Extreme learning machine for the predictions of length of day

• Autorzy: Lei Y. , Zhao D. , Cai H.

Identyfikatory

DOI

10.1515/arsa-2015-0002

• Języki publikacji: EN

Abstrakty

EN

This work presents short- and medium-term predictions of length of day (LOD) up to 500 days by means of extreme learning machine (ELM). The EOP C04 time-series with daily values from the International Earth Rotation and Reference Systems Service (IERS) serve as the data basis. The influences of the solid Earth and ocean tides and seasonal atmospheric variations are removed from the C04 series. The residuals are used for training of the ELM. The results of the prediction are compared with those from other prediction methods. The accuracy of the prediction is equal to or even better than that by other approaches. The most striking advantages of employing ELM instead of other algorithms are its noticeably reduced complexity and high computational efficiency.

Słowa kluczowe

EN

Earth orientation parameters; EOP; length of day; LOD; predictions; artificial neural networks; ANN; extreme learning machine; ELM

• Wydawca: Centrum Badań Kosmicznych PAN ; De Gruyter
• Czasopismo: Artificial Satellites : Journal of Planetary Geodesy
• Rocznik: 2015
• Tom: Vol. 50, No. 1
• Strony: 19--33
• Opis fizyczny: Bibliogr. 15 poz., tab., wykr.

Twórcy

autor

Lei Y.

• National Time Service Center, Chinese Academy of Sciences, Xi’an 710600, China
• Key Laboratory of Primary Time and Frequency Standards, Chinese Academy of Sciences, Xi’an 710600, China
• University of Chinese Academy of Sciences, Beijing 100049, China

autor

Zhao D.

• National Time Service Center, Chinese Academy of Sciences, Xi’an 710600, China
• University of Chinese Academy of Sciences, Beijing 100049, China

autor

Cai H.

• National Time Service Center, Chinese Academy of Sciences, Xi’an 710600, China
• Key Laboratory of Primary Time and Frequency Standards, Chinese Academy of Sciences, Xi’an 710600, China

Bibliografia

• Akyilmaz O., Kutterer H. (2004) Prediction of Earth rotation parameters by fuzzy inference systems. Journal of Geodesy, Vol. 78, No. 1-2, 2004, pp. 82-93.
• Akyilmaz O., Kutterer H., Shum CK. and Ayan T. (2011) Fuzzy-wavelet based prediction of Earth rotation parameters. Applied Soft Computing, Vol. 11, No. 1, 2011, pp. 837-841.
• Gross RS., Marcus SL., Eubanks TM., Dickey JO. and Keppenne CL. (1996) Detection of an ENSO signal in seasonal length-of-day variations. Geophysical Research Letters, Vol. 23, No. 23, 1996, pp. 3373-3376.
• Gross RS., Eubanks TM., Steppe JA., Freedman AP., Dickey JO. and Runge TF. (1998) A Kalman-filter-based approach to combining independent Earth-orientation series. Journal of Geodesy, Vol. 72, No. 4, 1998, pp. 215-235.
• Huang GB., Zhu QY. and Siew CK. (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. Proceedings of 2004 IEEE International Joint Conference on Neural Networks, Budapest, Hungary, pp. 985-990.
• Huang GB., Zhu QY. and Siew CK. (2006) Extreme learning machine: theory and applications, Neurocomputing, Vol. 70, No. 1-3, 2006, pp. 489-501.
• Johnson T., Luzum BJ., Ray JR. (2005) Improved near-term Earth rotation predictions using atmospheric angular momentum analysis and forecasts. Journal of Geodynamics, Vol. 39, No. 3, 2005, pp. 209-221.
• Kalarus M., Schuh H., Kosek W., et al. (2010) Achievements of the Earth orientation parameters prediction comparison campaign. Journal of Geodesy, Vol. 84, No. 10, 2010, pp. 587-596.
• Kosek W., McCarthy DD. and Luzum BJ. (1998) Possible improvement of Earth orientation forecast using autocovariance prediction procedures. Journal of Geodesy, Vol. 72, No. 4, 1998, pp. 189-199.
• Malkin Z., Skurikhina E. (1996) On prediction of EOP, Communications of IAA, No. 93.
• Niedzielski T., Kosek W. (2008) Prediction of UT1-UTC, LOD and AAM by combination of least-squares and multivariate stochastic methods. Journal of Geodesy, Vol. 82, No. 2, 2008, pp. 83-92.
• Petit G., Luzum B. (2010) IERS Conventions (2010). Verlag des Bundesamts für Kartographie und Geodasie, Frankfurt am Main, pp. 123-131.
• 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, 2002, pp. 247-258.
• Xu XQ., Zotov L. and Zhou YH. (2012) Combined prediction of Earth orientation parameters. Chinese Satellite Navigation Conference (CSNC) 2012 Proceedings, Lecture Notes in Electrical Engineering 160, pp. 361-369.
• Zhang XH., Wang QJ., Zhu JJ. and Zhang H. (2012) Application of general regression neural network to the prediction of LOD change. Chinese Astronomy and Astrophysics, Vol. 36, No. 1, 2012, pp. 86-96.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).