Advanced Tree-Based Techniques for Predicting Unconfined Compressive Strength of Rock Material Employing Non-Destructive and Petrographic Tests
The accurate estimation of rock strength is an essential task in almost all rock-based projects, such as tunnelling and excavation. Numerous efforts to create indirect techniques for calculating unconfined compressive strength (UCS) have been attempted. This is often due to the complexity of collect...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/16/10/3731 |
| _version_ | 1797599293611180032 |
|---|---|
| author | Yuzhen Wang Mahdi Hasanipanah Ahmad Safuan A. Rashid Binh Nguyen Le Dmitrii Vladimirovich Ulrikh |
| author_facet | Yuzhen Wang Mahdi Hasanipanah Ahmad Safuan A. Rashid Binh Nguyen Le Dmitrii Vladimirovich Ulrikh |
| author_sort | Yuzhen Wang |
| collection | DOAJ |
| description | The accurate estimation of rock strength is an essential task in almost all rock-based projects, such as tunnelling and excavation. Numerous efforts to create indirect techniques for calculating unconfined compressive strength (UCS) have been attempted. This is often due to the complexity of collecting and completing the abovementioned lab tests. This study applied two advanced machine learning techniques, including the extreme gradient boosting trees and random forest, for predicting the UCS based on non-destructive tests and petrographic studies. Before applying these models, a feature selection was conducted using a Pearson’s Chi-Square test. This technique selected the following inputs for the development of the gradient boosting tree (XGBT) and random forest (RF) models: dry density and ultrasonic velocity as non-destructive tests, and mica, quartz, and plagioclase as petrographic results. In addition to XGBT and RF models, some empirical equations and two single decision trees (DTs) were developed to predict UCS values. The results of this study showed that the XGBT model outperforms the RF for UCS prediction in terms of both system accuracy and error. The linear correlation of XGBT was 0.994, and its mean absolute error was 0.113. In addition, the XGBT model outperformed single DTs and empirical equations. The XGBT and RF models also outperformed KNN (R = 0.708), ANN (R = 0.625), and SVM (R = 0.816) models. The findings of this study imply that the XGBT and RF can be employed efficiently for predicting the UCS values. |
| first_indexed | 2024-03-11T03:32:11Z |
| format | Article |
| id | doaj.art-470025f83bc8490d9762f20ed2a97f75 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-11T03:32:11Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-470025f83bc8490d9762f20ed2a97f752023-11-18T02:15:19ZengMDPI AGMaterials1996-19442023-05-011610373110.3390/ma16103731Advanced Tree-Based Techniques for Predicting Unconfined Compressive Strength of Rock Material Employing Non-Destructive and Petrographic TestsYuzhen Wang0Mahdi Hasanipanah1Ahmad Safuan A. Rashid2Binh Nguyen Le3Dmitrii Vladimirovich Ulrikh4School of Civil Engineering, Henan Vocational College of Water Conservancy and Environment, Zhengzhou 450008, ChinaInstitute of Research and Development, Duy Tan University, Da Nang 550000, VietnamFaculty of Civil Engineering, Universiti Teknologi Malaysia, Johor Bahru 81310, MalaysiaInstitute of Research and Development, Duy Tan University, Da Nang 550000, VietnamDepartment of Urban Planning, Engineering Networks and Systems, Institute of Architecture and Construction, South Ural State University, Lenin Prospect 76, 454080 Chelyabinsk, RussiaThe accurate estimation of rock strength is an essential task in almost all rock-based projects, such as tunnelling and excavation. Numerous efforts to create indirect techniques for calculating unconfined compressive strength (UCS) have been attempted. This is often due to the complexity of collecting and completing the abovementioned lab tests. This study applied two advanced machine learning techniques, including the extreme gradient boosting trees and random forest, for predicting the UCS based on non-destructive tests and petrographic studies. Before applying these models, a feature selection was conducted using a Pearson’s Chi-Square test. This technique selected the following inputs for the development of the gradient boosting tree (XGBT) and random forest (RF) models: dry density and ultrasonic velocity as non-destructive tests, and mica, quartz, and plagioclase as petrographic results. In addition to XGBT and RF models, some empirical equations and two single decision trees (DTs) were developed to predict UCS values. The results of this study showed that the XGBT model outperforms the RF for UCS prediction in terms of both system accuracy and error. The linear correlation of XGBT was 0.994, and its mean absolute error was 0.113. In addition, the XGBT model outperformed single DTs and empirical equations. The XGBT and RF models also outperformed KNN (R = 0.708), ANN (R = 0.625), and SVM (R = 0.816) models. The findings of this study imply that the XGBT and RF can be employed efficiently for predicting the UCS values.https://www.mdpi.com/1996-1944/16/10/3731rock strength predictionphysical propertiesnon-destructive testsregression tree techniquesgradient boosting treerandom forest |
| spellingShingle | Yuzhen Wang Mahdi Hasanipanah Ahmad Safuan A. Rashid Binh Nguyen Le Dmitrii Vladimirovich Ulrikh Advanced Tree-Based Techniques for Predicting Unconfined Compressive Strength of Rock Material Employing Non-Destructive and Petrographic Tests Materials rock strength prediction physical properties non-destructive tests regression tree techniques gradient boosting tree random forest |
| title | Advanced Tree-Based Techniques for Predicting Unconfined Compressive Strength of Rock Material Employing Non-Destructive and Petrographic Tests |
| title_full | Advanced Tree-Based Techniques for Predicting Unconfined Compressive Strength of Rock Material Employing Non-Destructive and Petrographic Tests |
| title_fullStr | Advanced Tree-Based Techniques for Predicting Unconfined Compressive Strength of Rock Material Employing Non-Destructive and Petrographic Tests |
| title_full_unstemmed | Advanced Tree-Based Techniques for Predicting Unconfined Compressive Strength of Rock Material Employing Non-Destructive and Petrographic Tests |
| title_short | Advanced Tree-Based Techniques for Predicting Unconfined Compressive Strength of Rock Material Employing Non-Destructive and Petrographic Tests |
| title_sort | advanced tree based techniques for predicting unconfined compressive strength of rock material employing non destructive and petrographic tests |
| topic | rock strength prediction physical properties non-destructive tests regression tree techniques gradient boosting tree random forest |
| url | https://www.mdpi.com/1996-1944/16/10/3731 |
| work_keys_str_mv | AT yuzhenwang advancedtreebasedtechniquesforpredictingunconfinedcompressivestrengthofrockmaterialemployingnondestructiveandpetrographictests AT mahdihasanipanah advancedtreebasedtechniquesforpredictingunconfinedcompressivestrengthofrockmaterialemployingnondestructiveandpetrographictests AT ahmadsafuanarashid advancedtreebasedtechniquesforpredictingunconfinedcompressivestrengthofrockmaterialemployingnondestructiveandpetrographictests AT binhnguyenle advancedtreebasedtechniquesforpredictingunconfinedcompressivestrengthofrockmaterialemployingnondestructiveandpetrographictests AT dmitriivladimirovichulrikh advancedtreebasedtechniquesforpredictingunconfinedcompressivestrengthofrockmaterialemployingnondestructiveandpetrographictests |