Baishuihe Landslide Research Articles

Deformation mechanism-assisted deep learning architecture for predicting step-like displacement of reservoir landslide

Reservoir landslides in the Three Gorges Reservoir, China, exhibit prolonged slow motion and the potential for catastrophic events due to fluctuations in reservoir levels and intense rainfall episodes. Their distinct step-like deformation characteristics, involving rapid transformation processes of different states, pose challenges for accurate early warning and prediction. Previous forecasting models have often struggled with limited accuracy. This study introduces a mechanism-assisted deep learning model, leveraging the Informer architecture, to predict prolonged step-like reservoir landslide displacement. Utilizing a 15-year continuous monitoring dataset of the Baishuihe landslide, this model investigates the landslide mechanism, identifies influencing conditions underlying the step-wise behavior, and customizes input features for the prediction model by integrating optimized variational mode decomposition and wavelet analysis. Additionally, the dynamic correlation and hysteresis analysis between triggering factors and displacement offer valuable physical insights into the model and enhance the interpretability of the model. The model is further tailored to accommodate features of the monitoring dataset associated with landslide evolution by integrating a global multi-head attention mechanism and pooling layers, enabling the capture of both globe dependencies and local critical features of the model inputs. Through rigorous model training, performance evaluation, and tuning, the proposed model efficiently predicts step-wise landslide displacement, particularly during short-term rapid transitions between creep-mutation states.

Structural characterization and attempted displacement interpretation of the Baishuihe landslide using integrated geophysical methods

The Baishuihe landslide, a typical large-scale deposit landslide in the Three Gorges Reservoir area, has attracted considerable societal and scholarly attention. Since 2003, 11 displacement monitoring points have been established on the landslide mass for monitoring displacement data. Displacement monitoring data from 14 years have been widely applied in landslide displacement prediction research. However, there is a lack of research involving interpretations of displacement data. To interpret landslide displacement from geological and hydrodynamic perspectives, we applied integrated geophysical methods, including electrical resistivity tomography (ERT), self-potential (SP), and surface nuclear magnetic resonance (SNMR), to model the landslide structure and investigate groundwater activity. The results indicate that the landslide deposit is predominantly located at the foot of the landslide, with a total volume of approximately 7.7 × 106 cubic meters. The thickness gradually increases in the eastern direction of the landslide along the sliding direction, while in the western direction, it initially increases and then decreases. The SNMR results reveal that groundwater is primarily situated in the gravel soil layer, demonstrating a volumetric water content of approximately 2.8% per unit volume. The SP results suggest that below an elevation of 190 m, the groundwater flow field is turbulent and irregular. Above an elevation of 190 m, the general direction of the groundwater flow field tends to align roughly with the sliding direction. Through the integration of GPS displacement monitoring data and comprehensive geophysical analysis, we discerned that the thickness of the deposit layer, the morphology of the sliding surface, and the interaction with groundwater recharge collectively exert significant influences on the displacement of the Baishuihe landslide. Generally, the thickness of the deposit layer and the morphology of the sliding surface determine whether the landslide will exhibit significant displacement. At a more detailed level, the weight of the accumulated mass and the influence of groundwater play a significant role in determining the displacement velocity.

Deformation evaluation and displacement forecasting of baishuihe landslide after stabilization based on continuous wavelet transform and deep learning

Deformation evaluation and displacement forecasting of baishuihe landslide after stabilization based on continuous wavelet transform and deep learning

Data-augmented landslide displacement prediction using generative adversarial network

Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide. Accurately predicting landslide displacement enables effective early warning and risk management. However, the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models, such as state-of-the-art machine learning (ML) models. To address these challenges, this study proposes a data augmentation framework that uses generative adversarial networks (GANs), a recent advance in generative artificial intelligence (AI), to improve the accuracy of landslide displacement prediction. The framework provides effective data augmentation to enhance limited datasets. A recurrent GAN model, RGAN-LS, is proposed, specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data. A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data. Then, the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory (LSTM) networks and particle swarm optimization-support vector machine (PSO-SVM) models for landslide displacement prediction tasks. Results on two landslides in the Three Gorges Reservoir (TGR) region show a significant improvement in LSTM model prediction performance when trained on augmented data. For instance, in the case of the Baishuihe landslide, the average root mean square error (RMSE) increases by 16.11%, and the mean absolute error (MAE) by 17.59%. More importantly, the model's responsiveness during mutational stages is enhanced for early warning purposes. However, the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM. Further analysis indicates that an optimal synthetic-to-real data ratio (50% on the illustration cases) maximizes the improvements. This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results. By using the powerful generative AI approach, RGAN-LS can generate high-fidelity synthetic landslide data. This is critical for improving the performance of advanced ML models in predicting landslide displacement, particularly when there are limited training data. Additionally, this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas.

Slope stability analysis with a hypoplastic constitutive model: Investigating a stochastic anisotropy model and a hydro‐mechanical coupled simulation

AbstractA reliable constitutive model is essential for accurately predicting slope deformation in numerical analysis, which includes assessing slope stability as an integral component. However, calculating slope stability in numerical models can be challenging due to complex boundary conditions and advanced constitutive models, especially when probabilistic and hydro‐mechanical coupled simulations are required. In this paper, we use a vector‐sum method‐based framework for slope stability analysis that incorporates a critical state hypoplastic constitutive model. The rationality and accuracy of the stability results are initially verified through critical slip surface analysis and a factor of safety evaluation. Subsequently, we investigate the probability‐based slope stability and failure characteristics by incorporating the spatial variability of strength parameters into the hypoplastic model. Finally, the Baishuihe landslide in the Three Gorges Reservoir Region is examined as a case study, where hydro‐mechanical coupled simulations are conducted under actual water level and rainfall conditions. The time‐varying stability and deformation characteristics of the landslide are analyzed and compared with the results obtained from the Mohr‐Coulomb model. The analysis results demonstrate the practicality and efficiency of using a hypoplastic model for probabilistic and time‐varying slope stability calculations. Furthermore, it highlights the superior ability of the hypoplastic model to accurately describe reservoir landslide deformation processes.

Conditional random field-based stochastic analysis of unsaturated slope stability combining Hoffman method and Bayesian updating

This paper proposes a new framework for discretizing the conditional random fields that combines the Hoffman method and Bayesian updating, where multiple types of geotechnical data can be utilized, such as the field monitoring data and the site investigation geological borehole data. The feasibility of the proposed method is demonstrated using a rainfall-induced slope example in spatially varying soils. Results showed that the proposed framework of incorporating Bayesian updating to Hoffman method can effectively reduce the uncertainty in site characterization and guarantee precise risk assessment of unsaturated slope stability. Otherwise, the slope failure probability and landslide sliding volume would be overestimated when only the Hoffman method is adopted for site characterization. Subsequently, the developed method is further used to estimate the probabilistic stability of Baishuihe landslide in the presence of rainfall infiltration and reservoir water level fluctuation. It is hoped that this study can provide a reference for risk assessment of the unsaturated slope stability in reservoir areas.

Landslide displacement forecasting using deep learning and monitoring data across selected sites

Accurate early warning systems for landslides are a reliable risk-reduction strategy that may significantly reduce fatalities and economic losses. Several machine learning methods have been examined for this purpose, underlying deep learning (DL) models’ remarkable prediction capabilities. The long short-term memory (LSTM) and gated recurrent unit (GRU) algorithms are the sole DL model studied in the extant comparisons. However, several other DL algorithms are suitable for time series forecasting tasks. In this paper, we assess, compare, and describe seven DL methods for forecasting future landslide displacement: multi-layer perception (MLP), LSTM, GRU, 1D convolutional neural network (1D CNN), 2xLSTM, bidirectional LSTM (bi-LSTM), and an architecture composed of 1D CNN and LSTM (Conv-LSTM). The investigation focuses on four landslides with different geographic locations, geological settings, time step dimensions, and measurement instruments. Two landslides are located in an artificial reservoir context, while the displacement of the other two is influenced just by rainfall. The results reveal that the MLP, GRU, and LSTM models can make reliable predictions in all four scenarios, while the Conv-LSTM model outperforms the others in the Baishuihe landslide, where the landslide is highly seasonal. No evident performance differences were found for landslides inside artificial reservoirs rather than outside. Furthermore, the research shows that MLP is better adapted to forecast the highest displacement peaks, while LSTM and GRU are better suited to model lower displacement peaks. We believe the findings of this research will serve as a precious aid when implementing a DL-based landslide early warning system (LEWS).

Advance Landslide Prediction and Warning Model Based on Stacking Fusion Algorithm

In landslide disaster warning, a variety of monitoring and warning methods are commonly adopted. However, most monitoring and warning methods cannot provide information in advance, and serious losses are often caused when landslides occur. To advance the warning time before a landslide, an innovative advance landslide prediction and warning model based on a stacking fusion algorithm using Baishuihe landslide data is proposed in this paper. The Baishuihe landslide area is characterized by unique soil and is in the Three Gorges region of China, with a subtropical monsoon climate. Based on Baishuihe historical data and real-time monitoring of the landslide state, four warning level thresholds and trigger conditions for each warning level are established. The model effectively integrates the results of multiple prediction and warning submodels to provide predictions and advance warnings through the fusion of two stacking learning layers. The possibility that a risk priority strategy can be used as a substitute for the stacking model is also discussed. Finally, an experimental simulation verifies that the proposed improved model can not only provide advance landslide warning but also effectively reduce the frequency of false warnings and mitigate the issues of traditional single models. The stacking model can effectively support disaster prevention and reduction and provide a scientific basis for land use management.

A DES-BDNN based probabilistic forecasting approach for step-like landslide displacement

Accurate and reliable displacement prediction is very important for landslide early warning. However, various uncertainties contained in landslide displacement prediction will greatly affect the prediction accuracy, and reduce the credibility of prediction results. Probability prediction is an efficient way to assess the uncertainties associated landslide displacement and improve the reliability of prediction. This paper proposes a new probabilistic forecasting framework for landslide displacement based on exponential smoothing (DES) and Bayesian deep neural networks (BDNN), which can clearly distinguish the aleatoric uncertainty covered by the evolution of data itself and the epistemic uncertainty reflecting the unsteadiness of intelligent model. Therein, DES predicts the linear part contained in the total displacement, and BDNN predicts the residual nonlinear part. The optimal input features of BDNN model are determined by the maximum information coefficient and Pearson correlation coefficient. The Baishuihe landslide in the Three Gorges Reservoir area was selected to test the effectiveness of the proposed framework with three BDNN models, including Bayesian recurrent neural network (BRNN), Bayesian gated recurrent unit network (BGRU) and Bayesian long short-term memory network (BLSTM). The results suggest that the proposed framework can obtain considerable prediction effect, especially DES-BLSTM and DES-BGRU model. The variational mode decomposition (VMD) and interpolation are used to further optimize the DES-BDNN model from the perspective of reducing the complexity of nonlinear displacement and increasing training datasize. The comparison results show that the improved model can not only obtain high-precision point prediction results, but also accurately infer the total/aleatoric/epistemic uncertainty associated with landslide displacement prediction.

Time series analysis and gated recurrent neural network model for predicting landslide displacements

ABSTRACT An effiecient landslide displacement prediction is important for early warning system of landslides. Based on time series method, the cumulative deformation of a landslide is decomposed into periodic and trend ones. A cubic polynomial is employed to forecast the trend deformation. Considering the periodic changes in rainwater and reservoir levels, the proposed model combines a convolutional neural network (CNN) with a gated recurrent unit (GRU) neural network to forecast periodic deformations. CNN effectively identifies the characteristics of the raw data, and GRU automatically controls the impact of historical information by adjusting the weights of the reset and update gates. C-GRU performance in predicting the periodic displacement is compared with GRU, and a backpropagation neural network optimised using particle swarm optimisation (PSO-BP). Monitoring points of Baishuihe landslide are employed to compare the performance of the various models. The findings show that the proposed model has strong data mining performance and deals with time series data efficiently. The new model can incorporate historical information more effectively than PSO-BP. Compared with GRU, the proposed model better captures the input data characteristics and improves the prediction accuracy. C-GRU achieves a low mean square error, representing a significant improvement in the accuracy of landslide predictions.

Prediction Interval Estimation of Landslide Displacement Using Bootstrap, Variational Mode Decomposition, and Long and Short-Term Time-Series Network

Using multi-source monitoring data to model and predict the displacement behavior of landslides is of great significance for the judgment and decision-making of future landslide risks. This research proposes a landslide displacement prediction model that combines Variational Mode Decomposition (VMD) and the Long and Short-Term Time-Series Network (LSTNet). The bootstrap algorithm is then used to estimate the Prediction Intervals (PIs) to quantify the uncertainty of the proposed model. First, the cumulative displacements are decomposed into trend displacement, periodic displacement, and random displacement using the VMD with the minimum sample entropy constraint. The feature factors are also decomposed into high-frequency components and low-frequency components. Second, this study uses an improved polynomial function fitting method combining the time window and threshold to predict trend displacement and uses feature factors obtained by grey relational analysis to train the LSTNet networks and predict periodic and random displacements. Finally, the predicted trend, periodic, and random displacement are summed to the predicted cumulative displacement, while the bootstrap algorithm is used to evaluate the PIs of the proposed model at different confidence levels. The proposed model was verified and evaluated by the case of the Baishuihe landslide in the Three Gorges reservoir area of China. The case results show that the proposed model has better point prediction accuracy than the three baseline models of LSSVR, BP, and LSTM, and the reliability and quality of the PIs constructed at 90%, 95%, and 99% confidence levels are also better than those of the baseline models.

Optimized Apriori algorithm for deformation response analysis of landslide hazards

With the explosive development of data mining technology, higher requirements have been put forward to analyze the response of landslide deformation. However, related algorithms, such as the traditional Apriori and FP-Growth algorithms, are still in the starting period of being applied to landslide hazards. Due to monitoring data characteristics, some problems were encountered while applying these algorithms, such as poor applicability and low computational efficiency. Therefore, we propose an optimized Apriori algorithm to solve the above problems. The optimized algorithm strictly controls the front and rear itemsets' construction process and stores the factors and deformation events according to their dimensions and levels. In addition, some key calculation processes of the algorithm are well-parallelized. Based on the monitoring data of the Baishuihe landslide, three experiments were designed to verify the performance of the proposed algorithm. The results show that when the strong association rules with high factor dimension and level characteristics were obtained, the proposed algorithm's computation time was 1/432 and 1/80 of the Apriori and FP-Growth algorithms, respectively. The proposed algorithm has significant advantages in analyzing massive high-dimensional monitoring data of landslide hazards.

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 Based on Time Series Analysis and Double-BiLSTM Model.

In recent years, machine learning models facilitated notable performance improvement in landslide displacement prediction. However, most existing prediction models which ignore landslide data at each time can provide a different value and meaning. To analyze and predict landslide displacement better, we propose a dynamic landslide displacement prediction model based on time series analysis and a double-bidirectional long short term memory (Double-BiLSTM) model. First, the cumulative landslide displacement is decomposed into trend and periodic displacement components according to time series analysis via the exponentially weighted moving average (EWMA) method. We consider that trend displacement is mainly influenced by landslide factors, and we apply a BiLSTM model to predict landslide trend displacement. This paper analyzes the internal relationship between rainfall, reservoir level and landslide periodic displacement. We adopt the maximum information coefficient (MIC) method to calculate the correlation between influencing factors and periodic displacement. We employ the BiLSTM model for periodic displacement prediction. Finally, the model is validated against data pertaining to the Baishuihe landslide in the Three Gorges, China. The experimental results and evaluation indicators demonstrate that this method achieves a better prediction performance than the classical prediction methods, and landslide displacement can be effectively predicted.

Data Mining and Deep Learning for Predicting the Displacement of "Step-like" Landslides.

Landslide displacement prediction is one of the unsolved challenges in the field of geological hazards, especially in reservoir areas. Affected by rainfall and cyclic fluctuations in reservoir water levels, a large number of landslide disasters have developed in the Three Gorges Reservoir Area. In this article, the Baishuihe landslide was taken as the research object. Firstly, based on time series theory, the landslide displacement was decomposed into three parts (trend term, periodic term, and random term) by Variational Mode Decomposition (VMD). Next, the landslide was divided into three deformation states according to the deformation rate. A data mining algorithm was introduced for selecting the triggering factors of periodic displacement, and the Fruit Fly Optimization Algorithm–Back Propagation Neural Network (FOA-BPNN) was applied to the training and prediction of periodic and random displacements. The results show that the displacement monitoring curve of the Baishuihe landslide has a “step-like” trend. Using VMD to decompose the displacement of a landslide can indicate the triggering factors, which has clear physical significance. In the proposed model, the R2 values between the measured and predicted displacements of ZG118 and XD01 were 0.977 and 0.978 respectively. Compared with previous studies, the prediction model proposed in this article not only ensures the calculation efficiency but also further improves the accuracy of the prediction results, which could provide guidance for the prediction and prevention of geological disasters.

Landslide evolution state prediction and down-level control based on multi-task learning

In this paper, multi-task learning is introduced into the study of landslide evolution state prediction and control. Firstly, we define two landslide evolution states and propose a method of landslide evolution state level classification prediction. Specifically, we use Gaussian mixture model (GMM) to reconstruct labeled data sets and establish a landslide evolution state level prediction model based on Multi-Task Learning-Stacked Long-Short Term Memory (MTL-SLSTM), and then use task weight rules to design multi-task losses for network training. The parallel multi-step prediction of the evolution state is achieved by the above works. Secondly, considering the spatial–temporal correlation of different monitoring points on the same landslide, we analyze spatial–temporal data to construct spatial–temporal features, and design a multi-task correlation learning mechanism combined multi-task weight learning and multi-task relationship learning methods to construct spatial–temporal relation. The landslide multi-point prediction model based on Multi-Task Correlation Learning-Stacked Long-Short Term Memory (MTCL-SLSTM) achieves single-step prediction of the evolution state of multiple monitoring points with high accuracy. Finally, according to the idea of neural direct inverse model control, we propose down-level control method based on the prediction of the landslide evolution state. We build an interval prediction network based on bootstrap method and model selection strategies, and then a safe rainfall interval predictor is trained offline. Moreover, we design an online landslide down-level control process combined the landslide evolution state level predictor, which realizes single-step control of single-point of the dangerous landslide. Furthermore, the effectiveness of the proposed method is verified on Baishuihe landslide.

Initiation mechanism and deformation tendency of a high-position landslide at Ningnan County, China

High-position landslides mainly occur in the upper part of the steep slope wherein the shear outlet is much higher than the toe of the slope. It often transforms into the rapid and long-runout debris flow, causing severe loss of life and property. This paper describes a high-position landslide that occurred on the right bank of the Heishui River in Songxin Town, Ningnan County, southwestern China, on June 28 and August 16, 2012, resulting in five deaths. Based on the field investigations, borehole drilling, in situ, and laboratory experiments, the initiation mechanism of the landslides are unraveled. Detailed crack surveys are conducted to identify the deformation tendency of this landslide in the future. The Baishuihe landslide originated on a 310 m-high hillslope, which provided a favorable free surface for the landslide occurrence. The Baishuihe landslide is located in the influence zone of the Zemuhe fault, and the active fault activities dramatically contribute to the fragmented stratigraphic structures and well-developed minor structures. The initiation of the June 28 landslide is considered a long-term creep under the inner and outer integrations, while the consequent bedding slope and persistent precipitation are the primary factors. The failure of the August 16 landslide is analyzed using the retrogressive slide in the source area of the first landslide. The sustaining deformation of the landslide is controlled via cracks on the surface of the main deformation zone and hydraulic influences induced by rainfall. The slip process follows creep deformation and can be aggravated under rainfall. Based on the crack distribution, the potential instability volume is calculated as 1.66 × 104 m3 ∼ 54 × 104 m3. The Baishuihe landslide provides a crucial case study for evaluating high-position landslide and zoning risk areas in mountainous areas.

Uncertainty elevation of landslide displacement prediction based on LSTM and Mixture Density Network

Considering monitoring noise and complexity of landslide movement, quantify the uncertainty of landslide displacement prediction is crucial and challenging. Traditional data-driven models such as long short-term memory networks (LSTM), support vector regression, and extrema learning machines, etc, give the predicted displacement without considering the uncertainty of the predictions. Moreover, the loss function of the data-driven model is mainly taken as mean square error, which may lead to a worse performance when the training data follows non-normal distribution and thus reduces the robustness of the model. This study tends to propose a novel hybrid model based on LSTM and mixture density network to quantify each data point’s probability density distribution. By introducing the mixture density network and the maximum likelihood loss function, this model can get rid of the limitation that the data needs to obey the normal distribution. The mixed probability density parameters of each data point were predicted accurately due to the dynamic learning process in time series by LSTM. Moreover, we introduce the ensemble prediction to consider the uncertainty of model parameters. The performance of the model was validated based on a typical landslide in the Three Gorges Reservoir Area (TGRA), the Baishuihe landslide. Application results demonstrate that the proposed model provides accurate mean predictions and reasonable confidence displacement intervals.

PPP-BOTDA Distributed Optical Fiber Sensing Technology and Its Application to the Baishuihe Landslide

Serious landslide hazards are prevalent along the Yangtze River in China, particularly in the Three Gorges Reservoir area. Thus, landslide monitoring and forecasting technology research is critical if landslide geological hazards are to be prevented and controlled. Pulse-prepump brillouin optical time domain analysis (PPP-BOTDA) distributed optical fiber sensing technology is a recently developed monitoring method with evident advantages in precision and spatial resolution. Herein, fixed-point immobilization and direct burying methods were adopted to arrange parallel distribution of the strain and temperature-compensated optical fibers along the Baishuihe landslide’s front edge, in order to carry out ground surface deformation monitoring. The strain data acquired from both optical fibers were processed with temperature compensation to obtain the actual optical fiber strain produced by deformation. Butterworth low-pass filter denoising method was employed to determine the filter order (n) and cut-off frequency (Wn). The area differences between the two optical fiber monitoring curves and the fixed horizontal axis were selected as evaluation indexes to obtain the area difference along the optical fiber. This data were then leveraged to determine the positive correlation between the area difference and the optical fiber strain variation degree. Finally, these results were compared with the GPS and field measured data. This study shows that when PPP-BOTDA technology is used for landslide surface deformation monitoring in conjunction with Butterworth filter denoising and strain area difference, the optical fiber strain variation degree analysis results are consistent with the GPS monitoring data and the actual landslide deformation. As such, this methodology is highly relevant for reducing the workload and improving the monitoring precision in landslide monitoring, which in turn will protect lives and property.

Prediction of landslide displacement with step-like curve using variational mode decomposition and periodic neural network

Landslide deformation characterized with step-like curves often presents periodicity implicitly. This paper proposed a novel data-driven approach that adopted periodic neural network (PNN) and variational mode decomposition (VMD) to conduct displacement prediction based on the intrinsic seasonality of step-like landslide displacement. PNN was a novel neural network designed for capturing the seasonality of the time series. Firstly, the initial displacement would be decomposed into trend component, periodic component, and random component using the variational mode decomposition (VMD). Then, the external triggering factors were also decomposed by VMD into several subsequences. Subsequences with periodic and random characteristics were selected as the input datasets to forecast the periodic and random components by PNN. Finally, the total displacement was obtained by superimposing the three predictive components to validate the model performance. The Baishuihe landslide was taken as a case study to validate the high effectiveness and efficiency of our method. The result proved that our new model presented satisfactory prediction accuracy without complex training process. Meanwhile, PNN performed a strong robustness to the missing values due to the advantage of its structure. In addition, we clarified a corrective data processing mode as “strict” mode: the dataset has to be divided into training and validation sets firstly to avoid the leakage of the future data.