Landslide Susceptibility Models Research Articles

Environmental critical thresholds based on statistical analysis for modelling landslide susceptibility in Continental Basaltic Provinces

Abstract. The study aims to estimate the environmental critical thresholds using statistical approaches to understand the landslide conditioning factors that can trigger landslides in the Continental Basaltic Provinces a landslide-prone area, using as reference the landslides that occurred in an extreme rainfall event. The study area is a region that was the scene of an extreme hydrological event in January 2017, with an accumulated volume of rain of 163.9 mm in 8 hours, causing a widespread event of shallow planar landslides with more than 400 scars detected. Hydrological, anthropic, geological, geomorphological, and topographical features of this region were analyzed considering landslides and non-landslides samples set, and their influence in the event was carried out using the Frequency Ratio method, followed by Pearson's Linear Correlation Coefficient and Linear Regression. The results showed that this process helped us to understand environmental critical thresholds based on classes of conditioning factors that have a greater influence on rainfall-triggered landslide occurrences and, consequently, higher predictive capacity in the landslide susceptibility models with the same geoenvironmental parameters which is a valuable insight for risk management.

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.

Multi-hazard modeling of erosion and landslide susceptibility at the national scale in the example of North Macedonia

Abstract Due to favorable natural conditions and human impact, the territory of North Macedonia is very susceptible to natural hazards. Steep hillslopes combined with soft rocks (schists on the mountains; sands and sandstones in depressions), erodible soils, semiarid continental climate, and sparse vegetation cover give a high potential for soil erosion and landslides. For this reason, this study presents a multi-hazard approach to geohazard modeling on the national extent in the example of North Macedonia. Utilizing Geographic Information Systems, relevant data about the entire research area were employed to analyze and assess soil erosion and susceptibility to landslides and identify areas prone to both hazards. Using the Gavrilović Erosion Potential Method (EPM), an average value of 0.36 was obtained for the erosion coefficient Z, indicating low to moderate susceptibility to erosion. However, a significant area of the country (9.6%) is susceptible to high and excess erosion rates. For the landslide susceptibility assessment (LSA), the Analytical hierarchy process approach is combined with the statistical method (frequency ratio), showing that 29.3% of the territory belongs to the zone of high and very high landslide susceptibility. Then, the accuracy assessment is performed for both procedures (EPM and LSA), showing acceptable reliability. By overlapping both models, a multi-hazard map is prepared, indicating that 22.3% of North Macedonia territory is highly susceptible to erosion and landslides. The primary objective of multi-hazard modeling is to identify and delineate hazardous areas, thereby aiding in activities to reduce the hazards and mitigate future damage. This becomes particularly significant when considering the impact of climate change, which is associated with increased landslide and erosion susceptibility. The approach based on a national level presented in this work can provide valuable information for regional planning and decision-making processes.

Benchmarking data handling strategies for landslide susceptibility modeling using random forest workflows

Machine learning (ML) algorithms are frequently used in landslide susceptibility modeling. Different data handling strategies may generate variations in landslide susceptibility modeling, even when using the same ML algorithm. This research aims to compare the combinations of inventory data handling, cross validation (CV), and hyperparameter tuning strategies to generate landslide susceptibility maps. The results are expected to provide a general strategy for landslide susceptibility modeling using ML techniques. The authors employed eight landslide inventory data handling scenarios to convert a landslide polygon into a landslide point, i.e., the landslide point is located on the toe (minimum height), on the scarp (maximum height), at the center of the landslide, randomly inside the polygon (1 point), randomly inside the polygon (3 points), randomly inside the polygon (5 points), randomly inside the polygon (10 points), and 15 m grid sampling. Random forest models using CV–nonspatial hyperparameter tuning, spatial CV–spatial hyperparameter tuning, and spatial CV–forward feature selection–no hyperparameter tuning were applied for each data handling strategy. The combination generated 24 random forest ML workflows, which are applied using a complete inventory of 743 landslides triggered by Tropical Cyclone Cempaka (2017) in Pacitan Regency, Indonesia, and 11 landslide controlling factors. The results show that grid sampling with spatial CV and spatial hyperparameter tuning is favorable because the strategy can minimize overfitting, generate a relatively high-performance predictive model, and reduce the appearance of susceptibility artifacts in the landslide area. Careful data inventory handling, CV, and hyperparameter tuning strategies should be considered in landslide susceptibility modeling to increase the applicability of landslide susceptibility maps in practical application.

A QGIS framework for physically-based probabilistic modelling of landslide susceptibility: QGIS-FORM

A QGIS framework for physically-based probabilistic modelling of landslide susceptibility: QGIS-FORM

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.

An updated landslide susceptibility model and a log-Gaussian Cox process extension for Scotland

AbstractAt the time of its development, GeoSure was created using expert knowledge based on a thorough understanding of the engineering geology of the rocks and soils of Great Britain. The ability to use a data-driven methodology to develop a national-scale landslide susceptibility was not possible due to the relatively small size of the landslide inventory at the time. In the intervening 20 years, the National Landslide Database has grown from around 6000 points to over 18,000 records today and continues to be added to. With the availability of this additional inventory, new data-driven solutions could be utilised. Here, we tested a Bernoulli likelihood model to estimate the probability of debris flow occurrence and a log-Gaussian Cox process model to estimate the rate of debris flow occurrence per slope unit. Scotland was selected as the test site for a preliminary experiment, which could potentially be extended to the whole British landscape in the future. Inference techniques for both of these models are applied within a Bayesian framework. The Bayesian framework can work with the two models as additive structures, which allows for the incorporation of spatial and covariate information in a flexible way. The framework also provides uncertainty estimates with model outcomes. We also explored consideration on how to communicate uncertainty estimates together with model predictions in a way that would ensure an integrated framework for master planners to use with ease, even if administrators do not have a specific statistical background. Interestingly, the spatial predictive patterns obtained do not stray away from those of the previous GeoSure methodology, but rigorous numerical modelling now offers objectivity and a much richer predictive description.

Fatal landslides in Kencho, Shacha & Gozdi villages, Gofa zone, Ethiopia: A detailed investigation (Geological, Geotechnical, geophysical & geospatial) of the July 22, 2024 catastrophe and its socioeconomic repercussions

A landslide is one of the geological hazards that cause the most disaster in densely populated areas. The landslide that occurred in Gezie Gofa woreda, Gofa Zone, Kencho Shacha Gozdi village, killed more than 250 people. Two landslides occurred on July 22, 2024, at 8:30 and 10:40 AM The first landslide killed six people and demolished three houses. The second landslide killed more than 245 people, including those who came to the site to excavate the buried bodies during the first landslide. The primary objective of this research is to evaluate the landslide causative factors, model the landslide susceptibility, and characterize the landslide disaster on socioeconomic effects that occurred on July 22, 2024. The landslide inventory data, field surveys, laboratory analyses, and various geophysical surveys characterized the current and past landslides of the area. The landslide susceptibility model was modeled using a statistical approach in the GIS. environment. The socioeconomic effects were assessed using field surveys and systematic interviews with the victims. The conditioning factors selected for landslide susceptibility modeling are lithology, geological structures, groundwater, slope, land use or land cover, aspect, curvature, and elevation. The major triggering factor of the landslide in the area was heavy rainfall, which occurred on July 21–22, 2024, between 3:00 a.m.-8:30 a.m. The results reveal that the significant conditioning factors of the landslide in the study area are geological structures (both visible and inferred), groundwater, slopes, and human activities. The characterized socioeconomic effects include the destruction of agricultural land, the demolishing of houses, and the loss of human lives, as well as several people evacuated and sheltered under tents and churches. However, the most momentous disaster in the area is the loss of human life. Based on the research results, it would be better to relocate those people living in the high landslide susceptible zones, and all high landslide-prone areas and mountainous terrain in southern Ethiopia should be mapped, and the people should be aware of the landslide risk areas.

Sample size effects on landslide susceptibility models: A comparative study of heuristic, statistical, machine learning, deep learning and ensemble learning models with SHAP analysis

In landslide susceptibility assessment (LSA), inventory incompleteness impacts the accuracy of different models to varying degrees. However, this area remains under-researched. This study investigated six LSA models from heuristic, statistical, machine learning and ensemble learning models (analytical hierarchy process (AHP), frequency ratio (FR), logistic regression (LR), Keras based deep learning (KBDL), XGBoost, and LightGBM) across six different sample sizes (100%, 90%, 75%, 50%, 25%, and 10%). Results revealed that XGBoost and LightGBM consistently outperformed other models across all sample sizes. The LR and KBDL models followed, while FR model was the most affected by sample size variations. AHP, an empirical model, remained unaffected by sample size. Through SHapley Additive exPlanations (SHAP) analysis, elevation, NDVI, slope, land use, and distance to roads and rivers emerged as pivotal indicators for landslide occurrences in the study area, suggesting that human activities significantly influence these events. Five time-varying indicators regarding human activity and climate validated this inference, which provides a new method to identify landslide triggering factors, especially in areas of intense human activity. Based on the findings, a comprehensive framework for LSA is proposed to assist landslide managers in making informed decisions. Future research should focus on expanding model diversity to address the effects of sample size, enhancing the adaptability of the LSA framework, deepening the analysis of human activity impacts on landslides using explainable machine learning techniques, addressing temporal inventory incompleteness in LSA, and critically evaluating model sensitivity to sample size variations across multiple disciplines.

Parsimonious High‐Resolution Landslide Susceptibility Modeling at Continental Scales

AbstractLandslide susceptibility maps are fundamental tools for risk reduction, but the coarse resolution of current continental‐scale models is insufficient for local application. Complex relations between topographic and environmental attributes characterizing landslide susceptibility at local scales are not transferrable across areas without landslide data. Existing maps with multiple susceptibility classifications under‐represent landslide potential in moderate and gently sloping terrain. We leverage an extensive landslide database (N = 613,724), a high‐resolution digital elevation model (10‐m), and high‐performance computing resources, to develop a new nationwide susceptibility map for the contiguous United States, Hawaii, Alaska, and Puerto Rico. We calculate four alternative linear and nonlinear thresholds of topographic slope and relief using an objective split‐sample calibration. We down‐sample our results to a 90‐m grid to account for uncertainty in the digital elevation model and landslide position, and evaluate these thresholds' ability to differentiate areas of greater susceptibility. The less conservative nonlinear model optimally balances our priorities of capturing observed landslides (99%) while minimizing area covered by susceptible terrain (43%). Independent evaluation with four statewide landslide inventories (N = 172,367) reinforces our model selection but highlights spatially variable performance. Therefore, we propose a novel approach to susceptibility classification using the concentration of landslide‐prone terrain within each down‐sampled grid. While landslides are possible within any cells containing susceptible terrain, those with the highest concentration capture the majority of observed landslides. Our new map characterizes landside susceptibility more consistently than prior models; our transparent classification approach also provides flexibility for accommodating different tolerances in risk reduction measures.

GIS-based spatial modeling of landslide susceptibility using BWM-LSI: A case study – city of Smederevo (Serbia)

Abstract Landslides and slope processes constitute one of the most frequent natural hazards in valleys near major rivers and mountainous regions. The surface layer, characterized by its relatively loose composition, is prone to sliding due to a combination of distinct natural and human-related factors. Specific sections along the right bank of the Danube River in Smederevo city exhibit significant susceptibility to landslide activation, often leading to substantial material losses and posing a risk to the local population. The initial step in the provided research involves analyzing existing literature and mapping landslides within the study area. The initial analysis covers both natural conditions and anthropogenic activities. The second step includes establishing a geospatial database in the Geographic Information System and generating eight thematic maps. In the third step, different weight coefficients were assigned to the criteria, which facilitated the creation of the Landslide Susceptibility Index using the Best–Worst Method. Subsequently, in the fourth step, a composite map illustrating landslide susceptibility was produced. According to this research, about 4% of the territory of Smederevo, or 19.3 km2, is highly or very highly susceptible to landslides. These localities are located on the right bank of the Danube River and around the Ralja River. Receiver operating characteristic-area under the curve value indicates very high predictive power (approximately 1), thus suggesting the reliability of the used methodology. This visualization of areas highly prone to such occurrences empowers policymakers to implement more effective environmental protection measures and institute sustainable management practices for agricultural parcels in this region. Also, the provided research represents the inaugural integration of advanced remote sensing techniques and interdisciplinary investigations, offering deeper insights into landslide activity in the study area and yielding more comprehensive results.

An update on the landslide inventory and susceptibility modelling in the Illawarra with an analysis of the 2022 rainfall events

An update on the landslide inventory and susceptibility modelling in the Illawarra with an analysis of the 2022 rainfall events

A Novel Dataset Replenishment Strategy Integrating Time-Series InSAR for Refined Landslide Susceptibility Mapping in Karst Regions

The accuracy of landslide susceptibility mapping is influenced by the quality of sample data, factor systems, and assessment methods. This study aims to enhance the representativeness and overall quality of the sample dataset through an effective sample expansion strategy, achieving greater precision and reliability in the landslide susceptibility model. An integrated interpretative framework for landslide susceptibility assessment is developed using the XGBoost-SHAP-PDP algorithm to deeply investigate the key contributing factors of landslides in karst areas. Firstly, 17 conditioning factors (e.g., surface deformation rate, land surface temperature, slope, lithology, and NDVI) were introduced based on field surveys, satellite imagery, and literature reviews, to construct a landslide susceptibility conditioning factor system in line with karst geomorphology characteristics. Secondly, a sample expansion strategy combining the frequency ratio (FR) with SBAS-InSAR interpretation results was proposed to optimize the landslide susceptibility assessment dataset. The XGBoost algorithm was then utilized to build the assessment model. Finally, the SHAP and PDP algorithms were applied to interpret the model, examining the primary contributing factors and their influence on landslides in karst areas from both global and single-factor perspectives. Results showed a significant improvement in model accuracy after sample expansion, with AUC values of 0.9579 and 0.9790 for the training and testing sets, respectively. The top three important factors were distance from mining sites, lithology, and NDVI, while land surface temperature, soil erosion modulus, and surface deformation rate also significantly contributed to landslide susceptibility. In summary, this paper provides an in-depth discussion of the effectiveness of LSM in predicting landslide occurrence in complex terrain environments. The reliability and accuracy of the landslide susceptibility assessment model were significantly improved by optimizing the sample dataset within the karst landscape region. In addition, the research results not only provide an essential reference for landslide prevention and control in the karst region of Southwest China and regional central engineering construction planning but also provide a scientific basis for the prevention and control of geologic hazards globally, showing a wide range of application prospects and practical significance.

Comprehensive spatial analysis landslide susceptibility modelling, spatial cluster analysis and priority zoning for environment analysis

Comprehensive spatial analysis landslide susceptibility modelling, spatial cluster analysis and priority zoning for environment analysis

Improving generalization performance of landslide susceptibility model considering spatial heterogeneity by using the geomorphic label-based LightGBM

Improving generalization performance of landslide susceptibility model considering spatial heterogeneity by using the geomorphic label-based LightGBM

A Comprehensive Comparison of Stable and Unstable Area Sampling Strategies in Large-Scale Landslide Susceptibility Models Using Machine Learning Methods

A Comprehensive Comparison of Stable and Unstable Area Sampling Strategies in Large-Scale Landslide Susceptibility Models Using Machine Learning Methods

A global-scale applicable framework of landslide dam formation susceptibility

The formation and failure of landslide dams is an important and understudied, multi-hazard topic. A framework of landslide dam formation susceptibility evaluation was designed for large-scale studies to avoid the traditional dependence on landslide volume calculations based on empirical relationships, which requires comprehensive local inventories of landslides and landslide dams. The framework combines logistic regression landslide susceptibility models and global fluvial datasets and was tested in Italy and Japan based on landslide and landslide dam inventories collected globally. The final landslide dam formation susceptibility index identifies which river reach is most prone to landslide dam formation, based on the river width and the landslide susceptibility in the adjacent delineated slope drainage areas. The logistic regression models showed good performances with area under the receiver operating characteristics curve values of 0.89 in Italy and 0.74 in Japan. The index effectively identifies the probability of landslide dam formation for specific river reaches, as demonstrated by the higher index values for river reaches with past landslide dam records. The framework is designed to be applied globally or for other large-scale study regions, especially for less studied data-scarce regions. It also provides a preliminary evaluation result for smaller catchments and has the potential to be applied at a more detailed scale with local datasets.

Landslide Susceptibility Modelling of Central Highland Part of Chaliyar River Basin, Kerala, India with Integrated Algorithms of Frequency Ratio and Shannon Entropy

An integrated landslide susceptibility analysis is carried out for the central highland region of the Chaliyar River Basin in Kerala, India using bivariate statistical methods, namely the Frequency Ratio (FR) and Shannon Entropy (SE). The study addresses the complex nature of landslides, influenced by natural as well as anthropogenic factors, with specific focus on assessing the landslide likelihood of the study area. The methodology involves a systematic approach of collecting the inventory data, identifying various landslide causative factors and developing their corresponding thematic maps, spatial analysis of landslide occurrence and causative factors using GIS software and generation of Landslide Susceptibility Model (LSM) employing FR and SE algorithm, followed by model validation. Various causative factors considered for the study include slope angle, slope aspect, slope curvature, elevation, lithology, drainage density, landuse and landcover (LULC), Topographic Wetness Index (TWI) and Normalized Difference Vegetation Index (NDVI). The FR and SE algorithm enable the spatial classification of the study area into four landslide susceptibility categories namely Low, Moderate, High, and Very High. Validation of both the LSMs was carried out using Landslide Density Index (LDI) and Area Under the Curve (AUC) methods. LDI demonstrate a positive fit for both the models, which is indicative of reliability of the susceptibility predictions of the study area. A slightly higher AUC value of SE model is an indication of a high accuracy rate of SE model over FR model. This research brings out a robust methodology for predicting and identifying the landslide risks of the study area.The outcomes of this study will help in developing effective strategies to manage the landslide hazards in geologically vulnerable areas. Keywords: Landslide Susceptibility, Landslide Conditioning Factors, Frequency Ratio, Shannon Entropy, Landslide Density Index(LDI), Area Under the Curve (AUC)

Leveraging Artificial Neural Networks for Robust Landslide Susceptibility Mapping: A Geospatial Modeling Approach in the Ecologically Sensitive Nilgiri District, Tamil Nadu

Landslides pose a significant threat to the lives and livelihoods of marginalised communities residing in rural areas and the delicate ecological balance of the environment. Implementing advanced technologies is crucial for improving hazard risk assessment and enhancing preparedness measures in regions characterised by diverse topography and complex geological formations. Geospatial applications and modelling techniques have emerged as indispensable in mitigating landslide risks, particularly in environmentally sensitive areas. This study presents a comprehensive approach to landslide susceptibility mapping in the Nilgiri District of Tamil Nadu, India, leveraging the power of Artificial Neural Networks (ANNs) and integrating multi-dimensional geospatial datasets. Integrating ANN-based modelling and geospatial techniques offers significant advantages in terms of statistical robustness, reproducibility, and the ability to analyse the complex interplay of factors influencing landslide hazards quantitatively. The methodology involves rigorous pre-processing and integrating spatial data, including landslide event occurrences as the dependent variable and ten independent parameters influencing landslide susceptibility. These parameters encompass elevation, slope aspect, slope degree, distance to roads, land use patterns, geomorphology, lithology, drainage density, lineament density, and rainfall distribution. Feature extraction and selection techniques are employed to effectively model the complex interactions between these factors and landslide occurrences. This process identifies the most relevant variables influencing landslide susceptibility, enhancing the model's predictive capabilities. The state-of-the-art ANNs are trained using historical landslide occurrence data and the selected influencing factors, enabling the development of a robust and accurate landslide susceptibility model. The performance of the developed model is rigorously evaluated using a comprehensive suite of metrics, including accuracy, precision, and the Area under the Receiver Operating Characteristic (ROC) curve. Preliminary results indicate that the ANN-based landslide susceptibility model outperforms traditional zonation methods, demonstrating higher accuracy and reliability in predicting landslide-prone areas. The resulting Landslide Susceptibility Map (LSM) categorises the study area into five distinct hazard zones, ranging from very high (664.1 km2), high (598.9 km2), moderate (639.7 km2), low (478.9 km2) and to very low (170.9 km2) . Notably, the eastern and central regions of the district emerge as particularly vulnerable to landslide occurrences. The study's findings have far-reaching implications for disaster risk reduction efforts, land-use planning, and sustainable development strategies in the ecologically sensitive Nilgiri District and beyond.

Interferometric Synthetic Aperture Radar (InSAR)-Based Absence Sampling for Machine-Learning-Based Landslide Susceptibility Mapping: The Three Gorges Reservoir Area, China

The accurate prediction of landslide susceptibility relies on effectively handling landslide absence samples in machine learning (ML) models. However, existing research tends to generate these samples in feature space, posing challenges in field validation, or using physics-informed models, thereby limiting their applicability. The rapid progress of interferometric synthetic aperture radar (InSAR) technology may bridge this gap by offering satellite images with extensive area coverage and precise surface deformation measurements at millimeter scales. Here, we propose an InSAR-based sampling strategy to generate absence samples for landslide susceptibility mapping in the Badong–Zigui area near the Three Gorges Reservoir, China. We achieve this by employing a Small Baseline Subset (SBAS) InSAR to generate the annual average ground deformation. Subsequently, we select absence samples from slopes with very slow deformation. Logistic regression, support vector machine, and random forest models demonstrate improvement when using InSAR-based absence samples, indicating enhanced accuracy in reflecting non-landslide conditions. Furthermore, we compare different integration methods to integrate InSAR into ML models, including absence sampling, joint training, overlay weights, and their combination, finding that utilizing all three methods simultaneously optimally improves landslide susceptibility models.