Landslide Surface Displacement Prediction Based on VSXC-LSTM Algorithm
This work addresses landslide prediction for disaster management, but it is incremental as it builds on existing methods like LSTM and XGBoost.
The paper tackles landslide surface displacement prediction by proposing the VSXC-LSTM framework, which combines variational mode decomposition and machine learning techniques, achieving low error rates such as an RMSE as low as 0.006 for periodic item predictions.
Landslide is a natural disaster that can easily threaten local ecology, people's lives and property. In this paper, we conduct modelling research on real unidirectional surface displacement data of recent landslides in the research area and propose a time series prediction framework named VMD-SegSigmoid-XGBoost-ClusterLSTM (VSXC-LSTM) based on variational mode decomposition, which can predict the landslide surface displacement more accurately. The model performs well on the test set. Except for the random item subsequence that is hard to fit, the root mean square error (RMSE) and the mean absolute percentage error (MAPE) of the trend item subsequence and the periodic item subsequence are both less than 0.1, and the RMSE is as low as 0.006 for the periodic item prediction module based on XGBoost\footnote{Accepted in ICANN2023}.