Prediction of Liquefaction-Induced Lateral Displacements Using Gaussian Process Regression
During severe earthquakes, liquefaction-induced lateral displacement causes significant damage to designed structures. As a result, geotechnical specialists must accurately estimate lateral displacement in liquefaction-prone areas in order to ensure long-term development. This research proposes a Ga...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/4/1977 |
| _version_ | 1797483076690903040 |
|---|---|
| author | Mahmood Ahmad Maaz Amjad Ramez A. Al-Mansob Paweł Kamiński Piotr Olczak Beenish Jehan Khan Arnold C. Alguno |
| author_facet | Mahmood Ahmad Maaz Amjad Ramez A. Al-Mansob Paweł Kamiński Piotr Olczak Beenish Jehan Khan Arnold C. Alguno |
| author_sort | Mahmood Ahmad |
| collection | DOAJ |
| description | During severe earthquakes, liquefaction-induced lateral displacement causes significant damage to designed structures. As a result, geotechnical specialists must accurately estimate lateral displacement in liquefaction-prone areas in order to ensure long-term development. This research proposes a Gaussian Process Regression (GPR) model based on 247 post liquefaction in-situ free face ground conditions case studies for analyzing liquefaction-induced lateral displacement. The performance of the GPR model is assessed using statistical parameters, including the coefficient of determination, coefficient of correlation, Nash–Sutcliffe efficiency coefficient, root mean square error (<i>RMSE</i>), and ratio of the <i>RMSE</i> to the standard deviation of measured data. The developed GPR model predictive ability is compared to that of three other known models—evolutionary polynomial regression, artificial neural network, and multi-layer regression available in the literature. The results show that the GPR model can accurately learn complicated nonlinear relationships between lateral displacement and its influencing factors. A sensitivity analysis is also presented in this study to assess the effects of input parameters on lateral displacement. |
| first_indexed | 2024-03-09T22:41:45Z |
| format | Article |
| id | doaj.art-8b82636d60844c3bafac943007d806a0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:41:45Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-8b82636d60844c3bafac943007d806a02023-11-23T18:37:13ZengMDPI AGApplied Sciences2076-34172022-02-01124197710.3390/app12041977Prediction of Liquefaction-Induced Lateral Displacements Using Gaussian Process RegressionMahmood Ahmad0Maaz Amjad1Ramez A. Al-Mansob2Paweł Kamiński3Piotr Olczak4Beenish Jehan Khan5Arnold C. Alguno6Department of Civil Engineering, Faculty of Engineering, International Islamic University Malaysia, Jalan Gombak, Selangor 50728, MalaysiaDepartment of Civil Engineering, University of Engineering and Technology, Peshawar 25120, PakistanDepartment of Civil Engineering, Faculty of Engineering, International Islamic University Malaysia, Jalan Gombak, Selangor 50728, MalaysiaFaculty of Civil Engineering and Resource Management, AGH University of Science and Technology, 30-059 Krakow, PolandMineral and Energy Economy Research Institute, Polish Academy of Sciences, Wybickiego St. 7A, 31-261 Krakow, PolandDepartment of Civil Engineering, CECOS University of IT and Emerging Sciences, Peshawar 25000, PakistanDepartment of Physics, Mindanao State University-Iligan Institute of Technology, Iligan City 9200, PhilippinesDuring severe earthquakes, liquefaction-induced lateral displacement causes significant damage to designed structures. As a result, geotechnical specialists must accurately estimate lateral displacement in liquefaction-prone areas in order to ensure long-term development. This research proposes a Gaussian Process Regression (GPR) model based on 247 post liquefaction in-situ free face ground conditions case studies for analyzing liquefaction-induced lateral displacement. The performance of the GPR model is assessed using statistical parameters, including the coefficient of determination, coefficient of correlation, Nash–Sutcliffe efficiency coefficient, root mean square error (<i>RMSE</i>), and ratio of the <i>RMSE</i> to the standard deviation of measured data. The developed GPR model predictive ability is compared to that of three other known models—evolutionary polynomial regression, artificial neural network, and multi-layer regression available in the literature. The results show that the GPR model can accurately learn complicated nonlinear relationships between lateral displacement and its influencing factors. A sensitivity analysis is also presented in this study to assess the effects of input parameters on lateral displacement.https://www.mdpi.com/2076-3417/12/4/1977lateral displacementliquefactionGaussian process regressionsensitivity analysismachine learning |
| spellingShingle | Mahmood Ahmad Maaz Amjad Ramez A. Al-Mansob Paweł Kamiński Piotr Olczak Beenish Jehan Khan Arnold C. Alguno Prediction of Liquefaction-Induced Lateral Displacements Using Gaussian Process Regression Applied Sciences lateral displacement liquefaction Gaussian process regression sensitivity analysis machine learning |
| title | Prediction of Liquefaction-Induced Lateral Displacements Using Gaussian Process Regression |
| title_full | Prediction of Liquefaction-Induced Lateral Displacements Using Gaussian Process Regression |
| title_fullStr | Prediction of Liquefaction-Induced Lateral Displacements Using Gaussian Process Regression |
| title_full_unstemmed | Prediction of Liquefaction-Induced Lateral Displacements Using Gaussian Process Regression |
| title_short | Prediction of Liquefaction-Induced Lateral Displacements Using Gaussian Process Regression |
| title_sort | prediction of liquefaction induced lateral displacements using gaussian process regression |
| topic | lateral displacement liquefaction Gaussian process regression sensitivity analysis machine learning |
| url | https://www.mdpi.com/2076-3417/12/4/1977 |
| work_keys_str_mv | AT mahmoodahmad predictionofliquefactioninducedlateraldisplacementsusinggaussianprocessregression AT maazamjad predictionofliquefactioninducedlateraldisplacementsusinggaussianprocessregression AT ramezaalmansob predictionofliquefactioninducedlateraldisplacementsusinggaussianprocessregression AT pawełkaminski predictionofliquefactioninducedlateraldisplacementsusinggaussianprocessregression AT piotrolczak predictionofliquefactioninducedlateraldisplacementsusinggaussianprocessregression AT beenishjehankhan predictionofliquefactioninducedlateraldisplacementsusinggaussianprocessregression AT arnoldcalguno predictionofliquefactioninducedlateraldisplacementsusinggaussianprocessregression |