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.

Purpose: The purpose of this paper is to investigate the anisotropic characteristics of the special structure of a columnar jointed rock masses and provide reference to forecast the behavioral characteristics of real samples. Design/methodology/approach: This study used FLAC3D numerical software to simulate the mechanical behavior of columnar jointed rock masses with different columns angles (ß) under different stress conditions. The peak strength, elastic modulus and Poisson’s ratio were obtained to investigate the strength, deformation characteristics and failure modes of the rock masses under conventional and true triaxial compression. Findings: The results showed that the compressive strength of the specimens presents a U-shape under different joint inclinations. The strength of the specimens reaches a maximum value when ß = 90°, and the value for ß = 0° is slightly lower and reaches a minimum value when ß = 50°. The elastic modulus and Poisson’s ratio of the samples are obviously anisotropic, the anisotropic coefficient decreases with increasing confining pressure. When σ₂ ≠ σ₃, the peak strengths of the samples are related to the direction of the minor principal stress, and the failure modes of the samples are related to the confining pressure and joint inclination. Originality/value: The present paper uses a numerical simulation method to examine the strength and deformation characteristics of a columnar jointed rock mass under conventional and true triaxial compression. The aim is to provide a reference to forecast the mechanical characteristics of test samples in the laboratory.