Slope stability prediction using integrated metaheuristic and machine learning approaches: A comparative study

Chongchong Qi, Xiaolin Tang

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Advances in dataset collection and machine learning (ML) algorithms are important contributors to the stability analysis in industrial engineering, especially to slope stability analysis. In the past decade, various ML algorithms have been used to estimate slope stability on different datasets, and yet a comprehensive comparative study of the most advanced ML algorithms is lacking. In this article, we proposed and compared six integrated artificial intelligence (AI) approaches for slope stability prediction based on metaheuristic and ML algorithms. Six ML algorithms, including logistic regression, decision tree, random forest, gradient boosting machine, support vector machine, and multilayer perceptron neural network, were used for the relationship modelling and firefly algorithm (FA) was used for the hyper-parameters tuning. Three performance measures, namely confusion matrices, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC), were used to evaluate the predictive performance of AI approaches. We first demonstrated that integrated AI approaches had great potential to predict slope stability and FA was efficient in the hyper-parameter tunning. The AUC values of all AI approaches on the testing set were between 0.822 and 0.967, denoting excellent performance was achieved. The optimum support vector machine model with the Youden's cutoff was recommended in terms of the AUC value, the accuracy, and the true negative rate. We also investigated the relative importance of influencing variables and found that cohesion was the most influential variable for slope stability with an importance score of 0.310. This research provides useful recommendations for future slope stability analysis and can be used for a wider application in the rest of industrial engineering.

Original languageEnglish
Pages (from-to)112-122
Number of pages11
JournalComputers and Industrial Engineering
Volume118
DOIs
Publication statusPublished - 1 Apr 2018

Fingerprint

Slope stability
Learning systems
Learning algorithms
Artificial intelligence
Industrial engineering
Support vector machines
Multilayer neural networks
Decision trees
Logistics
Tuning
Neural networks
Testing

Cite this

@article{7adf0ed00a784a8d97589d656312b798,
title = "Slope stability prediction using integrated metaheuristic and machine learning approaches: A comparative study",
abstract = "Advances in dataset collection and machine learning (ML) algorithms are important contributors to the stability analysis in industrial engineering, especially to slope stability analysis. In the past decade, various ML algorithms have been used to estimate slope stability on different datasets, and yet a comprehensive comparative study of the most advanced ML algorithms is lacking. In this article, we proposed and compared six integrated artificial intelligence (AI) approaches for slope stability prediction based on metaheuristic and ML algorithms. Six ML algorithms, including logistic regression, decision tree, random forest, gradient boosting machine, support vector machine, and multilayer perceptron neural network, were used for the relationship modelling and firefly algorithm (FA) was used for the hyper-parameters tuning. Three performance measures, namely confusion matrices, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC), were used to evaluate the predictive performance of AI approaches. We first demonstrated that integrated AI approaches had great potential to predict slope stability and FA was efficient in the hyper-parameter tunning. The AUC values of all AI approaches on the testing set were between 0.822 and 0.967, denoting excellent performance was achieved. The optimum support vector machine model with the Youden's cutoff was recommended in terms of the AUC value, the accuracy, and the true negative rate. We also investigated the relative importance of influencing variables and found that cohesion was the most influential variable for slope stability with an importance score of 0.310. This research provides useful recommendations for future slope stability analysis and can be used for a wider application in the rest of industrial engineering.",
keywords = "Firefly algorithm, Integrated AI approaches, Machine learning algorithms, Slope stability prediction, Variable importance",
author = "Chongchong Qi and Xiaolin Tang",
year = "2018",
month = "4",
day = "1",
doi = "10.1016/j.cie.2018.02.028",
language = "English",
volume = "118",
pages = "112--122",
journal = "Computers and Industrial Engineering",
issn = "0360-8352",
publisher = "Elsevier",

}

Slope stability prediction using integrated metaheuristic and machine learning approaches : A comparative study. / Qi, Chongchong; Tang, Xiaolin.

In: Computers and Industrial Engineering, Vol. 118, 01.04.2018, p. 112-122.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Slope stability prediction using integrated metaheuristic and machine learning approaches

T2 - A comparative study

AU - Qi, Chongchong

AU - Tang, Xiaolin

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Advances in dataset collection and machine learning (ML) algorithms are important contributors to the stability analysis in industrial engineering, especially to slope stability analysis. In the past decade, various ML algorithms have been used to estimate slope stability on different datasets, and yet a comprehensive comparative study of the most advanced ML algorithms is lacking. In this article, we proposed and compared six integrated artificial intelligence (AI) approaches for slope stability prediction based on metaheuristic and ML algorithms. Six ML algorithms, including logistic regression, decision tree, random forest, gradient boosting machine, support vector machine, and multilayer perceptron neural network, were used for the relationship modelling and firefly algorithm (FA) was used for the hyper-parameters tuning. Three performance measures, namely confusion matrices, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC), were used to evaluate the predictive performance of AI approaches. We first demonstrated that integrated AI approaches had great potential to predict slope stability and FA was efficient in the hyper-parameter tunning. The AUC values of all AI approaches on the testing set were between 0.822 and 0.967, denoting excellent performance was achieved. The optimum support vector machine model with the Youden's cutoff was recommended in terms of the AUC value, the accuracy, and the true negative rate. We also investigated the relative importance of influencing variables and found that cohesion was the most influential variable for slope stability with an importance score of 0.310. This research provides useful recommendations for future slope stability analysis and can be used for a wider application in the rest of industrial engineering.

AB - Advances in dataset collection and machine learning (ML) algorithms are important contributors to the stability analysis in industrial engineering, especially to slope stability analysis. In the past decade, various ML algorithms have been used to estimate slope stability on different datasets, and yet a comprehensive comparative study of the most advanced ML algorithms is lacking. In this article, we proposed and compared six integrated artificial intelligence (AI) approaches for slope stability prediction based on metaheuristic and ML algorithms. Six ML algorithms, including logistic regression, decision tree, random forest, gradient boosting machine, support vector machine, and multilayer perceptron neural network, were used for the relationship modelling and firefly algorithm (FA) was used for the hyper-parameters tuning. Three performance measures, namely confusion matrices, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC), were used to evaluate the predictive performance of AI approaches. We first demonstrated that integrated AI approaches had great potential to predict slope stability and FA was efficient in the hyper-parameter tunning. The AUC values of all AI approaches on the testing set were between 0.822 and 0.967, denoting excellent performance was achieved. The optimum support vector machine model with the Youden's cutoff was recommended in terms of the AUC value, the accuracy, and the true negative rate. We also investigated the relative importance of influencing variables and found that cohesion was the most influential variable for slope stability with an importance score of 0.310. This research provides useful recommendations for future slope stability analysis and can be used for a wider application in the rest of industrial engineering.

KW - Firefly algorithm

KW - Integrated AI approaches

KW - Machine learning algorithms

KW - Slope stability prediction

KW - Variable importance

UR - http://www.scopus.com/inward/record.url?scp=85042691366&partnerID=8YFLogxK

U2 - 10.1016/j.cie.2018.02.028

DO - 10.1016/j.cie.2018.02.028

M3 - Article

VL - 118

SP - 112

EP - 122

JO - Computers and Industrial Engineering

JF - Computers and Industrial Engineering

SN - 0360-8352

ER -