The development of landslide hazards is spatially scattered, temporally random, and poorly characterized. Given the advantages of the large spatial scale and high sensitivity of InSAR observations, InSAR is becoming one of the main techniques for active landslide identification. The difficult problem is how to quickly extract landslide information from extensive InSAR image data. Since the instance segmentation model (Mask R-CNN) in deep learning can provide highly robust target recognition, we select the landslide-prone eastern edge of the Tibetan Plateau as a specific test area. Introducing and optimizing this model achieves high-speed and accurate recognition of InSAR observations. First, the InSAR patch landslide instance segmentation dataset (SLD) is established by developing a common object in context (COCO) annotation format conversion code based on InSAR observations. The Mask R-CNN+++ is found by adding three functions of the ResNext module to increase the fineness of the network segmentation results and enhance the noise resistance of the model, the DCB (deformable convolutional block) to improve the feature extraction ability of the network for geometric morphological changes of landslide patches, and an attention mechanism to selectively enhance usefully and suppress features less valuable to the native Mask R-CNN network. The model achieves 92.94% accuracy on the test set, and the active landslide recognition speed based on this model under ordinary computer hardware conditions is 72.3 km²/s. The overall characteristics of the results of this study show that the optimized model effectively enhances the perceptibility of image morphological changes, thereby resulting in smoother recognition boundaries and further improvement of the generalization ability of segmentation detection. This result is expected to serve to identify and monitor active landslides in complex surface conditions on a large spatial scale. Moreover, active landslides of different geometric features, motion patterns, and intensities are expected to be further segmented.

At present, Synthetic Aperture Radar Interferometry (InSAR) has been an important technique for active landslides recognition in the geological survey field. However, the traditional interpretation method through human–computer interaction highly relies on expert experience, which is time-consuming and subjective. To solve the problem, this study designed an end-to-end semantic segmentation network, called deep residual shrinkage U-Net (DRs-UNet), to automatically extract potential active landslides in InSAR imagery. The proposed model was inspired by the structure of U-Net and adopted a residual shrinkage building unit (RSBU) as the feature extraction block in its encoder part. The method of this study has three main advantages: (1) The RSBU in the encoder part incorporated with soft thresholding can reduce the influence of noise from InSAR images. (2) The residual connection of the RSBU makes the training of the network easier and accelerates the convergency process. (3) The feature fusion of the corresponding layers between the encoder and decoder effectively improves the classification accuracy. Two widely used networks, U-Net and SegNet, were trained under the same experiment environment to compare with the proposed method. The experiment results in the test set show that our method achieved the best performance; specifically, the F1 score is 1.48% and 4.1% higher than U-Net and SegNet, which indicates a better balance between precision and recall. Additionally, our method has the best IoU score of over 90%. Furthermore, we applied our network to a test area located in Zhongxinrong County along Jinsha River where landslides are highly evolved. The quantitative evaluation results prove that our method is effective for the automatic recognition of potential active landslide hazards from InSAR imagery.

Reservoir impoundment significantly impacts the hydrogeological conditions of reservoir bank slopes, and bank slope deformation or destruction occurs frequently under cyclic impoundment conditions. Ground deformation prediction is crucial to the early warning system for slow-moving landslides. Deep learning methods have developed rapidly in recent years, but only a few studies are on combining deep learning and landslide warning. This paper proposes a slow-moving landslide displacement prediction method based on the Informer deep learning model. Firstly, the Sentinel-1 (S1) data are processed to obtain the cumulative displacement time-series image of the bank slope by the Small-BAseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) method. Then, combining data on rainfall, humidity, and horizontal and vertical distances of pixel points from the water table line, this study created a dataset with landslide displacement as the target feature. After that, this paper improves the Informer model to make it applicable to our dataset. This study chose the Dawanzi landslide in the Baihetan reservoir area, China, for validation. After training with 50-time series deformation data points, the model can predict the displacement results of 12-time series deformation data points using 12-time series multi-feature data, and compared with the monitoring values, its Mean Square Error (MSE) was 11.614. The results show that the multivariate dataset is better than the deformation univariate data in predicting the displacement in the large deformation zone of bank slopes, and our model has better complexity and prediction performance than other deep learning models. The prediction results show that among zones I–IV, where the Dawanzi Tunnel is located, significant deformation with the maximum deformation rate detected exceeding –100mm/year occurs in Zones I and III. In these two zones, the initiation of deformation relates to the drop in water level after water storage, with the deformation rate of Zone III exhibiting a stronger correlation with the change in water level. It is expected that deformation in Zone III will either remain slow or stop, while deformation in Zone I will continue at the same or a decreased rate. Our proposed method for slow-moving landslide displacement forecasting offers fast, intuitive, and economically feasible advantages. It can provide a feasible research idea for future deep learning and landslide warning research.

The present study proposes a preliminary analysis method for rock mass joint acquisition, analysis, and slope stability assessment based on unmanned aerial vehicle (UAV) photogrammetry to extract the joint surface attitude in Geographic Information Systems (GIS). The method effectively solves the difficulties associated with the above issues. By combining terrain-following photogrammetry (TFP) and perpendicular and slope surface photogrammetry (PSSP), the three-dimensional (3D) information can be efficiently obtained along the slope characteristics’ surface, which avoids the information loss involved in traditional single-lens aerial photography and the information redundancy of the five-eye aerial photography. Then, a semi-automatic geoprocessing tool was developed within the ArcGIS Pro 3.0 environment, using Python for the extraction of joint surfaces. Multi-point fitting was used to calculate the joint surface attitude. The corresponding attitude symbols are generated at the same time. Finally, the joint surface attitude information is used to perform stereographic projection and kinematic analysis. The former can determine the dominant joint group, and the latter can obtain the probability of four types of failure, including planar sliding, wedge sliding, flexural toppling, and direct toppling. The integrated stability evaluation method studied in this paper, which combines a 3D interpretation of UAV and GIS stereographic projection statistical analysis, has the advantages of being efficient and user-friendly, and requires minimal prior knowledge. The results can aid in the geological surveys of slopes and guide engineering practices.

In recent years, due to adverse geological conditions, intense human engineering activities, and extreme weather conditions, catastrophic landslides have frequently occurred in southwest China, causing severe loss of life and property. Identifying the kinematic features of potential landslides can effectively support landslide hazard prevention. This study proposes a remote sensing identification method for rotational, planar traction, and planar thrust slides based on geomorphic features as well as vertical and slope-oriented deformation rates. Rotational landslides are characterized by similar vertical and horizontal deformation rates, with vertical deformation mainly occurring at the head and gradually decreasing along the slope, while horizontal deformation mainly occurs at the foot and gradually increases along the slope. As for the planar slide, the dominant deformation is in the horizontal direction. It is further classified into the planar traction and planar thrust types according to the driving position. The vertical deformation of planar traction slides is concentrated at the foot, while the vertical deformation of planar thrust slides is concentrated at the head of the landslide. We identified 1 rotational landslide, 10 planar traction landslides and 10 planar thrust landslides in the basalt weathering crust area of Guizhou. Field investigations of three landslides verified the method’s accuracy. Combining two-dimensional rainfall and time-series deformations, we found that there is a significant positive correlation between landslide deformation acceleration and precipitation. The landslide kinematic identification method proposed in this paper overcomes the shortcomings of the inability to accurately characterize landslide motion by line-of-sight displacement and realizes the non-contact identification of active landslide motion patterns, which is an essential reference value for geological disaster prevention and control in the study area.