Landslide susceptibility mapping is very important for landslide risk evaluation and land use planning. Toward this end, this paper presents a case study in Ningqiang County, Shanxi Province, China. Slope units were selected as the basic mapping units. A traditional statistical certainty factor model (CF), a machine learning support vector machine model (SVM) and random forest model (RF), along with a hybrid CF-SVM model and a CF-RF model were applied to analyze landslide susceptibility. Firstly, 10 landslide conditioning factors were selected, namely slope-angle, altitude, slope aspect, degree of relief, lithology, distance to rivers, distance to faults, distance to roads, average annual rainfall and normalized difference vegetation index. The 23,169 slope units were generated from a Digital Elevation Model and the corresponding 10 conditioning factor layers were produced from both geological and geographical data. Then, landslide susceptibility mapping was carried out using the five models, respectively. Next, the landslide density (LD), frequency ratio (FR), the area under the curve (AUC) and other indicators were used to validate the rationality, performance and accuracy of the models. The results showed that the susceptibility maps produced from the different models were all reasonable. In each map, the LD and FR were greatest in the zones classed as having very high landslide susceptibility, followed by the high, moderate, low and very low landslide susceptibility classes, respectively. From the comparison of the different maps and ROC curves, the RF model based on slope units was the most appropriate for landslide susceptibility mapping in the study area. It was also found that the combination of weaker learner model (CF model here) with a stronger learner model (SVM and RF model here) can impact the applicability of the stronger model.

The main purpose of this study aims to apply and compare the rationality of landslide susceptibility maps using support vector machine (SVM) and particle swarm optimization coupled with support vector machine (PSO-SVM) models in Lueyang County, China, enhance the connection with the natural terrain, and analyze the application of grid units and slope units. A total of 186 landslide locations were identified by earlier reports and field surveys. The landslide inventory was randomly divided into two parts: 70% for training dataset and 30% for validation dataset. Based on the multisource data and geological environment, 16 landslide conditioning factors were selected, including control factors and triggering factors (i.e., altitude, slope angle, slope aspect, plan curvature, profile curvature, SPI, TPI, TRI, lithology, distance to faults, TWI, distance to rivers, NDVI, distance to roads, land use, and rainfall). The susceptibility between each conditioning factor and landslide was deduced using a certainty factor model. Subsequently, combined with grid units and slope units, the landslide susceptibility models were carried out by using SVM and PSO-SVM methods. The precision capability of the landslide susceptibility mapping produced by different models and units was verified through a receiver operating characteristic (ROC) curve. The results showed that the PSO-SVM model based on slope units had the best performance in landslide susceptibility mapping, and the area under the curve (AUC) values of training and validation datasets are 0.945 and 0.9245, respectively. Hence, the machine learning algorithm coupled with slope units can be considered a reliable and effective technique in landslide susceptibility mapping.

In coal mines, underground roadways are required to transport coal and personnel. Such tunnels can become unstable and hazardous. This study simulates deformation and damage in the rock surrounding a shallow coal seam roadway using particle flow code. A numerical model of particle flow in the surrounding rock was constructed based on field survey and drilling data. Microcharacteristic indices, including stress, displacement, and microcrack fields, were used to study deformation and damage characteristics and mechanisms in the surrounding rocks. The results show that the stress within the rock changed gradually from a vertical stress to a circumferential stress pattern. Stress release led to self‐stabilizing diamond‐shaped and X‐shaped tensile stress distribution patterns after the excavation of the roadway. Cracking increased and eventually formed cut‐through cracks as the concentrated stress transferred to greater depths at the sides, forming shear and triangular‐shaped failure regions. Overall, the roof and floor were relatively stable, whereas the sidewalls gradually failed. These results provide a reference for the control of rock surrounding roadways in coal mines.

The Loess Plateau region of China has an anomalous climate and frequent geological disasters. Hipparion laterite in seasonally frozen regions exhibits heightened susceptibility to freeze–thaw (F-T) cycling, which induces progressive structural weakening and significantly elevates the risk of slope instability through mechanisms including pore water phase transitions, aggregate disintegration, and shear strength degradation. This study focuses on the slip zone Hipparion laterite from the Nao panliang landslide in Fugu County, Shaanxi Province. We innovatively integrated F-T cycling tests with ring-shear experiments to establish a hydro-thermal–mechanical coupled multi-scale evaluation framework for assessing F-T damage in the slip zone material. The microstructural evolution of soil architecture and pore characteristics was systematically analyzed through scanning electron microscopy (SEM) tests. Quantitative characterization of mechanical degradation mechanisms was achieved using advanced microstructural parameters including orientation frequency, probabilistic entropy, and fractal dimensions, revealing the intrinsic relationship between pore network anisotropy and macroscopic strength deterioration. The experimental results demonstrate that Hipparion laterite specimens undergo progressive deterioration with increasing F-T cycles and initial moisture content, predominantly exhibiting brittle deformation patterns. The soil exhibited substantial strength degradation, with total reduction rates of 51.54% and 43.67% for peak and residual strengths, respectively. The shear stress–displacement curves transitioned from strain-softening to strain-hardening behavior, indicating plastic deformation-dominated shear damage. Moisture content critically regulates pore microstructure evolution, reducing micropore proportion to 23.57–28.62% while promoting transformation to mesopores and macropores. At 24% moisture content, the areal porosity, probabilistic entropy, and fractal dimension increased by 0.2263, 0.0401, and 0.0589, respectively. Temperature-induced pore water phase transitions significantly amplified mechanical strength variability through cyclic damage accumulation. These findings advance the theoretical understanding of Hipparion laterite’s engineering geological behavior while providing critical insights for slope stability assessment and landslide risk mitigation strategies in loess plateau regions.