volume | PIER Journals

Abstract

The research on landslide displacement prediction can help the early warning and prevention of landslide disasters in mining areas. In view of the problem that BP neural network is prone to local convergence, and considering that the network trained based on time-series cumulative displacement may produce large errors in prediction, this paper proposes a method combining displacement increment and CS-BP (Cuckoo Search-Back Propagation) neural network to predict landslide displacement. Compared with the conventional landslide displacement prediction methods, this method uses displacement increment instead of the commonly used cumulative displacement as the network input data, and selects the CS algorithm with few parameters and easy to implement to optimize the BP network to construct the prediction model, and predicts the corresponding amount of displacement change at the next moment by the historical landslide displacement increment. Combined with the measured data of three feature points of a mine in Xinjiang, China, obtained by the micro-deformation monitoring radar, the displacement prediction accuracy of the proposed model on the three measured data sets is compared with the prediction accuracy of the BP, GA-BP (Genetic Algorithm, GA), and FA-BP (Firefly Algorithm, FA) network prediction models based on cumulative displacement and incremental displacement, respectively. The experimental results show that this method achieves superior performance with an average root mean square error of 0.3261 and an average mean absolute error of 0.2785 across the three feature points, outperforming the other models, and holds promising applications in disaster prevention and control work.

1. Zhou, S., "Research on micro-deformation monitoring radar deformation information extraction and early warning method,", Inner Mongolia University of Technology, 2021.
doi:10.3390/s19102306

2. Alibakhshikenari, M., S. Virdee, H. See, et al. "Super-wide impedance bandwidth planar antenna for microwave and millimeter-wave applications," Sensors, Vol. 19, No. 10, 2019.
doi:10.3390/s19102306

3. Alibakhshikenari, M., A. And´ujar, and J. Anguera, "New compact printed leakywave antenna with beam steering," Microwave and Optical Technology Letters , Vol. 58, No. 1, 2016.

4. Alibakhshikenari, M., M. Naser-Moghadasi, A. Sadeghzadeh, et al. "Hexa-band planar antenna with asymmetric fork-shaped radiators for multiband and broadband communication applications," IET Microwaves, Antennas & Propagation, Vol. 10, No. 5, 2016.

5. Liang, Y., T. Xiao, C. Hu, et al. "Landslide displacement prediction based on long-term monitoring data and LSTM network," Journal of Signal Processing, Vol. 38, No. 1, 19-27, 2022.

6. Liu, R., J. Huang, Q. Li, et al. "Application of EEMD-GA-SVM model in landslide displacement prediction," People’s Changjiang, Vol. 50, No. 11, 134-139, 2019.

7. Duan, Y., "Research on landslide displacement prediction based on hybrid machine learning,", Northwestern University, 2022.

8. Zhang, B. and Y. Men, "Research on landslide deformation prediction report based on neural network," Journal of Xi’an Engineering College, No. 3, 69-71, 1998.

9. Yue, Q., J. Yuan, and T. Hu, "Landslide displacement prediction based on wavelet analysis and gray BP neural network," Hydropower Energy Science, Vol. 37, No. 10, 88-91, 2019.

10. Cheng, S., W. Ma, X. Gao, et al. "Landslide displacement prediction by CPSO-BP combined optimization model," Survey and Mapping Science, Vol. 44, No. 10, 65-71, 2019.

11. Qiao, S. and C. Wang, "Landslide displacement prediction based on genetic simulated annealing algorithm," Journal of Civil and Environmental Engineering, Vol. 43, No. 1, 25-35, 2021.

12. Qu, W., X. Liu, J. Li, and et al, "A high accuracy prediction model of landslide displacement by improving the combination of Harris Hawk optimization algorithm and BP neural network," Journal of Earth Sciences and Environment, Vol. 45, No. 3, 522-534, 2023.
doi:10.1504/IJMMNO.2010.035430

13. Yang, X. and S. Deb, "Engineering optimisation by cuckoo search," Int. J. of Mathematical Modelling and Numerical Optimisation, Vol. 1, No. 4, 330-343, 2010.
doi:10.1504/IJMMNO.2010.035430

14. Gandomi, A., X. Yang, and A. Alavi, "Cuckoo search algorithm: A metaheuristic approach to solve structural optimization problems," Engineering with Computers, Vol. 29, 17-35, 2013.
doi:10.1007/s00366-011-0241-y

15. Peng, B., K. Ho, and Y. Liu, "A novel and fast MPPT method suitable for both fast changing and partially shaded conditions," IEEE Transactions on Industrial Electronics, Vol. 65, No. 4, 3240-3251, 2018.
doi:10.1109/TIE.2017.2736484

16. Wang, M., Y. Wan, Z. Ye, et al. "Remote sensing image classification based on the optimal support vector machine and modified binary coded ant colony optimization algorithm," Information Sciences, Vol. 402, 50-68, 2017.
doi:10.1016/j.ins.2017.03.027

17. Xiao, L., W. Shao, M. Yu, et al. "Research and application of a hybrid wavelet neural network model with the improved cuckoo search algorithm for electrical power system forecasting," Applied Energy, Vol. 198, No. 15, 203-222, 2017.
doi:10.1016/j.apenergy.2017.04.039

18. Zhou, J. and X. Yao, "Multi-objective hybrid artificial bee colony algorithm enhanced with L´evy flight and self-adaption for cloud manufacturing service composition," Applied Intelligence, Vol. 47, No. 3, 721-742, 2017.
doi:10.1007/s10489-017-0927-y

19. Lin, S., A. Su, and S. Yang, "Prediction of reservoir bank landslide displacement based on MIV-BP neural network," Journal of Gansu Science, Vol. 33, No. 6, 121-125, 2021.

20. Fu, W., "A cuckoo search algorithm with a gravitational acceleration mechanism," Journal of Software, Vol. 32, No. 5, 1480-1494, 2021.

Professor Yaolong Qi

Dr. Lu Bai

Dr. Ting Hou

Professor Pingping Huang

Professor Weixian Tan

Dr. Wei Xu