Estimating Coastal Dyke Leakage Flow Using Support Vector Machine (SVM) and Multivariate Adaptive Regression Spline (MARS) Model

Asakereh, Adel; Choobi, Farhad; Bagherzadeh, Mohammad; Mirzaee, Reza

doi:10.61186/NMCE.2309.1030

Estimating Coastal Dyke Leakage Flow Using Support Vector Machine (SVM) and Multivariate Adaptive Regression Spline (MARS) Model

Document Type : Research

Authors

Adel Asakereh ¹

Farhad Choobi ²

mohammad bagherzadeh ³

reza mirzaee ⁴

¹ Associate Professor, Faculty of Civil Engineering, Semnan University, Semnan, Iran.

² MSc student, Faculty of Civil Engineering, Semnan University, Semnan, Iran

³ PhD student, Department of Civil Engineering, Urmia University, Urmia, Iran

⁴ PhD student, Faculty of Civil Engineering, Semnan University, Semnan, Iran.

10.61186/NMCE.2309.1030

Abstract

It is important to check for leakage flow in hydraulic and marine structures during design, as uncontrolled leakage can cause irreparable damage. Soft computing methods can be used to easily model, analyze and control complex systems. This study uses Support Vector Machine (SVM) method to predict leakage discharge of coastal dykes. Five different models are used to achieve this goal, with parameters including the length of the cutoff blanket, dyke depth, and water head considered. The best support vector machine model is checked using a multivariate adaptive regression spline model (MARS) for prediction. Results show that the model including all parameters predicts settlement discharge with very good accuracy compared to the laboratory model, with a coefficient of determination and root mean square coefficient of 0.949 and 0.058 respectively in the test stage and 0.93 and 0.06 in the test phase estimates. The dyke depth parameter has the greatest effect on leakage flow, while the water head has the least effect among input parameters to the model. Although the adaptive regression multivariate spline model accurately estimates the annual dyke leakage flow rate, it is less accurate than the support vector machine method.

Keywords

Soft computing

seepage discharge

coastal dyke

SVM method

MARS model

Subjects

Hydraulic Engineering

[1] Terzaghi, K. (1943). Theoretical soil mechanics, Wiley, New York.

[2] Bligh, W. G. (1910). Dams, barrages and weirs on porous foundations. Engineering news, 64(26), 708-710.

[3] Lane, E. W. (1935). Security from under-seepage-masonry dams on earth foundations. Transactions of the American Society of Civil Engineers, 100(1), 1235-1272.

[4] Neuman, S. P., & Witherspoon, P. A. (1970). Finite element method of analyzing steady seepage with a free surface. Water Resources Research, 6(3), 889-897.

[5] United States Department of the Interior, Bureau of Reclamation (USBR). (1977). Design of small dams. Washington, DC.

[6] Ojha, C. S. P., Singh, V. P., & Adrian, D. D. (2003). Determination of critical head in soil piping. Journal of Hydraulic Engineering, 129(7), 511-518.

[7] Benmebarek, N., Benmebarek, S., & Kastner, R. (2005). Numerical studies of seepage failure of sand within a cofferdam. Computers and Geotechnics, 32(4), 264-273.

[8] Fontana, N. (2008). Experimental analysis of heaving phenomena in sandy soils. Journal of Hydraulic Engineering, 134(6), 794-799.

[9] Yousefi, M., Sedghi-Asl, M., & Parvizi, M. (2016). Seepage and boiling around a sheet pile under different experimental configuration. Journal of Hydrologic Engineering, 21(12), 06016015.

[10] Irzooki, R. H. (2016). Computation of seepage through homogenous earth dams with horizontal toe drain. Engineering and Technology Journal, 34(3 part), 430-440.

[11] Kheiri, G., Javdanian, H., & Shams, G. (2020). A numerical modeling study on the seepage under embankment dams. Modeling Earth Systems and Environment, 6(2), 1075-1087.

[12] Sharghi, E., Nourani, V., & Behfar, N. (2019). Evaluation and application of ensemble AIbased models for estimating piezometric heads in earth fill dams. Iran-Water Resources Research, 14(4), 160-169.

[13] Najafzadeh, M. (2020). Projection of seepage and piezometric pressure in earth dams using soft computational models. Amirkabir Journal of Civil Engineering, 52(7), 1783-1796 (In Persian).

[14] Bagherzadeh, M., Mousavi, F., Manafpour, M., Mirzaee, R., & Hoseini, K. (2022). Numerical simulation and application of soft computing in estimating vertical drop energy dissipation with horizontal serrated edge. Water Supply, 22(4), 4676-4689.

[15] Mirzaee, R., Mohammadi, M., Mousavi, S. F., Bagherzadeh, M., & Hosseini, K. (2023). Application of soft computing techniques to estimate the scouring depth formed by crossing jets. Water Science and Technology, 87(8), 1853-1865.

[16] Sedghi-Asl, M., Rahimi, H., & Khaleghi, H. (2010). Experimental analysis of seepage flow under coastal dikes. Experimental techniques, 34(4), 49-54.

[17] Vapnik. V. (1995). The Nature of Statistical Learning Theory. Springer-Verlag, New York.

[18] Roushangar, K., & Koosheh, A. (2015). Evaluation of GA-SVR method for modeling bed load transport in gravel-bed Rivers. Journal of Hydrology, 527, 1142-1152.

[19] Daneshfaraz, R., Bagherzadeh, M., Esmaeeli, R., Norouzi, R., & Abraham, J. (2021a). Study of the performance of support vector machine for predicting vertical drop hydraulic parameters in the presence of dual horizontal screens. Water supply, 21(1), 217-231.

[20] Bagherzadeh, M., & Mohammadi, M. (2023). Estimation of the Scouring Depth of the Plunge Pool of the Symmetrical Crossing Jets by Support Vector Machine. Journal of Water and Sustainable Development, 9(4), 1-12 (In Persian).

[21] Friedman, J. H. (1991). Multivariate adaptive regression splines. The annals of statistics, 19(1), 1-67.

[22] Zhang, W., & Goh, A. T. (2016). Multivariate adaptive regression splines and neural network models for prediction of pile drivability. Geoscience Frontiers, 7(1), 45-52.

[23] Rezaie-Balf, M., Zahmatkesh, Z., & Kim, S. (2017). Soft computing techniques for rainfall-runoff simulation: local non–parametric paradigm vs. model classification methods. Water Resources Management, 31, 3843-3865.