Search

Displacement prediction is a direct and effective method for mitigating geohazards. Due to the influence of rainfall and reservoir water level variations, landslides often display step-like deformations with an increasing trend and periodic fluctuation, indicating long-term memory in displacement time series. Traditional data-driven methods are mostly suitable for short-term prediction, and extra data processing is applied to solve this problem. This paper proposes a novel deep learning-based displacement prediction method using long short-term memory (LSTM) networks. Based on open-source frameworks for deep learning, namely, Keras and TensorFlow, a detailed implementation of displacement prediction is proposed and illustrated. The Baishuihe landslide, a typical landslide with long-term monitoring, is taken as a case study, and both single-factor and multi-factor predictions are performed. The results indicate that multi-factor prediction can reduce overfitting and improve accuracy. Compared with the existing method, the multi-factor deep-learning model displays better performance. This study indicates that the LSTM-based deep-learning model is suitable and convenient for displacement prediction and has broad prospects in safety monitoring of water-induced landslides. [ABSTRACT FROM AUTHOR]

Spatial variability of properties of geo-materials has a significant impact on the stability of landslides. In this paper, the spatial variability of soil properties of a landslide is modelled using random-field generated by the discrete cosine transform. The method developed can be readily applied to determine the probability of failure of the landslide using Monte Carlo simulation. A case study of a landslide with spatially variable properties is performed and discussed. The proposed approach is shown to be effective and efficient for probabilistic stability analysis of landslides modelled using 2-D random-field. [ABSTRACT FROM AUTHOR]

Many models have been developed for landslide displacement prediction, but owing to complex landslide-formation mechanisms and landslide-inducing factors, such models have different prediction accuracies. Thus, landslide displacement prediction remains a popular but difficult topic of research. In this paper, a landslide prediction model is proposed by combining extreme learning machine (ELM) and random search support vector regression (RS-SVR) sub-models. Particularly, the combined model decomposed accumulative landslide displacement into two terms, trend and periodic displacements, using a time series model, and simulated and predicted the two terms using the ELM and RS-SVR sub-models, respectively. The predicted trend and periodic terms are then summed to obtain the total displacement. The ELM and RS-SVR sub-models are applied to predict the deformation of Baishuihe landslide in the Three Gorges Reservoir Area (TGRA) as an example. The results showed that the model effectively improved the accuracy, stability, and scope of application of landslide displacement prediction, thus providing a new method for landslide displacement prediction. [ABSTRACT FROM AUTHOR]

The paper develops an analytical method to design the plane arrangement of stabilising piles under spatial lateral load of 3D colluvial landslides with multilayer sliding masses. Firstly, an approach based on the geological map and binary Lagrange Interpolation method was presented to establish 3D landslide calculation models. The improved 3D limit equilibrium method was then proposed to calculate the stability coefficient and spatial distributed lateral load of landslide with multilayer sliding masses. And main sliding direction of 3D multilayer landslide can be determined by the developed principle of minimum potential energy. Moreover, through assuming the piles and soil as elastic transversely isotropic continuum medium, analytical approach was employed to accurately calculate the stress distribution of soil between adjacent piles; and the maximum pile spacing can be calculated. Finally, the reasonable arrangement of stabilising piles can be determined based on Monte-Carlo method and cost of all piles. The finite difference method was employed to validate the theoretical results through the case study of Bazimen landslide. And it is found that the proposed method for the design of piles' arrangement is economically beneficial compared with the traditional method on the premise of ensuring safety. [ABSTRACT FROM AUTHOR]

Uncertainties of geotechnical parameters in landslide engineering mainly arise from their spatial variabilities, measuring error and inaccurate constitutive model. Interval limit equilibrium method (ILEM) is used to analyse the stability of landslides with uncertain geotechnical parameters. However, the method suffers from the issue of overestimation in the calculation of the safety factor (FS) interval while using the basic interval operations. To overcome the limitation, an improved ILEM based on particle swarm optimisation (ILEM-PSO) is proposed in the article. In the method, the uncertain parameters and their intervals are taken as the search variables and search space of PSO, and the FS functions are used as the fitness functions. A predefined number of iterations are executed to search the minimal and maximal FS, which are the lower and upper bound of the FS interval. The proposed method is validated with a testing function and ACADS benchmark question EX11, and then applied to the stability analysis of Dahua landslide. Comparisons with ILEM and Monte Carlo simulation are also given in the article. Results show that the proposed method is effective in solving the issue of overestimation in ILEM and obtains accurate FS intervals of landslides. [ABSTRACT FROM AUTHOR]

Rainfall represents one of the most significant cause of landslide hazards. With runoff in the saturated zone of shallow soil considered, an improved Green–Ampt model was proposed to depict the rainfall infiltration process. Furthermore, a formula for calculating the depth of wetting front was derived, and the slope stability was evaluated accordingly. Finally, a formula for calculating the safety factor of multilayer slopes above different surfaces was obtained via the limit equilibrium method. An illustration is a multilayer colluvial slope in Guangdong Province of China, the results indicated that the downward speed of wetting front decreases gradually within the same layer with continuous rainfall but increases significantly when it extends to the interfaces between the soil layers. Safety factor of the slope decreases sharply at the initial stage of rainfall but then more slowly. Slope failure is more likely to occur along the first interface between the soil layers than along the surface of wetting front. The result from the proposed model is closer to the result of the physical model test than from the existed Green–Ampt model. The improved Green–Ampt model for multilayer slopes can accurately evaluate the infiltration process and related stability of multilayer slopes under rainfall. [ABSTRACT FROM AUTHOR]