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.

No abstract

After the first impoundment of the reservoir, many landslides seriously threatened the safety of the reservoir. Accurate determination of the relationship between the landslide deformation characteristics and water-level fluctuations is crucial. However, with the increasing number of water-level fluctuation cycles, the deformation characteristics of the landslides were also changing, and long-term continuous monitoring to capture the failure process of reservoir landslides is necessary. A large reacted landslide in the Xiluodu reservoir was set as an example, using InSAR technology to seek its variations of deformation characteristics over nine years. The local deformation rate and annual maximum deformation area variation were analyzed by InSAR technology based on Sentinel-1 descending SAR data from October 2014 to June 2022. According to the regional deformation characteristics, the landslide was divided into three zones: Zone I above the elevation of 950 m; Zone II below it; the front edge of Zone II, where the collapse happened, was further divided into Zone III. In general, the accumulated deformation in Zone I was the largest, followed by Zone III, and Zone II was the smallest. The average deformation rate of Zone II was the smallest. Zone I of NLJL was mainly affected by the drawdown of reservoir water level, and the impacts of water-level rising and drawdown on Zone II and Zone III were similar. After analyzing a nine-year variation of the deformation area, the deformation mechanism of NLJL changed from a retrogressive type to a progressive one after the first impoundment and then changed back to a retrogressive one after 2017. The impact of reservoir impoundment on NLJL was most substantial in the first three years after the first impoundment.