Slope deformation prediction is one of the critical factors in the early warning of slope failure. Establishing an accurate slope deformation prediction model is important. Time-series displacement data of slopes directly reflect the deformation characteristics and stability properties of slopes. The use of existing data analysis approaches, such as statistical methods and machine learning algorithms, to establish a reasonable and accurate prediction model based on the monitored time-series displacement data is a common solution to slope deformation prediction. In this paper, we conduct a comparative investigation of machine learning approaches for slope deformation prediction based on monitored time-series displacement data. First, we established eleven slope deformation prediction models based on the time-series displacement data obtained from seven in situ monitoring points of the Huanglianshu landslide using machine learning approaches. Second, four evaluation metrics were used to comparatively analyze the prediction performance of all models at each monitoring point. The experimental results of the Huanglianshu landslide indicated that the long-short-term memory (LSTM) model with an attention mechanism and the transformer model achieved the highest prediction accuracy. The comparative analysis of model characteristics suggested that the Transformer model is better adapted to predict nonlinear landslide displacements that are affected by multiple factors. The drawn conclusion could help select a suitable slope deformation model for early landslide warnings.

Mesh quality is a critical issue in numerical computing because it directly impacts both computational efficiency and accuracy. Tetrahedral meshes are widely used in various engineering and science applications. However, in large-scale and complicated application scenarios, there are a large number of tetrahedrons, and in this case, the improvement of mesh quality is computationally expensive. Laplacian mesh smoothing is a simple mesh optimization method that improves mesh quality by changing the locations of nodes. In this paper, by exploiting the parallelism features of the modern graphics processing unit (GPU), we specifically designed a parallel adaptive Laplacian smoothing algorithm for improving the quality of large-scale tetrahedral meshes. In the proposed adaptive algorithm, we defined the aspect ratio as a metric to judge the mesh quality after each iteration to ensure that every smoothing improves the mesh quality. The adaptive algorithm avoids the shortcoming of the ordinary Laplacian algorithm to create potential invalid elements in the concave area. We conducted 5 groups of comparative experimental tests to evaluate the performance of the proposed parallel algorithm. The results demonstrated that the proposed adaptive algorithm is up to 23 times faster than the serial algorithms; and the accuracy of the tetrahedral mesh is satisfactorily improved after adaptive Laplacian mesh smoothing. Compared with the ordinary Laplacian algorithm, the proposed adaptive Laplacian algorithm is more applicable, and can effectively deal with those tetrahedrons with extremely poor quality. This indicates that the proposed parallel algorithm can be applied to improve the mesh quality in large-scale and complicated application scenarios.

Landslide displacement monitoring can directly reflect the deformation process of a landslide. Predicting landslide displacements using monitored time series data through deep learning is a useful method for landslide early warning. Currently, existing prediction models mainly focus on single-point time series displacement prediction and do not consider the spatial relationship between monitoring points. To fully take into account the temporal and spatial correlation of displacement monitoring data, this paper proposes two models based on the graph convolutional network (GCN) to perform spatiotemporal prediction of the displacement of the Tangjiao 1# landslide. Firstly, the landslide monitoring system is transformed into a fully connected graph (FCG) to depict the spatial relationship among monitoring points on the landslide. Secondly, a temporal graph convolutional network (T-GCN) model and an attention temporal graph convolutional network (A3T-GCN) model of landslide displacement based on the GCN and GRU models are established respectively. Thirdly, the two models are used to predict the displacement of the Tangjiao 1# landslide. The results show that the established spatiotemporal prediction models are effective in predicting the displacement of the Tangjiao 1# landslide, and the proposed A3T-GCN model achieves the highest prediction accuracy. Our conclusion validates the effectiveness of the attention mechanism in predicting landslide displacement.

High-quality mesh generation is critical in the finite element analysis of displacements and stabilities of geological bodies. In this paper, we propose a clustering-based bubble method for generating high-quality tetrahedral meshes of geological models. The proposed bubble method is conducted based on the spatial distribution of the point set of given surface meshes using the clustering method. First, the inputted geological models consisting of triangulated surface meshes are divided into several parts based on spatial distribution of point set, which can be used for the determination of the positions and radii of initial bubbles. Second, a procedure based on distance of nearby bubbles is used to obtain the initial size of bubbles. Third, by enforcing the forces acting on bubbles, all bubbles inside the 3D domain reach an equilibrium state by the motion control equations. Finally, the center nodes of the bubbles can form a high-quality node distribution in the domain, and then the required tetrahedral mesh is generated. Comparative benchmarks are presented to demonstrate that the proposed method is capable of generating highly well-shaped tetrahedral meshes of geological models.

High-altitude rock slides frequently occur in the high-mountain canyon regions of the eastern Tibetan Plateau, posing significant disaster risks. The Baige landslide catastrophically failed in October 2018, blocking the Jinsha River and forming a major landslide-dammed lake. However, quantitative understanding of the spatiotemporal evolution and environmental control mechanisms remains insufficient, particularly regarding stage-dependent driving mechanisms. This study investigates the Baige landslide using mall Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR), Seasonal-Trend decomposition based on Loess (STL) time-series decomposition, Principal Component Analysis–Independent Component Analysis (PCA-ICA) signal analysis, and slope-unit spatial statistics. Results indicate that: (1) deformation exhibited three stages separated by October 2018: slow pre-slide deformation, post-slide residual creep, and long-term sustained acceleration; (2) instability caused systematic restructuring of the deformation field, with valid pixels decreasing from 2766 to 560, deformation changing from slight positive line-of-sight (LOS) displacement to pronounced negative LOS displacement, and global standard deviation increasing from 21.40 mm to 40.55 mm, with stronger disturbances in the steep front zone; and (3) the driving mechanism shifted from short-term multi-factor control to a temperature-dominated long-term environmental control regime after failure, while gravity-driven creep and post-failure structural adjustment remained important background controls. Slope fragmentation and structural reorganization likely contributed to this transition.