Sun Jian, Cao Zhuo, Li Heng, et al. Application of artificial intelligence technology to numerical weather prediction. J Appl Meteor Sci, 2021, 32(1): 1-11. DOI:  10.11898/1001-7313.20210101.
Citation: Sun Jian, Cao Zhuo, Li Heng, et al. Application of artificial intelligence technology to numerical weather prediction. J Appl Meteor Sci, 2021, 32(1): 1-11. DOI:  10.11898/1001-7313.20210101.

Application of Artificial Intelligence Technology to Numerical Weather Prediction

DOI: 10.11898/1001-7313.20210101
  • Received Date: 2020-08-25
  • Rev Recd Date: 2020-11-02
  • Publish Date: 2021-01-31
  • Numerical weather prediction technology plays an increasingly important role in improving accuracy and service level of modern weather forecast. With the development of observation system and higher resolution and complexity of the numerical weather prediction model, the products of numerical weather forecast have been greatly improved in quantity and quality, and can offer rich information at high spatial-temporal frequency. However, such a large amount of prediction data are not fully explored. Artificial intelligence has achieved great success in many fields, such as pattern recognition and natural language processing, which provides an opportunity for further improving numerical weather prediction. It's also employed in initialization, numerical model and production of weather forecast service, involving observation system, data assimilation, model integration, ensemble forecast and high-performance computing methods. Both the accuracy of forecast results and computational efficiency have been improved by using error correction, parameter estimation, local surrogate model and so on. In addition, some end-to-end neural network models also show the potential of pure data-driven weather forecast. These models use spatial-temporal observation data as input and directly output the prediction results in terms of deterministic results or probabilities. Some of them perform well in short-term severe convective weather, precipitation, and long-term climate forecast. Existing works employ various artificial intelligence technology methods, mainly including large-scale calculation of neural network, feature analysis, interpretability, and customized loss function. However, there are still some challenges, the potential of artificial intelligence needs to be further explored. Some issues should be carefully considered, including weak interpretability, uncertainty analysis and the coupling with conventional numerical models, and how to use physical knowledge to guide the design of artificial intelligence model is also worth addressing. To deal with these challenges, some promising suggestions are proposed. Bayesian network and causal network will help to establish more comprehensive and profound feature engineering. Using Bayesian inference to generate distribution characteristics of current meteorological states may be an alternative to efficient and effective uncertainty quantification. The development of some standard workflow and framework will contribute to the coupling of conventional numerical model and artificial intelligence module. Successful artificial intelligence applications in weather forecast require deep cooperation between meteorological experts and computer experts who focus on artificial intelligence and high-performance computing.
  • Fig. 1  Workflow of numerical weather prediction

    Fig. 2  Components of artificial intelligence technology

    Fig. 3  Weather prediction workflow based on artificial intelligence models

    Table  1  Artificial intelligence applications to numerical weather prediction

    功能 模块 人工智能技术 目标 效果
    初值生成 观测资料处理及质量控制 贝叶斯方案、全卷积网络、极限学习机等 观测偏差纠正[43]、雷达及卫星图像资料预处理[44-45] 提高观测资料质量,优化高分辨率图像资料分割、资料填补等
    资料同化 随机森林、深度神经网络、支持向量机等 同化算法参数优化[46]、部分替代资料同化方法[47]、聚焦观测区域[48] 提高同化质量,提高同化速度,更好利用高分辨率资料等
    预报 模式积分 深度神经网络、卷积网络、随机森林等 模式代理[49]、替代物理过程参数化方案[50-53]、参数校正[54-55] 提高模式计算速度,优化次网格物理过程的表示,提高参数校正效果与速度等
    产品应用 后处理 随机森林、深度神经网络、卷积神经网络等 确定性及集合预报结果后处理[56-58]、替代集合预报[59-60] 后处理偏差订正、质量更好、效率更高等
    DownLoad: Download CSV
  • [1]
    Duan Hailai, Qian Huaisui.Responses of the electric power consumption to climate change in Guangzhou City.J Appl Meteor Sci, 2009, 20(1): 80-87. doi:  10.3969/j.issn.1001-7313.2009.01.010
    [2]
    Guo Jianping.Research progress on agricultural meteorological disaster monitoring and forecasting.J Appl Meteor Sci, 2016, 27(5): 620-630. doi:  10.11898/1001-7313.20160510
    [3]
    Wang Chunzhi, Huo Zhiguo, Zhang Lei, et al.Construction of forecasting model of meteorological suitability for wheat aphids in the Northern China.J Appl Meteor Sci, 2020, 31(3): 280-289. doi:  10.11898/1001-7313.20200303
    [4]
    Zhou Yu, Liu Zhiping, Zhang Guoping.Probability forecasting model of geological disaster along the Yingxia Railway induced by precipitation with its application.J Appl Meteor Sci, 2015, 26(6): 743-749. doi:  10.11898/1001-7313.20150611
    [5]
    Hou Yingyu, Zhang Lei, Wu Menxin, et al.Advances of modern agrometeorological service and technology in China.J Appl Meteor Sci, 2018, 29(6): 641-656. doi:  10.11898/1001-7313.20180601
    [6]
    Gao Taichang, Liu Lei, Zhao Shijun, et al.The actuality and progress of whole sky cloud sounding techniques.J Appl Meteor Sci, 2010, 21(1): 101-109. doi:  10.3969/j.issn.1001-7313.2010.01.014
    [7]
    Zhai Panmao, Liu Jing.Extreme weather/climate events and disaster prevention and mitigation under global warming background.Engineering Sciences, 2012, 14(9): 55-63.
    [8]
    Mu Mu, Chen Boyu, Zhou Feifan, et al.Methods and uncertainties of meteorological forecast.Meteorological Monthly, 2011, 37(1): 1-13.
    [9]
    Zeng Xiaomei.Application of artificial intelligence technology in weather forecast abroad.Meteorological Science and Technology, 1999, 27(1): 4-10. https://www.cnki.com.cn/Article/CJFDTOTAL-QXKJ901.001.htm
    [10]
    Cleveland A.The physical basis of long-range weather forecasts.Mon Wea Rev, 1901, 29(12): 551.
    [11]
    Bjerknes V.Das Problem der Wettervorhersage betrachtet vomStandpunkt der Mechanik und Physik.Meteorol Z, 1904, 21: 1-7.
    [12]
    Richardson L F.Weather Prediction by Numerical Process.Cambridge:Cambridge University Press, 1922.
    [13]
    Charney J G, Fjoertoft R, Von Neumann J.Numerical integration of the barotropic vorticity equation.Tellus, 1950, 2: 237-254.
    [14]
    Lynch P.The origins of computer weather prediction and climate modeling.J Comput Phys, 2008, 227: 3431-3444. doi:  10.1016/j.jcp.2007.02.034
    [15]
    Li Zechun, Chen Dehui.The development and application of the operational ensemble prediction system at National Meteorological Center.J Appl Meteor Sci, 2002, 13(1): 1-15. doi:  10.3969/j.issn.1001-7313.2002.01.001
    [16]
    Shen Xueshun, Su Yong, Hu Jianglin, et al.Development and operation transformation of GRAPES global middle-range forecast system.J Appl Meteor Sci, 2017, 28(1): 1-10. doi:  10.11898/1001-7313.20170101
    [17]
    He Yanan, Gao Song, Xue Feng, et al.Design and implementation of intelligent grid forecasting platform based on MICAPS4.J Appl Meteor Sci, 2018, 29(1): 13-24. doi:  10.11898/1001-7313.20180102
    [18]
    Li Zechun, Bi Baogui, Jin Ronghua, et al.The development and application of the modern weather forecast in China for the recent 10 years.Acta Meteorologica Sinica, 2014, 72(6): 1069-1078. doi:  10.3969/j.issn.1004-4965.2014.06.007
    [19]
    Bauer P, Thorpe A, Brunet G.The quiet revolution of numerical weather prediction.Nature, 2015, 525(7567): 47-55. doi:  10.1038/nature14956
    [20]
    Goodfellow I, Bengio Y, Courville A.Deep Learning.Cambridge:MIT Press, 2016.
    [21]
    Jain A K.Data clustering: 50 years beyond k-means.Pattern Recognition Letters, 2009, 31(8): 651-666.
    [22]
    Yang J, Zhang D, Frangi A F, et al.Two-dimensional PCA:A new approach to appearance-based face representation and recognition.IEEE Transactions on Pattem Analysis and Machine Intelligence, 2004, 26(1): 131-137. doi:  10.1109/TPAMI.2004.1261097
    [23]
    Zhou Zhihua.Machine Learning.Beijing:Tsinghua University Press, 2016.
    [24]
    Hadji I, Wildes R P.What Do We Understand About Convolutional Networks?Preprint at https://arxiv.org/abs/1803.08834,2018:1-94.
    [25]
    Graves A.Supervised sequence labelling with recurrent neural networks.Studies in Computational Intelligence, 2012, 385: 1-131.
    [26]
    Goodfellow I, Pouget-Abadie J, Mirza M, et al.Generative Adversarial Nets//Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014: 2672-2680.
    [27]
    Qin Z, Yu F, Liu C, et al.How convolutional neural networks see the world-A survey of convolutional neural network visualization methods.Mathematical Foundations of Computing, 2018, 1(2): 149-180. doi:  10.3934/mfc.2018008
    [28]
    Pearl J, Mackenzie D.The Book of Why.London:Allen Lane, 2019.
    [29]
    Yosinski J, Clune J, Bengio Y, et al.How Transferable are Features in Deep Neural Networks?//Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014: 3320-3328.
    [30]
    Akhtar N M A.Threat of adversarial attacks on deep learning in computer vision:A Survey.IEEE Access, 2018, 6: 14410-14430. doi:  10.1109/ACCESS.2018.2807385
    [31]
    Feurer M, Klein A, Eggensperger K, et al.Efficient and robust automated machine learning.Advances in Neural Information Processing Systems, 2016, 28: 2944-2952.
    [32]
    Jin H, Song Q, Hu X.Auto-Keras: An Efficient Neural Architecture Search System//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019: 1946-1956.
    [33]
    Francois-Lavet V, Henderson P, Islam R, et al.An introduction to deep reinforcement learning.Foundations and Trends in Machine Learning, 2018, 11(3-4), DOI:  10.1561/2200000071.
    [34]
    Pedregosa F, Varoquaux G, Gramfort A, et al.Scikit-learn:Machine Learning in Python.Journal of Machine Learning Research, 2011, 12: 2825-2830.
    [35]
    Chollet F.Keras(2020-04-28)[2020-06-20].https://keras.io,2020.
    [36]
    Abadi M, Barham P, Chen Jianmin, et al.TensorFlow: A System for Large-scale Machine Learning//Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation, 2016: 265-283.
    [37]
    Paszke A, Gross S, Chintala S, et al.Automatic Differentiation in PyTorch//31st Conference on Neural Information Processing Systems, 2017: 1-4.
    [38]
    Yin S, Ouyang P, Tang S, et al.A high energy efficient reconfigurable hybrid neural network processor for deep learning applications.IEEE Journal of Solid-State Circuits, 2018, 53(4): 968-982. doi:  10.1109/JSSC.2017.2778281
    [39]
    Vazhkudai S, Supinski B R, Bland A S.The Design, Deployment, and Evaluation of the CORAL Pre-exascale Systems//The InternationalConference for High Performance Computing, Networking, Storage, and Analysis, 2018: 661-672.
    [40]
    Reichstein M, Camps-Valls G, Stevens B, et al.Deep learning and process understanding for data-driven earth system science.Nature, 2019, 566(7743): 195-204. doi:  10.1038/s41586-019-0912-1
    [41]
    Karpatne A, Watkins W, Read J, at al.Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling.Preprint at https://arxiv.org/abs/1710.11431v2,2017:1-11.
    [42]
    Karpatne A, Atluri G, Faghmous J, et al.Theory-guided data science:A new paradigm for scientific discovery from data.IEEE Transactions on Knowledge & Data Engineering, 2017, 29(10): 2318-2331.
    [43]
    Berry T, Harlim J.Correcting biased observation model error in data assimilation.Mon Wea Re, 2017, 145(7): 2833-2853. doi:  10.1175/MWR-D-16-0428.1
    [44]
    An Jie, Ma Jinwen.Automatic cloud segmentation based on the fully convolutional neural networks.Journal of Signal Processing, 2019, 35(4): 556-562.
    [45]
    Chang Nibin, Bai Kaixu, Chen Chifarn.Smart information reconstruction via time-space-spectrum continuum for cloud removal in satellite images.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(5): 1898-1912. doi:  10.1109/JSTARS.2015.2400636
    [46]
    Moosavi A, Attia A, Sandu A.A Machine Learning Approach to Adaptive Covariance Localization.Preprint at https://arxiv.org/abs/1801.00548,2018:1-24.
    [47]
    Cintra R, de Campos Velho H, Cocke S.Tracking the Model: Data Assimilation by Artificial Neural Network//2016 International Joint Conference on Neural Networks(IJCNN), 2016: 403-410.
    [48]
    Lee Y J, Hall D, Stewart J, et al.Machine learning for targeted assimilation of satellite data.Machine Learning and Knowledge Discovery in Databases, 2018, 11053: 53-68.
    [49]
    Scher S.Toward data-driven weather and climate forecasting approximating a simple general circulation model with deep learning.Geophys Res Lett, 2018, 45(22): 12616-12622. doi:  10.1029/2018GL080704
    [50]
    Brenowitz N D, Bretherton C S.Prognostic validation of a neural network unified physics parameterization.Geophys Res Lett, 2018, 45: 6289-6298. doi:  10.1029/2018GL078510
    [51]
    Pan B, Hsu K, AghaKouchak A, et al.Improving precipitation estimation using convolutional neural network.Water Resources Research, 2019, 55(3): 2301-2321. doi:  10.1029/2018WR024090
    [52]
    O'Gorman P A, Dwyer J G.Using machine learning to parameterize moist convection:Potential for modeling of climate, climate change, and extreme events.Journal of Advances in Modeling Earth Systems, 2018, 10(10): 2548-2563. doi:  10.1029/2018MS001351
    [53]
    Rasp S, Pritchard M S, Gentine P.Deep learning to represent subgrid processes in climate models.Proceedings of the National Academy of Sciences, 2018, 115(39): 9684-9689. doi:  10.1073/pnas.1810286115
    [54]
    Xu H, Zhang T, Luo Y, et al.Parameter calibration in global soil carbon models using surrogate-based optimization.Geoscientific Model Development, 2018, 11(7): 3027-3044. doi:  10.5194/gmd-11-3027-2018
    [55]
    Wu L, Zhang T, Qin Y, et al.An effective parameter optimization with radiation balance constraint in CAM5.Geophys Res Lett, 2020, 13: 41-53.
    [56]
    Burke A.Calibration of machine learning-based probabilistic hail predictions for operational forecasting.Bull Amer Meteor Soc, 2020, 35: 149-168.
    [57]
    Taillardat M.Calibrated ensemble forecasts using quantile regression forests and ensemble model output statistics.Mon Wea Rev, 2016, 144(6): 2375-2393. doi:  10.1175/MWR-D-15-0260.1
    [58]
    Rasp S, Lerch S.Neural networks for postprocessing ensemble weather forecasts.Mon Wea Rev, 2018, 146(11): 3885-3900. doi:  10.1175/MWR-D-18-0187.1
    [59]
    Scher S, Messori G.Predicting weather forecast uncertainty with machine learning.Quart J Roy Meteor Soc, 2018, 144(717): 2830-2841. doi:  10.1002/qj.3410
    [60]
    Sonderby C K, Espeholt L, Heek J, et al.MetNet: A Neural Weather Model for Precipitation Forecasting.Preprint at https://arxiv.org/abs/2003.12140,2020:1-17.
    [61]
    Ham Y G, Kim J H, Luo J J.Deep learning for multi-year ENSO forecasts.Nature, 2019, 573(7775): 568-572. doi:  10.1038/s41586-019-1559-7
    [62]
    Zhou K, Zheng Y, Li B, et al.Forecasting different types of convective weather:a deep learning approach.J Meteor Res, 2019, 33(5): 797-809. doi:  10.1007/s13351-019-8162-6
    [63]
    Kurth T, Treichler S, Romero J, et al.Exascale Deep Learning for Climate Analytics//Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, 2018: 1-12.
    [64]
    Rojek K.Machine learning method for energy reduction by utillzing dynamic mixed precision on GPU-based supercomputers.Concurrency and Computation:Practice and Experience, 2019, 31(6):e4644.1-e4644.12.
    [65]
    Manandhar S, Dev S, Lee Y H, et al.A data-driven approach for accurate rainfall prediction.IEEE Trans Geosci Remote Sens, 2019, 57(11): 9323-9331. doi:  10.1109/TGRS.2019.2926110
    [66]
    Gagne D, Haupt S, Nychka D, et al.Interpretable deep learning for spatial analysis of severe hailstorms.Mon Wea Rev, 2019, 147(8): 2827-2845. doi:  10.1175/MWR-D-18-0316.1
    [67]
    Karevan Z, Suykens J.Transductive LSTM for time-series prediction:An application to weather forecasting.Neural Networks, 2020, 125: 1-9. doi:  10.1016/j.neunet.2019.12.030
    [68]
    Qiu M, Zhao P, Zhang K, et al.A Short-term Rainfall Prediction Model Using Multi-task Convolutional Neural Networks//2017 IEEE International Conference on Data Mining, 2017: 395-404.
    [69]
    Yuan M, Ji X, Lu T, et al.A Novel Two-Factor Attention Encoder-Decoder Network through Combining Temporal and Prior Knowledge for Weather Forecasting//2019 International Joint Conference on Neural Networks, 2019: 1-8.
    [70]
    Prasetya E P, Djamal E C.Rainfall Forecasting for the Natural Disasters Preparation Using Recurrent Neural Networks//2019 International Conference on Electrical Engineering and Informatics, 2019: 52-57.
    [71]
    Tan C, Feng X, Long J, et al.FORECAST-CLSTM: A New Convolutional LSTM Network for Cloudage Nowcasting//2018 IEEE Visual Communications and Image Processing, 2018: 1-4.
  • 加载中
  • -->

Catalog

    Figures(3)  / Tables(1)

    Article views (6633) PDF downloads(970) Cited by()
    • Received : 2020-08-25
    • Accepted : 2020-11-02
    • Published : 2021-01-31

    /

    DownLoad:  Full-Size Img  PowerPoint