Hybrid Wavelet-SVM Method to Predict the Occurrence of Abnormal Waves

Document Type : Research Article

Authors

1 Ph.D. Student, Faculty of Marine Technology, Amirkabir University of Technology, Tehran, Iran

2 Associate Professor, Faculty of Marine Technology, Amirkabir University of Technology, Tehran, Iran

3 Professor, Faculty of Marine Technology, Amirkabir University of Technology, Tehran, Iran.

Abstract

Abnormal waves are extremely large and unusual which rarely occur, but cause serious damages. Various factors such as extreme storms, particular topography of the seabed, marine currents, wave-wave interaction with different wavelengths and frequencies may cause wave occurrence and transformation. The main objective of this study is to propose a new hybrid approach to predict the occurrence of abnormal waves using wavelet transform and support vector machines (SVM) classifier based on meteorological data. The data sets used in this paper are from two major hurricanes Dean 2007 and Irene 2011 at four locations namely, 41004 and41041 in the Gulf of Mexico. To predict the occurrence of abnormal waves, at the first extreme waves are detected using wavelet transform. The outputs of this method are considered as SVM classifier targets. Wavelet transform is applied on the significant wave height data samples. The abnormal waves are readily identified from the wavelet spectrum as an area of high energy. The inputs of SVM classifier models are historical metrological data, including: Wind direction (WDIR), Wind speed (WSPD), Sea level pressure (PRES), Air temperature (ATMP), and Sea surface temperature (WTMP). The experiment results show that the proposed method is able to predict the occurrence of extreme wave heights with height accuracy.

Keywords

References

Cherneva, Z., and Soares, C. (2014). “Time–frequency analysis of the sea state with the "Andrea" freak wave”, Nat. Hazards Earth Syst. Sci. 14: 3143–3150.
Chien, H., Kao, C. C., and Chuang, L. Z. H. (2002). “On the characteristics of observed coastal freak waves”, Coast. Eng. J. 44 (4): 302–319.
Clauss, G. (2000). “Dramas of the sea: episodic wave sand their impact on offshore structures”, Applied Ocean Research, 24: 147–161, 2000.
Dean, R. (1990). “Abnormal waves: a possible explanation”, Torum, A., Gudmestad, O. (Eds.), Water Wave Kinematics. Kluwer, NewYork, 609–612.
Didenkova, I. (2011). “Shapes of freak waves in the coastal zone of the Baltik Sea (TallinBay)”, Boreal Environ. Res., 16: 138–148.
Ewans, K., and Buchner, B. (2008). “Wavelet analysis of an extreme wave in a model basin”, In: Proceedings of the 27th International Conference on Offshore Mechanics and Arctic Technology, vol. 2: Structures, Safety and Reliability, Portugal. Paper No. OMAE 2008-57499: 455–464.
Haver, S. (2005). “Freak waves—a suggested definition and consequences for marine structures”, Rogue Waves 2004. IFREMER, Brest, France.
http://www .ndbc.noaa.gov
Huang, M. C. (2004). “Wave parameters and functions in wavelet analysis”, Ocean Eng. 31: 111–125.
Lavine, B.K., and  Blank, T.R., (2009). 3.18 - Feed-forward neural networks, in comprehensive chemometrics, Edited by Steven D. Brown, Romá Tauler and Beata Walczak, Elsevier, Oxford, 2009, Pages 571-586, ISBN 9780444527011, https://doi.org/10.1016/B978-044452701-1.00026-0.
Liu, P., and Mori, N. (2000). “Characterizing freak waves with wavelet transform analysis”, Rouge Waves 2000, Brest, France, 151–156.
Massel, S. (2001). “Wavelet analysis for processing of ocean surface records”, Ocean Eng. 28: 957–987.
Scholkopf, B., and Smola, AJ. (2002). “Learning with kernels”. Cambridge, MA: The MIT Press.
Scholkopf, B., Burges, C., and Smola, A. (1998). “Advances in kernel methods support vector learning”. MIT Press.
Scholkopf, B., Mika, C.J., Burges, P, Knirsch, RR., and Muller, K.G. (1999). “Input space versus feature space in kernel-based methods”, IEEE Trans Neural Network,10 (5):1000–1017.
Taylor, SJ. and Cristianini, N. (2004). “Kernel methods for pattern analysis”, Cambridge University
Tomita, H., and Kawamura, T. (2000). “Statistical analysis and inference from the in-situ data of the Sea of Japan with reference to abnormal and/or freak waves”, Proceedings of the 10th ISOPE Conference, Seattle, USA,  116–122.
Vapnik, VN. (2000). “The nature of statistical learning theory”, 2nd ed. NY (USA): Springer-Verlag; 2000, p. 131.
Veltcheva, A., and Guedes Soares, C. (2015). “Wavelet analysis of non-stationary sea waves during Hurricane Camille”, Ocean  Technology 95: 166–174.
 
 

Files

History

  • Receive Date: 04 August 2017
  • Revise Date: 30 December 2017
  • Accept Date: 31 December 2017

Share

How to cite

Statistics