Evaluation of Deep Learning against Conventional Limit Equilibrium Methods for Slope Stability Analysis

Featured Application This paper presents a comparison study with well-controlled data to evaluate two new deep learning methods and their relationships and differences with traditional methods. We implemented four widely accepted limit equilibrium analysis methods and compared their implementations and results with the newly proposed deep learning methods. This will lend engineers a clear reference regarding how deep learning works in comparison with traditional methods. With this paper, readers can easily see the potential and technical advantages of the new methods. This presents a good example to show the comparison between traditional physics-based approaches and the data-driven approaches and demonstrate how data-driven approaches can change or complement the traditional engineering practices. The work will help bridge the gap between traditional engineering analysis of geosystems and advanced engineering informatics and explore "big data" solutions for many similar engineering applications (e.g., with mechanical or stability analysis). This paper presents a comparison study between methods of deep learning as a new category of slope stability analysis, built upon the recent advances in artificial intelligence and conventional limit equilibrium analysis methods. For this purpose, computer code was developed to calculate the factor of safety (FS) using four limit equilibrium methods: Bishop's simplified method, the Fellenius method, Janbu's simplified method, and Janbu's corrected method. The code was verified against Slide2 in RocScience. Subsequently, the average FS values were used to approximate the "true" FS of the slopes for labeling the images for deep learning. Using this code, a comprehensive dataset of slope images with wide ranges of geometries and soil properties was created. The average FS values were used to label the images for implementing two deep learning models: a multiclass classification and a regression model. After training, the deep learning models were used to predict the FS of an independent set of slope images. Finally, the performance of the models was compared to that of the conventional methods. This study found that deep learning methods can reach accuracies as high as 99.71% while improving computational efficiency by more than 18 times compared with conventional methods.