Abstract
Harmonic analysis, the traditional tidal forecasting method, cannot take into account the impact of noncyclical factors, and is also based on the BP neural network tidal prediction model which is easily limited by the amount of data. According to the movement of celestial bodies, and considering the insufficient tidal characteristics of historical data which are impacted by the nonperiodic weather, a tidal prediction method is designed based on support vector machine (SVM) to carry out the simulation experiment by using tidal data from Xiamen Tide Gauge, Luchaogang Tide Gauge and Weifang Tide Gauge individually. And the results show that the model satisfactorily carries out the tide prediction which is influenced by noncyclical factors. At the same time, it also proves that the proposed prediction method, which when compared with harmonic analysis method and the BP neural network method, has faster modeling speed, higher prediction precision and stronger generalization ability.
Similar content being viewed by others
References
Cartwright D E, Eddon A C. 1965. Corrected tables of tidal harmonics. Geophys J R astr oc, 33(2): 253–264
Chen Manchun, Chu Yingjie, Liu Kexiu, et al. 2006. Improved schemes of quasi-harmonic method for tide prediction of shallow water ports. Acta Oceanologica Sinica, 28(1): 9–17
Darwin G H. 1907. Ocean tides and Lunar disturbance of gravity. Scientific Papers I. Cambridge: Cambridge University Press
Doodson A T. 1921. The harmonic development of tidegenerating potential. Intern Hydrogr Rev, 31(1): 37–61
Doodson A T. 1982. The analysis of tidal observations. Phil. London: Tran Roy Soc, A227: 223–279
Li Qihua, Ji Haipeng, Zhang Gao. 2007. Study of tidal prediction of harbor baredon neural network. Journal of Guangzhou Mar Itime College (in Chinese), 15(1): 1–4
Mercer J. 1990. Functions of positive and negative type and their connection with the theory of integral equations. London: Philos Trans Roy Soc, A209: 415–446
Mukherjee S, Osuna E, Girosi F. 1997. Nonlinear prediction of chaotic time series using support vector machines. Amelia Island, FL: Proc Of IEEE NNSP’97
Mukherjee S, Osuna E, Girosi F. 1999. Nonlinear prediction of chaotic time series using support vector machines. NNSP’97: Neural Networks for Signal Processing: VII. Amelia Island, FL, USA: Proceedings of the IEEE Signal Processing Society Workshop, 511–520
Tay F E H, Cao L J. 2001. Application of Support Vector Machines in Financial Time Series Forecasting. Omega, 29(4): 309–317
Tsai C P, Lee T L. 2000. Back-Propagation neural Networkin tidal-level forecasting. Pro 22th Conf on Ocean Engineeringin, 147–153
Vapnik V N. 1995. The nature of statistical learning theory. New York: Springer
Wang Changhai. 1995. A model of the harmonic analysis of tides. Marine Forcasts, 12(4): 71–76
Xu Hanxing. 1982. Studies on prediction of shallowwater tides. Oceanologia et Limnologia Sinica, 13(3): 207–217
Zetler B D, Cummings R A. 1967. A harmonic method for predicting shallow-water tides. Journal of Marine Research USA, 25(1): 103–114
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: The Shanghai Committee of Science and Technology of China under contract No. 10510502800; the Graduate Student Education Innovation Program Foundation of Shanghai Municipal Education Commission of China; the National Key Science Foundation Research “973” Project of the Ministry of Science and Technology of China under contract No. 2012CB316200.
Rights and permissions
About this article
Cite this article
He, S., Zhou, W., Zhou, R. et al. Study of tide prediction method influenced by nonperiodic factors based on support vector machines. Acta Oceanol. Sin. 31, 160–164 (2012). https://doi.org/10.1007/s13131-012-0245-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13131-012-0245-5