Landslide Prediction Research Articles

Physically based probabilistic prediction of regional rainfall-induced shallow landslides: from initiation to runout analysis

ABSTRACT In this study, a physically based method is proposed to estimate the exceedance probability of the intensity measure of the regional rainfall-induced shallow landslides. This method consists of a digital elevation model, an initiation model, a runout model and a probabilistic analysis model. In the suggested method, a study area is discretised into a grid of cells, and the stability of each cell can be evaluated through the initiation model. Then, the runout behaviour of the unstable cells can be simulated by the runout model. Finally, the exceedance probability of the intensity measures of each cell can be estimated through Monte Carlo simulation considering the uncertainties in the initiation model and runout model. The proposed method is applied to analyse the rainfall-induced landslides in a study area in the southwest of China, which can provide a reasonably accurate prediction of the impact zones of the landslides. The suggested method provides a useful tool to probabilistically predict the impacted area of the rainfall-induced landslides at a regional scale.

Integrating Physical and Machine Learning Models for Enhanced Landslide Prediction in Data-Scarce Environments

Integrating Physical and Machine Learning Models for Enhanced Landslide Prediction in Data-Scarce Environments

Triggering mechanics and early warning for snowmelt-rainfall-induced loess landslide.

Loess landslides represent a significant natural hazard, especially in arid and semi-arid regions where slopes are exposed to prolonged snowmelt and rainfall infiltration. To analyze landslide stability and conduct early warning evaluations effectively, a robust monitoring system and appropriate equipment are crucial. This study utilizes historical data from the Kalahaisu landslide in Xinyuan County, Ili region, which was monitored using various techniques. The research assesses the time resolution, spatial resolution, and data accuracy of these monitoring methods. Additionally, the study explores the landslide disaster patterns and early warning indicators for the Kalahaisu landslide. It suggested that the deformation of the rainfall- and snowmelt- landslide is not only affected by the seasonal climates but also closely related to the internal structures of the loess. The other observation is that the respective time and spatial resolution of monitoring instrument would significantly affect the the interpretation time of the landslide deformation. Instruments with higher spatial resolution can more effectively identify unstable areas within a landslide, while instruments with higher temporal resolution can provide detailed time-series deformation data. Therefore, real-time and comprehensive monitoring of landslides using a suitable combination of monitoring equipment can provide strong data support for landslide stability evaluation and deformation trend prediction. Full-area monitoring techniques, such as Synthetic Aperture Radar (SAR) and equipment that measures changes in internal properties like deep water content, deep displacement, and pore pressure, offer a more comprehensive and effective approach to monitoring and interpreting landslide deformation. The insights gained from this research may enhance the prediction and prevention of loess landslides in the Ili River valley.

Landslide Displacement Prediction Stacking Deep Learning Algorithms: A Case Study of Shengjibao Landslide in the Three Gorges Reservoir Area of China

Computational models enable accurate, timely prediction of landslides based on the monitoring data on-site as the development of artificial intelligence technology. The most existing prediction methods focus on finding a single prediction algorithm with excellent performance or an integrated and efficient hyperparameter optimization algorithm with a highly accurate regression prediction algorithm. In order to break through the limitation of generalization of prediction models, this paper proposes an ensemble model that combines deep learning algorithms, with a stacking framework optimized with the sliding window method. Multiple deep learning algorithms are set as the first layer of the stacking framework, which is optimized with the sliding window method to avoid confusion in the time order of datasets based on time series analysis. The Shengjibao landslide in the Three Gorges Reservoir is used as a case study. First, the cumulative displacement is decomposed into a trend and a periodic term using a moving average method. A single-factor and a multi-factor superposition model based on multiple deep learning algorithms are used to predict the trend and periodic term of the displacement, respectively. Finally, the predicted values of the trend and periodic terms are added to obtain the total predicted landslide displacement. For monitoring point ZK2-3, the values of RMSE and MAPE of the total displacement prediction with the stacking model are 15.93 mm and 0.54%, and the values of RMSE and MAPE of the best-performing individual deep learning model are 20.00 mm and 0.64%. The results show that the stacking model outperforms other models by combining the advantages of each individual deep learning algorithm. This study provides a framework for integrating landslide displacement prediction models. It can serve as a reference for the geological disaster prediction and the establishment of an early warning system in the Three Gorges Reservoir Area.

Large-scale geohazards risk of submarine landslides considering the subsea cables vulnerability: A case study from the northern continental slopes of South China Sea

Submarine landslides pose significant threats to subsea cables distributed on the global seabed. However, regional scale risk assessment of landslide geohazards is rarely reported. This study introduces a methodology for regional-scale geohazard risk prediction of submarine landslides, focusing on the northern continental slopes of the South China Sea. Initially, the study employed the infinite-slope method to calculate safety factors for typical submarine slopes. Addressing uncertainties in geotechnical and seismic parameters, Monte Carlo simulations determine slope failure probabilities. Using kriging interpolation, localized failure probabilities are extrapolated to regional scales, establishing a spatiotemporal distribution method for large-scale geohazard susceptibility. Hazard levels are subsequently determined considering the volumes of potential landslides. The density of subsea cables is used as a vulnerability factor to guide the regional-scale assessment of cable vulnerability. Finally, integrating vulnerability with hazard levels provides a comprehensive assessment of landslide-induced large-scale geohazard risks. The findings highlight elevated geohazard risks in the Taiwan Bank slope segment, moderate risks in the Zhujiang Valley and Shenhu slope segments, with lower risks in other areas.

Slope stability analysis of unsaturated colluvial slopes based on case studies of rainfall-induced landslides

Landslides in colluvial soils under rainfall have been identified as a significant problem due to their loose, heterogeneous nature and low shear strength. Evaluation of the stability of colluvial slopes under rainfall conditions is challenging. This study investigated two landslide failure case studies of colluvial soils to understand the failure patterns using finite element (FE) and limit equilibrium (LE) slope stability analysis methods under unsaturated conditions. Transient seepage conditions due to rainfall infiltration and failure were analysed using hydromechanical models. Here, a FE fully coupled hydromechanical model and a sequential coupling of a FE hydrological and LE mechanical model were used to evaluate the failure of variably saturated slopes. Results from the case studies revealed that the failure occurred due to the rise in the groundwater table in both cases. It was evident that there can be significant disparities in the pore water pressure profiles with the fully coupled and sequentially coupled analysis. The dynamic capability of the two models can also affect the interplay between the hydrological and mechanical aspects. When the thickness of the colluvium layer is large, the failure could potentially occur as a deep-seated failure along the boundary of overburden and the bedrock surface due to the large driving force. However, when the thickness is small, failure can occur along the colluvium-weathered rock surface. The outcomes from the study will contribute to mitigate the uncertainty of failure prediction of landslides in colluvial soils.

Machine learning-based assessment of regional-scale variation of landslide susceptibility in central Vietnam.

Recurrent landslide events triggered by typhoons and tropical storms over Vietnam pose a longstanding threat to the nation's population and infrastructure. Changes in hydroclimatic conditions, especially the growing intensity and frequency of storms, have elevated landslide susceptibility in many parts of the country. This research examines the spatio-temporal variations in landslide susceptibility across central Vietnam over several years, using multi-temporal landslide inventories from Typhoon Ketsana (2009), Tropical Storm Podul (2013), and Typhoon Molave (2020). Additionally, the research explores the impact of individual landslide causative factors on the probabilistic occurrences of landslides. The post-event landslide susceptibility models of these three climate extreme events were developed using nine causative factors and a Random Forest machine learning algorithm. The results indicate a notable areal expansion of high to very high landslide susceptibility in the northern and eastern regions and a moderate reduction in the central and southern areas during the post-Molave period compared to the post-Ketsana period. These changes may be early indicators of increasing landslide susceptibility in response to changing hydro-climatic conditions. The research found that annual average rainfall and topographic elevation are the two most important variables influencing landslide prediction, showing a nonlinear relationship with landslide probability. The landslide susceptibility models achieved high Area Under the Receiver Operating Characteristic Curve (AUC) (>95%), accuracy (>89%), and sensitivity (>90%) scores, signifying the robustness of the models. Additionally, the uncertainty of the models was quantified and spatially mapped. This multi-temporal analysis of landslide susceptibility is crucial for understanding the regional susceptibility trends and identifying areas with increasing, decreasing, and consistently high susceptibility to landslides. These insights are invaluable for prioritizing mitigation and risk reduction strategies in landslide-prone regions and guiding appropriate land use planning.

Landslide Displacement Prediction Using Kernel Extreme Learning Machine with Harris Hawk Optimization Based on Variational Mode Decomposition

Displacement deformation prediction is critical for landslide disaster monitoring, as a good landslide displacement prediction system helps reduce property losses and casualties. Landslides in the Three Gorges Reservoir Area (TGRA) are affected by precipitation and fluctuations in reservoir water level, and displacement deformation shows a step-like curve. Landslide displacement in TGRA is related to its geology and is affected by external factors. Hence, this study proposes a novel landslide displacement prediction model based on variational mode decomposition (VMD) and a Harris Hawk optimized kernel extreme learning machine (HHO-KELM). Specifically, VMD decomposes the measured displacement into trend, periodic, and random components. Then, the influencing factors are also decomposed into periodic and random components. The feature data, with periodic and random data, are input into the training set, and the trend, periodic, and random term components are predicted by HHO-KELM, respectively. Finally, the total predicted displacement is calculated by summing the predicted values of the three components. The accuracy and effectiveness of the prediction model are tested on the Shuizhuyuan landslide in the TGRA, with the results demonstrating that the new model provides satisfactory prediction accuracy without complex parameter settings. Therefore, under the premise of VMD effectively decomposing displacement data, combined with the global optimization ability of the HHO heuristic algorithm and the fast-learning ability of KELM, HHO-KELM can be used for displacement prediction of step-like landslides in the TGRA.

Landslide susceptibility mapping and similar case matching based on case library: a case study of Xinjing landslide, China

Landslide susceptibility mapping (LSM) predicts potential landslide risks based on historical landslides, playing a crucial role in landslide prevention and control. This study proposes a novel approach for LSM in open-pit mines, leveraging a comprehensive landslide case database. This method addresses the limitations of traditional LSM approaches, such as sensitivity to historical landslide records, low-quality inventories, and limited dataset size. By expanding the training set and incorporating case-based reasoning (CB-LSM) using Long Short-Term Memory (LSTM) for machine learning, the model demonstrated a 10% improvement in predictive accuracy compared to statistical models, showing strong applicability even in areas with low-quality landslide inventories. Additionally, this study enhances the practical utility of LSM by introducing a similar case matching method, employing Fuzzy C-Means (FCM) clustering, which links high-risk areas identified by LSM with specific landslide prevention measures. The proposed approach not only improves the accuracy of landslide predictions but also strengthens the connection between LSM results and effective landslide prevention strategies. Given the higher risks associated with landslides in open-pit mines, the proposed method significantly lowers the threshold for applying LSM in these environments, offering a valuable tool for safeguarding personnel and property.

Neural network approaches for enhanced landslide prediction: a comparative study for Mawiongrim, Meghalaya, India

Neural network approaches for enhanced landslide prediction: a comparative study for Mawiongrim, Meghalaya, India

Landslide hazard mapping in Chefchaouen, Morocco: AHP-GIS integration

ABSTRACT Chefchaouen province, located in northern Morocco, is prone to landslides because of its geological features, climate change, and human activities. We investigated landslide dynamics in this mountainous province using a multi-criteria spatial approach and GIS, applying the Analytical Hierarchy Process (AHP). Our findings identified 1267.877 km2 as low-risk, 1695.334 km2 as moderate-risk, and 904.2071 km2 as high-risk, mainly in the northern and northwestern regions. Forests were the most susceptible at 13.83%, followed by agricultural and bare lands, with water bodies least affected. Contributing factors include deforestation, wildfires, and agricultural practices. Our results highlight the need for targeted risk mitigation and continuous land use monitoring. Strategies like slope stabilisation and reforestation can improve landslide prediction and prevention, enhancing community resilience in Chefchaouen. This study’s innovative approach and insights into landslide prediction and prevention provide valuable knowledge to the field.

Evaluating landslide susceptibility: the impact of resolution and hybrid integration approaches

The present study investigates the effectiveness of various landslide susceptibility machine learning (ML) models at multiple spatial resolutions. Using various conditioning factors, including topography, hydrology, and human influences, the study analyzed the predictive power of single, integrated, and comparative ML models. Alternating Decision Tree (ADT), Forest by Penalizing Attributes (FPA), and Random Forest (RAF), and integrated approaches such as Rotation Forest (RF) and Random Subspace (RS) that were based on ADT and FPA were utilized for the study. All models were trained and validated using a ten-fold cross-validation technique and evaluated by various statistical metrics, across resolutions from 12.5 m to 200 m. Shenmu City in China was chosen as an ideal test site to evaluate the developed methodology. The study reveals that finer spatial resolutions significantly enhance the accuracy of landslide predictions and that integrated models have superior performance over single models. The Frequency Ratio method identified elevation, slope, and hydrological factors as the key predictors concerning landslide occurrences. According to the results the RS-ADT model at a 12.5 m resolution achieved the highest evaluation accuracy (ROC = 0.907). The research highlights the possibility of combining multiple modeling techniques and high-resolution data to improve the predictive accuracy of landslide susceptibility models.

Comparative Analysis of Machine Learning Models and Hybrid Ensemble Approach’s for Landslide Prediction

The NH-44 Jammu Srinagar National Highway in India is susceptible to landslides, rock falls and shooting stones due to its geological characteristics and steep slopes. This study aims to compare the performance of various Machine Learning (ML) algorithms and hybrid models in predicting landslides using historical data. Seven optimized ML approaches Support Vector Classifier (SVC), Logistic Regression (LR), Decision Tree (DT), K Nearest Classifier (KNC), Random Forest (RF), GaussianNB (GNB) and AdaBoost Classifier (ABC) are used. Additionally, two Hybrid Ensemble methods, the Voting Hybrid Model (VHM) and Stacking Hybrid Model (SHM), are introduced. The performance of each model is evaluated using accuracy, precision, recall, F1-score and AUC metrics. Results indicate that all the models performed well, with hybrid ensemble models surpassing all individual algorithms. The Stacking Hybrid Model (SHM) excels achieving 99.4% accuracy and 98.5% AUC, outperforming the Voting Hybrid Model (VHM). Hybrid models consistently outperform individual models in accuracy and AUC. These proposed methods exhibit robustness and enhanced results in addressing this issue. This framework can help to predict the landslides with high accuracy which can save the lives through timely evacuations from high-risk areas.

Landslide predictions through combined rainfall threshold models

Landslide predictions through combined rainfall threshold models

Advancing predictive accuracy of shallow landslide using strategic data augmentation

Rainfall-induced shallow landslides pose one of significant geological hazards, necessitating precise monitoring and prediction for effective disaster mitigation. Most studies on landslide prediction have focused on optimizing machine learning (ML) algorithms, very limited attention has been paid to enhancing data quality for improved predictive performance. This study employs strategic data augmentation (DA) techniques to enhance the accuracy of shallow landslide prediction. Using five DA methods including singular spectrum analysis (SSA), moving averages (MA), wavelet denoising (WD), variational mode decomposition (VMD), and linear interpolation (LI), we utilize strategies such as smoothing, denoising, trend decomposition, and synthetic data generation to improve the training dataset. Four machine learning algorithms, i.e. artificial neural network (ANN), recurrent neural network (RNN), one-dimensional convolutional neural network (CNN1D), and long short-term memory (LSTM), are used to forecast landslide displacement. The case study of a landslide in southwest China shows the effectiveness of our approach in predicting landslide displacements, despite the inherent limitations of the monitoring dataset. VMD proves the most effective for smoothing and denoising, improving R2, RMSE, and MAPE by 172.16%, 71.82%, and 98.9%, respectively. SSA addresses missing data, while LI is effective with limited data samples, improving metrics by 21.6%, 52.59%, and 47.87%, respectively. This study demonstrates the potential of DA techniques to mitigate the impact of data defects on landslide prediction accuracy, with implications for similar cases.

A Machine Learning-Driven Approach to Uncover the Influencing Factors Resulting in Soil Mass Displacement

For most landslides, several destabilising processes act simultaneously, leading to relative sliding along the soil or rock mass surface over time. A number of machine learning approaches have been proposed recently for accurate relative and cumulative landside displacement prediction, but researchers have limited their studies to only a few indicators of displacement. Determining which influencing factors are the most important in predicting different stages of failure is an ongoing challenge due to the many influencing factors and their inter-relationships. In this study, we take a data-driven approach to explore correlations between various influencing factors triggering slope movement to perform dimensionality reduction, then feature selection and extraction to identify which measured factors have the strongest influence in predicting slope movements via a supervised regression approach. Further, through hierarchical clustering of the aforementioned selected features, we identify distinct types of displacement. By selecting only the most effective measurands, this in turn informs the subset of sensors needed for deployment on slopes prone to failure to predict imminent failures. Visualisation of the important features garnered from correlation analysis and feature selection in relation to displacement show that no one feature can be effectively used in isolation to predict and characterise types of displacement. In particular, analysis of 18 different sensors on the active and heavily instrumented Hollin Hill Landslide Observatory in the north west UK, which is several hundred metres wide and extends two hundred metres downslope, indicates that precipitation, atmospheric pressure and soil moisture should be considered jointly to provide accurate landslide prediction. Additionally, we show that the above features from Random Forest-embedded feature selection and Variational Inflation Factor features (Soil heat flux, Net radiation, Wind Speed and Precipitation) are effective in characterising intermittent and explosive displacement.

Feasibility of Coseismic Landslide Prediction Based on GNSS Observations: A Case Study of the 2022 Ms 6.8 Luding, China, Earthquake

Abstract On 5 September 2022, an M 6.8 earthquake struck Luding County in Sichuan Province, China, triggering extensive landslides and causing severe damages. In this study, taking this event as an exemplary case study, we test the feasibility of fast earthquake-induced landslide prediction utilizing Global Navigation Satellite System (GNSS) observations. Particularly, we construct finite-slip models based on static offsets and 1 Hz displacement waveforms. Employing these slip models, physics-based simulation (PBS) is applied separately to obtain peak ground velocity (PGV). The PGVs are then integrated into landslide spatial distribution probability prediction based on the Deep Forest algorithm. Our results show that the predicted landslides probability distribution of fast inversion models using static and high-rate GNSS data align well with the landslide catalog. Furthermore, high-rate GNSS data can improve the model performance by providing the evolution information of rupture. In addition, we also derive PGV from the empirically regressed ground-motion prediction equations (GMPEs) and incorporate it into landslide prediction. The GMPEs exhibits an advantage in terms of prediction recall for landslides and a relatively reduced accuracy compared with the PBS. Despite the inherent uncertainties in this study, based on the case study of the 2022 M 6.8 Luding earthquake, we utilize GNSS data and present a set of methods for real-time landslide prediction. The achieved model performance is relatively satisfactory, considering the challenges and uncertainties involved.

Near real-time spatial prediction of earthquake-triggered landslides based on global inventories from 2008 to 2022

Near real-time prediction of earthquake-triggered landslides can rapidly forecast the spatial distribution of coseismic landslides just after a great earthquake, and provide effective support for emergency response. However, the prediction of earthquake-triggered landslides has always been a great challenge because of low accuracy and high false alarms. This work proposes a novel fuzzy deep learning (FuDL) model for near real-time earthquake-triggered landslide spatial prediction. Fuzzy learning theory is for the first time employed in earthquake-triggered landslide prediction. The FuDL has high generalization and robustness, effectively improving the accuracy of earthquake-triggered landslide prediction. Eighteen earthquake-triggered landslide inventories worldwide from 2008 to 2022 are employed to conduct ETL prediction. According to the chronological order, 15 earthquake-triggered landslides from 2008 to 2018 are adopted to train the FuDL model, and 3 earthquake-triggered landslides from 2019 to 2022 are utilized for near real-time earthquake-triggered landslide prediction. Furthermore, this work reveals that ground movement, relatively steep and high topography, and strong seismic intensity are critical factors affecting the spatial distribution of earthquake-triggered landslides. In addition, this work conducted a detailed analysis of the distribution patterns of earthquake-triggered landslides on a global scale.

Monitoring and disaster prevention of high and steep sandstone slopes along highways under construction

High and steep sandstone slopes along highway line are at high risk of disasters such as landslides, cracking of support structures, and so on. The monitoring, early warning, and emergency response of such slope disaster face enormous challenges, especially during the rainy season. In this paper, intelligent monitoring, early warning and forecasting system were carried out for the high steep sandstone slope with a transmission line tower at the slope crest along the highway under construction in Guangxi, China. The automatic monitoring data, emergency rescue program and rescue effect were analyzed, and emergency rescue measures for high steep slope protection were taken. The research results show that timely access to disaster warning information can effectively support the analysis of disaster causes and the evaluation of disposal programs. Deep-hole monitoring of deformation characteristics can determine the stable state of slopes, and the tangent angle warning criterion can be used for early warning and prediction of high steep slope landslides. By analyzing the location of the sliding surface and taking timely emergency disposal measures such as layered counterpressure method and micropipes, the landslide activities can be effectively controlled to prevent further acceleration of slope collapse. This study can provide an important reference for the monitoring, early warning, forecasting and emergency rescue of sandstone slopes along highways under construction.

Prediction of retrogressive landslide in sensitive clays by incorporating a novel strain softening law into the Material Point Method

Sensitive clays, when subjected to large strains, exhibit a unique strain-softening behavior, transforming into a remolded liquid with remarkably low shear strength. When a slope fails, this behavior leads to the remolded clay moving away from its original position, triggering subsequent failures and catastrophic outcomes. To accurately predict such scenarios, it is crucial to incorporate realistic strain-softening characteristics into the constitutive soil model. This paper presents a novel yet practical strain-softening law developed by the authors that effectively captures the post-peak behavior of sensitive clays down to their remolded strength. The softening law is implemented in an elastoplastic Mohr-Coulomb model and incorporated into Anura3D, an open-source software that uses the Material Point Method to simulate large deformations. The constitutive model is calibrated by simulating the stress-strain behavior through direct shear tests conducted at three sensitive clay landslide locations. The accuracy of the overall numerical framework is assessed by predicting the post-failure movements of these landslides. Notably, two of the landslides, Sainte-Monique (1994) and Saint-Jude (2010), have previously been analyzed using other numerical tools, allowing for a comparative analysis with the method presented here. The third landslide, the Saint-Luc-de-Vincennes landslide, representing a composite flow slide and spread, has been numerically simulated for the first time. The post-failure behavior observed in the landslide events is compared with field observations and other numerical analyses. The results show that the MPM models with the proposed strain-softening law can reasonably predict post-failure retrogression and runout distance, which are crucial parameters for determining the risk of landslides in sensitive clays.