Accurately predicting the surface displacement of the landslide is important and necessary. However, most of the existing research has ignored the frequency component of inducing factors and how it affects the landslide deformation. Therefore, a hybrid displacement prediction model based on time series theory and various intelligent algorithms was proposed in this paper to study the effect of frequency components. Firstly, the monitoring displacement of landslide from the Three Gorges Reservoir area (TGRA) was decomposed into the trend and periodic components by complete ensemble empirical mode decomposition (CEEMD). The trend component can be predicted by the least square method. Then, time series of inducing factors like rainfall and reservoir level was reconstructed into high frequency components and low frequency components with CEEMD and t-test, respectively. The dominant factors were selected by the method of dynamic time warping (DTW) from the frequency components and other common factors (e.g., current monthly rainfall). Finally, the ant colony optimization-based support vector machine regression (ACO-SVR) is utilized for prediction purposes in the TGRA. The results demonstrate that after considering the frequency components of landslide-induced factors, the accuracy of the displacement prediction model based on ACO-SVR is better than that of other models based on SVR and GA-SVR.

The construction process of pile foundations can significantly disrupt the soil. Therefore, it is necessary to limit the degree of soil disturbance caused by pile foundation construction to an acceptable level. This paper examines the disturbance effects of pile driving on soft soil foundations, specifically analyzing the squeezing effect of squeezed soil piles and the unloading effect of non-squeezed soil piles. To investigate these effects, two typical squeezed soil piles, a hydrostatic pile, and a bag grouting pile, as well as a typical non-squeezed soil pile (a bored pile) are selected. Specifically, a novel construction method for numerical models, which simulates the mechanical processes of different pile types under standard grids, is proposed. Three crucial indicators—soil displacement field, stress field, and disturbance influence range—are chosen to compare the disturbance effects of three types of piles on the soil. Results indicate that the two types of squeezed soil piles cause significant disturbance to the soil displacement field, especially in the horizontal direction, while causing a relatively slight disturbance to the soil stress field. Among the two of them, the disturbance magnitude and range of the hydrostatic pile are greater than those of the bag grouting pile. For the non-squeezed soil pile, the soil displacement field changes minimally and the stress field remains basically unchanged during the pile driving process of the bored pile. To compare and quantify the disturbance effects of three types of piles on soil, the soil disturbance range in the horizontal direction of each pile is normalized by its radius. Results indicate that the horizontal disturbance values of maximum horizontal stress for all three types of piles are approximately 1/5 of the pile length above the pile tip, with normalized values of 7.6, 5.5, and 3.5, respectively. The maximum horizontal deformation disturbance range in the horizontal direction occurs near the ground surface and has normalized values of 15.2, 7.5, and 1.1 for the three types of piles, respectively. Therefore, the hydrostatic pile has the greatest disturbance effect, followed by the bag grouting pile and the bored pile. However, within the allowable range of disturbance in practical engineering, the optimal piling method can be selected by comprehensively considering factors such as the construction difficulty and economic costs.

In the process of rapid drawdown of reservoir water level, the seepage force in the slide mass is an important factor for the stability reduction and deformation increment of many landslides in the reservoir areas. It is feasible to improve the stability of seepage-induced landslide by employing a drainage well to reduce or eliminate the water head difference that generates the seepage force. In this paper, the Shuping landslide, a typical seepage-induced landslide in the Three Gorges Reservoir area of China, is taken as an example. A series of numerical simulations were carried out to figure out the seepage field, and the Morgenstein–Price method was adopted to calculate the landslide stability. Then the influence of horizontal location of the drainage well, drainage well depth, drainage mode on the landslide treatment effect, and the applicability of drainage well were analyzed. The results show that: (1) landslide stability increases obviously with the well depth in the slide mass, while the increment of landslide stability with the well depth is limited in the slide bed; (2) the sensitivity of the stability improvement with the depth is greater than that with the horizontal positions of the drainage wells in the slide mass; (3) the drainage well is suggested to be operated when the reservoir water falls rather than operates all the time; and (4) the drainage method is most suitable for landslides with low and medium permeability. These results provide deep insights into the treatment of seepage-induced landslides.