Model Error Correction in Data Assimilation by Integrating Neural Networks

被引:13
|
作者
Zhu, Jiangcheng [1 ]
Hu, Shuang [2 ,3 ]
Arcucci, Rossella [3 ]
Xu, Chao [1 ]
Zhu, Jihong [2 ,3 ]
Guo, Yi-ke [3 ]
机构
[1] Zhejiang Univ, State Key Lab Ind Control Technol, Hangzhou 310027, Peoples R China
[2] Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China
[3] Imperial Coll London, Data Sci Inst, London SW7 2AZ, England
来源
BIG DATA MINING AND ANALYTICS | 2019年 / 2卷 / 02期
基金
英国工程与自然科学研究理事会;
关键词
data assimilation; deep learning; neural networks; Kalman filter; variational approach; ROUTINE;
D O I
10.26599/BDMA.2018.9020033
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we suggest a new methodology which combines Neural Networks (NN) into Data Assimilation (DA). Focusing on the structural model uncertainty, we propose a framework for integration NN with the physical models by DA algorithms, to improve both the assimilation process and the forecasting results. The NNs are iteratively trained as observational data is updated. The main DA models used here are the Kalman filter and the variational approaches. The effectiveness of the proposed algorithm is validated by examples and by a sensitivity study.
引用
收藏
页码:83 / 91
页数:9
相关论文
共 50 条
  • [1] Model Error Correction in Data Assimilation by Integrating Neural Networks
    Jiangcheng Zhu
    Shuang Hu
    Rossella Arcucci
    Chao Xu
    Jihong Zhu
    Yi-ke Guo
    Big Data Mining and Analytics, 2019, 2 (02) : 83 - 91
  • [2] Integrating Recurrent Neural Networks With Data Assimilation for Scalable Data-Driven State Estimation
    Penny, S. G.
    Smith, T. A.
    Chen, T-C
    Platt, J. A.
    Lin, H-Y
    Goodliff, M.
    Abarbanel, H. D., I
    JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS, 2022, 14 (03)
  • [3] Ocean data assimilation using intermittent analyses and continuous model error correction
    Huang, BH
    Kinter, JL
    Schopf, PS
    ADVANCES IN ATMOSPHERIC SCIENCES, 2002, 19 (06) : 965 - 992
  • [4] Ocean Data Assimilation Using Intermittent Analyses and Continuous Model Error Correction
    BohuaHuang
    JamesL.KinterIII
    PaulS.Schopf
    AdvancesinAtmosphericSciences, 2002, (06) : 965 - 992
  • [5] Ocean data assimilation using intermittent analyses and continuous model error correction
    Bohua Huang
    James L. Kinter
    Paul S. Schopf
    Advances in Atmospheric Sciences, 2002, 19 : 965 - 992
  • [6] Neural networks in auroral data assimilation
    Haerter, Fabricio P.
    Velho, Haroldo F. de Campos
    Rempel, Erico L.
    Chian, Abraham C. -L.
    JOURNAL OF ATMOSPHERIC AND SOLAR-TERRESTRIAL PHYSICS, 2008, 70 (10) : 1243 - 1250
  • [7] Dynamic neural networks with data assimilation
    van den Boogaard, H
    Mynett, A
    HYDROLOGICAL PROCESSES, 2004, 18 (10) : 1959 - 1966
  • [8] On model error in variational data assimilation
    Shutyaev, Victor
    Vidard, Arthur
    Le Dimet, Francois-Xavier
    Gejadze, Igor
    RUSSIAN JOURNAL OF NUMERICAL ANALYSIS AND MATHEMATICAL MODELLING, 2016, 31 (02) : 105 - 113
  • [9] On error correction in matrix neural networks
    Shipilina, LB
    JOURNAL OF COMPUTER AND SYSTEMS SCIENCES INTERNATIONAL, 1997, 36 (05) : 734 - 736
  • [10] Observation error covariance specification in dynamical systems for data assimilation using recurrent neural networks
    Sibo Cheng
    Mingming Qiu
    Neural Computing and Applications, 2022, 34 : 13149 - 13167