Earticle

Landslide deformation signal processing is significant for landslide stability analysis. Global Position System (GPS) control networks were built to monitor landslide deformation and acquire landslide displacement time series. It was difficult to predict landslide displacement because of the highly non-linear and non-stationary characteristics contained in displacement time series. A Wavelet Analysis - Radial Basis Function Neural Network (WA-RBFNN) model was proposed to overcome this problem. Firstly, monthly cumulative displacement time series was decomposed into different frequency components using wavelet analysis. Then a RNFNN model was established to forecast each frequency component values. The final prediction results were obtained through the sum of the predictive values of each frequency component. GPS monitoring points ZG325 and ZG326 on Baijiabao landslide in the Three Gorges Reservoir Area were used as study cases. A single RBFNN model was also built as comparison. The experimental results show that GPS control network can monitor landslide deformation accurately and the WA-RBFNN model is of high prediction accuracy. What is more, WA-RBFNN model has better prediction effect than a single RBFNN model.