Intelligent Prediction and Visual Analysis of Slope Stability via Ensemble Learning Combined with Multialgorithm Collaborative Optimization and Dual Interpretability Framework
1 Faculty of Land Resource Engineering, Kunming University of Science and Technology, Kunming 650000, China
2 Key Laboratory of Geological Hazard Forecasting, Early Warning, and Ecological Protection and Restoration in Plateau Mountainous Areas, Ministry of Natural Resources, Kunming 650000, China
3 Yunnan Key Laboratory of Geohazard Forecast and Geoecological Restoration in Plateau Mountainous Area, Kunming 650000, China
Slope stability analysis is regarded as a critical issue in geotechnical engineering. However, inherent limitations exist in traditional evaluation methods, and complex nonlinear relationships among influencing factors cannot be fully characterized. Therefore, an intelligent prediction model for slope stability based on the integration of multiple optimization algorithms was proposed to improve prediction accuracy and model interpretability. First, eight widely used machine learning models were compared, and the random forest model was selected as the optimal baseline model. Then, its hyperparameters were collaboratively optimized using the lung performance optimization algorithm, the golden sine algorithm, and the slime mould algorithm to further enhance predictive performance. Subsequently, an ensemble learning framework was constructed, whose hyperparameters were optimized with the successive halving gridsearch method. The ensemble model was compared with individual models, and it is indicated that superior performance in both accuracy and stability is achieved. To improve model interpretability, the SHAP(shapley additive explanations) and LIME(local interpretable model-agnostic explanations)methods were employed to quantify feature contributions to prediction results and to identify key influencing factors and their relative importance. It is shown that the optimized random forest model achieves an accuracy of 0.935 9, while better performance is achieved by the ensemble model, with an accuracy of 0.948 7 and favorable F1-score and precision. Finally, a software system integrating data visualization and slope stability prediction functions was developed. Efficient and reliable support was provided by the system for intelligent slope stability evaluation.
WU Shun-chuan, CAO Yi-fan, HAN Long-qiang, PU Shi-jiang, GAO Yu-nuo, HUANG Shi-gui.
Intelligent Prediction and Visual Analysis of Slope Stability via Ensemble Learning Combined with Multialgorithm Collaborative Optimization and Dual Interpretability Framework[J].
Science Technology and Engineering, 2026, 26(31): 13423-13436 DOI:10.12404/j.issn.1671-1815.2507730
Ortiz-GiraldoL, BoteroB A, VegaJ. An integral assessment of landslide dams generated by the occurrence of rainfall-induced landslide and debris flow hazard chain[J]. Frontiers in Earth Science, 2023, 11: 1157881.
ZhangZhihui, KangJingyu, PangXin, et al. Parameter acquisition and stability evaluation method of high steep slope rock mass in open-pit mine[J]. Science Technology and Engineering, 2024, 24(12): 4916-4924.
[4]
WangY H, WangL Q, ZhangW G, et al. Knowledge data collaborative driven landslide vulnerability evaluation method based on 3D slope stability analysis[J]. Journal of Central South University, 2024, 31 (11): 3838-3853.
[5]
XuS G, ZhangS T, ZhuC B, et al. Three practical methods for analyzing slope stability[J]. Acta Geologica Sinica, 2008, 82(5): 1083-1088.
ChenJianfeng, SunLichuan, ShiZhenming, et al. Stability evaluation of artificial high slope at Sanmen Nuclear Power Plant in Zhejiang Province[J]. Rock and Soil Mechanics, 2005, 26 (S2): 33-35.
[8]
FentonG A, HicksM A, WangX, et al. Effect of slope height and gradient on failure probability[C]//Geo-Congress 2013: Stability and Performance of Slopes and Embankments III. Reston: American Society of Civil Engineers, 2013: 972-981.
NanNing, LiPeng, SuShengrui, et al. Optimization design of loess high slope based on wide and narrow platforms: a case study of a high slope in an industrial square in Zichang City, Shaanxi Province[J]. Coalfield Geology and Exploration, 2022, 50(6): 155-164.
[11]
TrivediA. Discussionof “exact solution of the friction circle method” by Jozsef Garai[J]. International Journal of Geomechanics, 2017, 17(10): 07017010.
ChenGang, HuangXiao, SunJinzhong. Application of Chi Ping Polar Projection in slope stability analysis[J]. Journal of Engineering Geology, 2008, 16(S1): 395-398.
[14]
LiuS Y, ShaoL T, LiH J. Slope stability analysis using the limit equilibrium method and two finite element methods[J]. Computers and Geotechnics, 2015, 63: 291-298.
[15]
SarkarK, SinghT N, VermaA K. A numerical simulation of landslide-prone slope in Himalayan region—a case study[J]. Arabian Journal of Geosciences, 2012, 5: 73-81.
ChenLei, ZhangQiang, JiaChaojun, et al. Centrifugal model test and numerical simulation study on the influence of heavy rainfall on the stability of reservoir bank slope[J]. Geotechnical Mechanics, 2024, 45(5): 1423-1434.
[18]
SalgadoR, KimD. Reliability analysis of load and resistance factor design of slopes[J]. Journal of Geotechnical and Geoenvironmental Engineering, 2014, 140(1): 57-73.
SongErxiang. Definition of slope stability safety factor calculation by strip method - discussion on the influence of load and resistance misalignment in the stability safety factor calculation formula[J]. Chinese Journal of Geotechnical Engineering, 2021, 43 (11): 2142-2143.
[21]
吴顺川, 金爱兵, 刘洋. 边坡工程[M]. 北京: 冶金工业出版社, 2020.
[22]
WuShunchuan, JinAibing, LiuYang. Slope engineering[M]. Beijing: Metallurgical Industry Press, 2020.
XuZhichao, ChenYunshan, DengChao, et al. Predicting slope stability using a PSO-SVM model[J]. Journal of Safety and Environment, 2025, 25(9): 3531-3537.
[27]
FoongL K, MoayediH. Slope stability evaluation using neural network optimized by equilibrium optimization and vortex search algorithm[J]. Engineering with Computers, 2022, 38(S2): 1269-1283.
PengZonghuan, ShengJianlong, YeZuyang, et al. Reliability analysis of 3D slope based on improved PSO-RBF neural network[J]. Earth Science, 2024, 49(5): 1706-1721.
[30]
SunJ, WuS, ZhangH, et al. Based on multi-algorithm hybrid method to predict the slope safety factor-stacking ensemble learning with bayesian optimization[J]. Journal of Computational Science, 2022, 59: 101587.
JinAibing, ZhangJinghui, SunHao, et al. Intelligent prediction and warning model for slope instability based on SSA-SVM[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2022, 50(11): 142-148.
[33]
ZhouJ, LiE, YangS, et al. Slope stability prediction for circular mode failure using gradient boosting machine approach based on an updated database of case histories[J]. Safety Science, 2019, 118: 505-518.
[34]
QiC, TangX. Slope stability prediction using integrated metaheuristic and machine learning approaches: a comparative study[J]. Computers & Industrial Engineering, 2018, 118: 112-122.
[35]
LiM, LiK, QinQ, et al. Slope stability prediction based on IPOARF algorithm: a case study of Lala Copper Mine, Sichuan, China[J]. Expert Systems with Applications, 2023, 229: 120595.
[36]
ZhangH, WuS, ZhangX, et al. Slope stability prediction method based on the margin distance minimization selective ensemble[J]. Catena, 2022, 212: 106055.
[37]
RukhaiyarS, AlamM N, SamadhiyaN K. A PSO-ANN hybrid model for predicting factor of safety of slope[J]. International Journal of Geotechnical Engineering, 2018, 12(6): 556-566.
[38]
SakellariouM G, FerentinouM D. A study of slope stability prediction using neural networks[J]. Geotechnical & Geological Engineering, 2005, 23: 419-445.
[39]
MageeJ F. Decision trees for decision making[M]. Brighton: Harvard Business Review, 1964.
[40]
BreimanL. Random forests[J]. Machine Learning, 2001, 45: 5-32.
HearstM A, DumaisS T, OsunaE, et al. Support vector machines[J]. IEEE Intelligent Systems and Their Applications, 1998, 13(4): 18-28.
[43]
RishI. An empirical study of the naive Bayes classifier[C]//IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence. Seattle: IJCAI, 2001: 41-46.
[44]
PetersonL E. K-nearest neighbor[J]. Scholarpedia, 2009, 4(2): 1883.
[45]
TaudH, MasJ F. Multilayer perceptron (MLP)[M]// Geomatic Approaches for Modeling Land Change Scenarios. Cham: Springer, 2018: 451-455.
[46]
KeG, MengQ, FinleyT, et al. Lightgbm: a highly efficient gradient boosting decision tree[J]. Advances in Neural Information Processing Systems, 2017, 30: 3146-3154.
[47]
GhasemiM, ZareM, ZahediA, et al. Optimization based on performance of lungs in body: lungs performance-based optimization (LPO)[J]. Computer Methods in Applied Mechanics and Engineering, 2024, 419: 116582.
[48]
TanyildiziE, DemirG. Golden sine algorithm: a novel math-inspired algorithm[J]. Advances in Electrical & Computer Engineering, 2017, 17(2): 71-78.
[49]
LiS, ChenH, WangM, et al. Slime mould algorithm: a new method for stochastic optimization[J]. Future Generation Computer Systems, 2020, 111: 300-323.
[50]
SoperD S. Hyperparameter optimization using successive halving with greedy cross validation[J]. Algorithms, 2022, 16(1): 17.
KongKunfeng, ChenYiling, ChenFeng, et al. Multi model decision level fusion soil slope stability prediction model and interpretability analysis[J/OL]. Journal of Railway Science and Engineering. (2025-07-01)[2026-03-29]. https://doi.org/10.19713/j.cnki.43-1423/u.T20250822.
[53]
LundbergS M, LeeS I. A unified approach to interpreting model predictions[C]//Advances in Neural Information Processing Systems. Long Beach: Curran Associates, Inc., 2017: 4765-4774.
[54]
RibeiroM T, SinghS, GuestrinC. “Why should I trust you?” Explaining the predictions of any classifier[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016: 1135-1144.
[55]
HoekE, BrayJ D. Rock slope engineering[M]. Boca Raton: CRC Press, 1981.
[56]
HudsonJ A. Rock engineering systems: theory and practice[M]. Oxford: Pergamon Press, 1992.
[57]
LinP S, LinM H, SuM B, et al. An investigation on the failure of a building constructed on hillslope[C]//5th International Symposium on Landslides. Rotterdam: A. A. Balkema, 1988: 445-449.