Abstract
In this work, three machine learning (ML) techniques i.e., multivariate adaptive regression splines (MARS), support vector machine (SVM), and least square vector machine (LSSVM) have been used to conduct a reliability analysis of a railway embankment situated in the Mokama district of the state of Bihar, India based on 3D slope failure investigation. The probabilistic assessment of the railway embankment is important as it incorporates risk estimates of a real-life structure against various uncertain loading conditions. The main goal of the analysis is to evaluate the stability of the embankment in three dimensions while taking pore pressure and seismic impacts into consideration. Using Scoops-3D software, the Factor of Safety (FOS) of the embankment is calculated based on Bishop’s Simplified Method. Notably, to determine the reliability index (β), the study takes uncertainties resulting from geographical differences in soil parameters into account. Our findings show that the railway embankment functions admirably under various loading conditions. For the training and testing datasets, error markers such as root mean squared error (RMSE), Weighted Mean Absolute Percentage Error (WMAPE), Nash–Sutcliffe coefficient (NS), Performance index (PI), Maximum determination coefficient value (R2), Adjusted R2, Scatter Index (SI), Uncertainty at 95% (U95), Objective function (OBJ) criterion values are determined to assess the models’ capacity for prediction. By proving the effectiveness of machine learning approaches in capturing complex interactions and uncertainties, this research advances the subject of railway embankment stability evaluation. Among the evaluated models, the LSSVM model proved to be the best accurate predictor.
Similar content being viewed by others
Data availability
Data will be made available on request.
Abbreviations
- \(c^{\prime}\) :
-
Cohesion
- \(\phi^{\prime}\) :
-
Internal frictional angle
- \(\gamma\) :
-
Unit weight of soil
- \({k}_{h}\) :
-
Horizontal seismic coefficient
- \({r}_{u}\) :
-
Pore water pressure coefficient
- \({\sigma }_{n}\) :
-
Normal stress
- \(u\) :
-
Developed pore water pressure on the shearing surface
- H :
-
Horizontal shear force
- X :
-
Vertical shear force
- E :
-
Inter-column normal force
- \({\varepsilon }_{j,k}\) :
-
True angle of dip
- \({\propto }_{j,k}\) :
-
Apparent angle of dip
- \({S}_{j,k}\) :
-
Mobilized shear resistance
- \({N}_{j,k}\) :
-
Normal force acting on a column \(j,k\)
- \({U}_{j,k}\) :
-
Uplifting force normal
- \(\tau\) :
-
Shear force
- \({W}_{j,k}\) :
-
Weight of \(j,k\) column
- \({h}_{j,k}\) :
-
The moment arm for horizontal driving force on a \(j,k\) column
- \({R}_{j,k}\) :
-
The distance from the axis of rotation to the centre of the base of a \(j,k\) column;
- \({\gamma }_{t}\) :
-
Is the total unit weight
- \({B}_{m} \left(x\right),\left({C}_{m}\right)\) :
-
Basis function used in MARS
- \({a}_{0}\) and \({a}_{m}\) :
-
Undetermined constants
- GCV:
-
Generalized cross-validation
- \(C\left(B\right),C(M)\) :
-
Penalty factor
- \(\xi\) :
-
Relaxation variable
- \({X}_{\mathrm{max}}\),\({ X}_{\mathrm{min}}\) and \({X}_{j}\) :
-
Maximum, minimum, and any values of the parameter under consideration, respectively
- R 2 :
-
Maximum determination coefficient value
- \({\mathrm{Adj}.R}^{2}\) :
-
Adjusted determination coefficient
- RMSE:
-
Root-mean-square error
- WMAPE:
-
Weighted mean absolute percentage error
- NS:
-
Nash–Sutcliffe coefficient
- PI:
-
Performance index
- SI:
-
Scatter Index
- \(\beta\) :
-
Reliability index
- \({P}_{\mathrm{f}}\) :
-
Probability of failure
- SD:
-
Standard deviation
- U95 :
-
Uncertainty at 95% confidence
- OBJ:
-
Objective function
References
Adamowski J, Chan HF, Prasher SO, Sharda VN (2012) Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data. J Hydroinf 14(3):731–744. https://doi.org/10.2166/hydro.2011.044
Alonso EE (1977) Risk analysis of slopes and its application to slopes in Canadian sensitive clays. Geotechnique 27(2):254–258. https://doi.org/10.1680/geot.1977.27.2.254
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
Azam A, Bardhan A, Kaloop MR, Samui P, Alanazi F, Alzara M, Yosri AM (2022) Modeling resilient modulus of subgrade soils using LSSVM optimized with swarm intelligence algorithms. Sci Rep 12(1):14454
Bardhan A, Samui P (2022) Application of artificial intelligence techniques in slope stability analysis. Int J Geotechn Earthq Eng 13(1):1–22. https://doi.org/10.4018/ijgee.298988
Bardhan A, Dhilipkumar B, Mulagala L, Samui P (2022a) Application of bi-directional extreme learning machine in predicting stability of slope of railway embankment in seismic condition. Lecture notes in civil engineering. Springer, Singapore, pp 11–22
Bardhan A, Kardani N, Alzo’ubi AK, Roy B, Samui P, Gandomi AH (2022b) Novel integration of extreme learning machine and improved Harris hawks optimization with particle swarm optimization-based mutation for predicting soil consolidation parameter. J Rock Mech Geotechn Eng 14(5):1588–1608. https://doi.org/10.1016/j.jrmge.2021.12.018
Bishop AW (1955) The use of the slip circle in the stability analysis of slopes. Geotechnique 5(1):7–17. https://doi.org/10.1680/geot.1955.5.1.7
Biswas R, Rai B, Samui P, Roy SS (2020) Estimating concrete compressive strength using MARS, LSSVM and GP. Eng J 24(2):41–52
Bucher CG, Bourgund U (1990) A fast and efficient response surface approach for structural reliability problems. Struct Saf 7(1):57–66. https://doi.org/10.1016/0167-4730(90)90012-E
Cavounidis S (1987) On the ratio of factors of safety in slope stability analyses. Geotechnique 37(2):207–210. https://doi.org/10.1680/geot.1987.37.2.207
Chakraborty A, Goswami D (2021) Three-dimensional (3D) slope stability analysis using stability charts. Int J Geotechn Eng 15(5):642–649. https://doi.org/10.1080/19386362.2018.1465743
Chen RH, Chameau JL (1983) Three-dimensional limit equilibrium analysis of slopes. Geotechnique 33(1):31–40. https://doi.org/10.1680/geot.1983.33.1.31
Christian JT, Ladd CC, Baecher GB (1994) Reliability applied to slope stability analysis. J Geotechn Eng 120(12):2180–2207. https://doi.org/10.1061/(ASCE)0733-9410(1994)120:12(2180)
Deng DP, Zhao LH, Li L (2015) Limit equilibrium slope stability analysis using the nonlinear strength failure criterion. Can Geotech J 52(5):563–576. https://doi.org/10.1139/cgj-2014-0111
El-Ramly H, Morgenstern NR, Cruden DM (2002) Probabilistic slope stability analysis for practice. Can Geotechn J 39(3):665–683. https://doi.org/10.1139/t02-034
El-Ramly H, Morgenstern NR, Cruden DM (2006) Probabilistic assessment of stability of a cut slope in residual soil. Risk and variability in geotechnical engineering, vol 55. Thomas Telford Ltd., London, pp 197–204
Esmaeili-Falak M, Benemaran RS (2023) Ensemble deep learning-based models to predict the resilient modulus of modified base materials subjected to wet-dry cycles. Geomech Eng 32(6):583–600
Falamaki A, Shafiee A, Shafiee AH (2021) Under and post-construction probabilistic static and seismic slope stability analysis of Barmshour Landfill, Shiraz City, Iran. Bull Eng Geol Environ 80(7):5451–5465. https://doi.org/10.1007/s10064-021-02277-4
Faravelli L (1989) Response-surface approach for reliability analysis. J Eng Mech 115(12):2763–2781. https://doi.org/10.1061/(asce)0733-9399(1989)115:12(2763)
Forrest WS, Orr TLL (2010) Reliability of shallow foundations designed to Eurocode 7. Georisk 4(4):186–207. https://doi.org/10.1080/17499511003646484
Friedman JH (2007) Rejoinder: multivariate adaptive regression splines. Ann Stat 19(1):123–141. https://doi.org/10.1214/aos/1176347973
Griffiths DV, Lane PA (1999) Slope stability analysis by finite elements. Geotechnique 49(3):387–403. https://doi.org/10.1680/geot.1999.49.3.387
Guan XL, Melchers RE (1997) Multitangent-plane surface method for reliability calculation. J Eng Mech 123(10):996–1002. https://doi.org/10.1061/(asce)0733-9399(1997)123:10(996)
Huang C-C, Tsai C-C, Chen Y-H (2002) Generalized method for three-dimensional slope stability analysis. J Geotechn Geoenviron Eng 128(10):836–848. https://doi.org/10.1061/(asce)1090-0241(2002)128:10(836)
Husein Malkawi AI, Hassan WF, Abdulla FA (2000) Uncertainty and reliability analysis applied to slope stability. Struct Saf 22(2):161–187. https://doi.org/10.1016/S0167-4730(00)00006-0
Jackson LE, Hungr O, Gardner JS, Mackay C (1989) Cathedral Mountain debris flows. Canada. Bull Int Assoc Eng Geol 40(1):35–54. https://doi.org/10.1007/BF02590340
Jiang SH, Huang JS (2016) Efficient slope reliability analysis at low-probability levels in spatially variable soils. Comput Geotechn 75:18–27. https://doi.org/10.1016/j.compgeo.2016.01.016
Jiao Y-Y, Zhang X-L, Zhao J (2012) Two-dimensional DDA contact constitutive model for simulating rock fragmentation. J Eng Mech 138(2):199–209. https://doi.org/10.1061/(asce)em.1943-7889.0000319
Kalatehjari R, Rashid A, A.S., Hajihassani, M., Kholghifard, M., and Ali, N. (2014) Determining the unique direction of sliding in three-dimensional slope stability analysis. Eng Geol 182:97–108. https://doi.org/10.1016/j.enggeo.2014.06.002
Kar SS, Roy LB (2022) Probabilistic based reliability slope stability analysis using FOSM, FORM, and MCS. Eng Technol Appl Sci Res 12(2):8236–8240
Kong X, He D, Liu X, Wang E, Li S, Liu T, Ji P, Deng D, Yang S (2022) Strain characteristics and energy dissipation laws of gas-bearing coal during impact fracture process. Energy 242:123028. https://doi.org/10.1016/j.energy.2021.123028
Kumar R, Samui P, Kumari S, Roy SS (2021) Determination of reliability index of cantilever retaining wall by RVM, MPMR and MARS. Int J Adv Intell Paradigms 18(3):316–336
Kumar S, Choudhary SS, Burman A (2022a) Recent advances in 3D slope stability analysis: a detailed review. Model Earth Syst Environ 9(2):1445–1462. https://doi.org/10.1007/s40808-022-01597-y
Kumar V, Rao B, Burman A, Kumar S, Bardhan A (2022b) An exact solution of three-dimensional rock mass strength criterion. Model Earth Syst Environ 14(3):731–744. https://doi.org/10.1007/s40808-022-01499-z
Kumar A, Burman A, Choudhary SS (2023a) A detailed study on the analysis and design of geotextile reinforced earth embankments. Eng Technol Appl Sci Res 13(3):10769–10775
Kumar P, Rao B, Burman A, Kumar S, Samui P (2023b) Spatial variation of permeability and consolidation behaviors of soil using ordinary kriging method. Groundw Sustain Dev 20:100856. https://doi.org/10.1016/j.gsd.2022.100856
Lam L, Fredlund DG (1994) A general limit equilibrium model for three-dimensional slope stability analysis: reply. Can Geotech J 31(5):795–796. https://doi.org/10.1139/t94-094
Lee S, Ryu JH, Won JS, Park HJ (2004) Determination and application of the weights for landslide susceptibility mapping using an artificial neural network. Eng Geol 71(3–4):289–302. https://doi.org/10.1016/S0013-7952(03)00142-X
Leshchinsky D, Baker R, Silver ML (1985) Three dimensional analysis of slope stability. Int J Numer Anal Meth Geomech 9(3):199–223. https://doi.org/10.1002/nag.1610090302
Li X, Chen S, Zhang Q, Gao X, Feng F (2021) Research on theory, simulation and measurement of stress behavior under regenerated roof condition. Geomech Eng 26(1):49–61. https://doi.org/10.12989/gae.2021.26.1.049
Liang RY, Nusier OK, Malkawi AH (1999) A reliability based approach for evaluating the slope stability of embankment dams. Eng Geol 54(3–4):271–285. https://doi.org/10.1016/S0013-7952(99)00017-4
Liu LL, Cheng YM (2016) Efficient system reliability analysis of soil slopes using multivariate adaptive regression splines-based Monte Carlo simulation. Comp Geotechn 79:41–54. https://doi.org/10.1016/j.compgeo.2016.05.001
Liu L, Zhang S, Cheng YM, Liang L (2019) Advanced reliability analysis of slopes in spatially variable soils using multivariate adaptive regression splines. Geosci Front 10(2):671–682. https://doi.org/10.1016/j.gsf.2018.03.013
Liu Y, Yang B, Han X, Tan C, Liu F, Zeng Z, Chen B, Song X (2022) Predicting laser penetration welding states of high-speed railway Al butt-lap joint based on EEMD-SVM. J Mater Res Technol 21:1316–1330
Metya S, Mukhopadhyay T, Adhikari S, Bhattacharya G (2017) System reliability analysis of soil slopes with general slip surfaces using multivariate adaptive regression splines. Comp Geotechn 87:212–228. https://doi.org/10.1016/j.compgeo.2017.02.017
Naser AH, Badr AH, Henedy SN, Ostrowski KA, Imran H (2022) Application of multivariate adaptive regression splines (MARS) approach in prediction of compressive strength of eco-friendly concrete. Case Stud Construct Mater 17:e01262
Niu Y, Wang E, Li Z, Gao F, Zhang Z, Li B, Zhang X (2022) Identification of coal and gas outburst-hazardous zones by electric potential inversion during mining process in deep coal seam. Rock Mech Rock Eng 55(6):3439–3450. https://doi.org/10.1007/s00603-022-02804-z
Qin C-B, Chian SC (2018) Kinematic analysis of seismic slope stability with a discretisation technique and pseudo-dynamic approach: a new perspective. Géotechnique 68(6):492–503
Rassam DW, Williams DJ (1999) 3-Dimensional effects on slope stability of high waste rock dumps. Int J Surf Min Reclam Environ 13(1):19–24. https://doi.org/10.1080/09208119908944197
Ray R, Choudhary SS, Roy LB (2021) Reliability analysis of layered soil slope stability using ANFIS and MARS soft computing techniques. Int J Performability Eng 17(7):647–656. https://doi.org/10.23940/ijpe.21.07.p9.647656
Reid ME, Christian SB, Brien DL, Henderson S (2015) Scoops3D—software to analyze three-dimensional slope stability throughout a digital landscape. U.S. geological survey techniques and methods, book 14, vol 14, p 218. https://doi.org/10.3133/tm14A1
Roh G, Hong HP (2009) Calibration of information-sensitive partial factors for assessing earth slopes. J Geoeng 4(3):93–102. https://doi.org/10.6310/jog.2009.4(3).3
Roy LB, Thakur PN, Rao B, Mishra SS (2020) Application of Gaussian process regression and least-square support vector machine to the soil–structure interaction of multi-storey buildings on Raft foundation using SAP2000. Lect Notes Civil Eng 85:423–440. https://doi.org/10.1007/978-981-15-6086-6_35
Salgado R, Kim D (2014) Reliability analysis of load and resistance factor design of slopes. J Geotechn Geoenviron Eng 140(1):57–73. https://doi.org/10.1061/(asce)gt.1943-5606.0000978
Samui P (2013) Multivariate adaptive regression spline (Mars) for prediction of elastic modulus of jointed rock mass. Geotechn Geol Eng 31(1):249–253. https://doi.org/10.1007/s10706-012-9584-4
Samui P, Dixon B (2012) Application of support vector machine and relevance vector machine to determine evaporative losses in reservoirs. Hydrol Process 26(9):1361–1369. https://doi.org/10.1002/hyp.8278
Sarkhani Benemaran R, Esmaeili-Falak M, Javadi A (2022) Predicting resilient modulus of flexible pavement foundation using extreme gradient boosting based optimised models. Int J Pavement Eng. https://doi.org/10.1080/10298436.2022.2095385
Sephton P (2001) Forecasting recessions: can we do better on MARS. Review. https://doi.org/10.20955/r.83.39-50
Shahin MA, Cheung EM (2011) Stochastic design charts for bearing capacity of strip footings. Geomech Eng 3(2):153–167. https://doi.org/10.12989/gae.2011.3.2.153
Sharda VN, Prasher SO, Patel RM, Ojasvi PR, Prakash C (2008) Performance of multivariate adaptive regression splines (MARS) in predicting runoff in mid-Himalayan micro-watersheds with limited data. Hydrol Sci J 53(6):1165–1175. https://doi.org/10.1623/hysj.53.6.1165
Shen W, Shi G, Wang Y, Bai J, Zhang R, Wang X (2021) Tomography of the dynamic stress coefficient for stress wave prediction in sedimentary rock layer under the mining additional stress. Int J Min Sci Technol 31(4):653–663. https://doi.org/10.1016/j.ijmst.2021.04.003
Shiau J, Lai VQ, Keawsawasvong S (2022) Multivariate adaptive regression splines analysis for 3D slope stability in anisotropic and heterogenous clay. J Rock Mech Geotechn Eng. https://doi.org/10.1016/j.jrmge.2022.05.016
Suykens JAK, De Brabanter J, Lukas L, Vandewalle J (2002) Weighted least squares support vector machines: robustness and sparce approximation. Neurocomputing 48(1–4):85–105. https://doi.org/10.1016/S0925-2312(01)00644-0
Tang XS, Li DQ, Zhou CB, Phoon KK (2015) Copula-based approaches for evaluating slope reliability under incomplete probability information. Struct Saf 52:90–99. https://doi.org/10.1016/j.strusafe.2014.09.007
Taylor S (2005) Taylor diagram primer Karl E. Taylor. Work. Pap (January): 1–4
Tiwari LB, Burman A, Samui P (2023) Modelling soil compaction parameters using a hybrid soft computing technique of LSSVM and symbiotic organisms search. Innov Infrastruct Solut 8(1):2
Ugai K (1988) Three-dimensional slope stability analysis by slice methods. In: 6th International conference on numerical methods in geomechanics, pp 1369–1374
Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10(5):988–999. https://doi.org/10.1109/72.788640
Vapnik V, Lerner A (1963) Pattern recognition using generalized portrait method. Automat Remont Contr 24:774–780. https://doi.org/10.1162/neco.1992.4.6.888
Wan Y, Gao Y, Zhang F (2018) Stability analysis of three-dimensional slopes considering the earthquake force direction. Math Problems Eng. https://doi.org/10.1155/2018/2381370
Wang Y, Du E, Yang S, Yu L (2022) Prediction and analysis of slope stability based on IPSO-SVM machine learning model. Geofluids. https://doi.org/10.1155/2022/8529026
Wong FS (1985) Slope reliability and response surface method. J Geotechn Eng 111(1):32–53. https://doi.org/10.1061/(ASCE)0733-9410(1985)111:1(32)
Wu TH, Kraft LM (1970) Safety analysis of slopes. J Soil Mech Found Div 96(2):609–630. https://doi.org/10.1061/jsfeaq.0001406
Xie M, Esaki T, Qiu C, Wang C (2006) Geographical information system-based computational implementation and application of spatial three-dimensional slope stability analysis. Comput Geotechn 33(4–5):260–274. https://doi.org/10.1016/j.compgeo.2006.07.003
Xue X, Makota C, Khalaf OI, Jayabalan J, Samui P, Abdulsahib GM (2023) Machine learning approach for prediction of lateral confinement coefficient of CFRP-wrapped RC columns. Symmetry 15(2):545
Zeng P, Jimenez R (2014) An approximation to the reliability of series geotechnical systems using a linearization approach. Comput Geotechn 62:304–309. https://doi.org/10.1016/j.compgeo.2014.08.007
Zhang D, Wang G, Yang T, Zhang M, Chen S, Zhang F (2013) Satellite remote sensing-based detection of the deformation of a reservoir bank slope in Laxiwa Hydropower Station, China. Landslides 10(2):231–238. https://doi.org/10.1007/s10346-012-0378-9
Acknowledgements
The authors acknowledge the support of the colleagues in the Dept. of Civil Engineering, National Institute of Technology, Patna.
Funding
No external funding was used for the present work.
Author information
Authors and Affiliations
Contributions
BR (first author): conceptualization, analysis, writing of the manuscript. AB (second and corresponding author): conceptualization, analysis, writing of the manuscript, overall supervision. LBR (third author): conceptualization and overall supervision.
Corresponding author
Ethics declarations
Conflict of interest
As per authors’ knowledge, the present work has no conflict interest with any other work. No financial assistance was required for this work.
Ethics approval and consent to participate
Yes.
Consent for publication
Yes.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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
Rao, B., Burman, A. & Roy, L.B. Application of AI models for reliability assessment of 3d slope stability of a railway embankment. Multiscale and Multidiscip. Model. Exp. and Des. 7, 1007–1029 (2024). https://doi.org/10.1007/s41939-023-00255-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41939-023-00255-9