Hybrid Machine Learning Model for Predicting Shear Strength of Rock Joints

The accurate prediction of joint shear strength is crucial for rock mass engineering design and geological hazard assessment. However, traditional machine learning (ML) models often suffer from local optima and limited generalization ability when dealing with complex nonlinear problems, thereby comp...

Full description

Saved in:
Bibliographic Details
Main Authors: Daxing Lei, Yaoping Zhang, Zhigang Lu, Hang Lin, Yifan Chen
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/13/7097
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850118903496179712
author Daxing Lei
Yaoping Zhang
Zhigang Lu
Hang Lin
Yifan Chen
author_facet Daxing Lei
Yaoping Zhang
Zhigang Lu
Hang Lin
Yifan Chen
author_sort Daxing Lei
collection DOAJ
description The accurate prediction of joint shear strength is crucial for rock mass engineering design and geological hazard assessment. However, traditional machine learning (ML) models often suffer from local optima and limited generalization ability when dealing with complex nonlinear problems, thereby compromising prediction accuracy and stability. To address these challenges, this study proposes a hybrid ML model that integrates a multilayer perceptron (MLP) with the slime mold algorithm (SMA), termed the SMA-MLP model. While MLP exhibits strong nonlinear mapping capability, SMA enhances its training process through global optimization and parameter tuning, thereby improving predictive accuracy and robustness. A dataset with five input variables was constructed to evaluate the performance of the SMA-MLP model comprehensively. The proposed model was compared with other ML models. The results indicate that SMA-MLP outperforms these models in key metrics such as the root mean squared error (RMSE) and the correlation coefficient (R<sup>2</sup>), achieving an R<sup>2</sup> of 0.97 and an RMSE as low as 0.10 MPa on the test set. Furthermore, feature importance analysis reveals that normal stress has the most significant influence on joint shear strength. This study demonstrates the superiority of SMA-MLP in predicting joint shear strength, highlighting its potential as an efficient and accurate tool for rock mass engineering analysis and providing reliable technical support for geological hazard assessment.
format Article
id doaj-art-384c805fdf9446da9646a0beafde6a2c
institution OA Journals
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-384c805fdf9446da9646a0beafde6a2c2025-08-20T02:35:46ZengMDPI AGApplied Sciences2076-34172025-06-011513709710.3390/app15137097Hybrid Machine Learning Model for Predicting Shear Strength of Rock JointsDaxing Lei0Yaoping Zhang1Zhigang Lu2Hang Lin3Yifan Chen4School of Resources and Civil Engineering, GanNan University of Science and Technology, Ganzhou 341000, ChinaSchool of Resources and Civil Engineering, GanNan University of Science and Technology, Ganzhou 341000, ChinaSchool of Resources and Civil Engineering, GanNan University of Science and Technology, Ganzhou 341000, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410083, ChinaSchool of Resources and Safety Engineering, Central South University, Changsha 410083, ChinaThe accurate prediction of joint shear strength is crucial for rock mass engineering design and geological hazard assessment. However, traditional machine learning (ML) models often suffer from local optima and limited generalization ability when dealing with complex nonlinear problems, thereby compromising prediction accuracy and stability. To address these challenges, this study proposes a hybrid ML model that integrates a multilayer perceptron (MLP) with the slime mold algorithm (SMA), termed the SMA-MLP model. While MLP exhibits strong nonlinear mapping capability, SMA enhances its training process through global optimization and parameter tuning, thereby improving predictive accuracy and robustness. A dataset with five input variables was constructed to evaluate the performance of the SMA-MLP model comprehensively. The proposed model was compared with other ML models. The results indicate that SMA-MLP outperforms these models in key metrics such as the root mean squared error (RMSE) and the correlation coefficient (R<sup>2</sup>), achieving an R<sup>2</sup> of 0.97 and an RMSE as low as 0.10 MPa on the test set. Furthermore, feature importance analysis reveals that normal stress has the most significant influence on joint shear strength. This study demonstrates the superiority of SMA-MLP in predicting joint shear strength, highlighting its potential as an efficient and accurate tool for rock mass engineering analysis and providing reliable technical support for geological hazard assessment.https://www.mdpi.com/2076-3417/15/13/7097rock jointsshear strengthmachine learningslime mold algorithm
spellingShingle Daxing Lei
Yaoping Zhang
Zhigang Lu
Hang Lin
Yifan Chen
Hybrid Machine Learning Model for Predicting Shear Strength of Rock Joints
Applied Sciences
rock joints
shear strength
machine learning
slime mold algorithm
title Hybrid Machine Learning Model for Predicting Shear Strength of Rock Joints
title_full Hybrid Machine Learning Model for Predicting Shear Strength of Rock Joints
title_fullStr Hybrid Machine Learning Model for Predicting Shear Strength of Rock Joints
title_full_unstemmed Hybrid Machine Learning Model for Predicting Shear Strength of Rock Joints
title_short Hybrid Machine Learning Model for Predicting Shear Strength of Rock Joints
title_sort hybrid machine learning model for predicting shear strength of rock joints
topic rock joints
shear strength
machine learning
slime mold algorithm
url https://www.mdpi.com/2076-3417/15/13/7097
work_keys_str_mv AT daxinglei hybridmachinelearningmodelforpredictingshearstrengthofrockjoints
AT yaopingzhang hybridmachinelearningmodelforpredictingshearstrengthofrockjoints
AT zhiganglu hybridmachinelearningmodelforpredictingshearstrengthofrockjoints
AT hanglin hybridmachinelearningmodelforpredictingshearstrengthofrockjoints
AT yifanchen hybridmachinelearningmodelforpredictingshearstrengthofrockjoints