Abstract
In the complex geological environments of cold regions, traditional methods struggle to address the multifactorial coupling and nonlinear dynamic evolution of hazardous rock mass driven by freeze‒thaw cycles. To overcome these challenges, this study investigates the applicability and optimization of intelligent prediction models tailored to cold regions. A long-term stability prediction framework is constructed by integrating the freeze–thaw–gravity coupling mechanism mechanism. Unlike generic hybrid models, this research systematically compares and optimizes various metaheuristic algorithms (SSA, PSO, GA) coupled with neural networks to identify an effective strategy for the high-dimensional, nonlinear characteristics of rock mass in these regions. Focusing on hazardous rock mass in western China, six primary influencing factors—cohesion, freezing depth, lowest temperature, freezing load, sunshine duration, and foot of slope displacement—were selected on the basis of the typical freeze–thaw–gravity coupling mechanism damage mechanism. Key control parameters were identified via gray relational analysis (GRA), and data normalization was applied to enhance model generalizability. The evaluation results demonstrate that hybrid algorithm models outperform traditional single-algorithm models for the investigated cases, with improved prediction accuracy and adaptability under freeze-thaw-dominated conditions. Specifically, the SSA-BP model reduced the root mean square error (RMSE) by approximately 30% compared with the standalone BP model, whereas the mean absolute error (MAE) and mean squared error (MSE) decreased by 28% and 35%, respectively, and achieved a goodness-of-fit with measured data exceeding 90%. Moreover, the PSO-BP model improved computational efficiency by approximately 40% while maintaining prediction accuracy, rendering it suitable for real-time monitoring and rapid warning scenarios. These findings indicate that hybrid algorithm models partially alleviate the limitations of single models—such as poor generalizability and susceptibility to local optima—by incorporating global optimization mechanisms and adaptive parameter adjustment, thereby demonstrating improved robustness and potential engineering-oriented applicability.
Data availability
If someone wants to request the data from this study, please contact the author Xiaoxue Liu.
References
Chen, H. K., Tang, H. M. & Ye, S. Q. Damage model of control fissure in perilous rock. Appl. Math. Mech. 27, 967–974. https://doi.org/10.1007/s10483-006-0713-y (2006).
Fan, H. et al. Advanced stability analysis of the tunnels in jointed rock mass based on TSP and DEM. KSCE J. Civ. Eng. 25 (4), 1491–1503. https://doi.org/10.1007/s12205-021-0136-4 (2021).
Jiang, H. M., Li, J. & Deng, S. X. Theoretical and experimental investigation of sliding instability in blocky rock system triggered by external disturbance. Acta Geophys. 67 (3), 775–787. https://doi.org/10.1007/s11600-019-00287-1 (2019).
Langet, N. & Silverberg, F. M. J. Automated classification of seismic signals recorded on the Åknes rock slope, Western Norway, using a convolutional neural network. Earth Surf. Dyn. 11 (1), 89–115. https://doi.org/10.5194/esurf-11-89-2023 (2023).
Li, R. et al. Rill erosion and controlling factors on highway side-slopes in the permafrost region. J. Mt. Sci. 21 (11), 3669–3682. https://doi.org/10.1007/s11629-024-8370-1 (2024).
Liu, G. et al. Impact failure and disaster processes associated with rockfalls based on three-dimensional discontinuous deformation analysis. Earth. Surf. Proc. Land. 49 (11), 3344–3366. https://doi.org/10.1002/esp.5678 (2024).
Liu, Y. et al. Seismic response and dynamic failure mode of a class of bedding rock slope subjected to freeze-thaw cycles. Rock Mech. Rock Eng. 58 (3), 3289–3307. https://doi.org/10.1007/s00603-024-0378-9 (2025).
Qin, Z., Lai, Y., Yan, T. & Zhang, M. Stability behavior of a reservoir soil bank slope under freeze-thaw cycles in cold regions. Cold Reg. Sci. Technol. 181, 103181. https://doi.org/10.1016/j.coldregions.2020.103181 (2021).
Xu, J., Liu, Y. & Ni, Y. Hierarchically weighted rough-set genetic algorithm of rock slope stability analysis in the freeze-thaw mountains. Environ. Earth Sci. 78, 227. https://doi.org/10.1007/s12665-019-8241-0 (2019).
Zhao, Y., Liu, K., Liu, H. & Xu, H. Study on stability analysis of soil-rock-mixture slopes under freeze-thaw erosion in greater Khingan mountains. Lithosphere 2022. https://doi.org/10.2113/2022/6936421 (2022).
Song, L. et al. A back-propagation neural network optimized by genetic algorithm for rock joint roughness evaluation. J. Rock Mech. Geotech. Eng. https://doi.org/10.1016/j.jrmge.2024.10.022 (2024).
Jiang, W. et al. A BP neural network-based micro particle parameters calibration and an energy criterion for the application of strength reduction method in MatDEM to evaluate 3D slope stability. Revista Int. De Métodos Numéricos Para Cálculo Y Diseño En Ingeniería. 39 (1), 1–14. https://doi.org/10.23967/j.rimni.2023.01.003 (2023).
Liu, Y. et al. Image analysis and LSTM methods for forecasting surficial displacements of a landslide triggered by snowfall and rainfall. Landslides 22 (3), 619–635. https://doi.org/10.1007/s10346-024-02328-3 (2025).
Zhao, L. H. et al. Sensitivity analysis of regional rainfall-induced landslide based on UAV photogrammetry and LSTM neural network. J. Mt. Sci. 20 (11), 3312–3326. https://doi.org/10.1007/s11629-023-7991-z (2023).
Singh, P., Samui, P., Mohamad, E. T., Bhatawdekar, R. M. & Zhang, W. Application of MCS, GRNN, and GPR for performing the reliability analysis of rock slope. Nat. Hazards. 120 (8), 7897–7917. https://doi.org/10.1007/s11069-024-06472-w (2024).
Wang, C., Wang, X. & Zhu, Y. Hazard assessment of debris flow based on infinite irrelevance method and probabilistic neural network coupling model. IEEE Access. 10, 36823–36833. https://doi.org/10.1109/ACCESS.2022.3164223 (2022).
Zheng, Y., Chen, C., Wang, R. & Meng, F. Stability analysis of rock slopes subjected to block-flexure toppling failure using adaptive moment Estimation method (Adam). Rock Mech. Rock Eng. 55 (6), 3675–3686. https://doi.org/10.1007/s00603-022-02828-5 (2022).
Zheng, Y. et al. Assessing the stability of rock slopes with respect to block-flexure toppling failure using a force-transfer model and genetic algorithm. Rock Mech. Rock Eng. 53 (8), 3433–3445. https://doi.org/10.1007/s00603-020-02122-2 (2020).
Li, X., Chen, S., Liu, S. & Li, Z. AE waveform characteristics of rock mass under uniaxial loading based on Hilbert-Huang transform. J. Cent. South. Univ. 28 (6), 1843–1856. https://doi.org/10.1007/s11771-021-4734-6 (2021).
Li, X., Chen, S., Wang, E. & Li, Z. Rockburst mechanism in coal rock with structural surface and the microseismic (MS) and electromagnetic radiation (EMR) response. Eng. Fail. Anal. 128, 105523. https://doi.org/10.1016/j.engfailanal.2021.105396 (2021).
Li, X. et al. Rock burst monitoring by integrated microseismic and electromagnetic radiation methods. Rock Mech. Rock Eng. 49 (11), 4393–4406. https://doi.org/10.1007/s00603-016-1037-6 (2016).
Liu, S. et al. Experimental study of effect of liquid nitrogen cold soaking on coal pore structure and fractal characteristics. Energy 275, 127470. https://doi.org/10.1016/j.energy.2023.127470 (2023).
Li, H. et al. Experimental study on compressive behavior and failure characteristics of imitation steel fiber concrete under uniaxial load. Constr. Build. Mater. 399, 132599. https://doi.org/10.1016/j.conbuildmat.2023.132599 (2023).
Guo, J. et al. Landslide hazard susceptibility evaluation based on SBAS-InSAR technology and SSA-BP neural network algorithm: A case study of Baihetan reservoir area. J. Mt. Sci. 21 (3), 952–972. https://doi.org/10.1007/s11629-023-8083-9 (2024).
Li, B. & Qiu, J. Displacement prediction of open-pit mine slope based on SSA-ELM. Front. Earth Sci. 11, 1126394. https://doi.org/10.3389/feart.2023.1126394 (2023).
Shu, J. Stability Deterioration Model and Parameter Analysis of Dangerous Rock Mass in Cold Regions Under the Effect of freeze-thaw Cycles (Jiangxi University of Science and Technology, 2022).
Shu, J. et al. Stability deterioration analysis of toppling dangerous rock mass under the combined effect of vibration and freeze-thaw cycles. KSCE J. Civ. Eng. 28 (5), 1729–1738. https://doi.org/10.1007/s12205-024-1120-7 (2024).
Deng, Z., Liu, S., Wei, J., Jiang, Z. & Hu, Q. Deformation characteristics and fracture damage model of freezing weakly cemented jointed rock masses. Comput. Geotech. 187, 107463. https://doi.org/10.1016/j.compgeo.2025.107463 (2025).
Horikawa, S. I., Furuhashi, T. & Uchikawa, Y. On fuzzy modeling using fuzzy neural networks with the backpropagation algorithm. IEEE Trans. Neural Networks. 3 (5), 801–806. https://doi.org/10.1109/72.159058 (1992).
Ding, S., Su, C. & Yu, J. An optimizing BP neural network algorithm based on genetic algorithm. Artif. Intell. Rev. 36 (2), 153–162. https://doi.org/10.1007/s10462-011-9218-9 (2011).
Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9 (8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 (1997).
Sherstinsky, A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Phys. D: Nonlinear Phenom. 404, 132306. https://doi.org/10.1016/j.physd.2019.132306 (2020).
Specht, D. F. A general regression neural network. IEEE Trans. Neural Networks. 2 (6), 568–576. https://doi.org/10.1109/72.97934 (1991).
Xiao, Z. et al. Use of general regression neural networks for generating the GLASS leaf area index product from time-series MODIS surface reflectance. IEEE Trans. Geosci. Remote Sens. 52 (1), 209–223. https://doi.org/10.1109/TGRS.2013.2238643 (2014).
Goldberg, D. E. Genetic algorithms in search, optimization, and machine learning. Choice Rev. 27 (02), 27–0936. https://doi.org/10.5860/CHOICE.27-0936 (1989).
Deb, K., Pratap, A., Agarwal, S. & Meyarivan, T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6 (2), 182–197. https://doi.org/10.1109/4235.996017 (2002).
Khan, K. & Sahai, A. A comparison of BA, GA, PSO, BP and LM for training feed forward neural networks in e-learning context. Int. J. Intell. Syst. Appl. 4 (7), 23–29. https://doi.org/10.5815/ijisa.2012.07.04 (2012).
Wang, J., Zhu, L. & Dai, H. An efficient state-of-health Estimation method for lithium-ion batteries based on feature-importance ranking strategy and PSO-GRNN algorithm. J. Energy Storage. 72, 108638. https://doi.org/10.1016/j.est.2023.108638 (2023).
Zheng, Y. et al. Sine-SSA-BP ship trajectory prediction based on chaotic mapping improved sparrow search algorithm. Sensors 23 (2), 704. https://doi.org/10.3390/s23020704 (2023).
Li, T., Shu, J. & Chang, D. Time-series prediction of settlement deformation in shallow buried tunnels based on EMD-SSA-GRNN model. Sci. Rep. https://doi.org/10.1038/s41598-024-42342-6 (2024). Article 4474.
Luo, Z., Bui, X. N., Nguyen, H. & Moayedi, H. A novel artificial intelligence technique for analyzing slope stability using PSO-CA model. Eng. Comput. 37 (1), 533–544. https://doi.org/10.1007/s00366-020-00984-6 (2021).
Wang, M., Zhao, G. & Wang, S. Hybrid random forest models optimized by sparrow search algorithm (SSA) and Harris Hawk optimization algorithm (HHO) for slope stability prediction. Transp. Geotechnics. 48, 101305. https://doi.org/10.1016/j.trgeo.2024.101305 (2024).
Funding
This research acknowledges the financial support provided by the Special Research Project of the Key Laboratory of Prefabricated Building and Intelligent Construction (Grant NO. PT2025KJT001).
Author information
Authors and Affiliations
Contributions
Xiaoxue Liu: Writing-original draft, Administration. Qian Liu: Writing-review & editing, Data curation, Investigation, Funding acquisition. He Guo : Data curation, Methodology. Jinsheng Sun : Data curation, Administration.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Liu, X., Liu, Q., Guo, H. et al. Stability analysis and prediction of hazardous rock mass in cold regions based on hybrid algorithm model. Sci Rep (2026). https://doi.org/10.1038/s41598-025-34840-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-025-34840-4
