Landslide Displacement Prediction Based on Time Series Analysis and Double-BiLSTM Model

Research on hand, foot and mouth disease incidence forecasting using hybrid model in mainland China

BACKGROUND

This study aimed to construct a more accurate model to forecast the incidence of hand, foot, and mouth disease (HFMD) in mainland China from January 2008 to December 2019 and to provide a reference for the surveillance and early warning of HFMD.

METHODS

We collected data on the incidence of HFMD in mainland China between January 2008 and December 2019. The SARIMA, SARIMA-BPNN, and SARIMA-PSO-BPNN hybrid models were used to predict the incidence of HFMD. The prediction performance was compared using the mean absolute error(MAE), mean squared error(MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), and correlation analysis.

RESULTS

The incidence of HFMD in mainland China from January 2008 to December 2019 showed fluctuating downward trends with clear seasonality and periodicity. The optimal SARIMA model was SARIMA(1,0,1)(2,1,2)_[12], with Akaike information criterion (AIC) and Bayesian Schwarz information criterion (BIC) values of this model were 638.72, 661.02, respectively. The optimal SARIMA-BPNN hybrid model was a 3-layer BPNN neural network with nodes of 1, 10, and 1 in the input, hidden, and output layers, and the R-squared, MAE, and RMSE values were 0.78, 3.30, and 4.15, respectively. For the optimal SARIMA-PSO-BPNN hybrid model, the number of particles is 10, the acceleration coefficients c1 and c2 are both 1, the inertia weight is 1, the probability of change is 0.95, and the values of R-squared, MAE, and RMSE are 0.86, 2.89, and 3.57, respectively.

CONCLUSIONS

Compared with the SARIMA and SARIMA-BPNN hybrid models, the SARIMA-PSO-BPNN model can effectively forecast the change in observed HFMD incidence, which can serve as a reference for the prevention and control of HFMD.

Capture and Prediction of Rainfall-Induced Landslide Warning Signals Using an Attention-Based Temporal Convolutional Neural Network and Entropy Weight Methods

The capture and prediction of rainfall-induced landslide warning signals is the premise for the implementation of landslide warning measures. An attention-fusion entropy weight method (En-Attn) for capturing warning features is proposed. An attention-based temporal convolutional neural network (ATCN) is used to predict the warning signals. Specifically, the sensor data are analyzed using Pearson correlation analysis after obtaining data from the sensors on rainfall, moisture content, displacement, and soil stress. The comprehensive evaluation score is obtained offline using multiple entropy weight methods. Then, the attention mechanism is used to weight and sum different entropy values to obtain the final landslide hazard degree (LHD). The LHD realizes the warning signal capture of the sensor data. The prediction process adopts a model built by ATCN and uses a sliding window for online dynamic prediction. The input is the landslide sensor data at the last moment, and the output is the LHD at the future moment. The effectiveness of the method is verified by two datasets obtained from the rainfall-induced landslide simulation experiment.

Landslide Displacement Prediction Based on a Two-Stage Combined Deep Learning Model under Small Sample Condition

The widely distributed “Step-type” landslides in the Three Gorges Reservoir (TGR) area have caused serious casualties and heavy economic losses. The prediction research of landslide displacement will be beneficial to the establishment of local geological hazard early warning systems for the realization of scientific disaster prevention and mitigation. However, the number of observed data like landslide displacement, rainfall, and reservoir water level in this area is very small, which results in difficulties for the training of advanced deep learning model to obtain more accurate prediction results. To solve the above problems, a Two-stage Combined Deep Learning Dynamic Prediction Model (TC-DLDPM) for predicting the typical “Step-type” landslides in the TGR area under the condition of small samples is proposed. The establishment process of this method is as follows: (1) the Dynamic Time warping (DTW) method is used to enhance the small samples of cumulative displacement data obtained by the Global Positioning System (GPS); (2) A Difference Decomposition Method (DDM) based on sequence difference is proposed, which decomposes the cumulative displacement into trend displacement and periodic displacement, and then the cubic polynomial fitting method is used to predict the trend displacement; (3) the periodic displacement component is predicted by the proposed TC-DLDPM model combined with external environmental factors such as rainfall and reservoir water level. The TC-DLDPM model combines the advantages of Convolutional Neural Network (CNN), Attention mechanism, and Long Short-term Memory network (LSTM) to carry out two-stage learning and parameter transfer, which can effectively realize the construction of a deep learning model for high-precision under the condition of small samples. A variety of advanced prediction models are compared with the TC-DLDPM model, and it is verified that the proposed method can accurately predict landslide displacement, especially in the case of drastic changes in external factors. The TC-DLDPM model can capture the spatio-temporal characteristics and dynamic evolution characteristics of landslide displacement, reduce the complexity of the model, and the number of model training calculations. Therefore, it provides a better solution and exploration idea for the prediction of landslide displacement under the condition of small samples.

Landslide Displacement Prediction Based on Time-Frequency Analysis and LMD-BiLSTM Model

In landslide displacement prediction, random factors that would affect the performance of prediction are usually ignored by using a time series analysis method. In order to solve this problem, in this paper, a landslide displacement prediction model, the local mean decomposition-bidirectional long short-term memory (LMD-BiLSTM), is proposed based on the time-frequency analysis method. The model uses the local mean decomposition (LMD) algorithm to decompose landslide displacement and obtains several subsequences of landslide displacement with different frequencies. This paper analyzes the internal relationship between the landslide displacement and rainfall, reservoir water level, and landslide state. The maximum information coefficient (MIC) algorithm is used to calculate the intrinsic correlation between each subsequence of landslide displacement and rainfall, reservoir water level, and landslide state. Subsequences of influential factors with high correlation are selected as input variables of the bidirectional long short-term memory (BiLSTM) model to predict each subsequence. Finally, the predicted results of each of the subsequences are added to obtain the final predicted displacement. The proposed LMD-BiLSTM model effectiveness is verified based on the Baishuihe landslide. The prediction results and evaluation indexes show that the model can accurately predict landslide displacement.

Landslide Displacement Prediction Model Using Time Series Analysis Method and Modified LSTM Model

Landslides are serious and complex geological and natural disasters that threaten the safety of people’s health and wealth worldwide. To face this challenge, a landslide displacement prediction model based on time series analysis and modified long short-term memory (LSTM) model is proposed in this paper. Considering that data from different time periods have different time values, the weighted moving average (WMA) method is adopted to decompose the cumulative landslide displacement into the displacement trend and periodic displacement. To predict the displacement trend, we combined the displacement trend of landslides in the early stage with an LSTM model. Considering the repeatability and periodicity of rainfall and reservoir water level in every cycle, a long short-term memory fully connected (LSTM-FC) model was constructed by adding a fully connected layer to the traditional LSTM model to predict periodic displacement. The two predicted displacements were added to obtain the final landslide predicted displacement. In this paper, under the same conditions, we used a polynomial function algorithm to compare and predict the displacement trend with the LSTM model and used the LSTM-FC model to compare and predict the displacement trend with eight other commonly used algorithms. Two prediction results indicate that the modified prediction model is able to effectively predict landslide displacement.