Environmental Assessment and Improvement of The Analysis of Forces on Marine Structures and Sediment Transfer Using Estimation of the Height of the Sea Index Wave with the Help of Artificial Intelligence

Subject Areas : Natural resources and environmental hazards

AMIR VAKILI ¹ , Roozbeh Aghamajidi ² , Mohammad Hossein Ahmadi ³

1 - Department of Civil Engineering, Beyza Branch, Islamic Azad University, Beyza, Iran
2 - Department of Civil Engineering, Sepidan Branch, Islamic Azad University, Sepidan, Iran
3 - Department of Civil Engineering, Beyza Branch, Islamic Azad University, Beyza, Iran

Received: 2024-08-29 Accepted : 2024-12-10 Published : 2024-12-19

Keywords: Efficiency, Marine Structures, Sediment Transport, Significant Wave Height, Artificial Intelligence,

Abstract :

Introduction: Accurate prediction of significant wave height is crucial for the analysis of marine structures. This prediction aids in optimizing the performance of structures and reducing the environmental impacts of marine activities. Existing empirical and numerical methods are typically costly and time-consuming. Recently, the use of artificial intelligence and soft computing methods has gained popularity; however, these methods face challenges such as training errors and insufficient performance. This study aims to improve the prediction of significant wave height by employing a combination of heterogeneous artificial intelligence methods.

Materials and Methods: In this research, the data is processed and divided into three categories: training, validation, and testing. Then, the artificial intelligence method is trained using the training data to achieve the desired accuracy.

Results and Discussion: In this research, data from the Coastal Data System is utilized to estimate the significant wave height and analyze the forces acting on marine structures and sediment transport. The evaluation criteria include the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE). The results indicate that the proposed hybrid artificial intelligence method achieves a coefficient of determination of 0.96, an MAE of 0.079827, and an RMSE of 0.10989. Similarly, the Gaussian process regression method also demonstrates suitable performance with an R² of 0.96, an MAE of 0.083455, and an RMSE of 0.11296 in estimating significant wave height.

Conclusion: In this research, the coefficient of determination (R²) for the proposed method is 0.96, indicating a high correlation between the estimated and actual results. Additionally, the mean absolute error (MAE) is 0.079827, which is 0.003628 lower than that of the Gaussian process regression method. The root mean square error (RMSE) is also 0.10989, which is 0.00307 lower than that of the Gaussian regression method. These results demonstrate that the proposed combined artificial intelligence method offers greater accuracy in estimating significant wave height and analyzing the forces acting on marine structures.

References:


1. Abualigah, L., Diabat, A., Mirjalili, S., Abd Elaziz, M., & Gandomi, A. H. (2021). The arithmetic optimization algorithm. Computer Methods in Applied Mechanics and Engineering, 376, 113609. https://doi.org/10.1016/j.cma.2020.113609
2. Atteia, G., Collins, M. J., Algarni, A. D., & Samee, N. A. (2022). Deep-learning-based feature extraction approach for significant wave height prediction in SAR mode altimeter data. Remote Sensing, 14(21), 5569. https://doi.org/10.3390/rs14215569
3. Behar Kamran, Z., Amir Etemad, S., & Mohsen, H. (2011). Determination of effective parameters in forecasting significant wave height in Neka. In 4th International Conference on Offshore Industries. [In Persian]
4. Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123-140. https://doi.org/10.1007/BF00058655
5. Chen, Y., Zhao, S., & Liu, X. (2019). Application of artificial neural networks for wave height forecasting. Journal of Coastal Research, 35(5), 989-998. https://doi.org/10.2112/JCOASTRES-D-18-00094.1
6. Cox, D. R., & van der Meer, J. W. (2010). Wave forces on marine structures. CRC Press.
7. Davis, R. E., Collins, D. C., & Wu, L. (2014). Effects of temperature and salinity on wave properties and their impact on coastal infrastructure. Journal of Coastal Research, 30(3), 578-588. https://doi.org/10.2112/JCOASTRES-D-13-00048.1
8. Dhodhi, J., Sharma, K., & Hassanin, A. (2017). Safety of offshore platforms. In Encyclopedia of Maritime and Offshore Engineering (pp. 1-10). Wiley. https://doi.org/10.1002/9781118476406.emoe0021
9. Feng, Z., Hu, P., Li, S., & Mo, D. (2022). Prediction of significant wave height in offshore China based on the machine learning method. Journal of Marine Science and Engineering, 10(6), 836. https://doi.org/10.3390/jmse10060836
10. Han, L., Ji, Q., Jia, X., Liu, Y., Han, G., & Lin, X. (2022). Significant wave height prediction in the South China Sea based on the ConvLSTM algorithm. Journal of Marine Science and Engineering, 10(11), 1683. https://doi.org/10.3390/jmse10111683
11. Harrison, S., & MacDonald, A. (2015). Influence of seabed sediment composition on wave propagation and sediment transport. Coastal Engineering, 102, 1-12. https://doi.org/10.1016/j.coastaleng.2015.04.001
12. Li, Z., Zhang, M., & Wang, X. (2021). Deep learning for predicting wave height and its implications for coastal engineering. Engineering Applications of Artificial Intelligence, 98, 104064. https://doi.org/10.1016/j.engappai.2021.104064
13. Lotfollahi Yeganeh, M., Lashtah Neshayi, M., Ghorbani, M., & Larian, M. B. (2013). Modeling and forecasting of significant wave height in the Caspian Sea using chaos theory. Amirkabir Journal of Civil Engineering, 45, 97-105. [In Persian]
14. Mishra, J. P., Singh, K., & Chaudhary, H. (2022). Intelligent ocean wave height prediction system using light GBM model. International Journal of Systematic Innovation, 7(2), 64-77. https://doi.org/10.20855/ijsi.2022.7.2.9
15. Obakrim, S., Ailliot, P., Monbet, V., & Raillard, N. (2022). Statistical modeling of the space-time relation between wind and significant wave height. Authorea Preprints. https://doi.org/10.31219/osf.io/j8vyr
16. Obara, Y., & Nakamura, R. (2022). Transfer learning of long short-term memory analysis in significant wave height prediction off the coast of western Tohoku, Japan. Ocean Engineering, 266, 113048. https://doi.org/10.1016/j.oceaneng.2022.113048
17. Özger, M. (2010). Significant wave height forecasting using wavelet fuzzy logic approach. Ocean Engineering, 37(16), 1443-1451. https://doi.org/10.1016/j.oceaneng.2010.06.003
18. Segal, M. R. (2004). Machine learning benchmarks and random forest regression. [Unpublished manuscript].
19. Schulz, E., Speekenbrink, M., & Krause, A. (2018). A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions. Journal of Mathematical Psychology, 85, 1-16. https://doi.org/10.1016/j.jmp.2018.09.003
20. Sutherland, J., Smith, J., & Nairn, R. (2016). Challenges in numerical modeling of wave forces on offshore structures. Applied Ocean Research, 59, 84-95. https://doi.org/10.1016/j.apor.2016.09.005
21. Xie, C., Liu, X., Man, T., Xie, T., Dong, J., Ma, X., Zhao, Y., & Dong, G. (2022). PWPNet: A deep learning framework for real-time prediction of significant wave height distribution in a port. Journal of Marine Science and Engineering, 10(9), 1375. https://doi.org/10.3390/jmse10091375
22. Yu, X., Liu, Y., Sun, Z., & Qin, P. (2022). Wavelet-based ResNet: A deep-learning model for prediction of significant wave height. IEEE Access, 10, 110026-110033. https://doi.org/10.1109/ACCESS.2022.3217812
23. Alireza, F., & Ali Akbar, A. (2013). Calculation of maximum probable wave height during the design life of offshore platforms in the Persian Gulf. Marine Engineering, 9, 83-91. [In Persian]