Comparative Analysis for Slope Stability by Using Machine Learning Methods

Earth slopes’ stability analysis is a key task in geotechnical engineering that provides detailed view of the slope conditions used to implement appropriate stabilizations. In process, calculating safety factor (F.S) plays an essential part assessment, which guarantees operations’ success. Providing accurate and reliable F.S can be improve procedure as well this regard, researchers computational intelligent methodologies reach highly calculations. The presented study focused on estimation process attempted provide comparative based intelligence machine learning methods. well-known multilayer perceptron (MLP), decision tree (DT), support vector machines (SVM), random forest (RF) algorithms were predict/calculate for earth slopes. These classifiers have strong capability predict under certain failures uncertainties. models implemented dataset containing 100 stabilities, recorded from various locations provinces Fars, Isfahan, Tehran Iran, randomly divided into training testing datasets. predictive validated by Janbu’s limit equilibrium method (LEM) GeoStudio commercial software. Regarding study’s results, MLP (accuracy = 0.901/precision 0.90) more results than other classifiers, with good agreement LEM results. SVM algorithm follows 0.873/precision 0.85). estimated loss function, obtained 0.29 average prediction lowest rate. SVM, DT, RF 0.41, 0.62, 0.45 losses, respectively. This article tried fill gap traditional procedures advanced assessments.