A large number of deposit landslides are induced by rainfall, and those with different weak layers may be subject to catastrophic failure. This research investigates the rainfall infiltration effect on the stability of deposit landslides with a weak layer at different slope angles. Four rainfall physical model tests were conducted with fixed double penetration artificial rainfall technique and dynamic sensor technologies by using the rainfall test methods as modified in the paper. Deformation and mechanics parameters, as well as water content parameters in the key position in the deposit landslide, were monitored by means of various displacement monitoring sensors, dynamic soil pressure sensors, pore water pressure (PWP) monitoring sensors, and water content sensors. The results show that, under the same rainfall conditions, the rule of displacement and mechanical changes of deposit slope with different angles are similar, that the displacement, soil pressure, and PWP are characterized by two stages of rising and falling, and that the displacement of deposit slope with weak layer remains creep after rainfall. In addition, the displacement at the rear edge of the slope with a small angle is larger than that at the front of the steep slope, but the displacement in the front of the slope is opposite. Furthermore, the slope with a smaller angle is prone to form a tensile crack in the back of the slope, and its deformation and failure have the characteristics of a progressive and thrust‐type landslide. While the failure in front of a steep slope (slope angle more than 60°) occurred first, the slope failure was characterized by sudden and retrogressive modes. The mathematical analysis of the model is also conducted which shows that deformation and failure can be divided into three stages, i.e., creep inoculation, accumulation uplift, and speed‐up sliding. The test results can provide a reference for the investigation, design, and assessment of similar deposit slopes.

Side scan sonar images have great application prospects in underwater surveys, target detection, and engineering activities. However, the acquired sonar images exhibit low illumination, scattered noise, distorted outlines, and unclear edge textures due to the complicated undersea environment and intrinsic device flaws. Hence, this paper proposes a multi-scale fusion strategy for side scan sonar (SSS) image correction to improve the low contrast and noise interference. Initially, an SSS image was decomposed into low and high frequency sub-bands via the non-subsampled shearlet transform (NSST). Then, modified multi-scale retinex (MMSR) was employed to enhance the contrast of the low frequency sub-band. Next, sparse dictionary learning (SDL) was utilized to eliminate high frequency noise. Finally, the process of NSST reconstruction was completed by fusing the emerging low and high frequency sub-band images to generate a new sonar image. The experimental results demonstrate that the target features, underwater terrain, and edge contours could be clearly displayed in the image corrected by the multi-scale fusion strategy when compared to eight correction techniques: BPDHE, MSRCR, NPE, ALTM, LIME, FE, WT, and TVRLRA. Effective control was achieved over the speckle noise of the sonar image. Furthermore, the AG, STD, and E values illustrated the delicacy and contrast of the corrected images processed by the proposed strategy. The PSNR value revealed that the proposed strategy outperformed the advanced TVRLRA technology in terms of filtering performance by at least 8.8%. It can provide sonar imagery that is appropriate for various circumstances.

The formation and dynamic process analysis of the rockslide avalanche in mountainous areas are one of the consequences of the catastrophic accident. Such loose accumulation in upslope may saturate partially or completely when the stability of their accumulation dam is distributed or affected by rainfall. We present a case study with respect to the southern Wuyi Mountain located in eastern China, where the wet and rainy climate has led to dozens of similar rockslide hazards. The purpose of this paper was to analyse the mechanism and dynamic characteristics of the rockslide influenced by the same geological conditions and to predict the outburst susceptibility of similar landslides in the future. Detail field surveys, 3D laser scanning, and high‐density electrical methods were used to collect the geotechnical information of the complex landslide, to identify the discontinuity between the landslide material and the bedrock, and to investigate the deformation characterization and dynamic process of the rockslide. Based on remote sensing interpretation and field investigation of the deformation process of a landslide in different times and different parts, the background, mechanism, and cause of the landslide were demonstrated. The landslide is controlled by the characteristics of the geological structure, including collapse, circular sliding, plane sliding, and debris flow. In addition, there are rock avalanches on the rear edge of the slope subjected to the combined action of rainfall and gravity. Moreover, there are some resistance anomaly areas of the aquifer and soil between 2 and 50 m where the resistivity is less than 120 ohm‐m, and they were deduced to be full of water, confirming a “bathtub” type structure. The mechanism of the catastrophic landslide was a combination of the upper pushing deformation induced by rainfall line uplift and rotational; due to the ancient landslide reactivation in the transposition area, the velocity of the rockslide reached 40.11 m/s.

The detection of landslide areas and surface characteristics is the prerequisite and basis of landslide hazard risk assessment. The traditional method relies mainly on manual field identification, and discrimination is based on the lack of unified quantitative standards. Thus, the use of neural networks for the quantitative identification and prediction of landslide surface deformation is explored. By constructing an integrated model based on YOLO X-CNN and Mask R-CNN, a deep learning-based feature detection method for landslide surface images is proposed. First, the method superimposes Unmanned Aerial Vehicle (UAV) oblique photography data (UOPD) and Internet heterosource image data (IHID) to construct a landslide surface image dataset and landslide surface deformation database. Second, an integrated model suitable for small- and medium-scale target detection and large-scale target edge extraction is constructed to automatically identify and extract landslide surface features and to achieve rapid detection of landslide surface features and accurate segmentation and deformation recognition of landslide areas. The results show that the detection accuracy for small rock targets is greater than 80% and that the speed is 57.04 FPS. The classification and mask segmentation accuracies of large slope targets are approximately 90%. A speed of 7.89 FPS can meet the needs of disaster emergency response; this provides a reference method for the accurate identification of landslide surface features.

On June 11, 2016, a landslide occurred in Miaoling village, Jiujiang city, Jiangxi Province, China, following continuous rainfall. An engineering geological profile indicated that the landslide consisted of a stiff crust of residual Quaternary deposits overlying a water-sensitive gravelly clay layer with a soft-plastic consistency. A geotechnical field investigation and physical models of rainfall-induced landslides were carried out in situ and in the laboratory and included the use of a new sensors to develop a geotechnical model of the cut slope. During the rainfall process in the physical simulation experiments, automatic rainfall, three-dimensional scanning, and multiparameter monitoring were conducted to analyze the resulting landslides. The results showed that the increase in moisture and the generation of pore water pressure led to changes in soil pressure and the development of plastic deformation. An analysis performed after rainfall using a strain-softening behavior model showed the initiation and propagation of plastic zones, as well as the development of landslide cracks close to the observed ones. Therefore, it was proposed that the Miaoling–Jiujiang landslide could be explained by a progressive failure mechanism.