Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Prediction of rock slope failure using multiple ML algorithms

  • Bowen Liu (School of Civil Engineering, North China University of Technology) ;
  • Zhenwei Wang (School of Civil Engineering, North China University of Technology) ;
  • Sabih Hashim Muhodir (Department of Architectural Engineering, Cihan University-Erbil) ;
  • Abed Alanazi (Department of Computer Science, College of Computer Engineering and Sciences in Al-Kharj, Prince Sattam bin Abdulaziz University) ;
  • Shtwai Alsubai (Department of Computer Science, College of Computer Engineering and Sciences in Al-Kharj, Prince Sattam bin Abdulaziz University) ;
  • Abdullah Alqahtani (Software Engineering Department, College of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University)
  • Received : 2023.11.19
  • Accepted : 2024.02.20
  • Published : 2024.03.10
⟨ Previous Next ⟩

Abstract

Slope stability analysis and prediction are of critical importance to geotechnical engineers, given the severe consequences associated with slope failure. This research endeavors to forecast the factor of safety (FOS) for slopes through the implementation of six distinct ML techniques, including back propagation neural networks (BPNN), feed-forward neural networks (FFNN), Takagi-Sugeno fuzzy system (TSF), gene expression programming (GEP), and least-square support vector machine (Ls-SVM). 344 slope cases were analyzed, incorporating a variety of geometric and shear strength parameters measured through the PLAXIS software alongside several loss functions to assess the models' performance. The findings demonstrated that all models produced satisfactory results, with BPNN and GEP models proving to be the most precise, achieving an R2 of 0.86 each and MAE and MAPE rates of 0.00012 and 0.00002 and 0.005 and 0.004, respectively. A Pearson correlation and residuals statistical analysis were carried out to examine the importance of each factor in the prediction, revealing that all considered geomechanical features are significantly relevant to slope stability. However, the parameters of friction angle and slope height were found to be the most and least significant, respectively. In addition, to aid in the FOS computation for engineering challenges, a graphical user interface (GUI) for the ML-based techniques was created.

Keywords

Acknowledgement

This work was supported by General Programs of the National Natural Science Foundation of China (Grant nos. 51774184), Excellent Research Team Fund in North China University of Technology (Grant no. 107051360019XN134/017), and Scientific Research Fund in North China University of Technology (Grant no. 110051360002). This study is supported via funding from Prince Satam bin Abdulaziz University project number (PSAU/2024/R/1445).

References

  1. Andreas. Z. (1994), "Simulation neuronaler netze-simulation of neural networks", Addison-Wesley, 1(5.3),
  2. Ahangari, N., Pusatli, T., Chengyong, J., Chen, J., Cemiloglu, A., Azarafza, M. and Derakhshani, R. (2022), "Application of ML techniques for the estimation of the safety factor in slope stability analysis", Water, 18(22), 3743. https://doi.org/10.3390/w14223743.
  3. Bai, G., Hou, Y., Wan, B., An, N., Yan, Y., Tang, Z., Yan, M., Zhang, Y. and Sun, D. (2022), "Performance evaluation and engineering verification of ML based prediction models for slope stability", Appl. Sci., 12(15), 7890. https://doi.org/10.3390/app12157890.
  4. Bishop, A.W. and Morgenstern, N. (1960), "Stability coefficients for earth slopes", Geotechnique, 10(4), 129-153. https://doi.org/10.1680/geot.1960.10.4.129.
  5. Chakraborty, A. and Goswami, D. (2017), "Prediction of slope stability using multiple linear regression (MLR) and artificial neural network (ANN)", Arab. J. Geosci., 385. https://doi.org/10.1007/s12517-017-3167-x.
  6. Das, S.K., Biswal, R.K., Sivakugan, N. and Das, B. (2011). "Classification of slopes and prediction of factor of safety using differential evolution neural networks", Environ. Earth. Sci., 64(1), 201-210. https://doi.org/10.1007/S12665-010-0839-1.
  7. Eberhardt, E. (2003), "Rock slope stability analysis-utilization of advanced numerical techniques", Earth and Ocean sci. at UBC., 41.
  8. Ferreira, C. (2001), "Gene expression programming: A new adaptive algorithm for solving problems", Comp. Sys., 13(2), 87-129. https://doi.org/10.48550/arXiv.cs/0102027.
  9. Guo, J.R., He, Y.G. and Liu, C.Q. (2011), "Nonlinear correction of photoelectric displacement sensor based on least square support vector machine", J. Cent. South. Univ., 18(5), 1614-1618. https://doi.org/10.1007/s11771-011-0880-6.
  10. Hoang, N.D. and Pham, A.D. (2016). "Hybrid artificial intelligence approach based on metaheuristic and ML for slope stability assessment: A multinational data analysis", Exp. Syst. Appl., 46, 60-68. https://doi.org/10.1016/j.eswa.2015.10.020
  11. Jagan, J., Meghana, G. and Samui, P. (2016), "Determination of stability number of layered slope using ANFIS, GPR, RVM and ELM", Int. J. Comput. Res., 23(4), 371-393.
  12. Karir, D., Ray, A., Bharati, A.K., Chaturvedi, U., Rai, R. and Khandelwal, M. (2022), "Stability prediction of a natural and man-made slope using various ML algorithms", Transport. Geotech., 34, 100745. https://doi.org/10.1016/j.trgeo.2022.100745.
  13. Li, S., Zhao, H.B. and Ru, Z. (2013), "Slope reliability analysis by updated support vector machine and Monte Carlo simulation", Nat. Hazards, 65, 707-722. https://doi.org/10.1007/s11069-012-0396-x.
  14. Liu, Z., Shao, J., Xu, W., Chen, H. and Zhang, Y. (2014), "An extreme learning machine approach for slope stability evaluation and prediction", Nat. Hazards, 73(2), 787-804. https://doi.org/10.1007/s11069-014-1106-7.
  15. Liu, Y.C. and Chen, C.S. (2007), "A new approach for application of rock mass classification on rock slope stability assessment", Eng. Geol., 89(1-2), 129-143. https://doi.org/10.1016/j.enggeo.2006.09.017.
  16. Lu, P. and Rosenbaum, M.S. (2003), "Artificial neural networks and grey systems for the prediction of slope stability", Nat. Hazards, 30(3), 383-398. https://doi.org/10.1023/B:NHAZ.0000007168.00673.27
  17. Mahmoodzadeh, A., Mohammadi, M., Hama Ali, H., Ibrahim, H., Abdulhamid, S. and Nejati, H. (2021), "Prediction of safety factors for slope stability: comparison of ML techniques", Nat. Hazards, 111, 1771-1799. https://doi.org/10.1007/s11069-021-05115-8.
  18. Omar, M., Che Mamat, R., Abdul Rasam, A.R., Ramli, A. and Samad, A. (2021), "Artificial intelligence application for predicting slope stability on soft ground: A comparative study", Int. J. Adv. Technol. Eng. Explor., 8(75), 362-370. https://doi.org/10.19101/IJATEE.2020.762139.
  19. Pantelidis, L. (2009), "Rock slope stability assessment through rock mass classification systems", Int. J. Rock Mech. Min. Sci., 46(2), 315-325. https://doi.org/10.1016/j.ijrmms.2008.06.003.
  20. Samadi, H., Hassanpour, J. and Farrokh, E. (2021), "Maximum surface settlement prediction in EPB TBM tunneling using soft computing techniques", J. Phys.: Conference Series, 1973(1), 012195. http://doi.org/10.1088/1742-6596/1973/1/012195.