Abstract
Interval estimation of landslide displacement prediction is significant for landslide early warning. The goal of this paper is to improve the accuracy of landslide displacement point prediction and quantify the uncertainties associated with the predicted values. To do so, a coupling prediction model based on double moving average (DMA) method and long short-term memory (LSTM) network is investigated. The DMA method is employed to decompose cumulative displacement of landslide into trend and periodic displacements, while the LSTM network is adopted to model and predict these two sub dis-placements. The sum of predicted sub displacements is considered as predicted cumulative displacement. Further, the probability estimation theory is utilized to derive confidence intervals that quantify the uncertainties of the point prediction. The proposed approach was validated on Baishuihe landslide in Three Gorges Reservoir area of China. Results show that the LSTM network performs better than support vector machine and Elman network, while the DMA decomposition method outperforms single moving average method. As a consequence, the coupling prediction model of DMA and LSTM network is a better solution for the point prediction of landslide displacement. Furthermore, the proposed probability estimation method can construct high-quality confidence intervals.
Highlights
Landslides are severe natural calamities that threaten human life and property [1]–[5]
The mean absolute error (MAE) value of the long short-term memory (LSTM) network is 6.02 mm, lower than 8.42 mm of the support vector machine (SVM) and 7.01 mm of the Elman network. These results show that for the trend displacement prediction, the LSTM network outperforms the SVM and Elman network
The MAE value of the LSTM network is 5.73 mm, lower than 11.85 mm of the SVM and 20.12 mm of the Elman network. These results show that for the periodic displacement prediction, the LSTM network outperforms the SVM and Elman network
Summary
Landslides are severe natural calamities that threaten human life and property [1]–[5]. The landslide displacement prediction approaches mainly invert inherent nonlinear dynamic evolution process of landslide by analyzing landslide displacement-time curve and monitoring information of various external influence factors. Y. Xing et al.: Interval Estimation of Landslide Displacement Prediction Based on Time Series Decomposition and LSTM Network utilized single moving average (SMA) method to decompose landslide cumulative displacement into two sub displacements. To address the two problems, we introduce a deep learning model, so-called long short-term memory (LSTM) network, and theoretically derive the confidence intervals of landslide displacement prediction at a certain confidence level. High predictive accuracy with optimal network parameters: The L2 regularization method is introduced to solve the LSTM network over-fitting problem, while the Adam algorithm is introduced to promote the network convergence. In this paper, we introduce the ‘‘Adam’’ and ‘‘L2 regularization’’ methods to assist the construction of LSTM network
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
