Prediction of Significant Wave Height Using Neural Network in the Java Sea (North of Surabaya)

Abstract:

Indonesia is an archipelago, Surabaya is the second crowded city in Indonesia. So the shipping lane and the city is comparable. Neural network is models inspired by biological neural networks and used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. Neural network is used to predict the wave height in Java Sea (The North of Surabaya). The Root Mean Square Error average for the next one hour is 0.03 and the Root Mean Square Error average for the next six hours is 0.09. That’s mean the longest the prediction, the biggest Root Mean Square error.

• Periodical: Applied Mechanics and Materials (Volume 862)
• Pages: 72-77
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.862.72
• Online since: January 2017
• Authors: Wimala L. Dhanistha*, R.A. Atmoko, P. Juniarko, Ridho Akbar
• Keywords: Neural Network, Significant Wave Height, Wind Speed

References

[1] Agrawal, J. Wave parameter estimation using neural networks. Marine Structures. (2004). 536–550.

DOI: 10.1016/j.marstruc.2005.01.001

[2] Ainsworth, T. Significant Wave Height, A closer look at wave forecasts. (2011).

[3] Akhir, B. Lintasan Gelombang Laut Menuju Pelabuhan Pulau Baai Bengkulu. rekayasa sipil . (2011). 47-60.

DOI: 10.25077/jrs.7.2.47-60.2011

[4] Bhattacharya, B. Neural Networks In Reconstructing Missing Wave Data In Sedimentation Modelling. Proceedings of the XXXth IAHR Congress . (2003).

[5] Deo, M. Real time wave forecasting using neural networks. 191-203.

[6] Etemad-Shahidi, A. On The Prediction of Wave Parameters Using Simplified Methods. Coastal Research. (2009). 505-509.

[7] Jain, P. Artificial Intelligence Tools to Forecast Ocean Waves in Real Time. The Open Ocean Engineering Journal . (2008). 13-20.

DOI: 10.2174/1874835x00801010013

[8] Makarynskyy, O. Predicting sea level variations with artificial neural networks at Hillarys Boat Harbour, Western Australia. Estuarine, Coastal and Shelf Science . (2004). 351–360.

DOI: 10.1016/j.ecss.2004.06.004

[9] Mandal, S. Ocean Wave Prediction Using Numerical and Neural Network Models. The Open Ocean Engineering Journal . (2010). 12-17.

DOI: 10.2174/1874835x01003010012

[10] Muhammad Umer Farooq, L. X. High Level Fault Modeling and Fault Propagation in Analog Circuits using NLARX Automated Model Generation Technique. 4th International Conference on Intelligent and Advanced Systems . (2012). 846-850.

DOI: 10.1109/icias.2012.6306132

[11] N, R. A, Variabilitas Gelombang Laut Di Laut Jawa Dan Selat Karimata Ditinjau Dari Perspektif Dinamika Meteorologi, FMIPA UNIVERSITAS INDONESIA, (2012).

DOI: 10.46824/megasains.v12i2.82

[12] naydın, K. G, The estimation of monthly mean significant wave heights by using artificial neural network and regression methods. Ocean Engineering , (2008) 1406–1415.

DOI: 10.1016/j.oceaneng.2008.07.008

[13] P.S. Srivastava, A comparative Study of Wave Forecasting Techniques. applied meteorology , (1963) 206-207.

[14] Paplinska-Swerpel, B, Application of Neural Networks to the Prediction of Significant Wave Height at Selected Locations on the Baltic Sea. Hydro-Engineering and Environmental Mechanics , (2006) 183–201.

[15] Paras, S. M, A Feature Based Neural Network Model for Weather Forecasting. World Academy of Science, Engineering and Technology , (2007) 66-73.

[16] Ramesh Kumar. P, a. B. (2013). The Forward Kinematic Modeling of a Stewart Platform using NLARX Model with Wavelet Network. IEEE (2013) 343-348.

DOI: 10.1109/indin.2013.6622907

[17] Sugianto, D. N, Model Distribusi Data Kecepatan Angin dan Pemanfaatannya dalam Peramalan Gelombang di Perairan Laut Paciran, Jawa Timur, ILMU KELAUTAN , (2010) 143-152.

[18] Triatmodjo, B, Teknik Pantai, Yogyakarta, (1999).

[19] Sutojo, T. (2010), Kecerdasan Buatan, Yogyakarta, (2010).

[20] Hermawan, A, Jaringan Syaraf Tiruan, Yogyakarta, (2006).

[21] BMKG Perak II Surabaya.