Mountainous areas have become among the most developed areas of geological hazards due to special geological environmental conditions and intensive human engineering activities. Geological hazards are a main threat to urbanization, rural revitalization, and new rural construction in complex mountainous areas. It is of great strategic significance to conduct large-scale geological hazard investigation and risk assessment in urban areas, control the risk of geological hazards at the source and propose risk control measures. In this paper, we established the technical methods of geologic hazard risk assessment and control in complex mountain towns by taking Longlin Town in the mountainous region of Gansu Longnan, China as the study area, with the Quanjia bay debris flows and Panping Village landslides as the typical pilot investigation and assessment. The methods consist of six stages—risk identification, hazard disaster model investigation, risk analysis, vulnerability assessment, risk evaluation and risk management and control measures and proposals. On this basis, the results of geological hazards with different precipitation frequencies (5%, 2%, 1%) are presented. The results show that 75.23% of the regions remained at low risk levels; 24.38% of the regions increased a risk level with decreasing precipitation frequency, and 0.39% of the regions remained at extremely high risk levels under different precipitation frequency conditions. For the Quanjia bay debris flows and Panping Village landslides case, we discussed the geological hazards risk source control contents, management and control technologies, engineering and non-engineering measures of disaster prevention and control for urban disasters and specific disaster areas. This research can provide technical support and reference for disaster prevention and mitigation, and territorial spatial planning.

Previous studies have shown that the mechanical effects of vegetation roots on slope stability can be classified as additional cohesion effects and anchorage effects. The present study investigated the combined mechanical effects (additional cohesion effects and anchorage effects) of vegetation on a slope with coarse-grained soil in the mountainous region (significantly prone to slope failure) of Gansu Province, China. A detailed survey of tree density, root system morphology and slope profiles was conducted, and we also assessed the soil cohesion provided by the root systems of monospecific stands of Robinia pseudoacacia growing in different locations on the slope. The measured data were incorporated into a numerical slope model to calculate the stability of the slope under the influence of trees. The results indicated that it was necessary to consider the anchoring effect of coarse roots when estimating the mechanical effects of trees on slope stability. In particular, the FoS (factor of safety) of the slope was increased by the presence of trees. The results also demonstrated that vegetation increased slope stability. The reinforcing effects were most significant when the trees were planted along the entire slope. Although the reinforcing effects contributed by trees were limited (only 4–11%), they were essential for making optimal use of vegetation for enhancing slope stability. Overall, vegetation development can make a major contribution to ecosystem restoration in the study region.

Accurately predicting landslide deformation based on monitoring data is key to successful early warning of landslide disasters. Landslide displacement–time curves offer an intuitive reflection of the landslide motion process and deformation predictions often reference the Saito curve for correlational analysis with cumulative deformation curves. Many scholars have applied machine learning techniques to individual landslide deformation predictions with considerable success. However, most landslide monitoring data lack a full lifecycle, making it challenging to predict unexperienced evolutionary stages. Cross-learning between similar landslide datasets provides a potential solution to issues of data scarcity and accurate prediction. First, this paper proposes a landslide classification and displacement machine learning method, along with predictive performance evaluation metrics. Further, it details a study of 13 landslides with evident deformation signs in the middle Qinling–Bashan Mountains area, conducting refined landslide classification. Based on a data-driven approach, this study conducts an analysis of the importance of characteristics influencing landslide deformation and establishes predictive models for similar-type landslide deformation, mixed-type landslide deformation, and individual landslide deformation using machine learning algorithms. The models trained on the dataset are used to predict the deformation of the West of Yinpo Yard landslide at different periods, with the predictive performance evaluated using two indices. The results indicate that the models trained on similar-type landslide data and those based on individual landslide data yielded comparable predictive performances, substantially addressing challenges such as insufficient early-stage monitoring data and low prediction accuracy.

The displacement–time curve of a landslide serves as a critical indicator of its movement state, with precise deformation prediction being essential for effective disaster early warning. While numerous studies have employed machine learning techniques to predict deformation at individual monitoring points, they often overlook the spatial correlations among monitoring points arranged along horizontal and vertical cross-sections. To address this limitation, this paper employs the Temporal Graph Convolutional Network (T-GCN) model, which integrates the strengths of Graph Convolutional Networks (GCNs) and Gated Recurrent Units (GRUs). The GCN captured spatial correlations among monitoring points, while the GRU modeled the temporal dynamics of displacement. The T-GCN model was applied to predict the spatio-temporal deformation of the Dawuchang landslide in the Three Gorges Reservoir area. Experimental results demonstrated that the T-GCN model effectively predicted the spatio-temporal displacement of landslides, offering a robust approach for landslide monitoring and early warning systems. The model also incorporated the temporal influence of external factors, such as rainfall and reservoir water levels, enhancing prediction accuracy and providing valuable insights for future research in landslide deformation forecasting.