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.

River channel change can be very sensitive to environmental change and human activities and it has been one of the main research topics in fluvial geomorphology. In this study, repeated channel geometric measurements were used to investigate the channel adjustment to water and sediment changes of the lower Yellow River in China in the past few decades. With a high sediment concentration and large variations of water discharge, the lower Yellow River has a much active channel in its form and location, which has hindered previous research efforts to study long-term differentiated erosion/deposition of different geomorphic units in the channel. In this study, we divided each of four typical channel across-sections at hydrological stations in the lower Yellow River into different units according to the geomorphological features, and give a detailed investigation of erosion/deposition processes of these geomorphic units and the interactions between them besides the influence of incoming water and sediment conditions. The results show that with a significant decreasing trend of both the annual runoff and sediment load of the river and abrupt changes in 1985–1996, the overall siltation trend in the river channel before 1990 had been replaced by a slight erosion trend after 2006. In the earlier period, the siltation in the upstream wandering and transitional reaches mainly occurred on floodplains and that in the downstream straight reaches principally on main channel bed. In the later period, erosion occurred mainly on high and low bank slopes in the wandering reaches and on main channel bed in the transitional reaches. The erosion became weak in the wandering reaches after 2010, continued in the transitional reaches, and was still relatively minor in the straight reaches, reflecting the downstream hysteresis channel response to changes in water and sediment discharges down dams. Our results suggest that the seasonal erosion/deposition of a geomorphic unit of the river channel can be attributed to the changes in water and sediment discharges as well as to the interaction between geomorphic units. Siltation on the main channel bed could be attributed to erosion on the bank slopes in both the sections in the wandering and transitional reaches, and erosion of the main channel bed in flood seasons was negatively related with the mean water discharge at the two sections in the straight reaches. This result implies that fixing the bank slopes in the wandering and transitional reaches and raising the water discharge in the straight reach in flood seasons are favorable options for controlling the development of the two-level perching channel of the lower Yellow River.

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.