Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction

Moussa Sobh Elbisy; Faisal Abdulrahman Osra

doi:doi:10.11648/j.ajnna.20190502.12

| Peer-Reviewed

Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction

Moussa Sobh Elbisy, Faisal Abdulrahman Osra

Published in American Journal of Neural Networks and Applications (Volume 5, Issue 2)

Received: 5 October 2019 Accepted: 22 October 2019 Published: 28 October 2019

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

The estimation of wave parameters is of great importance in coastal activities such as design studies for harbor, inshore and offshore structures, coastal erosion, sediment transport, and wave energy estimation. For this purpose, several models and approaches have been proposed to predict wave parameters, such as empirical, numerical-based approaches, and soft computing. In this study, the group method of data handling type neural network (GMDH-NN) was presented for significant wave height prediction in an attempt to suggest a new model with superior explanatory power and stability. The GMDH-NN results were compared with the field data and with a multilayer perceptron neural networks (MLPNN) model. The results indicate that the prediction accuracy and avoidance of over-fitting of the GMDH-NN method were superior to those of the MLPNN method. The percentage improvement in the root mean square error and the mean absolute percentage error of the GMDH-NN model over the MLPNN model were 72.92% and 81.02%, respectively. Also, according to the indices, the GMDH-NN model performs the best for predicting the Hs of all of the wave height ranges. That is, the GMDH-NN model is capable of predicting wave heights for different ranges. The results of the analysis suggest that the GMDH-NN-based modeling is effective in predicting significant wave height.

Published in	American Journal of Neural Networks and Applications (Volume 5, Issue 2)
DOI	10.11648/j.ajnna.20190502.12
Page(s)	51-57
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2019. Published by Science Publishing Group

Keywords

Significant Wave Height, Prediction, Group Method of Data Handling, Multilayer Perceptron

References

[1]	Deo, M. C., and Naidu, C. S. (1999). “Real time wave forecasting using neural networks.” Ocean Engineering, Vol. 26, pp. 191-203.
[2]	Deo, M. C.; Jha, A., Chaphekar, A. S., and Ravikant, K. (2001). “Neural networks for wave forecasting.” Ocean Engineering, Vol. 28, pp. 889–898.
[3]	Agrawal, J. D. and Deo, M. C. (2002). “On-line wave prediction.” Marine Structures, Vol. 15, pp. 57–74.
[4]	Tsai, C. P., Lin, C., and Shen, J. N. (2002). “Neural network for wave forecasting among multi-stations.” Ocean Engineering, Vol. 29, pp. 1683-1695.
[5]	Makarynskyy, O. (2004). “Improving wave predictions with artificial neural networks.” Ocean Engineering, Vol. 31, No. 5–6, pp. 709–724.
[6]	Makarynskyy, O., Pires-Silva, A. A., Makarynska, D., and Ventura-Soares, C. (2005). “Artificial neural networks in wave predictions at the west coast of Portugal.” Comput. Geosci., Vol. 31, No. 4, pp. 415–424.
[7]	Mandal, S., and Prabaharan, N. (2006). “Ocean wave forecasting using recurrent neural networks.” Ocean Engineering, Vol. 33, pp. 1401–1410.
[8]	Mahjoobi, J., Etemad-Shahidi, A., and Kazeminezhad, M. H. (2008). “Hindcasting of wave parameters using different soft computing methods.” Applied Ocean Research, Vol. 30, pp. 28–36.
[9]	Günaydın, K. (2008). “The estimation of monthly mean significant wave heights by using artificial neural network and regression methods.” Ocean Engineering, Vol. 35, pp. 1406–1415.
[10]	Elbisy, M. S. (2015). “Sea wave parameters prediction by support vector machine using a genetic algorithm.” Journal of Coastal Research, Vol. 31, No. 4, pp. 892-899.
[11]	Malekmohamadi, I., Ghiassia, R., and Yazdanpanah, M. J. (2008). “Wave hindcasting by coupling numerical model and artiﬁcial neural networks.” Ocean Engineering, Vol. 35, pp. 417–425
[12]	Londhe, S. N., and Panchang, V. (2016). “One-day wave forecasts based on artiﬁcial neural networks.” J. Atmos. Oceanic Tech- nol., Vol. 23, pp. 1593–1603.
[13]	Deshmukh, A. N., Deo, M. C., Bhaskaran, P. K., Balakrishnan Nair, T. M., and Sandhya K. G., (2016). “Neural-network-based data assimilation to improve numerical ocean wave forecast.” IEEE J. Oceanic Eng., Vol. 41, pp. 944–953.
[14]	Sadeghifar, T., Motlagh, M. N., Azad, M. T., and Mahdizadeh, M. M. (2017). “Coastal wave height prediction using Recurrent Neural Networks (RNNs) in the South Caspian Sea.” Marine Geodesy, Vol. 40, No. 2, pp. 454-465.
[15]	Elgohary, T., Elbisy, M. S., Mobasher, A. M., and Salah, H. (2018). “Deep wave height prediction for Alexandria sea region by using nonlinear regression method compared to support vector machines.” Current Development in Oceanography, Vol. 10, No. 1, pp. 1-14.
[16]	Haykin, S. (1999). “Neural networks: A comprehensive foundation.” New Jersey, NJ: Prentice Hall.
[17]	Garg, V. (2014). “Inductive group method of data handling neural network approach to model basin sediment yield.” J Hydrol Eng, Vol. 20, No. 6, C6014002.
[18]	Kalantary, F., Ardalan, H, and Nariman-Zadeh, N. (2009). “An investigation on the Su–NSPT correlation using GMDH type neural networks and genetic algorithms.” Eng Geol, Vol. 104, No. 1–2, pp. 44–55.
[19]	Amanifard, N., Nariman-Zadeh, N., Farahani, M. H., and Khalkhali, A. (2008). “Modeling of multiple short-length-scale stall cells in an axial compressor using evolved GMDH neural networks,” Energy Conversion and Management, vol. 49, No. 10, pp. 2588–94.
[20]	Nariman-Zadeh, N., Darvizeh, A., Felezi, M. E., and Gharababaei, H. (2002). “Polynomial modelling of explosive compaction process of metallic powders using GMDH-type neural networks and singular value composition.” Model. Simul. Mater. Sci. Eng., Vol. 10, No. 6, pp. 727-744.
[21]	Comola, F., Lykke Andersen, T., Martinelli, L., Burcharth, H. F., and Ruol, P.(2014). “Damage pattern and damage progression on breakwater roundheads under multidirectional waves.” Coastal Engineering, Vol. 83, pp. 24–35.
[22]	Kim, S. W., and Suh, K. D. (2014). “Determining the stability of vertical breakwaters against sliding based on individual sliding distances during a storm.” Coastal Engineering, Vol. 94, pp. 90–101.

Cite This Article

Plain Text BibTeX RIS

APA Style

Moussa Sobh Elbisy, Faisal Abdulrahman Osra. (2019). Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction. American Journal of Neural Networks and Applications, 5(2), 51-57. https://doi.org/10.11648/j.ajnna.20190502.12

Copy | Download

ACS Style

Moussa Sobh Elbisy; Faisal Abdulrahman Osra. Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction. Am. J. Neural Netw. Appl. 2019, 5(2), 51-57. doi: 10.11648/j.ajnna.20190502.12

Copy | Download

AMA Style

Moussa Sobh Elbisy, Faisal Abdulrahman Osra. Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction. Am J Neural Netw Appl. 2019;5(2):51-57. doi: 10.11648/j.ajnna.20190502.12

Copy | Download

@article{10.11648/j.ajnna.20190502.12,
  author = {Moussa Sobh Elbisy and Faisal Abdulrahman Osra},
  title = {Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction},
  journal = {American Journal of Neural Networks and Applications},
  volume = {5},
  number = {2},
  pages = {51-57},
  doi = {10.11648/j.ajnna.20190502.12},
  url = {https://doi.org/10.11648/j.ajnna.20190502.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20190502.12},
  abstract = {The estimation of wave parameters is of great importance in coastal activities such as design studies for harbor, inshore and offshore structures, coastal erosion, sediment transport, and wave energy estimation. For this purpose, several models and approaches have been proposed to predict wave parameters, such as empirical, numerical-based approaches, and soft computing. In this study, the group method of data handling type neural network (GMDH-NN) was presented for significant wave height prediction in an attempt to suggest a new model with superior explanatory power and stability. The GMDH-NN results were compared with the field data and with a multilayer perceptron neural networks (MLPNN) model. The results indicate that the prediction accuracy and avoidance of over-fitting of the GMDH-NN method were superior to those of the MLPNN method. The percentage improvement in the root mean square error and the mean absolute percentage error of the GMDH-NN model over the MLPNN model were 72.92% and 81.02%, respectively. Also, according to the indices, the GMDH-NN model performs the best for predicting the Hs of all of the wave height ranges. That is, the GMDH-NN model is capable of predicting wave heights for different ranges. The results of the analysis suggest that the GMDH-NN-based modeling is effective in predicting significant wave height.},
 year = {2019}
}

Copy | Download

TY  - JOUR
T1  - Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction
AU  - Moussa Sobh Elbisy
AU  - Faisal Abdulrahman Osra
Y1  - 2019/10/28
PY  - 2019
N1  - https://doi.org/10.11648/j.ajnna.20190502.12
DO  - 10.11648/j.ajnna.20190502.12
T2  - American Journal of Neural Networks and Applications
JF  - American Journal of Neural Networks and Applications
JO  - American Journal of Neural Networks and Applications
SP  - 51
EP  - 57
PB  - Science Publishing Group
SN  - 2469-7419
UR  - https://doi.org/10.11648/j.ajnna.20190502.12
AB  - The estimation of wave parameters is of great importance in coastal activities such as design studies for harbor, inshore and offshore structures, coastal erosion, sediment transport, and wave energy estimation. For this purpose, several models and approaches have been proposed to predict wave parameters, such as empirical, numerical-based approaches, and soft computing. In this study, the group method of data handling type neural network (GMDH-NN) was presented for significant wave height prediction in an attempt to suggest a new model with superior explanatory power and stability. The GMDH-NN results were compared with the field data and with a multilayer perceptron neural networks (MLPNN) model. The results indicate that the prediction accuracy and avoidance of over-fitting of the GMDH-NN method were superior to those of the MLPNN method. The percentage improvement in the root mean square error and the mean absolute percentage error of the GMDH-NN model over the MLPNN model were 72.92% and 81.02%, respectively. Also, according to the indices, the GMDH-NN model performs the best for predicting the Hs of all of the wave height ranges. That is, the GMDH-NN model is capable of predicting wave heights for different ranges. The results of the analysis suggest that the GMDH-NN-based modeling is effective in predicting significant wave height.
VL  - 5
IS  - 2
ER  -

Copy | Download

Author Information

Moussa Sobh Elbisy

Civil Engineering Department, Umm Al Qura University, Makkah, Saudi Arabia
Faisal Abdulrahman Osra

Civil Engineering Department, Umm Al Qura University, Makkah, Saudi Arabia

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Moussa Sobh Elbisy, Faisal Abdulrahman Osra. (2019). Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction. American Journal of Neural Networks and Applications, 5(2), 51-57. https://doi.org/10.11648/j.ajnna.20190502.12

Copy | Download

ACS Style

Moussa Sobh Elbisy; Faisal Abdulrahman Osra. Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction. Am. J. Neural Netw. Appl. 2019, 5(2), 51-57. doi: 10.11648/j.ajnna.20190502.12

Copy | Download

AMA Style

Moussa Sobh Elbisy, Faisal Abdulrahman Osra. Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction. Am J Neural Netw Appl. 2019;5(2):51-57. doi: 10.11648/j.ajnna.20190502.12

Copy | Download

@article{10.11648/j.ajnna.20190502.12,
  author = {Moussa Sobh Elbisy and Faisal Abdulrahman Osra},
  title = {Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction},
  journal = {American Journal of Neural Networks and Applications},
  volume = {5},
  number = {2},
  pages = {51-57},
  doi = {10.11648/j.ajnna.20190502.12},
  url = {https://doi.org/10.11648/j.ajnna.20190502.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20190502.12},
  abstract = {The estimation of wave parameters is of great importance in coastal activities such as design studies for harbor, inshore and offshore structures, coastal erosion, sediment transport, and wave energy estimation. For this purpose, several models and approaches have been proposed to predict wave parameters, such as empirical, numerical-based approaches, and soft computing. In this study, the group method of data handling type neural network (GMDH-NN) was presented for significant wave height prediction in an attempt to suggest a new model with superior explanatory power and stability. The GMDH-NN results were compared with the field data and with a multilayer perceptron neural networks (MLPNN) model. The results indicate that the prediction accuracy and avoidance of over-fitting of the GMDH-NN method were superior to those of the MLPNN method. The percentage improvement in the root mean square error and the mean absolute percentage error of the GMDH-NN model over the MLPNN model were 72.92% and 81.02%, respectively. Also, according to the indices, the GMDH-NN model performs the best for predicting the Hs of all of the wave height ranges. That is, the GMDH-NN model is capable of predicting wave heights for different ranges. The results of the analysis suggest that the GMDH-NN-based modeling is effective in predicting significant wave height.},
 year = {2019}
}

Copy | Download

TY  - JOUR
T1  - Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction
AU  - Moussa Sobh Elbisy
AU  - Faisal Abdulrahman Osra
Y1  - 2019/10/28
PY  - 2019
N1  - https://doi.org/10.11648/j.ajnna.20190502.12
DO  - 10.11648/j.ajnna.20190502.12
T2  - American Journal of Neural Networks and Applications
JF  - American Journal of Neural Networks and Applications
JO  - American Journal of Neural Networks and Applications
SP  - 51
EP  - 57
PB  - Science Publishing Group
SN  - 2469-7419
UR  - https://doi.org/10.11648/j.ajnna.20190502.12
AB  - The estimation of wave parameters is of great importance in coastal activities such as design studies for harbor, inshore and offshore structures, coastal erosion, sediment transport, and wave energy estimation. For this purpose, several models and approaches have been proposed to predict wave parameters, such as empirical, numerical-based approaches, and soft computing. In this study, the group method of data handling type neural network (GMDH-NN) was presented for significant wave height prediction in an attempt to suggest a new model with superior explanatory power and stability. The GMDH-NN results were compared with the field data and with a multilayer perceptron neural networks (MLPNN) model. The results indicate that the prediction accuracy and avoidance of over-fitting of the GMDH-NN method were superior to those of the MLPNN method. The percentage improvement in the root mean square error and the mean absolute percentage error of the GMDH-NN model over the MLPNN model were 72.92% and 81.02%, respectively. Also, according to the indices, the GMDH-NN model performs the best for predicting the Hs of all of the wave height ranges. That is, the GMDH-NN model is capable of predicting wave heights for different ranges. The results of the analysis suggest that the GMDH-NN-based modeling is effective in predicting significant wave height.
VL  - 5
IS  - 2
ER  -

Copy | Download