Journal Home > Volume 2 , Issue 2
Big Data Mining and Analytics 2019, 2(2): 83-91 https://doi.org/10.26599/BDMA.2018.9020033
Open Access | Issue | Published: 14 May 2019

Model Error Correction in Data Assimilation by Integrating Neural Networks

Show Author's Information Jiangcheng Zhu,  Shuang Hu,  Rossella Arcucci,  Chao Xu,  Jihong Zhu,  Yi-ke Guo( )
State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China.
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.
Data Science Institute, Imperial College London, London SW7 2AZ, UK.
Keywords:
deep learning, neural networks, data assimilation, Kalman filter, variational approach
Cite this article:
Zhu J, Hu S, Arcucci R, et al. Model Error Correction in Data Assimilation by Integrating Neural Networks. Big Data Mining and Analytics, 2019, 2(2): 83-91. https://doi.org/10.26599/BDMA.2018.9020033
Download citation
EndNote(RIS)
BibTeX

696

Views

64

Downloads

Citations

18

Crossref

11

WoS

14

Scopus

0

CSCD

Abstract Full text About this article

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.


menu
Abstract
Full text
Outline
About this article

Model Error Correction in Data Assimilation by Integrating Neural Networks

Show Author's information Jiangcheng Zhu, Shuang Hu, Rossella Arcucci, Chao Xu, Jihong Zhu, Yi-ke Guo( )
State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China.
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.
Data Science Institute, Imperial College London, London SW7 2AZ, UK.

Abstract

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.

Keywords: deep learning, neural networks, data assimilation, Kalman filter, variational approach

References(21)

[1]
E. Kalnay, Atmospheric Modeling, Data Assimilation and Predictability. Cambridge, MA, USA: Cambridge University Press, 2003.
DOI
[2]
J. Blum, F. X. De Dimet, and I. M. Navon, Data assimilation for geophysical fluids, in Hand-book of Numerical Analysis. Elsevier, 2005.
[3]
M. D’Elia, M. Perego, and A. Veneziani, A variational data assimilation procedure for the incompressible navier-stokes equations in hemodynamics, J. Sci. Comput., vol. 52, no. 2, pp. 340-359, 2012.
DOI Google Scholar
[4]
R. Potthast and P. B. Graben, Inverse problems in neural field theory, SIAM J. Appl. Dyn. Syst., vol. 8, no. 4, pp. 1405-1433, 2009.
DOI Google Scholar
[5]
R. E. Kalman, A new approach to linear filtering and prediction problems, Journal of Basic Engineering, vol. 82, no. 1, pp. 35-45, 1960.
DOI Google Scholar
[6]
D. Daescu and I. Navon, Sensitivity analysis in nonlinear variational data assimilation: Theoretical aspects and applications, in Advanced Numerical Methods for Complex Environmental Models: Needs and Availability, I. Farago, Z. Zlatev, eds. Sharjah, United Arab Emirates: Bentham Science Publishers, 2013.
[7]
D. Cacuci, I. Navon, and M. Ionescu-Bujor, Computational Methods for Data Evaluation and Assimilation. Boca Raton, FL, USA: CRC Press, 2013.
[8]
R. Arcucci, L. D’Amorea, J. Pistoia, R. Toumi, and A. Murli, On the variational data assimilation problem solving and sensitivity analysis, Journal of Computational Physics, vol. 335, pp. 311-326, 2017.
DOI Google Scholar
[9]
V. Babovic, M. Keijzer, and M. Bundzel, From global to local modelling: A case study in error correction of deterministic models, in Proceedings of the Fourth International Conference on Hydro Informatics, Iowa City, IA, USA, 2000.
[10]
V. Babovic, R. Caňizares, H. R. Jensen, and A. Klinting, Neural networks as routine for error updating of numerical models, Journal of Hydraulic Engineering, vol. 127, no. 3, pp. 181-193, 2001.
DOI Google Scholar
[11]
V. Babovic and D. R. Fuhrman, Data assimilation of local model error forecasts in a deterministic model, International Journal for Numerical Methods in Fluids, vol. 39, no. 10, pp. 887-918, 2002.
DOI Google Scholar
[12]
Y. Sun, V. Babovic, and E. S. Chan, Artificial neural networks as routine for error correction with an application in Singapore regional model, Ocean Dynamics, vol. 62, no. 5, pp. 661-669, 2012.
DOI Google Scholar
[13]
O. Makarynskyy, Improving wave predictions with artificial neural networks, Ocean Engineering, vol. 31, nos. 5&6, pp. 709-724, 2004.
DOI Google Scholar
[14]
D. I. Gopinath and G. Dwarakish, Wave prediction using neural networks at new Mangalore port along west coast of india, Aquatic Procedia, vol. 4, pp. 143-150, 2015.
DOI Google Scholar
[15]
P. Jain and M. Deo, Artificial intelligence tools to forecast ocean waves in real time, Open Ocean Engineering Journal, vol. 1, pp. 13-20, 2008.
DOI Google Scholar
[16]
A.-S. Chen and M. T. Leung, Regression neural network for error correction in foreign exchange forecasting and trading, Computers & Operations Research, vol. 31, no. 7, pp. 1049-1068, 2004.
DOI Google Scholar
[17]
M. Gevreya, I. Dimopoulosb, and S. Leka, Review and comparison of methods to study the contribution of variables in artificial neural network models, Ecological Modelling, vol. 160, no. 3, pp. 249-264, 2003.
DOI Google Scholar
[18]
Y. W. Foo, C. Goh, and Y. Li, Machine learning with sensitivity analysis to determine key factors contributing to energy consumption in cloud data centers, in 2016 International Conference on Cloud Computing Research and Innovations (ICCCRI), 2016, pp. 107-113.
DOI
[19]
N. Nichols, Mathematical concepts of data assimilation, in Data Assimilation, W. Lahoz, B. Khattatov, and R. Menard, eds. Springer, 2010.
[20]
E. N. Lorenz, Deterministric nonperiodic flow, in the Theory of Chaotic Attractors, B. R. Hunt, T. Li, J. A. Kennedy, H. E. Nusse, eds. Springer, 2004.
[21]
A. S. Lawless, Data assimiliation with the Lorenz equations, University of Reading, UK, 2002.
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 05 July 2018
Accepted: 19 September 2018
Published: 14 May 2019
Issue date: June 2019

Copyright

© The author(s) 2019

Acknowledgements

This work was supported by the EPSRC Grand Challenge grant "Managing Air for Green Inner Cities" (MAGIC) EP/N010221/1.

Rights and permissions

Return