Using Complementary Ensemble Empirical Mode Decomposition and Gated Recurrent Unit to Predict Landslide Displacements in Dam Reservoir

Abstract

It is crucial to predict landslide displacement accurately for establishing a reliable early warning system. Such a requirement is more urgent for landslides in the reservoir area. The main reason is that an inaccurate prediction can lead to riverine disasters and secondary surge disasters. Machine learning (ML) methods have been developed and commonly applied in landslide displacement prediction because of their powerful nonlinear processing ability. Recently, deep ML methods have become popular, as they can deal with more complicated problems than conventional ML methods. However, it is usually not easy to obtain a well-trained deep ML model, as many hyperparameters need to be trained. In this paper, a deep ML method—the gated recurrent unit (GRU)—with the advantages of a powerful prediction ability and fewer hyperparameters, was applied to forecast landslide displacement in the dam reservoir. The accumulated displacement was firstly decomposed into a trend term, a periodic term, and a stochastic term by complementary ensemble empirical mode decomposition (CEEMD). A univariate GRU model and a multivariable GRU model were employed to forecast trend and stochastic displacements, respectively. A multivariable GRU model was applied to predict periodic displacement, and another two popular ML methods—long short-term memory neural networks (LSTM) and random forest (RF)—were used for comparison. Precipitation, reservoir level, and previous displacement were considered to be candidate-triggering factors for inputs of the models. The Baijiabao landslide, located in the Three Gorges Reservoir Area (TGRA), was taken as a case study to test the prediction ability of the model. The results demonstrated that the GRU algorithm provided the most encouraging results. Such a satisfactory prediction accuracy of the GRU algorithm depends on its ability to fully use the historical information while having fewer hyperparameters to train. It is concluded that the proposed model can be a valuable tool for predicting the displacements of landslides in the TGRA and other dam reservoirs.

Forecasting step-like landslide displacement through diverse monitoring frequencies

“…the prediction of cumulative displacements, the triggering factor selection method for the reference monthly frequencies. As inputs to the displacement prediction model, seven triggering factors are selected for each monitoring frequency [29], and the selection principles are shown in Table 2. software.…”

“…In the past, the monitoring period of landslide displacement was usually 1 month in the Three Gorges reservoir area [31]. This situation has also led many scholars [29,[32][33][34] to use only data with a monitoring period of months when achieving landslide displacement forecasting. However, after conducting a number of studies on landslides, some scholars found that landslide displacement development would delay for a period of time, usually less than one month, after being affected by external factors.…”

Multi-output displacement health monitoring model for concrete gravity dam in severely cold region based on clustering of measured dam temperature field

“…However, the significant nonlinear relationship between dam displacement and explanatory factors restricts the accuracy of the models. With the advancement of artificial intelligence technologies, various machine learning (ML) approaches such as backpropagation [11][12][13] (BP) network, long-short term memory 14,15 (LSTM) network, extreme learning machine [16][17][18] , Gated Recurrent Units 19,20 (GRU) network and a series of network algorithms have been developed to provide new options for the DHM model. There are also support vector regression (SVR) and its derivate algorithms, [21][22][23][24] K-nearest neighbor, XGBoost, etc.…”

Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection

“…The other important condition of such a landslide inventory dataset is need to update the inventories multi-temporally to get precise information about landslide triggering period, lifetime, and velocity [1]. Since this phenomenon does not happen randomly, a landslide inventory can contribute to disaster preparedness and support early warning systems to warn government leaders and the population at risk [14], [15]. This can be done by using spatio-temporal variabilities from the landslide inventory dataset and related thematic environmental factors to model and map the geographic location and probability of future landslides based on the same conditions and triggers that caused previous land-slides [16]- [18].…”