Reliable slope stability prediction with guaranteed coverage: integrating conformal prediction and multi-method explainability

Abstract

The application of machine learning (ML) in slope stability assessment has been hindered by a lack of attention to uncertainty quantification and interpretability, which limits its adoption in engineering design. Prior studies have emphasized predictive accuracy without addressing the reliability and transparency necessary for decision-making in safety-critical contexts. This study introduces a novel framework for circular mode slope stability assessment that integrates split conformal prediction (SCP) with explainable ML to achieve statistically valid and interpretable predictions. The framework employs a Random Forest model optimized with the Artificial Hummingbird Algorithm (AHA) and implements SCP to generate calibrated prediction sets with guaranteed confidence. The dataset is divided into training, calibration, and testing subsets, where nonconformity scores derived from predicted probabilities are used to compute quantile thresholds. Both marginal coverage validity and class-wise (conditional) coverage were evaluated to ensure balanced reliability between stable and failure classifications under finite-sample conditions and minimal distributional assumptions. Interpretability is achieved through Shapley Additive Explanation (SHAP), Accumulated Local Effects (ALE), and Counterfactual Explanations (CFEs), which clarify the influence of geotechnical parameters and explain the reasoning behind each classification. The proposed AHA-RF-SCP framework establishes a transparent, statistically sound, and physically interpretable approach for slope stability assessment, promoting confidence and uncertainty-aware decision-making in geotechnical engineering practice.

Keywords

Uncertainty quantification / Conformal predictions / Interpretable machines / Slope stability / Shapley additive explanation / Accumulated local effects / Counterfactual explanations

References

[1] Huang YH. Slope stability analysis by the limit equilibrium method: fundamentals and methods, 2014American Society of Civil Engineers.

[2] Nanehkaran YA, Licai Z, Chengyong J, Chen J, Anwar S, Azarafza M, Derakhshani R. Comparative analysis for slope stability by using machine learning methods. Appl Sci, 2023, 13(3): 1555.

[3] Sakellariou, Ferentinou. A study of slope stability prediction using neural networks. Geotechnical Geological Eng, 2005, 23(4): 419-445.

[4] Wang HB, Xu WY, Xu RC. Slope stability evaluation using back propagation Neural Networks. Eng Geol, 2005, 80: 302-315.

[5] Kardani N, Zhou A, Nazem M, Shen S-L. Improved prediction of slope stability using a hybrid stacking ensemble method based on finite element analysis and field data. J Rock Mech Geotech Eng, 2021, 13(1): 188-201.

[6] Lin S, Zheng H, Han B, Li Y, Han C, Li W. Comparative performance of eight ensemble learning approaches for the development of models of slope stability prediction. Acta Geotechnica, 2022, 17(4): 1477-1502.

[7] Azarafza M, Akgün H, Ghazifard A, Asghari-Kaljahi E, Rahnamarad J, Derakhshani R. Discontinuous rock slope stability analysis by limit equilibrium approaches - a review. Int J Digit Earth, 2021, 14(12): 1918-1941.

[8] Mebrahtu TK, Heinze T, Wohnlich S, Alber M. Slope stability analysis of deep-seated landslides using limit equilibrium and finite element methods in Debre Sina area. Ethiopia. Bull Eng Geol The Environ, 2022, 81(10): 403.

[9] Nuric A, Nuric S, Kricak L, Husagic R. Numerical methods in analysis of slope stability. Int J Multiling Sci Eng Investigations, 2013, 2(14): 41-48

[10] Xiaoming Y, Xibing L (2011) Bayes discriminant analysis method for predicting the stability of open pit slope. In: 2011 International Conference on Electric Technology and Civil Engineering, ICETCE, 2011 - Proceedings. https://doi.org/10.1109/ICETCE.2011.5776304

[11] Shirago K, Dirate D (2023) Three-dimensional strength reduction and two-dimensional limit equilibrium methods of slope stability analysis. Heliyon 9(7). https://doi.org/10.1016/j.heliyon.2023.e17966

[12] Zebarjadi Dana H, Khaloo Kakaie R, Rafiee R, Yarahmadi Bafghi A. Effects of geometrical and geomechanical properties on slope stability of open-pit mines using 2D and 3D finite difference methods. J Educ Chang Min Environ, 2018, 9(4): 941-957.

[13] Feng X, Li S, Yuan C, Zeng P, Sun Y. Prediction of slope stability using naive Bayes classifier. KSCE J Civ Eng, 2018, 22(3): 941-950.

[14] Qi C, Tang X. Slope stability prediction using integrated metaheuristic and machine learning approaches: a comparative study. Comput Ind Eng, 2018, 118: 112-122.

[15] Bishop CM, Nasrabadi NM. Pattern recognition and machine learning, 2006Springer. 4

[16] Lary DJ, Alavi AH, Gandomi AH, Walker AL. Machine learning in geosciences and remote sensing. Geosci Front, 2016, 7(1): 3-10.

[17] Zhou J, Li E, Yang S, Wang M, Shi X, Yao S, Mitri HS. Slope stability prediction for circular mode failure using gradient boosting machine approach based on an updated database of case histories, 2019Safety Science: 505-518. 118

[18] Zhang W, Wu C, Tang L, Gu X, Wang L (2022) Efficient time-variant reliability analysis of Bazimen landslide in the Three Gorges Reservoir Area using XGBoost and LightGBM algorithms. Gondwana Res. https://doi.org/10.1016/j.gr.2022.10.004

[19] Wang L, Yang K, Wu C, Zhou Y, Liu J, Hu H (2024) Novel approach to quantitative risk assessment of reservoir landslides using a hybrid CNN-LSTM model. Landslides 22. https://doi.org/10.1007/s10346-024-02398-3

[20] Liu L, Zhao G, Liang W. Slope stability prediction using k-NN-based optimum-path forest approach. Mathematics, 2023, 11(14): 3071.

[21] Ma J, Jiang S, Liu Z, Ren Z, Lei D, Tan C, Guo H. Machine learning models for slope stability classification of circular mode failure: an updated database and automated machine learning (AutoML) approach. Sensors, 2022, 22(23): 9166.

[22] Lin Y, Zhou K, Li J. Prediction of slope stability using four supervised learning methods, 2018Ieee Access: 31169-311796

[23] Zhang H, Wu S, Zhang X, Han L, Zhang Z. Slope stability prediction method based on the margin distance minimization selective ensemble. Catena, 2022, 212: 106055.

[24] 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. Nat Hazards, 2024, 120(8): 6991-7014.

[25] Cai Y, Yuan Y, Zhou A. Predictive slope stability early warning model based on CatBoost. Sci Rep, 2024, 14(1): 25727.

[26] Demir S, Sahin EK. An innovative machine learning approach for slope stability prediction by combining shap interpretability and stacking ensemble learning. Environ Sci Pollut Res, 2025, 32(21): 12827-12843.

[27] Stracuzzi DJ, Chen MG, Darling MC, Peterson MG, Vollmer C. Uncertainty quantification for machine learning, 2017. Albuquerque, NM (United States), Sandia National Lab. (SNL-NM).

[28] Siddique T, Mahmud MS, Keesee AM, Ngwira CM, Connor H. A survey of uncertainty quantification in machine learning for space weather prediction. Geosciences, 2022, 12(1): 27.

[29] Choi J, Cho Y, Kim Y, Kim Y, Ji B. Machine learning-based slope failure prediction model considering the uncertainty of prediction. Eng Proc, 2023, 36(1): 6.

[30] Harle SM, Wankhade RL. Machine learning techniques for predictive modelling in geotechnical engineering: a succinct review. Discover Civ Eng, 2025, 2(1): 86.

[31] Hand DJ. Measuring classifier performance: a coherent alternative to the area under the ROC curve. Mach. Learn, 2009, 77(1): 103-123.

[32] Halligan S, Altman DG, Mallett S. Disadvantages of using the area under the receiver operating characteristic curve to assess imaging tests: a discussion and proposal for an alternative approach. Eur Radiol, 2015, 25(4): 932-939.

[33] Angelopoulos AN, Bates S (2021) A gentle introduction to conformal prediction and distribution-free uncertainty quantification. arXiv preprint arXiv:2107.07511. https://doi.org/10.1561/2200000101

[34] Vovk V, Gammerman A, Shafer G. Algorithmic learning in a random world, 2005Springer

[35] Johansson U, Boström H, Löfström T (2013) Conformal prediction using decision trees. In: 2013 IEEE 13th international conference on data mining, IEEE. https://doi.org/10.1007/0-387-25061-1_8

[36] Sheinkman A, Wade S (2025) Understanding the trade-offs in accuracy and uncertainty quantification: architecture and inference choices in Bayesian Neural Networks. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer. https://doi.org/10.1007/978-3-032-06109-6_8

[37] Romano Y, Patterson E, Candes E (2019) Conformalized quantile regression. Adv Neural Inf Process Syst 32

[38] Tibshirani R. Conformal prediction, 2023UC Berkeley

[39] Ahlberg E, Hammar O, Bendtsen C, Carlsson L. Current application of conformal prediction in drug discovery. Ann Math Artif Intell, 2017, 81(1): 145-154.

[40] Lindemann L, Cleaveland M, Shim G, Pappas GJ. Safe planning in dynamic environments using conformal prediction. IEEE Robot Automation Lett, 2023, 8(8): 5116-5123.

[41] Sreenivasan AP, Vaivade A, Noui Y, Khoonsari PE, Burman J, Spjuth O, Kultima K. Conformal prediction enables disease course prediction and allows individualized diagnostic uncertainty in multiple sclerosis. NPJ Digit Med, 2025, 8(1): 224.

[42] Ibrahim B, Ahenkorah I. Classifying rockburst with confidence: a novel conformal prediction approach. Int J Min Sci Technol, 2024, 34(1): 51-64.

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

[44] Ankah MLY, Adjei-Yeboah S, Ziggah YY, Asare EN. Advanced hybrid machine learning models with explainable AI for predicting residual friction angle in clay soils. Sci Rep, 2025, 15(1): 25868.

[45] Khan M, Gulaly L, Aziz A. Advancing pseudo-static slope stability predictions using explainable machine learning. Transp Infrastruct Geotech, 2025, 12(5): 161.

[46] Sia MK, Yew WC, Low XW. Exploring the causal effects of outdoor play on school readiness of preschoolers in the Klang Valley malaysia. Sustainability, 2023, 15(2): 1170.

[47] Freiesleben T (2023) What does explainable AI explain?, lmu https://doi.org/10.5282/edoc.31933

[48] Trinidad M, Momayez M. Machine learning in slope stability: a review with implications for landslide hazard assessment. GeoHazards, 2025, 6(4): 67.

[49] Lundberg, Lee (2017) A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 30

[50] Apley, Zhu. Visualizing the effects of predictor variables in black box supervised learning models. J R Stat Soc Ser B Stat Methodol, 2020, 82(4): 1059-1086.

[51] Wachter S, Mittelstadt B, Russell C. Counterfactual explanations without opening the black box: automated decisions and the GDPR. Harv, 2017JL & Tech: 841. 31

[52] Xu H, He X, Shan F, Niu G, Sheng D. Machine learning in the stochastic analysis of slope stability: a state-of-the-art review. Modelling, 2023, 4(4): 426-453.

[53] Bishop AW, Morgenstern N. Stability coefficients for earth slopes. Geotechnique, 1960, 10(4): 129-153.

[54] Fellenius W (1936) Calculation of the stability of earth dams. In: Proc. of the second congress on large dams

[55] Sun J, Zhao Z. Stability charts for homogenous soil slopes. J Geotech Geoenviron Eng, 2013, 139(12): 2212-2218.

[56] Nassirzadeh R, Dini A, Balagar V. Back analysis of cohesion and friction angle of failed slopes using probabilistic approach: two case studies. Int J Geo-Eng, 2024, 15(1): 3.

[57] Lade PV. Instability, shear banding, and failure in granular materials. Int J Soc Res Methodol Solids Struct, 2002, 39(13–14): 3337-3357.

[58] Kim JH. Multicollinearity and misleading statistical results. Korean J Anesthesiol, 2019, 72(6): 558-569.

[59] Molnar C. Introduction to conformal prediction with Python: a short guide for quantifying uncertainty of machine learning models, 2023Chistoph Molnar c/o MUCBOOK, Heidi Seibold

[60] Lei J, Wasserman L. Distribution-free prediction bands for non-parametric regression. J R Stat Soc Ser B Stat Methodol, 2014, 76(1): 71-96.

[61] Lee K, Zhang Y (2025) Leave-one-out Stable conformal prediction. arXiv preprint arXiv:2504.12189. https://doi.org/10.48550/arXiv.2504.12189

[62] Vovk V (2012) Conditional validity of inductive conformal predictors. In: Asian conference on machine learning. PMLR

[63] Shapley LS (1953) A value for n-person games

[64] Mosca E, Szigeti F, Tragianni S, Gallagher D, Groh G (2022) SHAP-based explanation methods: a review for NLP interpretability. In: Proceedings of the 29th international conference on computational linguistics

[65] Gebreyesus Y, Dalton D, Nixon S, De Chiara D, Chinnici M (2023) Machine learning for data center optimizations: feature selection using Shapley additive exPlanation (SHAP). Future internet 15(3):88. https://doi.org/10.3390/fi15030088

[66] Meng Y, Yang N, Qian Z, Zhang G. What makes an online review more helpful: an interpretation framework using XGBoost and SHAP values. J Retailing Theor Appl Electron Commerce Res, 2020, 16(3): 466-490.

[67] Van den Broeck G, Lykov A, Schleich M, Suciu D. On the tractability of SHAP explanations. J Artif Intell Res, 2022, 74: 851-886.

[68] Okoli C (2023) Statistical inference using machine learning and classical techniques based on accumulated local effects (ALE). arXiv preprint arXiv:2310.09877. https://doi.org/10.48550/arXiv.2310.09877

[69] Apley, Zhu (2020) Visualizing the effects of predictor variables in black box supervised learning models. J R Stat Soc Ser B (Stat Methodol) 82. https://doi.org/10.1111/rssb.12377

[70] Verma S, Boonsanong V, Hoang M, Hines K, Dickerson J, Shah C. Counterfactual explanations and algorithmic recourses for machine learning: a review. ACM Comput Surv, 2024, 56(12): 1-42.

[71] Verma S, Dickerson J, Hines K (2021) Counterfactual explanations for machine learning: challenges revisited. arXiv preprint arXiv:2106.07756. https://doi.org/10.48550/arXiv.2106.07756

[72] Salman HA, Kalakech A, Steiti A. Random forest algorithm overview. Babylon J Mach Learn, 2024, 2024: 69-79.

[73] Parmar A, Katariya R, Patel V (2018) A review on random forest: an ensemble classifier. In: International conference on intelligent data communication technologies and internet of things. Springer. https://doi.org/10.1007/978-3-030-03146-6_86

[74] Zhao W, Wang L, Mirjalili S (2022) Artificial hummingbird algorithm: a new bio-inspired optimizer with its engineering applications. Comput Meth Appl Mech Eng 388:114194. https://doi.org/10.1016/j.cma.2021.114194

[75] Bakır H. A novel artificial hummingbird algorithm improved by natural survivor method. Neural Comput Appl, 2024, 36(27): 16873-16897.

[76] Kaur S, Kaur L, Lal M (2024) Artificial hummingbird algorithm with chaotic-opposition-based population initialization for solving real-world problems. Neural Comput Appl 1–44. https://doi.org/10.1007/s00521-024-10621-4

[77] Elaziz MA, Dahou A, El-Sappagh S, Mabrouk A, Gaber MM. AHA-AO: artificial hummingbird algorithm with Aquila optimization for efficient feature selection in medical image classification. Appl Sci, 2022, 12(19): 9710.

[78] Baheri A, Shahbazi MA (2025) Multi-scale conformal prediction: a Theoretical framework with coverage guarantees. arXiv preprint arXiv:2502.05565. https://doi.org/10.48550/arXiv.2502.05565

[79] Shanmugam D, Lu H, Sankaranarayanan S, Guttag J (2025) Test-time augmentation improves efficiency in conformal prediction. In: Proceedings of the Computer Vision and Pattern Recognition Conference

[80] Molnar C. Interpretable machine learning, 2020Lulu.com

[81] 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): 1169.

[82] Lei H, Bellotti A. Reliable prediction intervals with directly optimized inductive conformal regression for deep learning. Neural Networks, 2023, 168: 194-205.

[83] Angelopoulos AN, Bates S (2023) Conformal prediction: a gentle introduction. Found Trends Mach Learn 16(4):494–591. https://doi.org/10.1561/2200000101

[84] Romano Y, Sesia M, Candès E (2020) Classification with valid and adaptive coverage

[85] Shafer G, Vovk V (2008) A tutorial on conformal prediction. J Mach Learn Res 9(3)

[86] Vovk V. Conditional validity of inductive conformal predictors. Mach Learn, 2013, 92(2): 349-376.

[87] Vovk V, Gammerman A, Shafer G (2022) Conformal prediction: general case and regression. In: Algorithmic learning in a random world. Springer, pp 19–69. https://doi.org/10.1007/0-387-25061-1_8

[88] Qi Y, Cao X, Cao R, Huang J, Yan A, Xu D (2024) The critical role of c and φ in ensuring stability: a study on rockfill dams. Open Geosci 16(1). https://doi.org/10.1515/geo-2022-0712

[89] Tian D, Zheng H. The generalized Mohr-Coulomb failure criterion. Appl Sci, 2023, 13(9): 5405.

[90] Lundberg, Lee (2017) A unified approach to interpreting model predictions

[91] Liu X, Sun Y, Li Y, Guo T, Chen Q, Wu N, Qu Z, Hou J, Rabiei M. New modified mohr-coulomb failure criterion for a hydrate-bearing sediment based on a triaxial shear test. Energy Fuels, 2022, 36(3): 1283-1293.

[92] Wang CY, Zhang F, Han WD (2014) Sensitivity analysis of slope stability influence factors based on BP Neural Network. Adv Mater Res Switz 1010–1012. p. 1544–1547. https://doi.org/10.4028/www.scientific.net/AMR.1010-1012.1544

[93] Zeng Y, Zhang Y, Hu W, Chen M, Hu Q, Liu X, Zhu X (2024) A case study on soil slope landslide failure and parameter analysis of influencing factors for safety factor based on strength reduction method and orthogonal experimental design. PLoS One 19(5):e0300586. https://doi.org/10.1371/journal.pone.0300586

[94] Terzaghi K (1943) Theoretical soil mechanics

RIGHTS & PERMISSIONS

The Author(s)