1029/2023EA003444 .

Zhang Y C , Long M S , Chen K Y et al . 2023 . Skilful nowcasting of extreme precipitation with NowcastNet . Nature , 619 ( 7970 ): 526 - 532 , https://doi.org/10.1038/s41586-023-06184-4 https://doi.org/10.1038/s41586-023-06184-4 .

Zhu H H , Jiang Z H , Li L . 2021 . Projection of climate extremes in China, an incremental exercise from CMIP5 to CMIP6 . Science Bulletin , 66 ( 24 ): 2528 - 2537 , https://doi.org/10.1016/j.scib.2021.07.026 https://doi.org/10.1016/j.scib.2021.07.026 .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

A physics-enhanced deep-learning model for estimating turbid shallow water depth from SAR images

Prediction of sea surface pCO₂ in the South China Sea using Spatiotemporal Convolutional LSTM model

A deep learning-based hybrid model for improved SST prediction in the tropical Pacific Ocean

Parameterization of turbulent mixing by deep learning in the continental shelf sea east of Hainan Island

Related Author

Nan YANG

Shuangjian JIAO

Kaiguo FAN

Letian LÜ

Yan LI

Xiaobin YIN

Qing XU

Tian MA

Related Institution

College of Marine Technology/Sanya Oceanographic Institution, Ocean University of China

National Key Laboratory of Intelligent Spatial Information

Laboratory for Regional Oceanography and Numerical Modeling, Qingdao Marine Science and Technology Center

Marine Science and Technology College, Zhejiang Ocean University

Ocean College, Zhejiang University

Address：Editorial Office of JOL, 88 Haijun Rd. Qingdao, 266000, China
Tel：+86-532-82898754 Email：jol@qdio.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰