Prediction of Rockfill Materials' Shear Strength Using Various Kernel Function-Based Regression Models-A Comparative Perspective

• Published in: Materials Vol. 15; no. 5; p. 1739
• Main Authors: Ahmad, Mahmood, Al-Mansob, Ramez A, Jamil, Irfan, Al-Zubi, Mohammad A, Sabri, Mohanad Muayad Sabri, Alguno, Arnold C
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 25-02-2022; MDPI
• Subjects: Algorithms; Civil engineering; Correlation analysis; Correlation coefficients; Dam design; Dam engineering; Density; Embankment dams; Gaussian functions; Gaussian process; Kernel functions; Laboratories; Machine learning; Mechanical properties; Particle size; Pearson universal kernel; Performance evaluation; polynomial kernel; radial basis function; Regression analysis; Regression models; Rockfill; rockfill materials; Root-mean-square errors; Shear strength; Shear tests; Variables; Gaussian functions; rockfill materials; polynomial kernel; shear strength; Pearson universal kernel; radial basis function
• ISSN: 1996-1944; 1996-1944
• DOI: 10.3390/ma15051739

The mechanical behavior of the rockfill materials (RFMs) used in a dam's shell must be evaluated for the safe and cost-effective design of embankment dams. However, the characterization of RFMs with specific reference to shear strength is challenging and costly, as the materials may contain particles larger than 500 mm in diameter. This study explores the potential of various kernel function-based Gaussian process regression (GPR) models to predict the shear strength of RFMs. A total of 165 datasets compiled from the literature were selected to train and test the proposed models. Comparing the developed models based on the GPR method shows that the superlative model was the Pearson universal kernel (PUK) model with an R-squared (R
) of 0.9806, a correlation coefficient (
) of 0.9903, a mean absolute error (MAE) of 0.0646 MPa, a root mean square error (RMSE) of 0.0965 MPa, a relative absolute error (RAE) of 13.0776%, and a root relative squared error (RRSE) of 14.6311% in the training phase, while it performed equally well in the testing phase, with R
= 0.9455,
= 0.9724, MAE = 0.1048 MPa, RMSE = 0.1443 MPa, RAE = 21.8554%, and RRSE = 23.6865%. The prediction results of the GPR-PUK model are found to be more accurate and are in good agreement with the actual shear strength of RFMs, thus verifying the feasibility and effectiveness of the model.