Abstract
Artificial intelligence (AI)-based methods have been widely applied to slope stability assessment, but due to the scarcity of samples, most AI models are used under certain working conditions, such as the homogeneous or fixed-size slopes. In actual situations, the slope stability is affected by factors such as geometries, weak layers, etc. Therefore, in order to further consider more parameters affecting slope stability in AI models, this study used digital twin (DT) technique to build a database of the slopes with weak layers through practical cases. Meanwhile, in order to improve the prediction performance of the model, a convolutional neural network (CNN) is constructed. In this paper, the process of establishing a database of slopes with weak layers is elaborated in detail. Meanwhile, the performance of the CNN models is investigated thoroughly through several evaluators. Finally, the trained CNN is applied to actual slope cases. The results show that the CNN achieves the highest scores in a range under the receiver operating characteristics (0.99), accuracy (95.4%), and F1 score (95.3%) compared with other machine learning (ML) methods on the testing dataset, and also correctly classifies the actual slope cases, which provides valuable practical and engineering insights for slope stability assessment with weak layers in terms of efficiency and accuracy, especially for practitioners with limited knowledge of slope stability assessment.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig11_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig12_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11069-024-06674-2/MediaObjects/11069_2024_6674_Fig13_HTML.png)
Similar content being viewed by others
Abbreviations
- ML:
-
Machine learning
- AI:
-
Artificial intelligence
- GBM:
-
Gradient boosting machine
- SVM:
-
Support vector machine
- ANN:
-
Artificial neural network
- ELM:
-
Extreme learning machine
- DT:
-
Digital twin
- CNN:
-
Convolutional neural network
- LEM:
-
Limit equilibrium method
- FEM:
-
Finite element method
- XFEM:
-
Extended finite element method
- MAXPS:
-
Maximum principal stress
- MAXAPS:
-
Maximum allowable principal stress
- TGRA:
-
Three Gorges Reservoir Area
- TP:
-
True positive
- FP:
-
False positive
- h :
-
Height, m
- c:
-
Cohesion, kPa
- \(\gamma\) :
-
Unit weight, kN/m3
- \(\varphi\) :
-
Angle of internal friction, °
- \(F\) :
-
Equivalent external load, kN/m2
- \(\beta\) :
-
Slope angle, °
- \(c_{w}\) :
-
Cohesion of weak layer, kPa
- \(\varphi_{w}\) :
-
Angle of internal friction of weak layer, °
- \(x\) :
-
x Coordinate of centroid point of weak layer, m
- \(y\) :
-
y Coordinate of centroid point of weak layer, m
- \(\alpha\) :
-
Inclination of weak layer, °
- \(\theta\) :
-
Angle of weak layer, °
- \(l\) :
-
Length of weak layer, °
- ROC:
-
Receiver operating characteristic
- AUC:
-
Area under the curve
- TN:
-
True negative
- FN:
-
False negative
References
Alrasheedi F, Zhong X, Huang P-C (2023) Padding module: learning the padding in deep neural networks. IEEE Access 11:7348–7357
Aminpour M, Alaie R, Khosravi S, Kardani N, Moridpour S, Nazem M (2023) Slope stability machine learning predictions on spatially variable random fields with and without factor of safety calculations. Comput Geotech 153:105094
Asteris PG, Rizal FIM, Koopialipoor M, Roussis PC, Ferentinou M, Armaghani DJ, Gordan B (2022) Slope stability classification under seismic conditions using several tree-based intelligent techniques. Appl Sci 12(3):1753
Cai G, Che R, Kong X, Liu C, Zhao C (2017) Experimental investigation on tensile strength of unsaturated fine sands. J Hydraul Eng 48:623–631
Chen ZY (2004) Rock slope stability analysis—principle, methods and programs. China WaterPower Press, Bei**g (in Chinese)
Chen G (2013) Study of crack growth in rock mass based on XFEM. Master, Chongqing University, Chongqing, China
Chen B, Shen L, Zhang H (2023a) A hybrid proper orthogonal decomposition-heteroscedastic sparse Gaussian process regression model for evaluating structural reliability with correlated stochastic material properties. Struct Saf 100:102289
Chen G, Kang X, Lin M, Teng S, Liu Z (2023b) Stability prediction of soil slopes based on digital twinning and deep learning. Appl Sci 13:6470
Chen G, Deng W, Lin M, Lv J (2023c) Slope stability analysis based on convolutional neural network and digital twin. Nat Hazards 118:1427–1443
Du PZ, Liu J, Han ZQ, Xu H (2013) Stability analysis of high rock slope based on description of complex structure meticulous. Rock Soil Mech 34(1):393
Duncan J, Wright S (2014) Soil strength and slope stability. Wiley, New York
Feng ZW (2021) Reliability analysis of jointed rock slopes based on Baysian updating. Master, Nanchang University, Nanchang, China
Fu YP, Lin MS, Zhang Y, Chen GF, Liu YJ (2022) Slope stability analysis based on big data and convolutional neural network. Front Struct Civ Eng 16(7):882–895
Gao F (2015) Study on the cracking process of rock using the extended finite element method. Ph.D., China University of Mining and Technology, Bei**g
Garrido-Merchán EC, Hernández-Lobato D (2020) Dealing with categorical and integer-valued variables in Bayesian optimization with Gaussian processes. Neurocomputing 380:20–35
Hoang N-D, Pham A-D (2016) Hybrid artificial intelligence approach based on metaheuristic and machine learning for slope stability assessment: a multinational data analysis. Expert Syst Appl 46:60–68
Itasca Consulting Group Inc (2011) UDEC (Universal Distinct Element Code), Ver. 5.0. Minneapolis: Itasca
Jia Z, Peng J, Lu Q, Ma P, Qiao J, Wang F, Zang M, Liu Y, Zhao J, Zhu F (2023) A comprehensive method for the risk assessment of ground fissures: case study of the eastern Weihe basin. J Earth Sci 34(6):1892–1907
Jiang H, Chen M, Zhang G, ** Y, Zhao Z, Guifang Z (2009) Impact of oriented perforation on hydraulic fracture initiation and propagation. Chin J Rock Mech Eng 28(7):1321
Jiang S-H, Huang J, Huang F, Yang J, Yao C, Zhou C-B (2018) Modelling of spatial variability of soil undrained shear strength by conditional random fields for slope reliability analysis. Appl Math Model 63:374–389
Kardani N, Zhou A, Nazem M, Shen S-L (2021) Improved prediction of slope stability using a hybrid stacking ensemble method based on finite element analysis and field data. J Rock Mech Geotech Eng 13(1):188–201
Li SH, Luo XH, Wu LZ (2021) A new method for calculating failure probability of landslide based on ANN and a convex set model. Landslides 18(8):2855–2867
Lin MS, Teng S, Chen GF, Lv JB, Hao ZY (2022a) Optimal CNN-based semantic segmentation model of cutting slope images. Front Struct Civ Eng 16(4):414–433
Lin S, Zheng H, Han B, Li YY, Han C, Li W (2022b) Comparative performance of eight ensemble learning approaches for the development of models of slope stability prediction. Acta Geotech 17(4):1477–1502
Lin MS, Teng S, Chen GF, Bassir D (2023a) Transfer learning with attributes for improving the landslide spatial prediction performance in sample-scarce area based on variational autoencoder generative adversarial network. Land 12(3):525
Lin MS, Teng S, Chen GF, Hu B (2023b) Application of convolutional neural networks based on Bayesian optimization to landslide susceptibility map** of transmission tower foundation. Bull Eng Geol Environ 82:51
Liu Z, Shao J, Xu W, Chen H, Zhang Y (2014) An extreme learning machine approach for slope stability evaluation and prediction. Nat Hazards 73(2):787–804
Liu Y, Xu C, Huang B, Ren XW, Liu CQ, Hu BD, Chen Z (2020) Landslide displacement prediction based on multi-source data fusion and sensitivity states. Eng Geol 271:105608
Liu Z, Ma J, **a D, Jiang S, Ren Z, Tan C, Lei D, Guo H (2023) Toward the reliable prediction of reservoir landslide displacement using earthworm optimization algorithm-optimized support vector regression (EOA-SVR). Nat Hazards 120:1–24
Long Y, Li W, Huang R, Xu Q, Yu B, Liu G (2023) A comparative study of supervised classification methods for investigating landslide evolution in the Mianyuan River Basin, China. J Earth Sci 34(2):316–329
Luo XQ, Zheng AX (2018) Application of extended finite element method in modelling fracture of rock mass. Rock Soil Mech 39(2):728–734
Ma J, Lei D, Ren Z, Tan C, ** for the Three Gorges Reservoir Area, China. Math Geosci. https://doi.org/10.1007/s11004-023-10116-3
Mahmoodzadeh A, Mohammadi M, Farid Hama Ali H, Hashim Ibrahim H, Nariman Abdulhamid S, Nejati HR (2021) Prediction of safety factors for slope stability: comparison of machine learning techniques. Nat Hazards 111(2):1771–1799
Mohanty M, Sarkar R, Das SK (2023) Seismic performance of coal mine overburden dump slope using extended finite-element method-based Voronoi Tessellation Scheme. Int J Geomech 23(11):04023194
Munkholm L, Schjønning P, Kay B (2002) Tensile strength of soil cores in relation to aggregate strength, soil fragmentation and pore characteristics. Soil till Res 64:125–135
Pham K, Kim D, Choi HJ, Lee IM, Choi H (2018) A numerical framework for infinite slope stability analysis under transient unsaturated seepage conditions. Eng Geol 243:36–49
Pham K, Kim D, Park S, Choi H (2021) Ensemble learning-based classification models for slope stability analysis. CATENA 196:104886
Pradhan SP, Siddique T (2020) Stability assessment of landslide-prone road cut rock slopes in Himalayan terrain: a finite element method based approach. J Rock Mech Geotech Eng 12:67–77
Qin C, Zhou J (2023) On the seismic stability of soil slopes containing dual weak layers: true failure load assessment by finite-element limit-analysis. Acta Geotech 18:3153–3175
Tamrakar S, Totosawa Y, Itoh K (2005) Tensile strength of soil measured using newly developed tensile strength apparatus. Research reports of National Institute of Industrial Safety, pp 41–51
Teng S, Chen G, Gong P, Liu G, Cui F (2019) Structural damage detection using convolutional neural networks combining strain energy and dynamic response. Meccanica 55(4):945–959
Teng S, Chen X, Chen G, Cheng L, Bassir D (2022) Structural damage detection based on convolutional neural networks and population of bridges. Measurement 202:111747
Teng S, Chen X, Chen G, Cheng L (2023) Structural damage detection based on transfer learning strategy using digital twins of bridges. Mech Syst Signal Process 191:110160
Ullah K, Wang Y, Fang Z, Wang L, Rahman M (2022) Multi-hazard susceptibility map** based on convolutional neural networks. Geosci Front 13(5):101425
Wang JF, Yan TZ (1995) The technical investigation into random search for the most dangerout sliding plane in fissured rock slope. Paper presented at the the first meeting of the third session of geotechnical engineering, Wuhan
Wang JC, Chang LS, **a CH, Shi W, Deng K (2005) Study on stability of jointed rock slope of an open iron mine. Chin J Rock Mech Eng 24(18):3350
Wang Y, Li X, Wang M, Li M, Tian H (2013) Failure mechanism of top** rock slope using jointed finete element simulation method. Chin J Rock Mech Eng 32(2):3945
Zhang JD (2021) Smulation study of multiple cracks propagation in rock based on extended finite element method. Master, Inner Mongolia University of Science & Technology, Inner Mongolia, China
Zhang H, Zhu J, Wang J, Yuan Y, Feng L (2006) Experimental study of tensile strength of compacted gravel soil. Chin J Rock Mech Eng 25:4186–4190
Zhang H, Wu S, Zhang X, Han L, Zhang Z (2022) Slope stability prediction method based on the margin distance minimization selective ensemble. CATENA 212:106055
Zhao L-H, Cao J, Zhang Y, Luo Q (2015) Effect of hydraulic distribution on the stability of a plane slide rock slope under the nonlinear Barton-Bandis failure criterion. Geomech Eng 8(3):391–414
Zheng A (2015) Research on extend finite element method and its application in simulation of fracture propagation of rock mass. Ph.D., Shanghai Jiao Tong University, Shanghai
Zhou X, Chen J (2019) Extended finite element simulation of step-path brittle failure in rock slopes with non-persistent en-echelon joints. Eng Geol 250:65–88
Zhou S, Zhuang X, Zhu H, Rabczuk T (2018) Phase field modelling of crack propagation, branching and coalescence in rocks. Theor Appl Fract Mech 96:174–192
Zhou J, Li E, Yang S, Wang M, Shi X, Yao S, Mitri HS (2019) Slope stability prediction for circular mode failure using gradient boosting machine approach based on an updated database of case histories. Saf Sci 118:505–518
Funding
This article was not funded.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix 1
As shown in Fig.
14, the purpose of Experiment 1 is to compare the stress situation of the bottom edge between two slope models (complete and simplified) in order to ensure the correct application of the load. Here, layer 1 and layer 2 are considered to be the same elastic material, E = 100,000 kPa and μ = 0.35. The x-direction displacement of the left boundary and y-direction displacement of the bottom boundary of the slope are constrained. The body forces of layer 1 and layer 2 are − 20.0 kPa and − 19.63 kPa, respectively. The Mises stress results are shown in Fig. 14, and the stress distribution of the two cases is consistent. In addition, the total force in the Y direction of the bottom nodes of the original model and the simplified model is 37,730.8 and 37,730.9, respectively.
The purpose of Experiment 2 is to compare the stability coefficients of the original model and the simplified model. Based on Experiment 1, the slope layers are assigned the Mohr–Coulomb plasticity for layer 1 (c = 33.5 kPa and φ = 11.0°) and layer 2 (c = 11.9 kPa and φ = 20.0°). The bottom boundary condition was changed to displacement constraint in x- and y-directions. The left and right boundary conditions were changed to x-direction displacement constraint only. According to the results, the safety factor of the original model and the simplified model are 1.4 and 1.5, respectively. Other 59 models are analyzed in the same way, and the results of the safety factor are shown in Fig.
15. The safety factor of the simplified model is lower than that of the original model. Compared to the original model, the equivalent load of the simplified model is completely applied to layer 1, resulting in a decrease in the safety factor. However, the R2 remained at 0.84 in both cases, indicating a small deviation. Therefore, this article simplifies the upper slope as an equivalent load in the stability analyses of the slopes.
Appendix 2
The hyperparameters of ELM are the transfer function and the number of hidden neurons, and their relationship with the prediction performance is shown in Fig.
16. It can be seen that the prediction performance of the model is mainly influenced by the transfer function compared to the number of hidden neurons. When Sine and Sigmoidal transfer functions are used, the effect is better than Hardlim.
For SVMs, there are five hyperparameters: standardization, kernel function, polynomial order, kernel scale and box constraint. Among them, polynomial order must be selected when polynomial is selected as the kernel function, and kernel scale must be selected when Gaussian is selected as the kernel function. The relationship between the five hyperparameters and prediction performance is shown in Fig.
17. For parameter sensitivity, model performance is less affected by standardization. For kernel functions, the Gaussian prediction model performs best, followed by the polynomial, and then the linear. Performance is not affected by the box constraint, but is more affected by the polynomial order or kernel scale values for certain kernel functions.
For decision trees, there are three hyperparameters to vary: minimum leaf size, Maximum number of splits and split criterion. The sensitivity of these parameters to the predictive performance is shown in Fig.
18. Compared to the split criterion, minimum leaf size and maximum split number have a strong correlation with the prediction performance. Smaller minimum leaf size and larger maximum split numbers are beneficial for improving the prediction performance of the model. When minimum leaf size = 1, maximum split number = 1024 and split criterion = deviation, the decision tree achieves the best predictive performance.
Overall, the sensitivity analysis of hyperparameters in traditional machine learning is best observed by the control variable method. However, due to the large number of hyperparameters, the sensitivity analysis of hyperparameters in traditional machine learning should be further explored in detail in future research.
Appendix 3
See Table 7.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Lin, M., Zeng, L., Teng, S. et al. Prediction of stability of a slope with weak layers using convolutional neural networks. Nat Hazards (2024). https://doi.org/10.1007/s11069-024-06674-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11069-024-06674-2