A machine learning-based method for predicting the shear behaviors of rock joints

In this study, machine learning prediction models (MLPMs), including artificial neural network (ANN), support vector regression (SVR), K-nearest neighbors (KNN), and random forest (RF) algorithms, were developed to predict the peak shear stress values and shear stress-displacement curves of rock joi...

Full description

Saved in:
Bibliographic Details
Main Authors: Liu He, Yu Tan, Timothy Copeland, Jiannan Chen, Qiang Tang
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Soils and Foundations
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0038080624000957
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850118720710508544
author Liu He
Yu Tan
Timothy Copeland
Jiannan Chen
Qiang Tang
author_facet Liu He
Yu Tan
Timothy Copeland
Jiannan Chen
Qiang Tang
author_sort Liu He
collection DOAJ
description In this study, machine learning prediction models (MLPMs), including artificial neural network (ANN), support vector regression (SVR), K-nearest neighbors (KNN), and random forest (RF) algorithms, were developed to predict the peak shear stress values and shear stress-displacement curves of rock joints. The database used contained 693 records of peak shear stress and 162 original shear stress-displacement curves derived from direct shear tests. The results demonstrated that the MLPMs provided reliable predictions for shear stress, with the mean squared errors (MSEs) between their predicted and measured shear stress varying from 0.003 to 0.069 and the coefficients of determination (R2 values) varying from 0.964 to 0.998. The feature importance values indicate that the joint surface roughness coefficient (JRC) is the most important influential factor in determining the peak shear stress, followed by the joint wall compressive strength (JCS), basic friction angle (φb), and shear surface area (As). Similarly, for the shear stress-displacement curve, the JRC is the dominant factor, followed by As, φb, and JCS. Additional direct shear tests were conducted for model validation. The validation shows that the MLPM predictions demonstrate improved consistency with the experimental results in relation to both the peak shear stress and peak shear displacement.
format Article
id doaj-art-61c5226ed3bb4f77b6eeba009f969f1e
institution OA Journals
issn 2524-1788
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Soils and Foundations
spelling doaj-art-61c5226ed3bb4f77b6eeba009f969f1e2025-08-20T02:35:47ZengElsevierSoils and Foundations2524-17882024-12-0164610151710.1016/j.sandf.2024.101517A machine learning-based method for predicting the shear behaviors of rock jointsLiu He0Yu Tan1Timothy Copeland2Jiannan Chen3Qiang Tang4Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, Sichuan, PR ChinaDepartment of Civil and Environmental Engineering, University of Wisconsin, Madison, WI, USAGeosyntec Consultants Inc., Orlando, FL, USA; Formerly Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL, USADepartment of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL, USASchool of Rail Transportation, Soochow University, Yangchenghu Campus, Xiangcheng District, Suzhou 215131, PR China; Corresponding author.In this study, machine learning prediction models (MLPMs), including artificial neural network (ANN), support vector regression (SVR), K-nearest neighbors (KNN), and random forest (RF) algorithms, were developed to predict the peak shear stress values and shear stress-displacement curves of rock joints. The database used contained 693 records of peak shear stress and 162 original shear stress-displacement curves derived from direct shear tests. The results demonstrated that the MLPMs provided reliable predictions for shear stress, with the mean squared errors (MSEs) between their predicted and measured shear stress varying from 0.003 to 0.069 and the coefficients of determination (R2 values) varying from 0.964 to 0.998. The feature importance values indicate that the joint surface roughness coefficient (JRC) is the most important influential factor in determining the peak shear stress, followed by the joint wall compressive strength (JCS), basic friction angle (φb), and shear surface area (As). Similarly, for the shear stress-displacement curve, the JRC is the dominant factor, followed by As, φb, and JCS. Additional direct shear tests were conducted for model validation. The validation shows that the MLPM predictions demonstrate improved consistency with the experimental results in relation to both the peak shear stress and peak shear displacement.http://www.sciencedirect.com/science/article/pii/S0038080624000957Rock jointMachine learning prediction modelsShear behavior predictionFeature importanceDirect shear test
spellingShingle Liu He
Yu Tan
Timothy Copeland
Jiannan Chen
Qiang Tang
A machine learning-based method for predicting the shear behaviors of rock joints
Soils and Foundations
Rock joint
Machine learning prediction models
Shear behavior prediction
Feature importance
Direct shear test
title A machine learning-based method for predicting the shear behaviors of rock joints
title_full A machine learning-based method for predicting the shear behaviors of rock joints
title_fullStr A machine learning-based method for predicting the shear behaviors of rock joints
title_full_unstemmed A machine learning-based method for predicting the shear behaviors of rock joints
title_short A machine learning-based method for predicting the shear behaviors of rock joints
title_sort machine learning based method for predicting the shear behaviors of rock joints
topic Rock joint
Machine learning prediction models
Shear behavior prediction
Feature importance
Direct shear test
url http://www.sciencedirect.com/science/article/pii/S0038080624000957
work_keys_str_mv AT liuhe amachinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT yutan amachinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT timothycopeland amachinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT jiannanchen amachinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT qiangtang amachinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT liuhe machinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT yutan machinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT timothycopeland machinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT jiannanchen machinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints
AT qiangtang machinelearningbasedmethodforpredictingtheshearbehaviorsofrockjoints