Abstract
Precipitation forecasting plays a key role in meteorological disaster prediction, and accurate weather forecasting can help to mitigate the adverse impacts of severe weather events on livelihoods and productivity. Radar precipitation images have complex spatiotemporal coupling characteristics. In order to improve the ability of spatiotemporal feature extraction in radar precipitation images, a spatiotemporal cooperative attention network (STC-UNet) is proposed in this study. In particular, we put forward a spatiotemporal feature extraction residual block (STRB) to extract multi-scale spatiotemporal features from the UNet encoder. The STRB module integrates channel and spatial parallel attention mechanism (CSPA) to enhance spatial feature capture. At the same time, the STRB module integrates the ConvLSTM network to improve the spatiotemporal feature extraction ability of precipitation images. Ultimately, an efficient sub-pixel convolutional neural network refines the decoder of UNet. We validate our approach using precipitation data from the Netherlands and cloud cover datasets from France, achieving future 30, 60, and 120-min precipitation forecasts. The results indicate the superiority of the proposed STC-UNet approach over the comparative models for precipitation nowcasting. The precipitation image predicted by this method is closer to the ground truth and can accurately capture the precipitation rain group, demonstrating good forecasting skills.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
An S, Oh T J, Kim S W and Jung J 2024 Self-clustered GAN for precipitation nowcasting; Sci. Rep. 14.
Bauer P, Thorpe A and Brunet G 2015 The quiet revolution of numerical weather prediction; Nature 525(7567) 47–55.
Berthomier L, Pradel B and Perez L 2020 Cloud cover nowcasting with deep learning; 2020 Tenth International Conference on Image Processing Theory Tools and Applications (IPTA), Paris, France, pp. 1–6.
Bi K, Xie L, Zhang H, Chen X, Gu X and Tian Q 2023 Accurate medium-range global weather forecasting with 3D neural networks; Nature 619(7970) 533–538.
Bosy J, Rohm W, Borkowski A, Kroszczynski K and Figurski M 2010 Integration and verification of meteorological observations and NWP model data for the local GNSS tomography; Atmos. Res. 96(4) 522–530.
Burton R, Blyth A M, Cui Z, Groves J, Lamptey B L, Fletcher J K and Roberts A 2022 Satellite-based nowcasting of west African mesoscale storms has skill at up to 4-h lead time; Weather Forecast. 37(4) 445–455.
Chen H, Qin H and Dai Y 2022 FC-ZSM: Spatiotemporal downscaling of rain radar data using a feature constrained zooming slow-Mo network; Front. Earth Sci. 10 887842.
Fernández J G and Mehrkanoon S 2021 Broad-UNet: Multi-scale feature learning for nowcasting tasks; Neural Netw. 144 419–427.
Gao J, Yi J and Murphey Y L 2022 Attention-based global context network for driving maneuvers prediction; Mach. Vision Appl. 33(4) 53.
Han L, Liang H, Chen H, Zhang W and Ge Y 2021 Convective precipitation nowcasting using U-Net Model; IEEE T. Geosci. Remote Sens., Brussels, Belgium, pp. 7134–7137.
Han L, Zhao Y, Chen H and Chandrasekar V 2022 Advancing radar nowcasting through deep transfer learning; IEEE T. Geosci. Remote Sens. 60 1–9.
Hu J, Shen L and Sun G 2018 Squeeze-and-excitation networks; CVPR Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 7132–7141.
Huang L X, Isaac G A and Sheng G 2012 Integrating NWP forecasts and observation data to improve nowcasting accuracy; Weather Forecast. 27(4) 938–953.
Hou Q, Zhou D and Feng J 2021 Coordinate attention for efficient mobile network design; CVPR Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 13713–13722.
Jeong C H and Yi M Y 2023 Correcting rainfall forecasts of a numerical weather prediction model using generative adversarial networks; J. Supercomput. 79(2) 1289–1317.
Kaparakis C and Mehrkanoon S 2023 Wf-UNet: Weather fusion UNet for precipitation nowcasting; arXiv preprint: arXiv:2302.04102.
Kilpeläinen M and Summala H 2007 Effects of weather and weather forecasts on driver behaviour; Transport Res. F-Traf. 10(4) 288–299.
Kingma D P and Ba J 2014 Adam: A method for stochastic optimization; arXiv preprint arXiv:1412.6980.
Leng J, Gao M, Gong H, Chen B, Zhou C, Shi M and Li X 2023 Spatio-temporal prediction of regional land subsidence via ConvLSTM; J. Geogr. Sci. 33(10) 2131–2156.
Li J, Jin K, Zhou D, Kubota N and Ju Z 2020 Attention mechanism-based CNN for facial expression recognition; Neurocomputing 411 340–350.
Li J, Shi Y, Zhang T, Li Z, Wang C and Liu J 2024 Radar precipitation nowcasting based on ConvLSTM model in a small watershed in north China; Nat. Hazards 120(1) 63–85.
Li Y, Zeng J, Shan S and Chen X 2018 Occlusion aware facial expression recognition using CNN with attention mechanism; IEEE Trans. Image Process. 28(5) 2439–2450.
Naskar P and Naskar S 2022 A new neurocomputing approach for medium-range temperature prediction; Mausam 73(3) 537–554.
Naskar P R and Naskar S 2023 The most suitable mode decomposition technique for machine learning in meteorological time series prediction; J. Earth Syst. Sci. 132(2) 84.
Niu D, Diao L, Xu L, Zang Z, Chen X and Liang S 2020 Precipitation forecast based on multi-channel ConvLSTM and 3d-CNN; 2020 International Conference on Unmanned Aircraft Systems (ICUAS) Athens, Greece, pp. 367–371.
Ronneberger O, Fischer P and Brox T 2015 U-net: Convolutional networks for biomedical image segmentation; In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference; Munich, Germany, October 5–9, proceeding part III 18 234–241.
Serifi A, Günther T and Ban N 2021 Spatio-temporal downscaling of climate data using convolutional and error-predicting neural networks; Front. Clim. 3 656479.
Shah N H, Priamvada A and Shukla B P 2023 Random forest-based nowcast model for rainfall; Earth Sci. Inform. 16(3) 2391–2403.
Shi W, Caballero J, Huszár F, Totz J, Aitken A P, Bishop R and Wang Z 2016 Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network; CVPR Proc. IEEE Conf. Comput. Vis. Pattern Recog., pp. 1874–1883.
Shi X, Chen Z, Wang H, Yeung D Y, Wong W K and Woo W C 2015 Convolutional LSTM network: A machine learning approach for precipitation nowcasting; NeurIPS 28.
Shi X, Gao Z, Lausen L, Wang H, Yeung D Y, Wong W K and Woo W C 2017 Deep learning for precipitation nowcasting: A benchmark and a new model; NeurIPS 30.
Spiridonov V, Ćurić M, Spiridonov V and Ćurić M 2021 Weather forecast and NWP; Fundamentals Meteorol., pp. 349–376.
Sutskever I, Vinyals O and Le Q V 2014 Sequence to sequence learning with neural networks; NeurIPS 27.
Tao P, Hao X, Cheng J and Chen L 2023 Predicting time series by data-driven spatiotemporal information transformation; Inf. Sci. 622 859–872.
Tekin S F, Fazla A and Kozat S 2024 Numerical weather forecasting using convolutional-LSTM with attention and Context Matcher Mechanisms; IEEE Trans. Geosci. Remote Sense. 62 1–13.
Trebing K, Sta\(\grave{{\rm n}}\)nczyk T and Mehrkanoon S 2021 SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture; Pattern Recogn. Lett. 145 178–186.
Van Houdt G, Mosquera C and Nápoles G 2020 A review on the long short-term memory model; Artif. Intell. Rev. 53(8) 5929–5955.
Wang Y, Wu H, Zhang J, Gao Z, Wang J, Philip S Y and Long M 2022 PredRNN: A recurrent neural network for spatiotemporal predictive learning; IEEE Trans. Pattern Anal. Mach. Intell. 45(2) 2208–2225.
Woo S, Park J, Lee J Y and Kweon I S 2018 CBAM: Convolutional block attention module; ECCV Proc. Eur. Conf. Comput. Vis., pp. 3–19.
Xiao Y, Yin H, Zhang Y, Qi H, Zhang Y and Liu Z 2021 A dual-stage attention-based Conv-LSTM network for spatio-temporal correlation and multivariate time series prediction; Int. J. Intell. Syst. 36(5) 2036–2057.
Xu M, Yang Y, Han M, Qiu T and Lin H 2018 Spatio-temporal interpolated echo state network for meteorological series prediction; IEEE Trans. Neural Netw. Learn. Syst. 30(6) 1621–1634.
Yin J, Gao Z and Han W 2021 Application of a radar echo extrapolation-based deep learning method in strong convection nowcasting; Earth Space Sci. 8(8) e2020EA001621.
Zhang Y, Long M, Chen K, Xing L, Jin R, Jordan M I and Wang J 2023 Skillful nowcasting of extreme precipitation with NowcastNet; Nature 619(7970) 526–532.
Acknowledgements
The authors would like to express their sincere gratitude to Parthasarathi Mukhopadhyay, Associate Editor and an anonymous reviewer, for their constructive comments, which helped to improve the quality and clarity of this paper. This work was supported in part by the Key Research and Development Plan project of Bozhou under Grant bzzc2023035.
Author information
Authors and Affiliations
Contributions
Xiangming Zheng initiated this research, participated in the construction of the model, analyzed and presented the data, and wrote the draft of the manuscript. Thanks to KNMI for the precipitation dataset. Weihao Lei provided support for model building. Weixi Wang accompanied in the field and carried out morphometric analysis. Piao Shi participated in editing and revising the manuscript. Huawang Qin supervised the entire work and was involved in designing the methodology followed in this work and manuscript drafting.
Corresponding author
Additional information
Communicated by Parthasarathi Mukhopadhyay
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zheng, X., Qin, H., Wang, W. et al. Research on precipitation nowcasting based on spatiotemporal cooperative attention. J Earth Syst Sci 134, 48 (2025). https://doi.org/10.1007/s12040-024-02508-8
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12040-024-02508-8