A Novel Hybrid LMD–ETS–TCN Approach for Predicting Landslide Displacement Based on GPS Time Series Analysis

Landslide disasters cause serious property losses and casualties every year. displacement prediction is fundamental for mitigating landslide disasters. Several approaches have been used to predict displacement, yet a more accurate reliable still has poor understanding of early warning systems mitigation, due limited data mutational displacements. To boost the robustness accuracy prediction, this paper assembled new hybrid model containing local mean decomposition (LMD), innovations state space models exponential smoothing (ETS), temporal convolutional network (TCN). The proposed model, which based on over 10 years long-term time series monitoring GPS data, was tested selected case—stepwise Baijiabao in Three Gorges Reservoir area China (TGRA) by model. results presented that LMD–ETS–TCN best performance comparison with other benchmark models. Compared autoregressive integrated moving average (ARIMA), support vector regression (SVR), long short-term memory neural (LSTM), noticeably improved an 40.9%, 46.2%, 22.1%, respectively. effectiveness approach are attested, it discernible improvements prediction.