The Use Support Vector Machine and Back Propagation Neural Network for Prediction of Daily Tidal Levels along the Jeddah Coast, Saudi Arabia

Authors: E. A. Mlybari, M. S. Elbisy, A. H. Alshahri, O. M. Albarakati

Abstract:

Sea level rise threatens to increase the impact of future  storms and hurricanes on coastal communities. Accurate sea level  change prediction and supplement is an important task in determining  constructions and human activities in coastal and oceanic areas. In  this study, support vector machines (SVM) is proposed to predict  daily tidal levels along the Jeddah Coast, Saudi Arabia. The optimal  parameter values of kernel function are determined using a genetic  algorithm. The SVM results are compared with the field data and  with back propagation (BP). Among the models, the SVM is superior  to BPNN and has better generalization performance.

 

Keywords: Tides, Prediction, Support Vector Machines, Genetic Algorithm, Back-Propagation Neural Network, Risk, Hazards.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1336214

References:

[1] G. H. Darwin, "On an apparatus for facilitating the reduction of tidal observations,” Proc. R. Soc. (London) Ser. A 52, 1892, pp. 345–376.
[2] A. T. Doodson, 1958 "The analysis and predictions of tides in shallow water,” Int. Hydrogr. Rev., Monaco, vol. 33, pp. 85–126, 1958.
[3] R. E. Kalman, 1960 "A new approach to linear filtering and prediction problems” Trans. ASME, J. Basic Eng., vol. 82, no. 2, pp. 35–45, 1960.
[4] K. Mizumura, "Application of Kalman filtering to ocean data,” J Waterway, Port, Coastal Ocean Eng., ASCE, vol. l10, no. 3, pp. 334–43, 1984.
[5] P. H.Yen, C. D.Jan, Y. P. Lee, and H. F. Lee, "Application of Kalman filter to short-term tide level prediction,” Journal of Waterway; Port; Coastal and Ocean Engineering; ASCE, vol. 122 no. 5, pp. 226–231, 1996.
[6] M. Vaziri, "Predicting Caspian Sea surface water level by ANN and ARIMA models. Journal of Waterway, Port, Coastal and Ocean Engineering, vol. 123, pp. 158–162, 1997.
[7] M. C. Deo, A. Jha, A. S. Chaphekar, and K. Ravicant "Neural networks for wave forecasting,” Ocean Engineering, vol. 26, pp. 191–303, 2001.
[8] Tsai, C.P., and Lee, T.L., "Back-propagation neural network in tidal level forecasting,” Journal of Waterway, Port, Coastal and Ocean Engineering, ASCE, vol. 12, no.4, pp. 195–202, 1999.
[9] T. L. Lee, and D. S. Jeng, "Application of artificial neural networks in tide forecasting,” Ocean Eng., vol. 29, no. 9, pp. 1003–1022, 2002.
[10] T. L. Lee, C. P. Tsai, D. S. Jeng, and R. J. Shieh, "Neural network for prediction and supplement of tidal record in Taichung harbor,” Taiwan. Adv. Eng. Softw. vol. 33, pp. 329–338, 2002.
[11] T. L. Lee, "Back-propagation neural network for long-term tidal predictions,” Ocean Eng., vol. 31, pp. 225–238, 2004.
[12] C. Steidley, A. Sadovski, P. Tissot, R. Bachnak, and Z. Bowles, "Using an artificial neural network to improve predictions of water levels where tide charts fail,” Innovations in Applied Artificial Intelligence, vol. 35, pp. 599–608, 2005.
[13] S. Rajasekaran, K. Thiruvenkatasamy and T. L. Lee, "Tidal level forecasting using functional and sequential learning neural networks,” Applied Mathematical Modelling, vol. 30, no. 1, pp. 85–103, 2005.
[14] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagation errors,” Nature, vol. 323, pp. 533- 536, 1986.
[15] M. S. El-Bisy, "Longshore current prediction with neural networks,” Ain Shams Univ, Eng. Bulletin, vol. 40, no. 4, pp. 489-503, 2005.
[16] A. J. Smola, Learning with kernels. Ph.D. dissertation, GMD, Birlinghoven, Germany, 1998.
[17] V. Cherkassky, and Y. Ma "Practical selection of SVM parameters and noise estimation for SVM regression,” Neural Network, vol. 17, pp.113- 126, 2004.
[18] P. S. Yu, S. T. Chen, and I. F. Chang, "Support vector regression for real-time flood stage forecasting,” J. Hydrology, vol. 328, pp. 704–716, 2006.
[19] U. Thissen, , R. Van Brakel, , A. P. De Weijer, , W. J. Melssen, and L .M. C. Buydens, " Using support vector machines for time series prediction,” Chemom. Intell. Lab. Syst., vol. 69, pp. 35–49, 2003.