Vol.35, NO.5, 2024
Turn off MathJax
Article Contents
Article Navigation >  Journal of Applied Meteorological Science  > 2024  >  35(5): 513-525
Zeng Xiaotuan, Zou Chenxi, Fan Jiao, et al. Short-term precipitation correction based on GRU deep learning. J Appl Meteor Sci, 2024, 35(5): 513-525. DOI:   10.11898/1001-7313.20240501.
Citation: Zeng Xiaotuan, Zou Chenxi, Fan Jiao, et al. Short-term precipitation correction based on GRU deep learning. J Appl Meteor Sci, 2024, 35(5): 513-525. DOI:   10.11898/1001-7313.20240501.
shu

Short-term Precipitation Correction Based on GRU Deep Learning

DOI: 10.11898/1001-7313.20240501
  • 1.

    Guangxi Meteorological Observatory, Nanning 530022

  • 2.

    Beijing Spider Information Technology Co., Ltd., Beijing 100088

  • Received Date: 2024-06-28
  • Rev Recd Date: 2024-07-29
  • Publish Date: 2024-09-30
    Abstract
  • To improve the accuracy of short-term precipitation forecasts, a deep learning method is proposed to correct numerical model precipitation forecast products. This method extracts spatiotemporal features from numerical model forecasts and observations using a neural network and performs corrections based on a gated recurrent unit (GRU) framework. Additionally, an atmospheric physics adaptor module is meticulously designed to address systematic errors in the intensity and displacement of numerical model forecast by leveraging physical condition mechanisms. The module plays a crucial role within the overarching model framework, which consists of three integrated components: Feature network, recurrent-revising network, and physical adaptor. The feature network extracts precipitation intensity, distribution, motion characteristics and other related atmospheric physical features from precipitation in situ and numerical model forecast data, serving as input to the recurrent-revising network. Recurrent-revising network utilizes a recurrent neural network structure to adjust grid point forecast results on a time-step basis. Deep neural networks are used to extract spatiotemporal variation features from numerical model forecast data and historical observations, learning systematic errors in the evolution processes to correct the precipitation magnitude and distribution. The physical adaptor is an atmospheric physics adaptation module, which preprocesses numerical model forecast data using frequency distribution fitting and distribution deviation correction methods. In Guangxi convective-scale model precipitation forecast data, when there are significant differences between numerous samples and the precipitation in situ, the feature correlation is low, making it a challenge to capture systematic error characteristics during neural network training. By preprocessing the samples with the physical adaptor, differences between forecasts and observations are reduced, enhancing feature correlation between training input datasets and observations, thus facilitating better neural network training and achieving superior correction skills. This method not only adheres to but also integrates fundamental atmospheric physical laws governing precipitation evolution, thereby offering a robust and innovative approach for post-processing numerical model short-term precipitation forecasts. By incorporating these physical principles into the model framework, corrected forecasts not only reflect statistical patterns but also adhere closely to the underlying physical processes driving precipitation dynamics. Experimental results in Guangxi indicate that the model demonstrates positive threat score skills across various forecast times and precipitation intensities. Specifically, for different precipitation intensities (average of all times), threat score skills for 0.1 mm·h-1, 2 mm·h-1, 7 mm·h-1, 15 mm·h-1, 25 mm·h-1, and 40 mm·h-1 are 5.67%, 3.59%, 2.18%, 1.46%, 1.01%, and 0.46%, respectively; for different lead times, threat score skills for 0-2 h, 2-4 h, and 4-6 h are 4.77%, 1.28%, and 0.91%, respectively; and the overall average threat score skill across all precipitation intensities and times is 2.21%.
    • FullText(HTML)
    References(30)

  • Fig. 1  ReviseGRU model architecture

    DownLoad: Full-Size Img PowerPoint

    Fig. 1  ReviseGRU model architecture

    DownLoad: Full-Size Img PowerPoint

    Fig. 1  ReviseGRU model architecture

    DownLoad: Full-Size Img PowerPoint

    Fig. 2  TS for different precipitation intensities

    DownLoad: Full-Size Img PowerPoint

    Fig. 2  TS for different precipitation intensities

    DownLoad: Full-Size Img PowerPoint

    Fig. 2  TS for different precipitation intensities

    DownLoad: Full-Size Img PowerPoint

    Fig. 3  Averaged TS for different lead times

    DownLoad: Full-Size Img PowerPoint

    Fig. 3  Averaged TS for different lead times

    DownLoad: Full-Size Img PowerPoint

    Fig. 3  Averaged TS for different lead times

    DownLoad: Full-Size Img PowerPoint

    Fig. 4  Comparison of precipitation intensity before and after correction for different lead times initiated at 0736 BT 27 Aug 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 4  Comparison of precipitation intensity before and after correction for different lead times initiated at 0736 BT 27 Aug 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 4  Comparison of precipitation intensity before and after correction for different lead times initiated at 0736 BT 27 Aug 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 5  Comparison of precipitation intensity before and after correction for different lead times initiated at 0224 BT 11 Sep 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 5  Comparison of precipitation intensity before and after correction for different lead times initiated at 0224 BT 11 Sep 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 5  Comparison of precipitation intensity before and after correction for different lead times initiated at 0224 BT 11 Sep 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 6  Comparison of precipitation intensity before and after correction at 1100 BT 17 Jul 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 6  Comparison of precipitation intensity before and after correction at 1100 BT 17 Jul 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 6  Comparison of precipitation intensity before and after correction at 1100 BT 17 Jul 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 7  Comparison of precipitation coverage area before and after correction for different lead times at 0800 BT 18 Jul 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 7  Comparison of precipitation coverage area before and after correction for different lead times at 0800 BT 18 Jul 2023

    DownLoad: Full-Size Img PowerPoint

    Fig. 7  Comparison of precipitation coverage area before and after correction for different lead times at 0800 BT 18 Jul 2023

    DownLoad: Full-Size Img PowerPoint
  • [1]
    Zhang B, Zhang F H, Li X L, et al. Verification and assessment of "23·7" severe rainstorm numerical prediction in North China. J Appl Meteor Sci, 2024, 35(1): 17-32. doi:  10.11898/1001-7313.20240102
    [2]
    Xing N, Zhong J Q, Lei L, et al. A probabilistic forecast experiment of short-duration heavy rainfall in Beijing based on CMA-BJ. J Appl Meteor Sci, 2023, 34(6): 641-654. doi:  10.11898/1001-7313.20230601
    [3]
    Huang L P, Deng L T, Wang R C, et al. Key technologies of CMA-MESO and application to operational forecast. J Appl Meteor Sci, 2022, 33(6): 641-654. doi:  10.11898/1001-7313.20220601
    [4]
    Xu C L, Wang J J, Huang L P. Evaluation on QPF of GRAPES-Meso4.0 model at convection-permitting resolution. Acta Meteor Sinica, 2017, 75(6): 851-876.
    [5]
    Xie Y Y, Wang J J. Preliminary study on the deviation and cause of precipitation prediction of GRAPES kilometer scale model in southwest complex terrain area. Acta Meteor Sinica, 2021, 79(5): 732-749.
    [6]
    Wang B M, Liu X N. Distribution of China Cloud. Beijing: China Meteorological Press, 2009.
    [7]
    Mo J F, Zhong S Q, Chen Y L, et al. Study on social-economic exposure degree model of basin flood hazard of extreme precipitation events in Guangxi. J Catastrophology, 2018, 33(2): 83-88. doi:  10.3969/j.issn.1000-811X.2018.02.016
    [8]
    Lin Z M, Huang R, Qi Y F, et al. Construction and benefit evaluation of convective scale numerical weather prediction model system in Guangxi. J Meteor Res Appl, 2022, 43(2): 105-110.
    [9]
    Boeing G. Visual analysis of nonlinear dynamical systems: Chaos, fractals, self-similarity and the limits of prediction. Systems, 2016, 4(4). DOI:  10.3390/systems4040037.
    [10]
    Yang X, Dai K, Zhu Y J. Progress and challenges of deep learning techniques in intelligent grid weather forecasting. Acta Meteor Sinica, 2022, 80(5): 649-667.
    [11]
    Zhi X F, Zhao C. Heavy precipitation forecasts based on multi-model ensemble members. J Appl Meteor Sci, 2020, 31(3): 303-314. doi:  10.11898/1001-7313.20200305
    [12]
    Wang J H, Li Q Q, Wang F, et al. Correction of precipitation forecast predicted by DERF2.0 during the pre-flood season in South China. J Appl Meteor Sci, 2021, 32(1): 115-128. doi:  10.11898/1001-7313.20210110
    [13]
    Xie S, Sun X G, Zhang S P, et al. Precipitation forecast correction in South China based on SVD and machine learning. J Appl Meteor Sci, 2022, 33(3): 293-304. doi:  10.11898/1001-7313.20220304
    [14]
    Wu Q S, Han M, Liu M, et al. A comparison of optimal-score-based correction algorithms of model precipitation prediction. J Appl Meteor Sci, 2017, 28(3): 306-317. doi:  10.11898/1001-7313.20170305
    [15]
    Li D, Lin W, Liu Q, et al. Application of machine learning to statistical evaluation of artificial rainfall enhancement. J Appl Meteor Sci, 2024, 35(1): 118-128. doi:  10.11898/1001-7313.20240110
    [16]
    Zhang Y C, Long M S, Chen K Y, et al. Skilful nowcasting of extreme precipitation with NowcastNet. Nature, 2023, 619(7970): 526-532. doi:  10.1038/s41586-023-06184-4
    [17]
    Sayeed A, Choi Y, Jung J, et al. A deep convolutional neural network model for improving WRF simulations. IEEE Trans Neural Netw Learn Syst, 2023, 34(2): 750-760. doi:  10.1109/TNNLS.2021.3100902
    [18]
    Zhang C J, Zeng J, Wang H Y, et al. Correction model for rainfall forecasts using the LSTM with multiple meteorological factors. Meteor Appl, 2020, 27(1). DOI:  10.1002/met.1852.
    [19]
    Han L, Chen M X, Chen K K, et al. A deep learning method for bias correction of ECMWF 24-240 h forecasts. Adv Atmos Sci, 2021, 38(9): 1444-1459. doi:  10.1007/s00376-021-0215-y
    [20]
    Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997, 9: 1735-1780. doi:  10.1162/neco.1997.9.8.1735
    [21]
    Mi Q C, Gao X N, Li Y, et al. Application of deep learning method to drought prediction. J Appl Meteor Sci, 2022, 33(1): 104-114. doi:  10.11898/1001-7313.20220109
    [22]
    Chung J, Gülçehre Ç, Cho K H, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. Eprint ArXiv, 2014. DOI:  10.48550/arXiv.1412.3555.
    [23]
    Zhuo J, Liao S S, Su C C, et al. Application of MLP in radar quantitative precipitation estimation. J Trop Meteor, 2023, 39(3): 289-299.
    [24]
    Zhuo J, Chen S B, Zhou D J, et al. An approach for radar quantitative precipitation estimate based on fast dynamic categorical method. J Trop Meteor, 2018, 34(6): 856-864.
    [25]
    Hu Y Y, Pang L, Wang Q G. Application of deep learning bias correction method to temperature grid forecast of 7-15 days. J Appl Meteor Sci, 2023, 34(4): 426-437. doi:  10.11898/1001-7313.20230404
    [26]
    Zhang L, Wu L, Li F, et al. Indentification of weather radar abnormal data based on deep learning. J Appl Meteor Sci, 2023, 34(6): 694-705. doi:  10.11898/1001-7313.20230605
    [27]
    Shi W Z, Caballero J, Huszár F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2016: 1874-1883.
    [28]
    Zhang X Z. Parameter estimation method of Weibull distribution and its application. Acta Meteor Sinica, 1996, 54(1): 108-116.
    [29]
    Laroche S, Zawadzki I. A variational analysis method for retrieval of three-dimensional wind field from single-Doppler radar data. J Atmos Sci, 1994, 51(18): 2664-2682.
    [30]
    Wilks D S. Statistical Methods in the Atmospheric Sciences. New York: Academic Press, 2019: 373-374.
    • Relative Articles
    • Supplements(0)
    • Cited By
  • 加载中
  • -->

Catalog

    Figures(21)

    Get Citation
    PDF
    XML
    Article views (831) PDF downloads(148) Cited by()
    • Received : 2024-06-28
    • Accepted : 2024-07-29
    • Published : 2024-09-30
    Journal Online
    Contact

    © 2020 Journal of Applied Meteorological Science   京ICP备15006967号-1

    Supported by Beijing Renhe Information Technology Co. Ltd

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return