Abstract

Slope stability remains a critical concern in geotechnical engineering, particularly when constructing infrastructure on inclined terrains. Ensuring the stability of such slopes is essential to mitigate risks associated with structural failures, including landslides and soil erosion. Despite extensive research in this field, accurately predicting slope stability continues to present significant challenges, primarily due to inadequate data preprocessing and the limited predictive accuracy of existing models. In this study, six machine learning (ML) techniques like linear regression (LR), neural networks (NN), support vector regression (SVR), random forest (RF), decision tree (DT), and k-nearest neighbor (KNN) were employed to develop and compare predictive models for slope stability. A dataset comprising 101 in-situ slope cases was utilized, with five key geotechnical parameters identified as input variables: soil unit weight, cohesion, internal friction angle, slope height, and slope angle. The safety factor, a widely accepted metric for stability assessment, was used as the output variable. Slope stability was evaluated using GeoStudio 2018 through the application of the Fellenius and Bishop’s Simplified methods. Model performance was assessed using standard statistical metrics, including mean squared error (MSE), root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R²), and bias factor. Among the models tested, the LR approach demonstrated superior predictive performance, yielding MSE, RMSE, MAE, and R² values of 0.0080, 0.0898, 0.0690, and 0.937, respectively. Furthermore, visual analyses, including residual plots, receiver operating characteristic (ROC) curves, and actual vs. predicted value graphs, reinforced the robustness and reliability of the LR model in forecasting slope stability outcomes.

Keywords

Slope stability, Soft computing, Linear regression, Machine learning models, Safety factor prediction, Geotechnical engineering.

References

[1] Bharti JP, Samui P. Predicting slope failure with intelligent hybrid modeling of ANFIS with GA and PSO. Multiscale and Multidisciplinary Modeling, Experiments and Design. 2024; 7(4):4539-55.

[2] Singh R, Umrao RK, Singh TN. Probabilistic analysis of slope in Amiyan landslide area, Uttarakhand. Geomatics, Natural Hazards and Risk. 2013; 4(1):13-29.

[3] Azarafza M, Hajialilue BM, Derakhshani R. A novel empirical classification method for weak rock slope stability analysis. Scientific Reports. 2022; 12(1):1-11.

[4] Rabbani A, Samui P, Kumari S. Optimized ANN-based approach for estimation of shear strength of soil. Asian Journal of Civil Engineering. 2023; 24(8):3627-40.

[5] Mustafa R, Kumar A, Kumar S, Sah NK, Kumar A. Application of soft computing techniques for slope stability analysis. Transportation Infrastructure Geotechnology. 2024; 11(6):3903-40.

[6] Wang G, Zhao B, Wu B, Zhang C, Liu W. Intelligent prediction of slope stability based on visual exploratory data analysis of 77 in situ cases. International Journal of Mining Science and Technology. 2023; 33(1):47-59.

[7] Nanehkaran YA, Licai Z, Chengyong J, Chen J, Anwar S, Azarafza M, et al. Comparative analysis for slope stability by using machine learning methods. Applied Sciences. 2023; 13(3):1-14.

[8] Singh SK, Chakravarty D. Assessment of slope stability using classification and regression algorithms subjected to internal and external factors. Archives of Mining Sciences. 2023; 68(1):87-102.

[9] Kurnaz TF, Erden C, Dağdeviren U, Demir AS, Kökçam AH. Comparison of machine learning algorithms for slope stability prediction using an automated machine learning approach. Natural Hazards. 2024; 120(8):6991-7014.

[10] Ahmad F, Samui P, Mishra SS. Probabilistic slope stability analysis using subset simulation enhanced by ensemble machine learning techniques. Modeling Earth Systems and Environment. 2024; 10(2):2133-58.

[11] Yang Y, Zhou W, Jiskani IM, Lu X, Wang Z, Luan B. Slope stability prediction method based on intelligent optimization and machine learning algorithms. Sustainability. 2023; 15(2):1-18.

[12] Şehmusoğlu EH, Kurnaz TF, Erden C. Estimation of soil liquefaction using artificial intelligence techniques: an extended comparison between machine and deep learning approaches. Environmental Earth Sciences. 2025; 84(5):1-22.

[13] Lin S, Liang Z, Zhao S, Dong M, Guo H, Zheng H. A comprehensive evaluation of ensemble machine learning in geotechnical stability analysis and explainability. International Journal of Mechanics and Materials in Design. 2024; 20(2):331-52.

[14] Junjia Y, Alias AH, Haron NA, Bakar NA. Machine learning algorithms for safer construction sites: critical review. Building Engineering. 2024; 2(1):1-23.

[15] Abdollahi A, Li D, Deng J, Amini A. An explainable artificial-intelligence-aided safety factor prediction of road embankments. Engineering Applications of Artificial Intelligence. 2024; 136:1-23.

[16] Ahangari NY, Pusatli T, Chengyong J, Chen J, Cemiloglu A, Azarafza M, et al. Application of machine learning techniques for the estimation of the safety factor in slope stability analysis. Water. 2022; 14(22):1-14.

[17] Liao M, Wen H, Yang L. Identifying the essential conditioning factors of landslide susceptibility models under different grid resolutions using hybrid machine learning: a case of Wushan and Wuxi counties, China. Catena. 2022; 217:106428.

[18] Lv L, Chen T, Dou J, Plaza A. A hybrid ensemble-based deep-learning framework for landslide susceptibility mapping. International Journal of Applied Earth Observation and Geoinformation. 2022; 108:1-14.

[19] Wei R, Ye C, Sui T, Ge Y, Li Y, Li J. Combining spatial response features and machine learning classifiers for landslide susceptibility mapping. International Journal of Applied Earth Observation and Geoinformation. 2022; 107:1-13.

[20] Ray R, Choudhary SS, Roy LB. Reliability analysis of soil slope stability using MARS, GPR and FN soft computing techniques. Modeling Earth Systems and Environment. 2022; 8(2):2347-57.

[21] Ray R, Roy LB. Reliability analysis of soil slope stability using ANN, Anfis, PSO-ANN soft computing techniques. NVEO-Nat Volatiles Essent Oils. 2021; 8:3478-91.

[22] Habtemariam BG, Shirago KB, Dirate DD. Effects of soil properties and slope angle on deformation and stability of cut slopes. Advances in Civil Engineering. 2022; 2022(1):1-10.

[23] Khajehzadeh M, Taha MR, Keawsawasvong S, Mirzaei H, Jebeli M. An effective artificial intelligence approach for slope stability evaluation. IEEE Access. 2022; 10:5660-71.

[24] Kumar R, Samui P, Kumari S. Reliability analysis of infinite slope using metamodels. Geotechnical and Geological Engineering. 2017; 35(3):1221-30.

[25] Chakraborty A, Goswami D. Prediction of slope stability using multiple linear regression (MLR) and artificial neural network (ANN). Arabian Journal of Geosciences. 2017; 10(17):385.

[26] Chakraborty A, Goswami D. Prediction of critical safety factor of slopes using multiple regression and neural network. Journal of Geo-Engineering Sciences. 2018: JGS-170047.

[27] Qian ZG, Li AJ, Chen WC, Lyamin AV, Jiang JC. An artificial neural network approach to inhomogeneous soil slope stability predictions based on limit analysis methods. Soils and Foundations. 2019; 59(2):556-69.

[28] Khan MI, Wang S. Slope stability analysis to develop correlations between different soil parameters and factor of safety using regression analysis. Polish Journal of Environmental Studies. 2021; 30(5):1-10.

[29] Wang S, Khan MI. Developing correlations for advance prediction of slope factor of safety using linear regression analysis–Karachi landslide as a case study. Polish Journal of Environmental Studies. 2021; 30(6):5849-62.

[30] Li AJ, Lim K, Fatty A. Stability evaluations of three-layered soil slopes based on extreme learning neural network. Journal of the Chinese Institute of Engineers. 2020; 43(7):628-37.

[31] Lin S, Zheng H, Han C, Han B, Li W. Evaluation and prediction of slope stability using machine learning approaches. Frontiers of Structural and Civil Engineering. 2021; 15(4):821-33.

[32] Khan MI, Wang S. Comparing the various slope stability methods to find the optimum method for calculating factor of slope safety. In IOP conference series: earth and environmental science 2020 (pp. 1-13). IOP Publishing.

[33] Ullah S, Khan MU, Rehman G. A brief review of the slope stability analysis methods. Geological Behavior (GBR). 2020; 4(2):73-7.

[34] IS-1893-Part-1, criteria for earthquake resistant design of structures - general provisions and buildings Part-1. Bur. Indian Stand. New Delhi, vol. Part 1. 2022:1–39.

[35] Raj P, Roy LB. Assessing slope stability reliability through visual exploratory data analysis and machine learning in Kumaon Region of Uttarakhand in India. SSRG International Journal of Civil Engineering.2025; 12(1): 46-66.

[36] Duncan JM, Wright SG, Brandon TL. Soil strength and slope stability. John Wiley & Sons; 2014.

[37] Feng X, Li S, Yuan C, Zeng P, Sun Y. Prediction of slope stability using naive bayes classifier. KSCE Journal of Civil Engineering. 2018; 22(3):941-50.

[38] Huang S, Huang M, Lyu Y. An improved KNN‐based slope stability prediction model. Advances in Civil Engineering. 2020; 2020(1):1-16.

[39] Abdulabbas AA, Ulabbas YK. Estimation of shear strength parameters of soils using ANN technique. International Journal of Civil, Structural, Environmental, and Infrastructure Engineering Research and Development. 2014; 4(3):1-10.

[40] Suman S, Khan SZ, Das SK, Chand SK. Slope stability analysis using artificial intelligence techniques. Natural Hazards. 2016; 84(2):727-48.

[41] Liu Z, Shao J, Xu W, Chen H, Zhang Y. An extreme learning machine approach for slope stability evaluation and prediction. Natural Hazards. 2014; 73(2):787-804.

[42] Komadja GC, Pradhan SP, Oluwasegun AD, Roul AR, Stanislas TT, Laïbi RA, et al. Geotechnical and geological investigation of slope stability of a section of road cut debris-slopes along NH-7, Uttarakhand, India. Results in Engineering. 2021; 10:100227.

[43] Zhang T, Cai Q, Han L, Shu J, Zhou W. 3D stability analysis method of concave slope based on the Bishop method. International Journal of Mining Science and Technology. 2017; 27(2):365-70.

[44] Pandit VM, Patel JB. Comparative study of advanced two dimensional methods of slope stability. International Journal of Advanced Technology in Civil Engineering. 2013; 2(1):92-5.

[45] Choobbasti AJ, Farrokhzad F, Barari A. Prediction of slope stability using artificial neural network (case study: Noabad, Mazandaran, Iran). Arabian Journal of Geosciences. 2009; 2(4):311-9.

[46] Alkasawneh W, Malkawi AI, Nusairat JH, Albataineh N. A comparative study of various commercially available programs in slope stability analysis. Computers and Geotechnics. 2008; 35(3):428-35.

[47] Cheng YM. Location of critical failure surface and some further studies on slope stability analysis. Computers and Geotechnics. 2003; 30(3):255-67.

[48] Yilmaz I, Yuksek AG. An example of artificial neural network (ANN) application for indirect estimation of rock parameters. Rock mechanics and Rock Engineering. 2008; 41(5):781-95.

[49] Das SK, Biswal RK, Sivakugan N, Das B. Classification of slopes and prediction of factor of safety using differential evolution neural networks. Environmental Earth Sciences. 2011; 64(1):201-10.

[50] Erzin Y, Cetin T. The prediction of the critical factor of safety of homogeneous finite slopes using neural networks and multiple regressions. Computers & Geosciences. 2013; 51:305-13.

[51] Mohamed T, Kasa A, Mukhlisin M. Prediction of slope stability using statistical method and fuzzy logic. TOJSAT. 2012; 2(4):68-73.

[52] Ray R, Choudhary SS, Roy LB, Kaloop MR, Samui P, Kurup PU, et al. Reliability analysis of reinforced soil slope stability using GA-ANFIS, RFC, and GMDH soft computing techniques. Case Studies in Construction Materials. 2023; 18:1-13.

Cite this article