Ultra Short-term Prediction of Pole Coordinates via Combination of Empirical Mode Decomposition and Neural Networks

Yu Lei; Danning Zhao; Hongbing Cai

doi:10.1515/arsa-2016-0013

Abstract

It was shown in the previous study that the increase of pole coordinates prediction error for about 100 days in the future is mostly caused by irregular short period oscillations. In this paper, the ultra short-term prediction of pole coordinates is studied for 10 days in the future by means of combination of empirical mode decomposition (EMD) and neural networks (NN), denoted EMD-NN. In the algorithm, EMD is employed as a low pass filter for eliminating high frequency signals from observed pole coordinates data. Then the annual and Chandler wobbles are removed a priori from pole coordinates data with high frequency signals eliminated. Finally, the radial basis function (RBF) networks are used to model and predict the residuals. The prediction performance of the EMD-NN approach is compared with that of the NN-only solution and the prediction methods and techniques involved in the Earth orientation parameters prediction comparison campaign (EOP PCC). The results show that the prediction accuracy of the EMD-NN algorithm is better than that of the NN-only solution and is also comparable with that of the other existing prediction method and techniques.

References

Chen, S., Cowan, C.F.N. and Grant, P.M. (1991). Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks. IEEE Transactions on Neural Networks, Vol. 2, No. 2, 302-309.
Search in Google Scholar Back to article
Flandrin, P., Rilling, G. and Goncalvés, P. (2004). Empirical Mode Decomposition as a Filter Bank, IEEE SIGNAL PROCESSING LETTERS, Vol. 11, No. 2, 112-114.
Search in Google Scholar Back to article
Gambis, D. and Luzum, B. (2011). Earth Rotation Monitoring, UT1 Determination and Prediction. Metrologia, Vol. 48, No. 4, 165-170.10.1088/0026-1394/48/4/S06
Search in Google Scholar Back to article
Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q., Yen, N.C., Tung, C.C. and Liu, H.H. (1998). The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-Stationary Time Series Analysis. Proceedings of the Royal Society London: A, Vol. 454, 903-995.10.1098/rspa.1998.0193
Search in Google Scholar Back to article
Huang, N.E., Wu, M.L., Qu, W., Long, S.R. and Shen, S.S.P.H. (2003). Application of Hilbert-huang Transform to Non-Stationary Financial Time Series Analysis. Applied Stochastic Models in Business and Industry, Vol. 19, No. 3, 245-268.
Search in Google Scholar Back to article
Kalarus, M., Kosek, W., Schuh, H. (2008). Summary of the Earth Orientation Parameters Prediction Comparison Campaign. EGU General Assembly 2008, EGU abstract: EGU2008-A-00595.
Search in Google Scholar Back to article
Kalarus, M., Schuh, H., Kosek, W., Akyilmaz, O. and Bizouard, Ch. (2010). Achievements of the Earth Orientation Parameters Prediction Comparison Campaign. Journal of Geodesy, Vol. 84, No. 10, 587-596.10.1007/s00190-010-0387-1
Search in Google Scholar Back to article
Kosek, W. (2011). Future Improvements in EOP Prediction. Geodesy for Plant Earth, International Association of Geodesy Symposia, Vol. 136, 513-520.
Search in Google Scholar Back to article
Kosek, W., Kalarus, M., Johnson, T.J., Wooden, W.H., McCarthy, D.D. and Popiński, W. (2005). A Comparison of LOD and UT1-UTC Forecasts by Different Combined Prediction Techniques. Artificial Satellites, Vol. 40, No. 2, 119-125.
Search in Google Scholar Back to article
Kurkova, V. (1992). Kolmogorov’s Theorem and Multilayer Neural Networks. Neural Networks, Vol. 5, No. 3, 501-506.10.1016/0893-6080(92)90012-8
Search in Google Scholar Back to article
Lei, Y., Zhao, D.N. and Cai, H.B. (2015). Extreme Learning Machines for the Predictions of Length of Day. Artificial Satellites, Vol. 50, No. 1, 19-33.10.1016/j.geog.2014.12.007
Search in Google Scholar Back to article
Liao, D.C., Wang, Q.J., Zhou, Y.H., Liao, X.H. and Huang, C. L. (2012). Long-term Prediction of the Earth Orientation Parameters by the Artificial Neural Network Technique. Journal of Geodynamics, Vol. 62, No. 8, 87-92.
Search in Google Scholar Back to article
Park, J. and Sandberg, I.W. (1991). Universal Approximation Using Radial-Basis-Function Networks. Neural Computing, Vol. 3, No. 2, 246-257.10.1162/neco.1991.3.2.24631167308
Search in Google Scholar Back to article
Schuh, H., Ulrich, M., Egger, D., Müller, J. and Schwegmann, W. (2002). Prediction of Earth Orientation Parameters by Artificial Neural Networks. Journal of Geodesy, Vol. 76, No. 5, 247-258.10.1007/s00190-001-0242-5
Search in Google Scholar Back to article
Wang, Q.J., Du, Y.N. and Liu, J. (2014). Introducing Atmospheric Angular Momentum into Prediction of Length of Day Change by Generalized Regression Neural Network Model. Journal of Central South University, Vol. 21, No. 4, 1396-1401.
Search in Google Scholar Back to article
Wang, Q.J., Liao, D.C. and Zhou, Y.H. (2008). Real-Time Rapid Prediction of Variations of Earth’s Rotational Rate. Chinese Science Bulletin, Vol. 53, No. 7, 969-973.
Search in Google Scholar Back to article
Xu, X.Q., Zotov, L. and Zhou, Y.H. (2012). Combined Prediction of Earth Orientation Parameters. China Satellite Navigation Conference (CSNC) 2012 Proceedings Lecture Notes in Electrical Engineering, Vol. 160, No. 2, 361-369.
Search in Google Scholar Back to article
Zhang, X.H., Wang, Q.J., Zhu, J.J. and Zhang, H. (2012). Application of General Regression Neural Network to the Prediction of LOD Change. Chinese Astronomy and Astrophysics, Vol. 36, No. 1, 86-96.
Search in Google Scholar Back to article

Ultra Short-term Prediction of Pole Coordinates via Combination of Empirical Mode Decomposition and Neural Networks

Abstract

Paradigm

My account