Landslide displacement prediction based on the ICEEMDAN,ApEn and the CNN-LSTM models

作     者：LI Li-min WANG Chao-yang WEN Zong-zhou GAO Jian XIA Meng-fan LI Li-min;WANG Chao-yang;WEN Zong-zhou;GAO Jian;XIA Meng-fan

作者机构：College of Electronics and InformationXi’an Polytechnic UniversityXi’an 710600 China Shaanxi Yixin Network Technology Co.LtdXi’an 710065China 

出 版 物：《Journal of Mountain Science》 (山地科学学报（英文）)

年 卷 期：2023年第20卷第5期

页      面：1220-1231页

核心收录：

学科分类：081803[工学-地质工程] 08[工学] 0818[工学-地质资源与地质工程] 

基　　金：funded by the technology innovation guidance special project of Shaanxi Province(Grant No.2020CGXNX009) the supported by the National Natural Science Foundation of China(Grant No.62203344) the Shaanxi Provincial Department of Education serves local special projects(Grant No.22JC036) the Natural Science Basic Research Plan of Shaanxi Province(Grant No.2022JM-322) 

主　　题：Displacement prediction ICEENDAN Approximate entropy Long short-term memory Bazimen landslide 

摘      要：Landslide deformation is affected by its geological conditions and many environmental *** it has the characteristics of dynamic,nonlinear and unstable,which makes the prediction of landslide displacement *** view of the above problems,this paper proposes a dynamic prediction model of landslide displacement based on the improvement of complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN),approximate entropy(ApEn)and convolution long short-term memory(CNN-LSTM)neural ***,ICEEMDAN and Ap En are used to decompose the cumulative displacements into trend,periodic and random ***,the least square quintic polynomial function is used to fit the displacement of trend term,and the CNN-LSTM is used to predict the displacement of periodic term and random ***,the displacement prediction results of trend term,periodic term and random term are superimposed to obtain the cumulative displacement prediction *** proposed model has been verified in Bazimen landslide in the Three Gorges Reservoir area of *** experimental results show that the model proposed in this paper can more effectively predict the displacement changes of *** compared with long short-term memory(LSTM)neural network,gated recurrent unit(GRU)network model and back propagation(BP)neural network,CNN-LSTM neural network had higher prediction accuracy in predicting the periodic displacement,with the mean absolute percentage error(MAPE)reduced by 3.621%,6.893% and 15.886% respectively,and the root mean square error(RMSE)reduced by 3.834 mm,3.945 mm and 7.422mm ***,this model not only has high prediction accuracy but also is more stable,which can provide a new insight for practical landslide prevention and control engineering.