Slope stability analysis based on big data and convolutional neural network

doi:10.1007/s11709-022-0859-4

Front. Struct. Civ. Eng.

2022, Vol. 16

Issue (7) : 882-895 https://doi.org/10.1007/s11709-022-0859-4

RESEARCH ARTICLE

Slope stability analysis based on big data and convolutional neural network

Yangpan FU, Mansheng LIN, You ZHANG, Gongfa CHEN(

), Yongjian LIU

School of Civil and Transportation Engineering, Guangdong University of Technology, Guangzhou 510006, China

Download: PDF(5282 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

The Limit Equilibrium Method (LEM) is commonly used in traditional slope stability analyses, but it is time-consuming and complicated. Due to its complexity and nonlinearity involved in the evaluation process, it cannot provide a quick stability estimation when facing a large number of slopes. In this case, the convolutional neural network (CNN) provides a better alternative. A CNN model can process data quickly and complete a large amount of data analysis in a specific situation, while it needs a large number of training samples. It is difficult to get enough slope data samples in practical engineering. This study proposes a slope database generation method based on the LEM. Samples were amplified from 40 typical slopes, and a sample database consisting of 20000 slope samples was established. The sample database for slopes covered a wide range of slope geometries and soil layers’ physical and mechanical properties. The CNN trained with this sample database was then applied to the stability prediction of 15 real slopes to test the accuracy of the CNN model. The results show that the slope stability prediction method based on the CNN does not need complex calculation but only needs to provide the slope coordinate information and physical and mechanical parameters of the soil layers, and it can quickly obtain the safety factor and stability state of the slopes. Moreover, the prediction accuracy of the CNN trained by the sample database for slope stability analysis reaches more than 99%, and the comparisons with the BP neural network show that the CNN has significant superiority in slope stability evaluation. Therefore, the CNN can predict the safety factor of real slopes. In particular, the combination of typical actual slopes and generated slope data provides enough training and testing samples for the CNN, which improves the prediction speed and practicability of the CNN-based evaluation method in engineering practice.

Keywords slope stability limit equilibrium method convolutional neural network database for slopes big data

Corresponding Author(s): Gongfa CHEN

Just Accepted Date: 17 August 2022 Online First Date: 20 October 2022 Issue Date: 17 November 2022

Cite this article:

Yangpan FU,Mansheng LIN,You ZHANG, et al. Slope stability analysis based on big data and convolutional neural network[J]. Front. Struct. Civ. Eng., 2022, 16(7): 882-895.

URL:

https://academic.hep.com.cn/fsce/EN/10.1007/s11709-022-0859-4
https://academic.hep.com.cn/fsce/EN/Y2022/V16/I7/882

Fig.1 Numerical analysis process.

Tab.1 Physical and mechanical parameters of slopes

Fig.2 Schematic diagram of extracting slope data.

Fig.3 Simplified real slope. (a) Landslide in Chengdu city (China); (b) the Frank slide (France); (c) soil vertical high slope in Jincheng city (China); (d) slope of Chongqing hydropower station (China).

Fig.4 Arc sliding surface.

Fig.5 Calculation process of soil strip weight.

Fig.6 Calculation of safety factor.

Fig.7 Sample amplification process of a single slope.

slope name	soil layer number	cohesion $c$ (kN/m²)	internal friction angle $φ$ (° )	natural bulk density $γ$ (kN/m³)	saturated unit weight $γ s a t$ (kN/m³)
original slope 1	first layer	15.0 ± R%	12.0 ± R%	20.0 ± R%	15.0 ± R%
	second layer	35.0 ± R%	30.0 ± R%	25.0 ± R%	23.0 ± R%
	third layer	39.0 ± R%	32.0 ± R%	27.0 ± R%	25.0 ± R%
	fourth layer	42.0 ± R%	36.0± R%	35.0 ± R%	30.0 ± R%
original slope 2	first layer	35.0 ± R%	24.0 ± R%	18.0 ± R%	19.0 ± R%
	second layer	35.0 ± R%	32.0 ± R%	24.0 ± R%	25.0 ± R%
	third layer	50.0 ± R%	46.0 ± R%	28.0 ± R%	29.0 ± R%
	fourth layer	54.0 ± R%	50.0 ± R%	34.0 ± R%	35.0 ± R%
original slope 3	first layer	10.0 ± R%	8.0 ± R%	15.0 ± R%	15.0 ± R%
	second layer	20.0 ± R%	8.0 ± R%	20.0 ± R%	20.0 ± R%
	third layer	50 ± R%	20.0 ± R%	25.0 ± R%	25.0 ± R%
	fourth layer	55 ± R%	50.0 ± R%	32.0 ± R%	33.0 ± R%

Tab.2 Modification rules of physical and mechanical parameters of soil laysers

Fig.8 Samples of original slopes. (a) Original slope 1; (b) original slope 2; (c) original slope 3.

Fig.9 Generated slope samples. (a) Generated slope 1-1; (b) generated slope 2-1; (c) generated slope 3-1; (d) generated slope 1-2; (e) generated slope 2-2; (f) generated slope 3-2; (g) generated slope 1-3; (h) generated slope 2-3; (i) generated slope 3-3.

column	description
1–4	$C, φ, γ, γ s$
5–44	key point coordinates
45–88	second layer data
89–132	third layer data
133–176	fourth layer data

Tab.3 Arrangement of slope data

Tab.4 CNN parameters

Fig.10 Network model structure.

Tab.5 Classification of slope stability

Tab.6 Prediction result and error value of CNN

Fig.11 Variation of accuracy rate.

Fig.12 Variation of loss function.

Fig.13 Classification and prediction results of slope stability of validation set (1D-CNN).

Fig.14 MSE value change of BP neural network.

Fig.15 Fitting effect of BP neural network. (a) Predictive effect of training samples; (b) predictive effect of validation samples; (c) predictive effect of test samples; (d) predictive effect of all samples.

Fig.16 Classification and prediction results of slope stability for validation set (BP).

Fig.17 Stability prediction results of actual slopes based on 1D-CNN.

Tab.7 Prediction result and error value of CNN

Fig.18 Errors of CNN prediction results.

1	G C Komadja, S P Pradhan, A R Roul, B Adebayo, J B Habinshuti, L A Glodji, A P Onwualu. Assessment of stability of a Himalayan road cut slope with varying degrees of weathering: A finite-element-model-based approach. Heliyon, 2020, 6(11): e05297
2	S P Pradhan, T Siddique. Stability assessment of landslide-prone road cut rock slopes in Himalayan terrain: A finite element method based approach. Journal of Rock Mechanics and Geotechnical Engineering, 2020, 12: 63–77
3	S Y Liu, L T Shao, H J Li. Slope stability analysis using the limit equilibrium method and two finite element methods. Computers and Geotechnics, 2015, 63: 291–298 https://doi.org/10.1016/j.compgeo.2014.10.008
4	M W Agam, M H M Hashim, M I Murad, H Zabidi. Slope sensitivity analysis using spencer’s method in comparison with general limit equilibrium method. Procedia Chemistry, 2016, 19: 651–658 https://doi.org/10.1016/j.proche.2016.03.066
5	B S Firincioglu, M Ercanoglu. Insights and perspectives into the limit equilibrium method from 2D and 3D analyses. Engineering Geology, 2021, 281: 105968 https://doi.org/10.1016/j.enggeo.2020.105968
6	J Liu, J Li, J Y Huo, L N Liu. Application of improved artificial fish swarm algorithm to slope stability analysis. Advanced Materials Research, 2012, 12: 1861–1866
7	J Ji, W Zhang, F Zhang, Y Gao, Q Lu. Reliability analysis on permanent displacement of earth slopes using the simplified bishop method. Computers and Geotechnics, 2020, 117: 103286 https://doi.org/10.1016/j.compgeo.2019.103286
8	M W Agam, M H M Hashim, M I Murad, H Zabidi. Slope sensitivity analysis using spencer’s method in comparison with general limit equilibrium method. Procedia Chemistry, 2016, 19: 651–658 https://doi.org/10.1016/j.proche.2016.03.066
9	R J Li, Q Xu, W Zheng, H C Lin. The stability analyses of unsaturated slope based on the sarma method. Advanced Materials Research, 2012, 393: 1569–1573 https://doi.org/10.4028/www.scientific.net/AMR.393-395.1569
10	X P Zhou, H Cheng. Stability analysis of three-dimensional seismic landslides using the rigorous limit equilibrium method. Engineering Geology, 2014, 174: 87–102 https://doi.org/10.1016/j.enggeo.2014.03.009
11	Y Zheng, C Chen, F Meng, T Liu, K Xia. Assessing the stability of rock slopes with respect to flexural toppling failure using a limit equilibrium model and genetic algorithm. Computers and Geotechnics, 2020, 124: 103619 https://doi.org/10.1016/j.compgeo.2020.103619
12	Y Zhang. Multi-slicing strategy for the three-dimensional discontinuity layout optimization (3D DLO). International Journal for Numerical and Analytical Methods in Geomechanics, 2017, 41(4): 488–507 https://doi.org/10.1002/nag.2566
13	Y Zhang, X Zhuang. Cracking elements: A self-propagating strong discontinuity embedded approach for quasi-brittle fracture. Finite Elements in Analysis and Design, 2018, 144: 84–100 https://doi.org/10.1016/j.finel.2017.10.007
14	Y Zhang, X Zhuang, R Lackner. Stability analysis of shotcrete supported crown of NATM tunnels with discontinuity layout optimization. International Journal for Numerical and Analytical Methods in Geomechanics, 2018, 42(11): 1199–1216 https://doi.org/10.1002/nag.2775
15	T Rabczuk, T Belytschko. Cracking particles: A simplified meshfree method for arbitrary evolving cracks. International Journal for Numerical Methods in Engineering, 2004, 61(13): 2316–2343 https://doi.org/10.1002/nme.1151
16	H Niu. Smart safety early warning model of landslide geological hazard based on BP neural network. Safety Science, 2020, 12(3): 154–172 https://doi.org/10.1016/j.ssci.2019.104572
17	Z G Qian, A J Li, W C Chen, A V Lyamin, J C Jiang. An artificial neural network approach to inhomogeneous soil slope stability predictions based on limit analysis methods. Soils and foundations, 2019, 59(2): 556–569
18	R B Kaunda, R B Chase, A E Kehew, K Kaugars, J P Selegean. Neural network modeling applications in active slope stability problems. Environmental Earth Sciences, 2010, 60(7): 1545–1558
19	A K Verma, T N Singh, N K Chauhan, K Sarkar. A hybrid FEM–ANN approach for slope instability prediction. Journal of the Institution of Engineers, 2016, 97(3): 1–10 https://doi.org/10.1007/s40030-016-0168-9
20	Z Teng, S Teng, J Zhang, G Chen, F Cui. Structural damage detection based on real-time vibration signal and convolutional neural network. Applied Sciences (Basel, Switzerland), 2020, 10(14): 4720 https://doi.org/10.3390/app10144720
21	Z Han, H Chen, Y Liu, Y Li, Y Du, H Zhang. Vision-based crack detection of asphalt pavement using deep convolutional neural network. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 2021, 45(3): 2047–2055 https://doi.org/10.1007/s40996-021-00668-x
22	M Islam, J M Kim. Vision-based autonomous crack detection of concrete structures using a fully convolutional encoder–decoder network. Sensors (Basel), 2019, 19(19): 4251 https://doi.org/10.3390/s19194251
23	X Yang, Y Chen, S Teng, G Chen. A novel method for predicting local site amplification factors using 1-D convolutional neural networks. Applied Sciences (Basel, Switzerland), 2021, 11(24): 11650 https://doi.org/10.3390/app112411650
24	S Teng, G Chen, P Gong, G Liu, F Cui. Structural damage detection using convolutional neural networks combining strain energy and dynamic response. Meccanica, 2020, 55(4): 945–959 https://doi.org/10.1007/s11012-019-01052-w
25	R Yang, Y Li, B Qin, D Zhao, Y Gan, J Zheng. Pesticide detection combining the Wasserstein generative adversarial network and the residual neural network based on terahertz spectroscopy. RSC Advances, 2022, 12(3): 1769–1776 https://doi.org/10.1039/D1RA06905E
26	Y Ishii, K Ota, S Kuraoka, R Tsunaki. Evaluation of slope stability by finite element method using observed displacement of landslide. Landslides, 2012, 9(3): 335–348 https://doi.org/10.1007/s10346-011-0303-7
27	D Li, L Yan, L Wu, K Yin, C Leo. The Hejiapingzi landslide in Weining County, Guizhou Province, southwest China: A recent slow-moving landslide triggered by reservoir drawdown. Landslides, 2019, 16(7): 1353–1365 https://doi.org/10.1007/s10346-019-01189-5
28	M Kumar, V Krishnaveni, S Muthukumar. Geotechnical investigation and numerical analysis of slope failure: A case study of landslide vulnerability zone in Kolli Hills, Tamil Nadu. Journal of the Geological Society of India, 2021, 97(5): 513–519 https://doi.org/10.1007/s12594-021-1717-z
29	A Kaya, Ü M Midilli. Slope stability evaluation and monitoring of a landslide: A case study from NE Turkey. Journal of Mountain Science, 2020, 17(11): 2624–2635 https://doi.org/10.1007/s11629-020-6306-x
30	F Tschuchnigg, I Oberhollenzer. Slope stability analysis: Limit analysis vs strength reduction FEA. In: International Conference of the International Association for Computer Methods and Advances in Geomechanics. Turin: Springer, 2021, 498–506
31	D V Griffiths. Advanced Numerical Applications and Plasticity in Geomechanics. Vienna: Springer, 2001, 159–229
32	D Aringoli, M Materazzi, B Gentili, G Pambianchi, N Sciarra. Engineering Geology for Society and Territory-Volume 2. Cham: Springer, 2015, 1371–1376
33	J S Cai, T Yeh, E C Yan, R Tang, Y H Hao. Design of borehole deployments for slope stability analysis based on a probabilistic approach. Computers and Geotechnics, 2021, 133: 103909 https://doi.org/10.1016/j.compgeo.2020.103909
34	Z Su, L Shao. A three-dimensional slope stability analysis method based on finite element method stress analysis. Engineering Geology, 2021, 280: 105910 https://doi.org/10.1016/j.enggeo.2020.105910
35	Baker RGarber M. Theoretical Analysis of The Stability of Slopes. London: Thomas Telford Limited, 1978
36	Z Chen, N R Morgenstern. Extensions to the generalized method of slices for stability analysis. Canadian Geotechnical Journal, 1983, 20(1): 104–119 https://doi.org/10.1139/t83-010
37	Z Chen. Soil Slope Stability Analysis: Theory, Methods, and Programs. Beijing: China Water Power Press, 2003 (in Chinese)

[1]	Shiguo XIAO, Shaohong LI. LSSVM-based approach for refining soil failure criteria and calculating safety factor of slopes[J]. Front. Struct. Civ. Eng., 2022, 16(7): 871-881.
[2]	Zaobao LIU, Yongchen WANG, Long LI, Xingli FANG, Junze WANG. Realtime prediction of hard rock TBM advance rate using temporal convolutional network (TCN) with tunnel construction big data[J]. Front. Struct. Civ. Eng., 2022, 16(4): 401-413.
[3]	Guangyu DAI, Fei ZHANG, Yuke WANG. Stability analysis of layered slopes in unsaturated soils[J]. Front. Struct. Civ. Eng., 2022, 16(3): 378-387.
[4]	Amit SHIULY, Debabrata DUTTA, Achintya MONDAL. Assessing compressive strengths of mortar and concrete from digital images by machine learning techniques[J]. Front. Struct. Civ. Eng., 2022, 16(3): 347-358.
[5]	Bernardino CHIAIA, Giulia MARASCO, Salvatore AIELLO. Deep convolutional neural network for multi-level non-invasive tunnel lining assessment[J]. Front. Struct. Civ. Eng., 2022, 16(2): 214-223.
[6]	Shan LIN, Hong ZHENG, Chao HAN, Bei HAN, Wei LI. Evaluation and prediction of slope stability using machine learning approaches[J]. Front. Struct. Civ. Eng., 2021, 15(4): 821-833.
[7]	Pierclaudio SAVINO, Francesco TONDOLO. Automated classification of civil structure defects based on convolutional neural network[J]. Front. Struct. Civ. Eng., 2021, 15(2): 305-317.
[8]	Suman HAZARI, Sima GHOSH, Richi Prasad SHARMA. New pseudo-dynamic analysis of two-layered cohesive-friction soil slope and its numerical validation[J]. Front. Struct. Civ. Eng., 2020, 14(6): 1492-1508.
[9]	Wengang ZHANG, Libin TANG, Hongrui LI, Lin WANG, Longfei CHENG, Tingqiang ZHOU, Xiang CHEN. Probabilistic stability analysis of Bazimen landslide with monitored rainfall data and water level fluctuations in Three Gorges Reservoir, China[J]. Front. Struct. Civ. Eng., 2020, 14(5): 1247-1261.
[10]	Yundong ZHOU, Fei ZHANG, Jingquan Wang, Yufeng GAO, Guangyu DAI. Seismic stability of earth slopes with tension crack[J]. Front. Struct. Civ. Eng., 2019, 13(4): 950-964.
[11]	Daniel R. VANDENBERGE. Total stress rapid drawdown analysis of the Pilarcitos Dam failure using the finite element method[J]. Front. Struct. Civ. Eng., 2014, 8(2): 115-123.
[12]	Liu HE, Guang WU, Hua WANG. Study of base friction simulation tests based on a complicated engineered bridge slope[J]. Front Struc Civil Eng, 2012, 6(4): 393-397.
[13]	LI Liang, CHI Shichun, LIN Gao, CHENG Yungming. Improved genetic algorithm and its application to determination of critical slip surface with arbitrary shape in soil slope[J]. Front. Struct. Civ. Eng., 2008, 2(2): 145-150.

Viewed

Full text

Abstract

Cited

Shared

Discussed