Ran Tang

Landslide susceptibility assessment in cold, high-altitude regions is complicated by interactions among topographic, lithological, hydrological, and anthropogenic factors. Machine learning methods are widely used, but model selection, spatially independent evaluation, and interpretation of covariate-adjusted associations remain challenging. This study developed an integrated framework for landslide susceptibility assessment in Tongren City, on the northeastern margin of the Qinghai–Tibet Plateau. The framework combined H₂O AutoML, nested spatial cross-validation, Shapley additive explanations (SHAP), partial dependence plots (PDPs), and double machine learning (DML). Each of the 20 sampling realizations included 217 landslide points and 217 non-landslide points, with 13 conditioning factors retained after collinearity screening. DML used partially linear regression with spatial cross-fitting across 200 repetitions to estimate covariate-adjusted associations. Stacked Ensemble achieved the highest mean area under the receiver operating characteristic curve (AUC) of 0.953 ± 0.009 across the 20 realizations. Spatial out-of-fold evaluation showed that the 20% of the study area with the highest susceptibility contained 93.27% ± 1.51% of held-out landslides (mean ± standard deviation). Elevation, distance to roads, lithology, distance to faults, and land use/land cover together accounted for 76.69% of the total mean absolute SHAP values. PDPs revealed nonlinear relationships between conditioning factors and model-predicted susceptibility. Elevation, interpreted as a proxy for valley position, and distance to roads were the only factors with statistically significant negative covariate-adjusted associations after multiple-testing correction. The random common cause (RCC) test indicated that DML estimates remained stable under the random-covariate perturbations examined. The framework distinguishes predictive contributions from covariate-adjusted associations and supports landslide monitoring and spatial planning in cold, high-altitude plateau transition zones.

Red mudstone fill material (RMF) has been used as a substitute fill material in railway subgrades, but its allowable dynamic response under long-term cyclic loading has not been clearly identified. This paper presents an experimental identification of the dynamic state boundary surface (DSBS) of RMF under different water contents and cyclic stress levels. A series of single-stage cyclic triaxial tests with up to 50,000 loading cycles was performed on compacted RMF specimens. The DSBS was illustrated by the isolines of loading cycles and cyclic stress in terms of permanent axial strain, strain amplitude, axial strain rate, equivalent Young’s modulus, and dissipated energy. Clear two-stage behavior was observed in the evolution of permanent deformation, equivalent Young’s modulus and dissipated energy, indicating that the effect of loading cycles should be incorporated into the state boundary framework. The DSBS based on deformation-related variables showed pronounced water content dependence, but the gradual variation in these variables led to ambiguity in identifying the shakedown ranges, especially the creep limit. In contrast, the dissipated-energy-based DSBS exhibited a stable lower boundary at high loading cycles. Two characteristic dissipated energy levels, 0.01 kPa and 0.04 kPa, were therefore defined as the boundaries for the shakedown limit and creep limit of RMF, respectively, regardless of water content and cyclic stress state. The energy classification was supported by saturated RMF tests and field excitation data from the Dazhou–Chengdu railway. These results suggest that dissipated energy can serve as a unified indicator for evaluating the stability of RMF subgrade, and that the DSBS provides a practical framework for characterizing the allowable dynamic response of clayey fill materials.

The mechanical behavior of gravelly soils in shallow overburden environments is significantly modulated by groundwater fluctuations, which govern the in situ moisture distribution and, consequently, control particle fragmentation processes and the evolution of shear strength. Fragmentation was quantitatively characterized through particle size distribution, fractal dimension, mean particle size, and statistical parameters derived from Weibull and generalized extreme value distributions. Shear strength was evaluated via consolidated–drained triaxial tests. The results demonstrate a clear depth dependency of the soil’s physical and mechanical properties. As the sampling depth increased from 3.0 m to 26.5 m, the natural moisture content decreased from 2.89% to 0.77%. Fractal analysis reveals that the fractal dimension of the particles increased from 2.304 to 2.671, reflecting an intensified fragmentation process at greater depths. Triaxial test results indicate that with increasing depth, the internal friction angle increased from 28.63° to 40°, while the cohesion decreased from 18.59 kPa to 5.47 kPa. These quantitative variations suggest that the coupled effects of groundwater variation and overburden pressure collectively govern the evolution of fragmentation characteristics and the divergent trends observed in shear strength components.

Accurate landslide susceptibility assessment remains challenging in mountainous regions with complex terrain, heterogeneous geology, and clustered landslide inventories. This study develops a slope–unit–based landslide susceptibility assessment framework for Tongren County, Qinghai Province, China, using a landslide inventory of 217 events, multi–source environmental data, Certainty Factor (CF)–based conditioning–factor analysis, and machine learning models. Eighteen conditioning factors derived from remote sensing, geological survey, and meteorological datasets were extracted at the slope–unit scale, and their collinearity was evaluated using Pearson’s correlation and the Variance Inflation Factor (VIF). Eight models—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), AdaBoost, Decision Tree (DT), XGBoost, K–Nearest Neighbors (KNN), and Convolutional Neural Network (CNN)—were evaluated under a 70:30 train/test split. The results show clear performance differences among the tested models: SVM achieved the best overall balance between discrimination and landslide detection (AUC = 0.9489; recall = 0.879). The tested CNN baseline showed relatively weak performance under the current slope–unit–based tabular–data setting. Susceptibility zoning results showed that high– and very–high–susceptibility zones were mainly concentrated along the Longwu River and its tributaries, where middle–elevation dissected terrain, weak lithological materials, river–valley erosion, and human engineering activities spatially coincide. These results provide a practical basis for slope monitoring and land–use planning in Tongren County.

Landslide disasters on the northeastern margin of the Qinghai-Tibet Plateau pose severe threats to safety and the environment. Traditional "gray engineering" relies heavily on energy-intensive cement and steel, leading to high carbon emissions that conflict with global carbon neutrality goals. This paper explores a low-carbon, sustainable management model for the Xishan Landslide in Tongren City. A phased strategy was implemented, integrating necessary engineering measures with a novel ecological restoration technology utilizing modified glutinous rice-based materials (MGRM). As a natural organic material, MGRM serves as an eco-friendly alternative to traditional high-carbon cementitious materials, significantly reducing carbon emissions during slope stabilization. The management effects were evaluated using real-time monitoring and Remote Sensing Ecological Index (RSEI) analysis. Results indicate the landslide has transitioned to a stable state, with surface displacement velocities maintained below 0.1 mm/d. Furthermore, the regional RSEI increased significantly from 2021 to 2025, revealing a benign trajectory of "engineering stabilization–vegetation recovery–carbon sequestration function." This study validates the efficacy of the " engineering + ecology " model, providing a sustainable reference for achieving carbon–neutral geological disaster mitigation in ecologically fragile alpine regions.

Landslides are a significant geological hazard with substantial socio-economic and environmental consequences, particularly in northwestern Sichuan, SW China, where complex geological and climatic conditions contribute to their occurrence. This study examines 1629 recorded landslide events, including 240 active landslides that have undergone substantial changes over the past two decades. By analyzing multi-temporal satellite imagery, this research investigates the relationship between landslide occurrence and key environmental factors such as annual rainfall and the Normalized Difference Vegetation Index (NDVI). The results reveal that landslides are most frequent on southwest-, south-, east-, and southeast-facing slopes, where the Föhn effect interacts with rainfall and vegetation patterns, thereby increasing landslide susceptibility. Rainfall intensity is identified as a critical factor, with landslide areas expanding significantly when annual rainfall exceeds 650 mm, while minimal changes are observed when rainfall is below 550 mm. The relationship between the NDVI and landslide occurrence is non-linear; higher vegetation cover does not necessarily correlate with reduced landslide frequency. Notably, landslide expansion is more pronounced when NDVI values are below 0.82, with a suppression effect occurring beyond this threshold. A threshold model based on the interaction between the NDVI and rainfall provides valuable insights into landslide dynamics, offering a framework for improved risk management. Slope characteristics are crucial in landslide evolution, with steeper slopes leading to greater vertical drops and more frequent events, making slope zone identification key for predicting future expansion.

On 1 September 2022, a landslide in Hongya Village, Weiyuan Town, Huzhu Tu Autonomous County, Qinghai Province, caused significant casualties and economic losses. To mitigate such risks, InSAR technology is employed due to its wide coverage, all-weather operation, and cost-effectiveness in detecting landslides. In this study, focusing on the landslide in Hongya Village, SBAS-InSAR and Sentinel-1A satellite data from July 2021 to September/October 2022 were used to accurately identify the areas of active landslides and to analyze the landslide deformation trends, in combination with the geological characteristics of the landslides and rainfall data. The results showed that strong deformation was detected in the middle and back of the landslide in Hongya Village, with a maximum deformation rate of approximately -13 mm/year. The surface of the landslide consisted of mainly Upper Pleistocene wind-deposited loess, which is extremely sensitive to water. The deformation of the landslide was closely related to the rainfall, and the deformation of the landslide increased with the increase in rainfall. The research results prove that the combination of ascending and descending orbit data based on SBAS-InSAR technology is highly feasible in the field of landslide deformation monitoring and is of great practical significance for landslide disaster prevention and mitigation.

As the Third Pole of the Earth and the Water Tower of Asia, the Tibetan Plateau (TP) nurtures large numbers of glacial lakes, which are sensitive to global climate change. These lakes modulate the freshwater ecosystem in the region but concurrently pose severe threats to the valley population by means of sudden glacial lake outbursts and consequent floods (GLOFs). The lack of high-resolution multi-temporal inventory of glacial lakes in TP hampers a better understanding and prediction of the future trend and risk of glacial lakes. Here, we created a multi-temporal inventory of glacial lakes in TP using a 30-year record of 42,833 satellite images (1990–2019), and we discussed their characteristics and spatio-temporal evolution over the years. Results showed that their number and area had increased by 3285 and 258.82 km² in the last 3 decades, respectively. We noticed that different regions of the TP exhibited varying change rates in glacial lake size; most regions show a trend of expansion and increase in glacial lakes, while some regions show a trend of decreasing such as the western Pamir and the eastern Hindu Kush. The mapping uncertainty is about 17.5%, which is lower than other available datasets, thus making our inventory reliable for the spatio-temporal evolution analysis of glacial lakes in the TP. Our lake inventory data are publicly published, it can help to study climate change–glacier–glacial lake–GLOF interactions in the Third Pole and serve as input to various hydro-climatic studies.