Prediction of Rockfill Materials’ Shear Strength Using Various Kernel Function-Based Regression Models—A Comparative Perspective
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 particle...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/15/5/1739 |
| _version_ | 1797474642119622656 |
|---|---|
| author | Mahmood Ahmad Ramez A. Al-Mansob Irfan Jamil Mohammad A. Al-Zubi Mohanad Muayad Sabri Sabri Arnold C. Alguno |
| author_facet | Mahmood Ahmad Ramez A. Al-Mansob Irfan Jamil Mohammad A. Al-Zubi Mohanad Muayad Sabri Sabri Arnold C. Alguno |
| author_sort | Mahmood Ahmad |
| collection | DOAJ |
| description | 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<sup>2</sup>) of 0.9806, a correlation coefficient (<i>r</i>) 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<sup>2</sup> = 0.9455, <i>r</i> = 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. |
| first_indexed | 2024-03-09T20:33:01Z |
| format | Article |
| id | doaj.art-5d54cd2c41064d61a769329b2b27bfde |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-09T20:33:01Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-5d54cd2c41064d61a769329b2b27bfde2023-11-23T23:18:01ZengMDPI AGMaterials1996-19442022-02-01155173910.3390/ma15051739Prediction of Rockfill Materials’ Shear Strength Using Various Kernel Function-Based Regression Models—A Comparative PerspectiveMahmood Ahmad0Ramez A. Al-Mansob1Irfan Jamil2Mohammad A. Al-Zubi3Mohanad Muayad Sabri Sabri4Arnold C. Alguno5Department of Civil Engineering, Faculty of Engineering, International Islamic University Malaysia, Jalan Gombak 50728, Selangor, MalaysiaDepartment of Civil Engineering, Faculty of Engineering, International Islamic University Malaysia, Jalan Gombak 50728, Selangor, MalaysiaDepartment of Civil Engineering, University of Engineering and Technology Peshawar, Peshawar 25000, PakistanDepartment of Mechanical Engineering, Hijjawai Faculty for Engineering, Yarmouk University, Irbid 21163, JordanPeter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaDepartment of Physics, Mindanao State University-Iligan Institute of Technology, Iligan City 9200, PhilippinesThe 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<sup>2</sup>) of 0.9806, a correlation coefficient (<i>r</i>) 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<sup>2</sup> = 0.9455, <i>r</i> = 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.https://www.mdpi.com/1996-1944/15/5/1739shear strengthrockfill materialsGaussian functionspolynomial kernelradial basis functionPearson universal kernel |
| spellingShingle | Mahmood Ahmad Ramez A. Al-Mansob Irfan Jamil Mohammad A. Al-Zubi Mohanad Muayad Sabri Sabri Arnold C. Alguno Prediction of Rockfill Materials’ Shear Strength Using Various Kernel Function-Based Regression Models—A Comparative Perspective Materials shear strength rockfill materials Gaussian functions polynomial kernel radial basis function Pearson universal kernel |
| title | Prediction of Rockfill Materials’ Shear Strength Using Various Kernel Function-Based Regression Models—A Comparative Perspective |
| title_full | Prediction of Rockfill Materials’ Shear Strength Using Various Kernel Function-Based Regression Models—A Comparative Perspective |
| title_fullStr | Prediction of Rockfill Materials’ Shear Strength Using Various Kernel Function-Based Regression Models—A Comparative Perspective |
| title_full_unstemmed | Prediction of Rockfill Materials’ Shear Strength Using Various Kernel Function-Based Regression Models—A Comparative Perspective |
| title_short | Prediction of Rockfill Materials’ Shear Strength Using Various Kernel Function-Based Regression Models—A Comparative Perspective |
| title_sort | prediction of rockfill materials shear strength using various kernel function based regression models a comparative perspective |
| topic | shear strength rockfill materials Gaussian functions polynomial kernel radial basis function Pearson universal kernel |
| url | https://www.mdpi.com/1996-1944/15/5/1739 |
| work_keys_str_mv | AT mahmoodahmad predictionofrockfillmaterialsshearstrengthusingvariouskernelfunctionbasedregressionmodelsacomparativeperspective AT ramezaalmansob predictionofrockfillmaterialsshearstrengthusingvariouskernelfunctionbasedregressionmodelsacomparativeperspective AT irfanjamil predictionofrockfillmaterialsshearstrengthusingvariouskernelfunctionbasedregressionmodelsacomparativeperspective AT mohammadaalzubi predictionofrockfillmaterialsshearstrengthusingvariouskernelfunctionbasedregressionmodelsacomparativeperspective AT mohanadmuayadsabrisabri predictionofrockfillmaterialsshearstrengthusingvariouskernelfunctionbasedregressionmodelsacomparativeperspective AT arnoldcalguno predictionofrockfillmaterialsshearstrengthusingvariouskernelfunctionbasedregressionmodelsacomparativeperspective |