Evaluation of Deep Learning against Conventional Limit Equilibrium Methods for Slope 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.

[1]  Hin Wai Lui,et al.  Multiclass classification of myocardial infarction with convolutional and recurrent neural networks for portable ECG devices , 2018 .

[2]  Buse Melis Ozyildirim,et al.  Comparison of convolutional neural network models for food image classification , 2017, INISTA.

[3]  Rodrigo Salgado,et al.  Stability Analysis of Complex Soil Slopes using Limit Analysis , 2002 .

[4]  Alexander Rohe,et al.  Experimental and numerical investigations of dyke failures involving soft materials , 2017 .

[5]  Jiahao Deng,et al.  Prediction of landslide displacement with an ensemble-based extreme learning machine and copula models , 2018, Landslides.

[6]  Hai‐Sui Yu,et al.  Limit Analysis versus Limit Equilibrium for Slope Stability , 1999 .

[7]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[8]  A. Troncone,et al.  Prediction of rainfall-induced landslide movements in the presence of stabilizing piles , 2021, Engineering Geology.

[9]  P. Zeng,et al.  Prediction of Slope Stability using Naive Bayes Classifier , 2018 .

[10]  R. Lewis,et al.  Associated and non-associated visco-plasticity and plasticity in soil mechanics , 1975 .

[11]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[12]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.

[13]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[14]  Kenichi Soga,et al.  Trends in large-deformation analysis of landslide mass movements with particular emphasis on the material point method , 2016 .

[15]  J. M. Duncan,et al.  Accuracy of Equilibrium Slope Stability Analysis , 1973 .

[16]  J. M. Duncan,et al.  The accuracy of equilibrium methods of slope stability analysis , 1980 .

[17]  Radu Horaud,et al.  A Comprehensive Analysis of Deep Regression , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  N. Janbu,et al.  Slope stability computations : In Embankment-dam Engineering. Textbook. Eds. R.C. Hirschfeld and S.J. Poulos. JOHN WILEY AND SONS INC., PUB., NY, 1973, 40P , 1975 .

[19]  Moncef Gabbouj,et al.  Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks , 2017 .

[20]  D. Fredlund,et al.  Comparison of slope stability methods of analysis , 1977 .

[21]  J. M. Duncan.  State of the Art: Limit Equilibrium and Finite-Element Analysis of Slopes , 1996 .

[22]  Michael S. Lew,et al.  Deep learning for visual understanding: A review , 2016, Neurocomputing.

[23]  Chongke Bi,et al.  Machine learning based fast multi-layer liquefaction disaster assessment , 2018, World Wide Web.

[24]  Y. M. Cheng,et al.  Two-dimensional slope stability analysis by limit equilibrium and strength reduction methods , 2007 .

[25]  A. Bishop.  The use of the Slip Circle in the Stability Analysis of Slopes , 1955 .

[26]  Hong Hao,et al.  Micro-seismic event detection and location in underground mines by using Convolutional Neural Networks (CNN) and deep learning , 2018 .

[27]  Qian Chen,et al.  Image enhancement based on equal area dualistic sub-image histogram equalization method , 1999, IEEE Trans. Consumer Electron..

[28]  Yuhao Wang,et al.  A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility prediction , 2019, Landslides.

[29]  Peiyun Xu,et al.  Dynamic development of landslide susceptibility based on slope unit and deep neural networks , 2020, Landslides.

[30]  R Whitman,et al.  USE OF COMPUTERS FOR SLOPE STABILITY ANALYSIS , 1966 .

[31]  D. Sulsky,et al.  A particle method for history-dependent materials , 1993 .

[32]  R. H. Chen,et al.  THREE-DIMENSIONAL LIMIT EQUILIBRIUM ANALYSIS OF SLOPES , 1983 .

[33]  A. Troncone,et al.  Post-failure analysis of the Maierato landslide using the material point method , 2020 .

[34]  Yang Liu,et al.  Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces Using a Deep‐Learning Network , 2017, Comput. Aided Civ. Infrastructure Eng..

[35]  Quoc-Lam Nguyen,et al.  Automatic recognition of asphalt pavement cracks using metaheuristic optimized edge detection algorithms and convolution neural network , 2018, Automation in Construction.

[36]  Qiang Xu,et al.  Modeling and predicting reservoir landslide displacement with deep belief network and EWMA control charts: a case study in Three Gorges Reservoir , 2019, Landslides.

[37]  Sung-Chi Hsu,et al.  Material Spatial Variability and Slope Stability for Weak Rock Masses , 2006 .

[38]  E. Alonso.  Triggering and motion of landslides , 2017 .