In this study, we employed various machine learning-based techniques in predicting factor of safety against slope failures. Different regression methods namely, multi-layer perceptron (MLP), Gaussian process regression (GPR), multiple linear regression (MLR), simple linear regression (SLR), support vector regression (SVR) were used. Traditional methods of slope analysis (e.g., first established in the first half of the twentieth century) used widely as engineering design tools. Offering more progressive design tools, such as machine learning-based predictive algorithms, they draw the attention of many researchers. The main objective of the current study is to evaluate and optimize various machine learning-based and multilinear regression models predicting the safety factor. To prepare training and testing datasets for the predictive models, 630 finite limit equilibrium analysis modelling (i.e., a database including 504 training datasets and 126 testing datasets) were employed on a single-layered cohesive soil layer. The estimated results for the presented database from GPR, MLR, MLP, SLR, and SVR were assessed by various methods. Firstly, the efficiency of applied models was calculated employing various statistical indices. As a result, obtained total scores 20, 35, 50, 10, and 35, respectively for GPR, MLR, MLP, SLR, and SVR, revealed that the MLP outperformed other machine learning-based models. In addition, SVR and MLR presented an almost equal accuracy in estimation, for both training and testing phases. Note that, an acceptable degree of efficiency was obtained for GPR and SLR models. However, GPR showed more precision. Following this, the equation of applied MLP and MLR models (i.e., in their optimal condition) was derived, due to the reliability of their results, to be used in similar slope stability problems.

Strong ground motions usually trigger lots of slope failures in the affected area. In this work, we analyse the occurrence likelihood of earthquake-triggered landslide by employing the ensembles of adaptive neuro-fuzzy inference systems (ANFIS) with four well-known metaheuristics techniques, namely particle swarm optimization (PSO), genetic algorithm (GA), ant colony optimization (ACO), and differential evolution (DE) algorithms. Twelve landslide conditioning factors namely, elevation, slope degree, lithology, peak ground acceleration (PGA), stream power index (SPI), topographic wetness index (TWI), distance to road, distance to river, distance to fault, normalized difference vegetation index (NDVI), slope aspect, and plan curvature are considered within the geographic information system (GIS) to produce the required spatial database. In this paper, frequency ratio (FR) model is used to evaluate the spatial interaction between the landslides and conditioning factors. Meantime, among a total of 458 marked earthquake-induced landslides, 366 (80%) are specified to the learning process, and the remaining 92 (20%) landslides are used to evaluate the accuracy of applied models. The landslide susceptibility maps are generated in the GIS environment. Three accuracy criteria of mean square error (MSE), root mean square error (RMSE), and area under the receiving operating characteristic curve (AUROC) are used to develop a ranking system for comparing the integrity of the designed models. The total ranking scores (TRSs) of 15, 8, 10, and 18, respectively, obtained for PSO-ANFIS, GA-ANFIS, ACO-ANFIS, and DE-ANFIS revealed the superiority of the DE algorithm compared to other metaheuristics techniques. Also, the DE-ANFIS emerged as the fastest ensemble, due to the highest convergence speed obtained for this model.