Three‐dimensional slope stability predictions using artificial neural networks

Abstract

To enable assess slope stability problems efficiently, various machine learning algorithms have been proposed recently. However, these developments are restricted to two‐dimensional slope stability analyses (plane strain assumption), although the two‐dimensional results can be very conservative. In this study, artificial neural networks are adopted and trained to predict three‐dimensional slope stability and a program, SlopeLab has been developed with a graphical user interface. To reduce the number of variables, groups of dimensionless parameters to express stability of slopes in classic stability charts are adopted to construct the neural network architecture. The model has been trained with a dataset from slope stability charts for fully cohesive and cohesive‐frictional soils. Furthermore, the impact of concave plan curvature on slope stability that is usually found by excavation in practice is investigated by introducing a dimensionless parameter, relative curvature radius. Slope stability analyses have been conducted with numerical calculations and the artificial neural networks are trained with dimensionless data. The performance of the trained artificial neural networks has been evaluated with the correlation coefficient (R) and root mean square error (RMSE). High accuracy has been found in all the trained models in which R > 0.999 and RMSE < 0.15. Most importantly, the proposed program can help engineers to estimate 3D effects of a slope quickly from the ratio of the factors of safety, FS3D/FS2D. When FS3D/FS2D is large (such as larger than 1.2), a 3D numerical modelling on slope stability analyses that can consider complex 3D geometry and boundary condition is advised.

3D large-scale numerical model of open-pit lake slope stability—case study of Lake Most

“…The slope safety is generally assessed with a global safety factor (SF) (the ratio of slip resistance forces to the shear forces). To compute a safety factor for a slope, 4 different numerical methods can be employed: the strength reduction method (Zienkiewicz et al 1975; Matsui and San 1992; Dawson et al 1999; Griffiths and Lane 1999; Soren et al 2014), the limit analysis (statically admissible stress field and kinematically admissible deformation, Qiujing et al 2017), the limit equilibrium method (an approximate method assuming the existence of a slip surface of simple shape, Bishop 1955;Jaeger 1971;Fredlund and Krahn 1977; Hoek and Bray 1981; Chen and Chameau 1982; Goodman 1989) and artificial neural networks (machine learning, Meng et al 2021). Nowadays, the coupled analysis approach is receiving more attention in recent years because powerful numerical tools (2D and 3D finite element/difference analyses) are becoming easily available (Vanneschi et al 2018).…”

Comparative Assessment of Various Artificial Neural Network Techniques for Estimating the Safety Factor of Road Embankments

“…Previously, ANN was used in various civil engineering problems, such as concrete mixtures' mechanical properties prediction [9,10,11,12], damage detection [13,14,15], structural response estimation [16,17,18], soil behavior modeling [19,20,21]. On the other hand, multiple models using the feed-forward back-propagation neural network technique were developed for slope stability evaluation [22,23,24,25,26]. Das et al [27] proposed a differential evolution neural network model for estimating slope safety factors.…”

Base resistance of super-large and long piles in soft soil: performance of artificial neural network model and field implications

“…In recent years, the use of data-based techniques such as machine learning (ML) to predict geotechnical issues has received increasing attentions [26,64,68,72]. Of numerous emerging ML techniques, artificial neural networks (ANN) is the most common approach to develop forecasting models of various geotechnical issues such as slope stability [40], soil properties [29,48], bearing capacity [7,28], deep excavation [2,71], mining [12,57], tunnelling [59], jet grouting [58], among others. As strictly developed based on existing data, the quality and size of data play a pivotal role in building ANN models.…”