Dynamic Prediction of Landslide Displacement Based on Multi-source Time Series
Displacement prediction plays an important role in the landslide early warning and forecasting system.In order to improve the accuracy of displacement prediction,a method for dynamic prediction of landslide displacement combining variational modal decomposition (VMD) and double exponential smoothing...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Pearl River
2023-01-01
|
| Series: | Renmin Zhujiang |
| Subjects: | |
| Online Access: | http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2023.04.007 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Displacement prediction plays an important role in the landslide early warning and forecasting system.In order to improve the accuracy of displacement prediction,a method for dynamic prediction of landslide displacement combining variational modal decomposition (VMD) and double exponential smoothing method (DES) and neural network was proposed.Firstly,the variational modal decomposition was performed on the historical monitoring displacement data to generate multiple modal components,and then the prediction was carried out using the double exponential smoothing method and the extreme learning machine (ELM) model.And the particle swarm optimization algorithm was used to optimize the ELM model to finally accumulate the predicted values of each modal to complete the prediction.Taking the Baijiabao landslide in the Three Gorges reservoir area as an example,the established model was compared with the period terms predicted by least squares support vector machine (LSSVM) and convolutional neural network-gated recurrent unit (CNN-GRU).The results show that the DES-PSO-ELM used can effectively predict the changes of landslide displacement with the of RMSE,root mean square error (RMSE),mean absolute error (MAE),MAPE (mean absolute percentage error) and Pearson correlations of 1.293 mm,0.993 mm,0.008 0 and 0.999 8,respectively,showing minimum prediction errors.The research results can provide a technical basis for the landslide early warning monitoring system. |
|---|---|
| ISSN: | 1001-9235 |