Huiming Tang

Displacement prediction model of landslide based on a modified ensemble empirical mode decomposition and extreme learning machine

In this paper, an M–EEMD–ELM model (modified ensemble empirical mode decomposition (EEMD)-based extreme learning machine (ELM) ensemble learning paradigm) is proposed for landslide displacement prediction. The nonlinear original surface displacement deformation monitoring time series of landslide is first decomposed into a limited number of intrinsic mode functions (IMFs) and one residual series using EEMD technique for a deep insight into the data structure. Then, these sub-series except the high frequency are forecasted, respectively, by establishing appropriate ELM models. At last, the prediction results of the modeled IMFs and residual series are summed to formulate an ensemble forecast for the original landslide displacement series. A case study of Baishuihe landslide in the Three Gorges reservoir area of China is presented to illustrate the capability and merit of our model. Empirical results reveal that the prediction using M–EEMD–ELM model is consistently better than basic artificial neural networks (ANNs) and unmodified EEMD–ELM in terms of the same measurements.

Ensemble of extreme learning machine for landslide displacement prediction based on time series analysis

Landslide hazard is a complex nonlinear dynamical system with uncertainty. The evolution of landslide is influenced by many factors such as tectonic, rainfall and reservoir level fluctuation. Using a time series model, total accumulative displacement of landslide can be divided into the trend component displacement and the periodic component displacement according to the response relation between dynamic changes in landslide displacement and inducing factors. In this paper, a novel neural network technique called ensemble of extreme learning machine (E-ELM) is proposed to investigate the interactions of different inducing factors affecting the evolution of landslide. Grey relational analysis is used to sieve out the more influential inducing factors as the inputs in E-ELM. Trend component displacement and periodic component displacement are forecasted, respectively; then, total predictive displacement is obtained by adding the calculated predictive displacement value of each sub. Performances of our model are evaluated by using real data from Baishuihe landslide in the Three Gorges Reservoir of China, and it provides a good representation of the measured slide displacement behavior.

Extreme learning machine for the displacement prediction of landslide under rainfall and reservoir level

Landslide prediction is always the emphasis of landslide research. Using global positioning system GPS technologies to monitor the superficial displacements of landslide is a very useful and direct method in landslide evolution analysis. In this paper, an EEMD–ELM model [ensemble empirical mode decomposition (EEMD) based extreme learning machine (ELM) ensemble learning paradigm] is proposed to analysis the monitoring data for landslide displacement prediction. The rainfall data and reservoir level fluctuation data are also integrated into the study. The rainfall series, reservoir level fluctuation series and landslide accumulative displacement series are all decomposed into the residual series and a limited number of intrinsic mode functions with different frequencies from high to low using EEMD technique. A novel neural network technique, ELM, is employed to study the interactions of these sub-series at different frequency affecting landslide occurrence. Each sub-series extracted from accumulative displacement of landslide is forecasted respectively by establishing appropriate ELM model. The final prediction result is obtained by summing up the calculated predictive displacement value of each sub. The EEMD–ELM model shows the best accuracy comparing with basic artificial neural network models through forecasting the displacement of Baishuihe landslide in the Three Gorges reservoir area of China.

Application of back-propagation neural network on bank destruction forecasting for accumulative landslides in the three Gorges Reservoir Region, China

In recent years, a large number of bank destruction occur in the reservoir area under the effect of water fluctuation, which may be lead to reservoir accumulative landslide geological hazards finally. The paper conducted the bank destruction forecasting study for accumulative landslides in the Three Gorges Reservoir Region, China utilizing back-propagation (BP) neural network approach. A representative scenario of Jinle landslide is then taken for analysis purposes. On the basis of the existing data sets of bank destruction cases, the BP neural network forecasting model and the corresponding programs for bank destruction are both presented, whose forecasting result is validated by two independent approaches, namely empirical method and numerical modeling method. Furthermore, the BP neural network model had obvious advantages over the convention approaches in the aspects of the fast calculation speed and high convenience. According to the bank destruction forecasting scale presented above, the corresponding revetment measures can be proposed to prevent the occurring of the bank destruction, whose effectiveness has been further validated by the actual engineering practice.

Stability of Huangtupo Riverside Slumping Mass II# under Water Level Fluctuation of Three Gorges Reservoir

After the normal operation of the Three Gorges Reservoir, the water level of the reservoir will fluctuate periodically. Water level fluctuation will soften the rock and soil on the banks, induce underground water fluctuation and decrease the shear strength of rock soil on the banks, and in turn affect the landslide stability. The Huangtupo (黄土坡) landslide is a typical large and complex landslide in the Three Gorges Reservoir region. In particular, the stability of its riverside slumping mass has a great stake. On the basis of the analysis of engineering geological condition and formation mechanism of the Huangtupo landslide, the authors established the 2D finite element model of riverside slumping mass II# and selected proper mechanical parameters of the rock. With the GeoStudio software, according to the reservoir running curve, the simulation on coupling effect of seepage field and stress field was conducted in 7 different modes in a year. The results showed that: ➀ Huangtupo landslide is a large and complex landslide composed of multiple slumping masses, which occurred at different phases. Before reservoir impoundment, it was stable; ➁ it is quite difficult for riverside slumping mass I# and II# to slide as a whole; ➂ the stability coefficient of riverside slumping mass II# changes with the reservoir water level fluctuations. The minimum stability coefficient occurs 48 days after the water level starts to fall and the moment when the water level falls by 11.9 m. Landslide monitoring result is consistent with the numerical simulation result, which shows that although the reservoir water level fluctuation will affect the foreside stability of the landslide and induce gradual damage, the riverside slumping mass II# is stable as a whole.

Displacement Prediction Model of Landslide Based on Ensemble of Extreme Learning Machine

Based on time series analysis, total accumulative displacement of landslide is divided into the trend component displacement and the periodic component displacement according to the response relation between dynamic changes of landslide displacement and inducing factors. In this paper, a novel neural network technique called the ensemble of extreme learning machine (E-ELM) is proposed to investigate the interactions of different inducing factors affecting the evolution of landslide. Trend component displacement and periodic component displacement are forecasted respectively, then total predictive displacement is obtained by adding the calculated predictive displacement value of each sub. A case study of Baishuihe landslide in the Three Gorges reservoir area is presented to illustrate the capability and merit of our model.

Study on estimation method of rock mass discontinuity shear strength based on three-dimensional laser scanning and image technique

The estimation of shear strength of rock mass discontinuity is always a focal, but difficult, problem in the field of geotechnical engineering. Considering the disadvantages and limitation of existing estimation methods, a new approach based on the shadow area percentage (SAP) that can be used to quantify surface roughness is proposed in this article. Firstly, by the help of laser scanning technique, the three-dimensional model of the surface of rock discontinuity was established. Secondly, a light source was simulated, and there would be some shadows produced on the model surface. Thirdly, to obtain the value of SAP of each specimen, the shadow detection technique was introduced for use. Fourthly, compared with the result from direct shear testing and based on statistics, an empirical formula was found among SAP, normal stress, and shear strength. Data of Yujian (鱼简) River were used as an example, and the following conclusions have been made. (1) In the case of equal normal stress, the peak shear stress is positively proportional to the SAP. (2) The formula for estimating was derived, and the predictions of peak-shear strength made with this equation well agreed with the experimental results obtained in laboratory tests.

A Description for Rock Joint Roughness Based on Terrestrial Laser Scanner and Image Analysis.

Shear behavior of rock mass greatly depends upon the rock joint roughness which is generally characterized by anisotropy, scale effect and interval effect. A new index enabling to capture all the three features, namely brightness area percentage (BAP), is presented to express the roughness based on synthetic illumination of a digital terrain model derived from terrestrial laser scanner (TLS). Since only tiny planes facing opposite to shear direction make contribution to resistance during shear failure, therefore these planes are recognized through the image processing technique by taking advantage of the fact that they appear brighter than other ones under the same light source. Comparison with existing roughness indexes and two case studies were illustrated to test the performance of BAP description. The results reveal that the rock joint roughness estimated by the presented description has a good match with existing roughness methods and displays a wider applicability.

Identification of causal factors for the Majiagou landslide using modern data mining methods

In this study, a data mining approach is proposed to investigate the hydrological causes of the Majiagou landslide, located in the Three Gorges Reservoir in China. It is possible to determine the cause-and-effect relationships between hydrological parameters and landslide movement. The data mining approach consists of two steps: first, hydrological indicators and landslide movements are discretized using the two-step cluster analysis; second, the association rule mining with the Apriori algorithm is employed to identify the contribution of each hydrological parameter to landslide movement. The results obtained suggest that deformation and later failure occurred first at the toe of the landslide and progressed upslope due to rising water level in the reservoir, prolonged heavy rainfall, and rapid drawdown in the reservoir. The proposed novel use of field data and data mining has the potential for providing procedures and solutions for an effective interpretation of landslide monitoring data.

Landslide Deformation Prediction Based on Recurrent Neural Network

Landslide deformation prediction has significant practical value that can provide guidance for preventing the disaster and guarantee the safety of people’s life and property. In this paper, a method based on recurrent neural network (RNN) for landslide prediction is presented. Genetic algorithm is used to optimize the initial weights and biases of the network. The results show that the prediction accuracy of RNN model is much higher than the feedforward neural network model for Baishuihehe landslide. Therefore, the RNN model is an effective and feasible method to further improve accuracy for landslide displacement prediction.