Search Results (3,899)

Landslides constitute one of the most lethal and costly hydrometeorological hazards at the global scale. There is a growing trend associated with the increase in extreme precipitation and the expansion of urban development on unstable slopes. In the tropical Andes, this problem is intensified under climate change scenarios. The objective of this study is to develop a logistic regression model to analyze socioeconomic risk due to landslides in the Bogotá Savannah (Colombia). An integrated risk model was developed using binary logistic regression and a socioeconomic vulnerability index. A total of 12 physical–biotic variables and SSP climate projections (2021–2040) were used. A GIS-based environment was implemented to generate prospective spatial risk scenarios. The model demonstrated high robustness and predictive capability, with an improvement in statistical goodness-of-fit of 8.2% (AIC: 2574–2367), adequate probabilistic calibration (Pseudo-R²: 0.675; Brier Score: 0.084), and excellent predictive performance (AUC: 0.935; sensitivity: 84.7%; specificity: 90.0%). Simulations estimated maximum risk probabilities close to 0.600 (scale between 0 and 1), concentrated in geomorphologically critical sectors. Simulations under SSP scenarios showed a progressive increase in risk toward 2040 (up to 0.673), associated with precipitation increases between 10 and 30%. Integrated modeling constitutes a reliable technical tool for land-use planning, climate adaptation, and prospective landslide risk management in urbanized Andean regions. Full article

Reliable prediction of landslide run-out distance is of great importance for hazard zoning and risk mitigation. However, most previous studies evaluate model performance within a single landslide inventory, while the transferability of models across different triggering mechanisms remains insufficiently explored. To evaluate whether landslide run-out-prediction models and their uncertainty estimates remain reliable when transferred between rainfall-induced and earthquake-induced landslide inventories, this study investigates trigger-dependent run-out behavior and cross-trigger transferability using a harmonized inventory of 10,158 rainfall-induced and 681 earthquake-induced records. Common geometric descriptors, including run-out distance L, elevation difference H, source area A, source volume V, and mean slope angle $\theta$, were used for distributional comparison, scaling-law analysis, machine-learning prediction, tail-risk assessment, and uncertainty quantification. The results show that earthquake-induced landslides occupy a larger geometric domain, whereas rainfall-induced landslides exhibit greater elevation-normalized mobility. Cross-trigger prediction experiments reveal substantial and asymmetric transfer degradation, with systematic overprediction in R→E and underprediction in E→R. Prediction-interval reliability also deteriorates markedly under cross-trigger transfer, indicating that uncertainty estimates calibrated within one trigger type may not remain reliable when applied to another. These findings suggest that trigger-associated inventory differences should be explicitly considered in landslide run-out modeling. Direct application of models across rainfall- and earthquake-induced landslide inventories may lead to biased predictions and unreliable uncertainty estimates. Full article

Landslides constitute a globally pervasive and highly destructive natural hazard. Although artificial intelligence (AI)-driven landslide susceptibility mapping has emerged as an effective tool for delineating high-risk zones, its predictive performance is frequently constrained by inherent data noise and insufficient characterization of landslide triggering factors, restricting the credibility of the mapping results. In this study, to remedy this limitation, we adopt fractal analysis to extract latent inherent information from topographic features. Specifically, the box-counting method and multifractal analysis are applied to excavate the intrinsic nonlinear characteristics embedded in eight topographic factors, and an improved K-means algorithm is utilized to perform feature selection and construct a dedicated fractal feature dataset, which is fed to advanced AI models. Our results indicate that the information dimension ($D_1$) of the slope gradient, the correlation dimension ($D_2$) of aspect, land relief, the $D_2$ of roughness, the $D_2$ of plan curvature, the multifractal spectrum width ($∆\mathsf{\alpha }$) of profile curvature, the $D_2$ of elevation, and the surface cutting depth were the most effective features, demonstrating superior performance in capturing landslide targets. Comparative performance evaluations reveal that AI models trained on fractal features demonstrate substantially superior predictive capabilities compared to AI models trained on raw features. This superiority is consistently evidenced across key evaluation metrics, including overall accuracy, kappa coefficient, F1-score, and predictive efficiency, demonstrating that the integration of fractal characteristics significantly augments model robustness and predictive efficacy. To mitigate the ‘black-box’ problem of AI modeling, Shapley additive explanations were employed to quantify individual feature contributions and elucidate the underlying predictive mechanisms. Our findings indicate that the integration of fractal analysis yields highly discriminative and robust feature representations, thereby expanding the representational capacity of the models and improving predictive accuracy. Furthermore, a joint assessment of spatial uncertainty and susceptibility maps demonstrates that these models exhibit low predictive variance and high spatial stability when delineating high-susceptibility zones. Notably, models utilizing fractal-derived features achieve superior spatial capture efficiency. The resultant topographic features characterized by fractal representation and selected via the improved K-means algorithm can significantly improve the predictive performance of trained AI models in landslide susceptibility mapping tasks, offering a scientific and viable technical approach for future landslide prediction and prevention. Full article

Landslide susceptibility is often treated as a static assessment of present-day conditions, overlooking the temporal evolution of geomorphological and anthropogenic drivers. This limitation is particularly relevant in rapidly urbanising areas, where land use change continuously alters environmental conditions influencing slope stability. This study examines the temporal evolution of landslide susceptibility in the Grigorescu neighbourhood of Cluj-Napoca, Romania, using environmental datasets representing conditions in 1971, 2009, and 2025, along with a projected land use scenario for 2047. The proposed framework integrates multi-temporal landslide inventories and conditioning factors with Maximum Entropy (MaxEnt) modelling and CA–Markov–MLP land use simulation (MOLUSCE). Results indicate a progressive shift towards higher susceptibility classes over time, accompanied by urban expansion onto increasingly steep terrain. However, slope gradient remained the dominant conditioning factor throughout all analysed periods, while land use change influenced the temporal evolution and spatial redistribution of susceptibility through progressive urban expansion into terrain already predisposed to instability. The 2047 scenario suggests that continued urban expansion may increase the exposure of built-up areas to zones of elevated susceptibility. Model performance was robust (AUC > 0.8; Kappa > 0.9). Beyond site-specific findings, the framework provides a transferable methodology for integrating urban growth dynamics into landslide susceptibility assessment, supporting sustainable spatial planning and risk-informed urban development in rapidly urbanising hilly environments. Full article

Geological disasters are frequently triggered in steep mountainous mining areas due to the coupling effects of underground excavation and slope stability, yet the applicability of traditional rock movement theories in such terrains remains unclear. This study investigates an extremely steep coal mine in southwestern China, integrating engineering geological surveys, unmanned aerial vehicle (UAV) measurements, InSAR monitoring, and rock movement theoretical calculations to analyze the impact of mining on mountain deformation and slope stability. The results show that the study area exhibits steep slopes (55–85°) and gently inclined, reverse-layered rock masses controlled by structural fracture zones, creating a geological environment prone to mining-induced landslides. The 1151 working face lies at a depth of 286–470 m, with a protective coal pillar of approximately 160 m left between the excavation and the cliff zone. InSAR monitoring indicates cumulative LOS deformation rates of −0.98 to 0.55 cm/a, with subsidence concentrated above the working face, while existing landslides in the cliff zone show no significant deformation. Comparison between theoretical calculations and InSAR inversion reveals that InSAR boundary angles (downslope 61–68°, upslope 67–73°) exceed theoretical predictions (downslope 48–52°, upslope 55°), indicating that complex topography and rock mass structure constrain mining-induced deformation propagation. The findings demonstrate that appropriately designed protective coal pillars and avoidance of unstable slopes can effectively mitigate the impact of mining-induced disturbances on existing hazards. This study provides valuable reference for landslide risk assessment and disaster prevention in extremely steep mining regions. Full article

Accurate delineation of landslide boundaries from remote sensing imagery remains challenging because landslides exhibit irregular geometry, substantial scale variation, and strong background interference. We propose DCA-UNet, a U-Net-style segmentation network that integrates deformable convolution and aggregated attention to jointly improve geometric adaptation and local-global context modeling. Deformable convolution adjusts spatial sampling locations to irregular landslide boundaries, whereas aggregated attention enhances contextual discrimination in visually ambiguous terrain. We evaluate the method on three public benchmarks—Landslide4Sense, HR-GLDD, and GDCLD—under a controlled from-scratch benchmark with dataset-specific preprocessing and official data splits. DCA-UNet achieves the best overall IoU/F1 ranking across the three datasets, reaching 61.92%/76.48% on Landslide4Sense, 59.24%/74.41% on HR-GLDD, and 58.40%/73.74% on GDCLD. The model contains 29.50 million parameters, which is close to vanilla U-Net and substantially fewer than several transformer-based baselines, although its training-side runtime and memory consumption are not the lowest. These results show that combining adaptive spatial sampling with local-global contextual aggregation is effective for landslide segmentation in both multispectral and RGB remote sensing imagery. Full article

Landslides cause thousands of fatalities and billions in economic losses annually, yet reliable susceptibility mapping across heterogeneous landscapes remains challenging because conventional models assume stationary relationships between landslide occurrence and environmental controls. Ensemble methods, though promising, rely on either globally fixed aggregation weights or kernel-constrained local averaging, failing to adapt when the reliability of base models varies nonlinearly across space. To overcome this, we propose a two-stage hierarchical spatial adaptive ensemble (HSE) framework. In stage one, three complementary base learners are deployed: geographically weighted regression (GWR) for local spatial non-stationarity; a geographically optimal similarity (GOS) model, grounded in the Third Law of Geography, to represent similarity-based local dependence; and a deep neural network (DNN) for nonlinear covariate interactions. In stage two, a multi-branch attention-based network learns spatially varying fusion weights via multi-scale feature extraction, abandoning fixed weights or kernel constraints. We validate HSE on a typical landslide-prone catchment, comparing against single models (GWR, DNN, GOS). Results demonstrate that our method consistently achieves superior predictive accuracy, spatial consistency, and out-of-sample robustness. Moreover, the attention-derived spatially varying weights provide interpretable insights into where each base learner dominates, bridging predictive performance with geophysical interpretability. These findings confirm that explicitly learning spatial heterogeneity during ensemble fusion is essential for reliable landslide susceptibility mapping, with strong potential for transfer to other geospatial prediction tasks. Full article

Rapid and accurate detection of landslide-affected areas is critical for disaster response and risk mitigation. Sentinel-1 SAR imagery offers all-weather, day-and-night observation capability, but existing deep learning approaches treat landslide detection as a single-pass segmentation problem, which limits performance in complex terrain where backscatter changes are confounded by soil moisture, surface roughness, urban double bounce, shadow, and layover effects. MAD-SAR, a rule-based agentic framework that coordinates anomaly detection, super-resolution, object detection, and semantic segmentation under a planning orchestrator and a physics-aware validation engine is proposed. The orchestrator selects specialist modules, their execution order, and the number of refinement iterations according to a scene complexity score computed from SAR-derived statistics. The physics-aware validation engine cross-checks every candidate detection against backscatter change thresholds, DEM-derived slope constraints, and radar geometry masks before any detection is committed to the output. MAD-SAR is evaluated on three Japanese disaster datasets: Hiroshima 2018, Kumamoto 2016, and Ibaraki 2019. On the held-out Ibaraki test event, the framework achieves an F1-score of 0.863 and IoU of 0.759, outperforming all baselines and reducing false alarms by 45% relative to standalone SegFormer. Ablation results confirm that each module contributes to the final performance. These results suggest that multi-module orchestration with embedded physical validation can meaningfully improve SAR-based landslide mapping, though broader validation across regions, sensor configurations, and failure mechanisms remains necessary. Full article

Earthquake-induced landslides represent a critical threat to transportation infrastructure in tectonically active mountainous regions, particularly in tropical volcanic settings where weak, highly weathered geomaterials dominate. This study develops an integrated framework that directly links physically based seismic threshold modelling with real-time landslide monitoring and operational early warning. The approach is demonstrated in the Cugenang area of Cianjur Regency, West Java, Indonesia, which was severely impacted by the moment magnitude (Mw) 5.6 earthquake in 2022. Slopes composed of highly weathered pyroclastic deposits [Plasticity Index (PI) = 54–68%; porosity > 60%] exhibit low shear strength and high sensitivity to seismic loading. Limit equilibrium analysis using the Morgenstern–Price method that combines the influence of seismic loading and groundwater conditions suggests that a horizontal seismic coefficient (kh) of approximately 0.06, corresponding to a Peak Ground Acceleration (PGA) of about 0.12 gravitational acceleration (g), is a critical threshold for initial landsliding. This comparatively low threshold challenges commonly reported values and demonstrates that slope failure in tropical volcanic terrains can occur under moderate ground shaking, reinforcing the need for site-specific hazard characterisation. The derived thresholds are operationalised within a multi-sensor early warning system integrating Micro-Electro-Mechanical Systems (MEMS) accelerometers and inclinometer measurements. Three hazard levels—Normal (<0.06 g), Alert (0.06–0.12 g), and Emergency (≥0.12 g)are combined with deformation thresholds [<10 milimeter (mm), 10–30 mm, >30 mm] to capture progressive failure processes and minimise false alarms. By coupling geotechnical modelling and real-time monitoring, this study provides a transferable and scalable framework for enhancing infrastructure resilience in landslide-prone regions. Full article

Landslide susceptibility algorithms demonstrate high reliability in quantifying the likelihood of landslide occurrence. However, traditional methods are often limited by computationally intensive sampling strategies and models with limited adaptability. In this study, we propose an adaptive sampling strategy based on hotspot analysis to enhance the reliability of the generated samples. Additionally, we develop an improved meta-ensemble (IME) stacking-based heterogeneous framework for landslide susceptibility assessment by integrating a support vector machine (SVM), random forest (RF), and XGBoost. To further reduce factor complexity, a Monte Carlo-based frequency ratio analysis is employed. The Baihetan Reservoir area along the Jinsha River was selected as the study area. A total of 26 conditioning factors were considered, supplemented by 120 Sentinel-1A images to cover the study area. The proposed sampling strategy was then used to generate high-quality samples. Finally, to evaluate the performance of the proposed method, the proposed ensemble learning framework was applied to assess landslide susceptibility with eight models using five evaluation metrics. The experimental results demonstrated that: (1) the adaptive sampling strategy improved both the quantity and quality of the training samples; (2) the adoption of the Monte Carlo strategy increased the sample partitioning rate; and (3) despite the formally highest IME metrics, the inclusion of InSAR information did not lead to a statistically significant improvement in the forecast compared to the high-quality basic sampling strategy. Overall, the proposed methodology provides valuable support for regional geohazard susceptibility assessment in dynamic environments. Full article

Accurate delineation of buried slip surfaces remains a major uncertainty in landslide hazard assessment, especially where subsurface data are limited. This study evaluates a displacement-based approach to estimate quasi-three-dimensional (quasi-3D) slip surfaces using ground-surface displacement vector gradients derived from multi-temporal UAV-based LiDAR data. Two landslides in Japan (Jimba and Kamitokitozawa), representing contrasting scales, were analyzed to assess the method’s applicability and limitations. Two-dimensional (2D) slip-surface profiles were derived through group-wise median grouping of displacement gradients and weighted non-uniform rational B-spline fitting along longitudinal sections. Transverse profiles were constrained using side-scarp gradients and depths estimated from longitudinal profiles. These profiles were integrated into quasi-3D surfaces and validated against borehole-derived slip surfaces. At the Jimba landslide, characterized by relatively coherent movement, the estimated surfaces closely match borehole data in both depth and geometry. At the larger Kamitokitozawa landslide, the method reproduces first-order geometry and extent but shows larger local deviations, particularly in a graben-like subsidence zone. Nevertheless, the estimated displaced volume reaches 96% of that derived from borehole data. These results demonstrate that the method provides useful first-order constraints on slip-surface geometry for preliminary hazard assessment, borehole planning, and 3D stability analysis. Full article

Accurate landslide identification is crucial for enhancing emergency response capabilities during destructive geological hazards. Although deep-learning-based semantic segmentation has demonstrated effectiveness, substantial variations in landslide scales and environmental similarities continue to challenge existing methods. This paper systematically constructs a new co-seismic landslide dataset for the Yarlung Zangbo River basin based on the 2017 Nyingchi earthquake, effectively filling a critical regional data gap. This paper proposes CETransUNet (coordinate attention and edge-guided attention transformer UNet), a novel landslide detection model that integrates ResNet and Transformer architectures. Specifically, a coordinate attention (CA) module is introduced within the skip connections between the encoder and decoder. This module encodes positional information along both horizontal and vertical spatial directions and dynamically re-weights the feature maps, thereby effectively suppressing background noise caused by semantic gaps and enhancing the model’s ability to localize landslide regions. Additionally, an edge-guided attention (EGA) module is incorporated into the decoder. This module extracts explicit edge priors from the input image using a Laplacian operator and imposes geometric constraints on the predictions via a boundary reverse attention mechanism, thereby significantly alleviating boundary ambiguity and morphological distortion of landslides. Evaluations across datasets from the Yarlung Zangbo River, Iburi-Tobu, and Bijie regions demonstrate that CETransUNet significantly outperforms state-of-the-art models—including TransUNet, SegFormer, and SwinUNet—in terms of IoU, MIoU, and F1-score. Overall, through the synergistic optimization of the coordinate attention and edge-guided attention modules, the CETransUNet model achieves synchronous enhancement of boundary integrity and geometric precision in complex scenarios, providing a reliable technical solution for large-scale intelligent landslide identification. Full article

Current landslide displacement prediction models often suffer from insufficient integration between physical mechanisms and data-driven approaches, weak model generalizability, and limited operational applicability. To address these issues, this study develops a physics-informed online learning framework for landslide displacement prediction. The core of this framework is a Physics-informed Long Short-Term Memory network (Phys-LSTM). By embedding discretized forms of the stress balance, creep constitutive, and kinematic equations as hard constraints into the LSTM’s gating mechanisms and loss function, the model ensures physically consistent predictions and enhanced interpretability throughout the learning process. Leveraging real-time data streams from the Sichuan Provincial Geological Hazard Monitoring and Warning Platform, we developed an online processing pipeline for real-time multi-source data ingestion, automated quality control, spatiotemporal alignment, and physics-informed feature engineering. A progressive three-stage learning algorithm was designed to support model cold-start, incremental training, and rolling prediction. Validation across 45 model-development landslide sites and one independent application case demonstrated the framework’s significant superiority over traditional models in displacement prediction accuracy (RMSE ≤ 1.78 mm, R² ≥ 0.96), cross-site generalization stability, and its capability to capture accelerated deformation phases. This research indicates that deeply integrating geomechanical prior knowledge into an online learning framework can effectively improve the reliability, interpretability, and operational applicability of landslide displacement prediction models, thereby providing methodological support for subsequent landslide early warning applications. Full article

Landslides are the most common geological hazards, and chemical reinforcement is an effective method for enhancing the stability of soil slopes. Based on the coupled Eulerian–Lagrangian method, finite element analyses were conducted to develop a simple design approach for soil slope reinforcement using the curing agent. First, the effects of internal friction angle, cohesion, soil unit weight, slope height and angle on the slope stability were systematically quantified through 93 numerical cases. On this basis, an empirical formula was established for the factor of safety (FOS) of soil slope, and a method for determining the failure mode was proposed using a dimensionless parameter and two critical values related to slope angle. Subsequently, the reinforcement performance of the SH curing agent was investigated by varying the reinforcement position and length. The results indicate that the reinforcement of Case I-II-III and Case I-II provide the best performance, and the optimum reinforcement length was determined for different slope conditions. For slope angles ranging from 25° to 65°, the FOS after reinforcement was found to increase by 12.1% to 18.8% compared with that before reinforcement. Based on the FE results, empirical formulae for predicting the FOS of reinforced slope were further developed. Finally, a simple design approach was proposed for soil slope reinforcement with curing agent. The proposed method provides a convenient and effective reference for engineering practice in soil slope reinforcement with curing agents. Full article

Rainfall is a critical factor inducing slope instability, and accurate prediction of the factor of safety (FOS) of slopes under rainfall conditions is of paramount importance for disaster prevention and mitigation. Conventional numerical simulation methods incur high computational costs, while individual machine learning models are often insufficient to adequately capture the nonlinear spatiotemporal evolution characteristics of multiple factors under coupled multi-physics fields. To address these limitations, this paper proposes a Transformer–LSTM prediction framework. First, a fluid–structure coupling model for rainfall-affected slopes is constructed using COMSOL, and multi-factor orthogonal experiments are performed to generate multi-dimensional time-series data. Subsequently, a Transformer–LSTM fusion deep learning model is built, in which LSTM is employed to extract the temporal dynamic characteristics of rainfall infiltration, and the self-attention mechanism of the Transformer is leveraged to enhance feature extraction and global dependency modeling of key disaster-causing factors. Experimental results demonstrate that the Transformer–LSTM model significantly outperforms traditional PSO-LSTM, PSO-SVM, and standalone Transformer or LSTM models in terms of both prediction accuracy and generalization capability. Its coefficient of determination (R²) remains above 0.94, and key evaluation metrics—including mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE)—attain the lowest values among the compared models. Furthermore, the SHAP (SHapley Additive exPlanations) interpretability framework is introduced to quantitatively elucidate the model’s predictive decision-making and to establish a physically grounded causal mapping with geotechnical mechanisms. It is confirmed that effective cohesion and slope angle exert a dominant interactive effect on the degradation of slope stability, providing data-driven support for wide-area monitoring of rainfall-induced landslides. Full article