Landslide Conditioning Factors Research Articles

Advancements in mapping landslide susceptibility in Bafoussam and its surroundings area using multi-criteria decision analysis, statistical methods, and machine learning models

Landslides pose a significant threat to lives and socio-economic stability globally. In this study, we conducted a comprehensive landslide susceptibility mapping (LSM) in the western region of Cameroon, focusing on Bafoussam and its surroundings. The integration of multi-criteria decision analysis models (AHP), statistical methods (Information Value IV, Shannon Entropy SE, Frequency Ratio FR), and machine learning algorithms (Naïve Bayes and Logistic Regression) provided a robust assessment of landslide risk. Our analysis, based on 54 recorded landslides, carefully selected Landslide Conditioning Factors (LCF), and influential parameters such as lithology, slope, altitude, and precipitation, resulted in susceptibility maps categorizing the area into five risk zones. The Spatial distribution shows the centre and northwestern regions as high-risk areas. Model sensitivity differences underscore the need for tailored LSM selection. Validation using the Area Under Curve/Receiver Operating Characteristics (AUC/ROC) method indicates the LR and NB methods have the highest accuracy (82.7% and 84.1%, respectively). Comparative analysis of landslide events in Gouaché, Sichuan, Souk Ahras, and Kekem reveals correlations between heavy rainfall and geological conditions. The study supplies valuable insights for decision-makers in landslide-prone areas, emphasizing the importance of integrating multiple methodologies for comprehensive risk assessment and management.

Hybrid Integration of Bagging and Decision Tree Algorithms for Landslide Susceptibility Mapping

Landslides represent a significant global natural hazard, threatening human settlements and the natural environment. The primary objective of the study was to develop a landslide susceptibility modeling approach that enhances prediction accuracy and informs land-use planning decisions. The study utilized a hybrid ensemble-based methodology to improve prediction accuracy and effectively capture the complexity of landslide susceptibility patterns. This approach harnessed the power of ensemble models, employing a bagging algorithm with base learners, including the reduced error pruning decision tree (REPTree) and functional tree (FT) models. Ensemble models are particularly valuable because they combine the strengths of multiple models, enhancing the overall performance and robustness of the landslide susceptibility prediction. The study focused on Yanchuan County, situated within the hilly and gully region of China’s Loess Plateau, known for its susceptibility to landslides, using sixteen critical landslide conditioning factors, encompassing topographic, environmental, and geospatial variables, namely elevation, slope, aspect, proximity to rivers and roads, rainfall, the normalized difference vegetation index, soil composition, land use, and more. Model performances were evaluated and verified using a range of metrics, including receiver operating characteristic (ROC) curves, trade-off statistical metrics, and chi-square analysis. The results demonstrated the superiority of the integrated models, particularly the bagging FT (BFT) model, in accurately predicting landslide susceptibility, as evidenced by its high area under the curve area (AUC) value (0.895), compared to the other models. The model excelled in both positive predictive rate (0.847) and negative predictive rate (0.886), indicating its efficacy in identifying landslide and non-landslide areas and also in the F-score metric with a value of 0.869. The study contributes to the field of landslide risk assessment, offering a significant investigation tool for managing and mitigating landslide hazards in Yanchuan County and similar regions worldwide.

Seismic landslide susceptibility assessment using principal component analysis and support vector machine

Seismic landslides are dangerous natural hazards that can cause immense damage to human lives and property. Susceptibility assessment of earthquake-triggered landslides provides the scientific basis and theoretical foundation for disaster emergency management in engineering projects. However, landslide susceptibility assessment requires a massive amount of historical landslide data. Evidence of past landslide activities may be lost due to changes in geographical conditions and human factors over time. The lack of landslide data poses difficulties in assessing landslide susceptibility. The aim of this study is to establish a generalized seismic landslide susceptibility assessment model for applying it to the Dayong highway in the Chenghai area, where earthquakes occur frequently but with a lack of landslide data. The landslide data used comes from the 2014 Ludian Ms (Surface wave magnitude) 6.5 earthquake in a region with geographical conditions similar to those in the Chenghai area. The influencing factors considered include elevation, slope, slope aspect, distance to streams, distance to faults, geology, terrain wetness index, normalized difference vegetation index, epicenter distance and peak ground acceleration. The frequency ratio method is used to eliminate influencing factors with poor statistical dispersion of landslides. Principal component analysis (PCA) is utilized to reduce the dimensionality of landslide conditioning factors and to improve the transferability of the assessment model to different regions. A support vector machine model is used to establish the susceptibility assessment model. The results show that the accuracy of the PCA–SVM model reaches 93.6%. The landslide susceptibility of the Chenghai area is classified into 5 classes, with the “Very high” landslide susceptibility class accounting for 0.63%. The 13-km section in the middle of the Dayong highway, which accounts for 8.9%, is identified as the high-risk area most obviously impacted by seismic landslides. This study provides a new approach for seismic landslide susceptibility assessment in areas lacking in landslide inventory data.

A novel deep learning framework for landslide susceptibility assessment using improved deep belief networks with the intelligent optimization algorithm

This research proposed a novel deep learning framework that combines the Laplace function sparse regularized continuous deep belief network (LSCDBN) and the Gray Wolf Optimization Algorithm (GWO) and the Whale Optimization Algorithm (WOA), to perform landslide susceptibility assessment. This framework mitigates the challenges of feature homogenization for continuous input variables for landslide condition factors, limited landslide samples, and local optima in the training process. To facilitate this investigation, a meticulous compilation of existing landslide occurrences was used to create a database comprising 18 landslide conditioning factors. To compare the performance of the model, a set of statistical indicators was employed. The results demonstrate the superior performance of both the LSCDBN-GWO model (AUC = 0.952, RMSE = 0.182) and LSCDBN-WOA model (AUC = 0.964, RMSE = 0.174) when compared to the alone LSCDBN model (AUC = 0.913, RMSE = 0.291). It is noteworthy that the performance of the LSCDBN model outperformed that of lone machine learning models (SVM, BP, RF, and LR), lone deep learning models (RNN and CNN), and hybrid deep learning models (CNN-GWO and CNN-WOA). Therefore, it is evident that the proposed LSCDBN-WOA framework can generate models that are optimally suited for landslide susceptibility assessment.

LCFSTE: Landslide Conditioning Factors and Swin Transformer Ensemble for Landslide Susceptibility Assessment

LCFSTE: Landslide Conditioning Factors and Swin Transformer Ensemble for Landslide Susceptibility Assessment

Landslide susceptibility mapping with feature fusion transformer and machine learning classifiers incorporating displacement velocity along Karakoram highway

The Karakoram Highway (KKH) is a pivotal gateway within the framework of the China-Pakistan Economic Corridor. Nevertheless, its distinct and intricate geographical characteristics make it susceptible to recurrent landslides. As an essential tool, landslide susceptibility mapping (LSM) is significant in managing and alleviating landslides near the KKH. Moreover, landslide conditioning factors (LCFs) are crucial determinants influencing the outcomes of LSM. However, existing methods primarily rely on machine learning algorithms, which do not adequately account for the intricate spatial characteristics and patterns between LCFs and landslide occurrences. In response, this study introduces the feature fusion transformer (FFTR) module, constructed based on the foundations of the transformer framework, to fuse the spatial information features of all LCFs. Subsequently, the abstract high-level spatial features obtained are fed into diverse machine learning classifiers, including random forest (RF), extreme gradient boosting (XGBoost), gradient boosting decision trees (GBDT), categorical boosting (CatBoost), and extremely randomized trees (ET), to generate landslide susceptibility maps. Displacement velocity calculated by Persistent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR) is incorporated in the LSM. The results demonstrate that FFTR-RF achieves premium performance in the area under the curve (AUC) (94%), accuracy (87.31%), precision (87.21%), recall (88.02%), and F1-score (87.61%). Incorporating displacement velocity into LSM results predicted by models enhances the comprehensiveness of LSM. These methods will furnish early warning systems for landslide disasters along the KKH, thus aiding recommendations for mitigating landslides’ social and economic losses.

GIS-based landslide susceptibility mapping using logistic regression, random forest and decision and regression tree models in Chattogram District, Bangladesh

The frequency of landslides and related economic and environmental damage has increased in recent decades across the hilly areas of the world, no exception is Bangladesh. Considering the first step in landslide disaster management, different methods have been applied but no methods found as best one. As a result, landslide assessment using different methods in different geographical regions has significant importance. The research aims to prepare and evaluate landslide susceptibility maps (LSMs) of the Chattogram district using three machine learning algorithms of Logistic Regression (LR), Random forest (RF) and Decision and Regression Tree (DRT). Sixteen landslide conditioning factors were determined considering topographic, hydro-climatic, geologic and anthropogenic influence. The landslide inventory database (255 locations) was randomly divided into training (80 %) and testing (20 %) sets. The LSMs showed that almost 9–12 % of areas of the Chattogram district are highly susceptible to landslides. The highly susceptible zones cover the Chattogram district's hill ranges where active morphological processes (erosion and denudation) are dominant. The ROC values for training data were 0.943, 0.917 and 0.947 and testing data were 0.963, 0.934 and 0.905 for LR, RF and DRT models, respectively. The accuracy is higher than the previous research in comparison to the extent of the study area and the size of the inventory. Among the models, LR showed the highest prediction rate and DRT showed the highest success rate. According to susceptibility zones, DRT is the more realistic model followed by LR. The maps can be applied at the local scale for landslide hazard management.

Frequency ratio analysis to determine the landslide susceptibility in East Sikkim district of Indian Himalayan region

Landslides are a significant natural disaster causing damage to many mountainous regions worldwide including the Indian Himalayan region. In the East Sikkim district of the Eastern Himalayas, the most used bivariate frequency ratio (FR) model was utilized with high-resolution satellite imagery to understand the susceptibility of the region to landslides. Conditioning factors such as slope aspect, slope angle, slope curvature, drainage density, land use and land cover (LULC), normalized difference vegetation index (NDVI), lithology, and geomorphology were considered in the analysis. LULC is the most crucial factor contributing to landslide susceptibility with a normalized FR value of 14.1. Slope and geomorphology followed closely with values of 12.5 and 11.8 respectively. In contrast, the least important factors were slope aspect and lithology with values of 8.7 and 9.3 respectively. These results can be used to prioritize landslide conditioning factors (LCF) and generate a final landslide susceptibility map (LSM). By adding the values of all LCFs, a landslide susceptibility index was obtained, and the LSM was zoned into high, medium, and low susceptibility classes covering 23.4%, 44.4%, and 32.2% of the study area respectively. The validity of the method used was confirmed using a receiver operating characteristic curve which yielded an accuracy of 78%. The findings highlight the importance of LULC, slope, and geomorphology as critical factors in landslide susceptibility in the East Sikkim district of the Eastern Himalayas.

Framework for risk assessment of economic loss from structures damaged by rainfall-induced landslides using machine learning

ABSTRACT Given the increased frequency of extreme rainfall events, pre-disaster countermeasures against landslides triggered by heavy rainfall are important to enhance disaster resilience. This study presents a methodology for economic risk assessment of structures affected by rainfall-induced landslides using machine learning (ML). Random Forest and LightGBM algorithms were applied to develop ML-based landslide prediction models considering the spatial distributions of landslide conditioning and triggering factors. The rainfall index was calculated considering the temporal variation in rainfall and was used as a feature associated with rainfall intensity. The rainfall hazard curve, representing the relationship between the rainfall index and its annual exceedance probability, was statistically estimated using a generalised extreme value distribution. Rainfall-induced landslide susceptibility was assessed using an ML-based landslide prediction model and rainfall hazard curve. Finally, the risk curve associated with the economic loss from structures damaged by rainfall-induced landslides was estimated based on landslide susceptibility and structure distribution maps. In this study, LightGBM showed better prediction performance for evaluating rainfall-induced landslide susceptibility than Random Forest. An illustrative example is presented to demonstrate that the proposed methodology can be used to develop an appropriate risk-based disaster mitigation strategy.

Uncertainties of landslide susceptibility prediction: Influences of random errors in landslide conditioning factors and errors reduction by low pass filter method

In the existing landslide susceptibility prediction (LSP) models, the influences of random errors in landslide conditioning factors on LSP are not considered, instead the original conditioning factors are directly taken as the model inputs, which brings uncertainties to LSP results. This study aims to reveal the influence rules of the different proportional random errors in conditioning factors on the LSP uncertainties, and further explore a method which can effectively reduce the random errors in conditioning factors. The original conditioning factors are firstly used to construct original factors-based LSP models, and then different random errors of 5%, 10%, 15% and 20% are added to these original factors for constructing relevant errors-based LSP models. Secondly, low-pass filter-based LSP models are constructed by eliminating the random errors using low-pass filter method. Thirdly, the Ruijin County of China with 370 landslides and 16 conditioning factors are used as study case. Three typical machine learning models, i.e. multilayer perceptron (MLP), support vector machine (SVM) and random forest (RF), are selected as LSP models. Finally, the LSP uncertainties are discussed and results show that: (1) The low-pass filter can effectively reduce the random errors in conditioning factors to decrease the LSP uncertainties. (2) With the proportions of random errors increasing from 5% to 20%, the LSP uncertainty increases continuously. (3) The original factors-based models are feasible for LSP in the absence of more accurate conditioning factors. (4) The influence degrees of two uncertainty issues, machine learning models and different proportions of random errors, on the LSP modeling are large and basically the same. (5) The Shapley values effectively explain the internal mechanism of machine learning model predicting landslide susceptibility. In conclusion, greater proportion of random errors in conditioning factors results in higher LSP uncertainty, and low-pass filter can effectively reduce these random errors.

High resolution landslide susceptibility mapping using ensemble machine learning and geospatial big data

Landslide susceptibility represents the potential of slope failure for given geo-environmental conditions. The existing landslide susceptibility maps suffer from several limitations, such as being based on limited data, heuristic methodologies, low spatial resolution, and small areas of interest. In this study, we overcome all these limitations by developing a probabilistic framework that combines imbalance handling and ensemble machine learning for landslide susceptibility mapping. We employ a combination of One -Sided Selection and Support Vector Machine Synthetic Minority Oversampling Technique (SVMSMOTE) to eliminate class imbalance and develop smaller representative data from big data for model training. A blending ensemble approach using hyperparameter tuned Artificial Neural Networks, Random Forests, and Support Vector Machine, is employed to reduce the uncertainty associated with a single model. The methodology provides the landslide susceptibility probability and a landslide susceptibility class. A thorough evaluation of the framework is performed using receiver operating characteristic curves, confusion matrices, and the derivatives of confusion matrices. This framework is used to develop India's first national-scale machine learning based landslide susceptibility map. The landslide database is carefully curated from global and local inventories, and the landslide conditioning factors are selected from a multitude of geophysical and climatological variables. The Indian Landslide Susceptibility Map (ILSM) is developed at a resolution of 0.001° (∼100 m) and is classified into five classes: very low, low, medium, high, and very high. We report an accuracy of 95.73 %, sensitivity of 97.08 %, and matthews correlation coefficient (MCC) of 0.915 on test data, demonstrating the accuracy, robustness, and generalizability of the framework for landslide identification. The model classified 4.75 % area in India as very highly susceptible to landslides and detected new landslide susceptible zones in the Eastern Ghats, hitherto unreported in the government landslide records. The ILSM is expected to aid policymaking in disaster risk reduction and developing landslide prediction models.

Comparative Analysis of Future Landslide Susceptible Areas Based on Climate Change Scenario Applications

Background and objective: Landslides have inflicted significant damage to human lives and property for many years, leading to substantial socio-economic costs and environmental degradation. With the advent of climate change, the increase and intensification of rainfall exacerbate the risk of landslides. Considering this scenario, understanding the priorities in landslide response becomes crucial. This study aims to compare methods of predicting future landslide-prone areas, explore accurate forecasting techniques, and determine the landslide response priorities at the municipal level in the study Methods: (1) Collection and development of the landslide inventory map and landslide conditioning factors. (2) Constructing the landslide susceptibility model (LSM) using the landslide inventory map and conditioning factors. (3) Projecting rainfall data from periods B and C onto the LSM of past period A. (4) Comparing and analyzing landslide-prone areas for each scenario and year. (5) Identifying areas vulnerable to landslides based on the scenario with the most frequent occurrence of landslide-prone areas during the rainy seasons in periods B and C.Results: From the LSM, the landslide susceptible area (LSA) for period A was identified as 31,902 ㎢. All Supply-side platform(SSP) scenarios displayed an increasing trend in landslide-prone areas, with the SSP5-8.5 scenario displaying the most significant increase. Taking this into consideration, landslide response priorities were established, with Goseong County in South Gyeongsang ranking first with an LSA ratio of 88.4%. This suggests that this area should be prioritized for future landslide risk mitigation.Conclusion: The study provides a foundational model for future landslide response strategies which consider environmental changes. limitations of the study were challenges in considering landslide conditioning factors other than rainfall when analyzing future landslide susceptibility. Future studies will aim to provide more reliable information through higher resolution analysis and damage scale predictions and to discern response priorities.

A GIS-based multi-objective evolutionary algorithm for landslide susceptibility mapping

AbstractLandslides pose a significant threat to human life and infrastructure, underscoring the ongoing need for accurate landslide susceptibility mapping (LSM) to effectively assess risks. This study introduces an innovative approach that leverages multi-objective evolutionary fuzzy algorithms for landslide modeling in Khalkhal town, Iran. Two algorithms, namely the non-dominated sorting genetic algorithm II (NSGA-II) and the evolutionary non-dominated radial slots-based algorithm (ENORA), were employed to optimize Gaussian fuzzy rules. By utilizing 15 landslide conditioning factors (aspect, altitude, distance from the fault, soil, slope, lithology, rainfall, distance from the road, the normalized difference vegetation index (NDVI), land cover, plan curvature, profile curvature, topographic wetness index (TWI), stream power index (SPI), and distance from the river) and historical landslide events (153 landslide locations), we randomly partitioned the input data into training (70%) and validation (30%) sets. The training set determined the weight of conditioning factor classes using the frequency ratio (FR) approach. These weights were then used as inputs for the NSGA-II and ENORA algorithms to generate an LSM. The NSGA-II algorithm achieved a root-mean-square error (RMSE) of 0.25 during training and 0.43 during validation. Similarly, the ENORA algorithm demonstrated an RMSE of 0.28 in training and 0.48 in validation. The findings revealed that the LSM created by the NSGA-II algorithm exhibited superior predictive capabilities (area under the receiver operating characteristic curve (AUC) = 0.867) compared to the ENORA algorithm (AUC = 0.844). Additionally, a particle swarm optimization (PSO) algorithm was employed to determine the importance of conditioning factors, identifying lithology, land cover, and altitude as the most influential factors.

Geographically weighted neural network considering spatial heterogeneity for landslide susceptibility mapping: A case study of Yichang City, China

Landslides are among the most devastating natural disasters worldwide. Landslide susceptibility mapping (LSM) is a scientific approach for assessing landslides-prone areas. Despite the use of various statistical and machine learning (ML) models to predict landslide susceptibility, few have considered the effect of spatial location on landslides. Geographically weighted regression (GWR) is a common method for modeling spatial heterogeneity, but it may not be effective in solving complex nonlinear problems. This leads to inadequate prediction accuracy for landslide susceptibility at the local scale. This study introduces a geographically weighted neural network (GWNN) model to address this problem. The GWNN model combines the advantages of GWR and neural networks (NN) to assess the effect of landslide conditioning factors on landslides. The effectiveness of the proposed method was evaluated using landslide data collected from Yichang City, Hubei Province. The results show that GWNN exhibits the higher performance (AUC = 0.788) compared with traditional ML models and GWR. Furthermore, the superior ability of GWNN is demonstrated to capture spatial heterogeneity and predict landslide susceptibility accurately at local scales. The proposed method provides a valuable reference for modeling landslide-prone areas that exhibit spatial heterogeneity.

Automatic Mapping of Potential Landslides Using Satellite Multitemporal Interferometry

Mapping potential landslides is crucial to mitigating and preventing landslide disasters and understanding mountain landscape evolution. However, the existing methods to map and demonstrate potential landslides in mountainous regions are challenging to use and inefficient. Therefore, herein, we propose a method using hot spot analysis and convolutional neural networks to map potential landslides in mountainous areas at a regional scale based on ground deformation detection using multitemporal interferometry synthetic aperture radar. Ground deformations were detected by processing 76 images acquired from the descending and ascending orbits of the Sentinel-1A satellite. In total, 606 slopes with large ground deformations were automatically detected using hot spot analysis in the study area, and the extraction accuracy rate and the missing rate are 71.02% and 7.89%, respectively. Subsequently, based on the high-deformation areas and potential landslide conditioning factors, we compared the performance of convolutional neural networks with the random forest algorithm and constructed a classification model with the area under the curve (AUC), accuracy, recall, and precision for testing being 0.75, 0.75, 0.82, and 0.75, respectively. Our approach underpins the ability of interferometric synthetic aperture radar (InSAR) to map potential landslides regionally and provide a scientific foundation for landslide risk management. It also enables an accurate and efficient identification of potential landslides within a short period and under extremely hazardous conditions.

Spatial Prediction of Landslide Susceptibility Using Logistic Regression (LR), Functional Trees (FTs), and Random Subspace Functional Trees (RSFTs) for Pengyang County, China

Landslides pose significant and serious geological threat disasters worldwide, threatening human lives and property; China is particularly susceptible to these disasters. This paper focuses on Pengyang County, which is situated in the Ningxia Hui Autonomous Region of China, an area prone to landslides. This study investigated the application of machine learning techniques for analyzing landslide susceptibility. To construct and validate the model, we initially compiled a landslide inventory comprising 972 historical landslides and an equivalent number of non-landslide sites (Data sourced from the Pengyang County Department of Natural Resources). To ensure an impartial evaluation, both the landslide and non-landslide datasets were randomly divided into two sets using a 70/30 ratio. Next, we extracted 15 landslide conditioning factors, including the slope angle, elevation, profile curvature, plan curvature, slope aspect, TWI (topographic wetness index), TPI (topographic position index), distance to roads and rivers, NDVI (normalized difference vegetation index), rainfall, land use, lithology, SPI (stream power index), and STI (sediment transport index), from the spatial database. Subsequently, a correlation analysis between the conditioning factors and landslide occurrences was conducted using the certainty factor (CF) method. Three landslide models were established by employing logistic regression (LR), functional trees (FTs), and random subspace functional trees (RSFTs) algorithms. The landslide susceptibility map was categorized into five levels: very low, low, medium, high, and very high susceptibility. Finally, the predictive capability of the three algorithms was assessed using the area under the receiver operating characteristic curve (AUC). The better the prediction, the higher the AUC value. The results indicate that all three models are predictive and practical, with only minor discrepancies in accuracy. The integrated model (RSFT) displayed the highest predictive performance, achieving an AUC value of 0.844 for the training dataset and 0.837 for the validation dataset. This was followed by the LR model (0.811 for the training dataset and 0.814 for the validation dataset) and the FT model (0.776 for the training dataset and 0.760 for the validation dataset). The proposed methods and resulting landslide susceptibility map can assist researchers and local authorities in making informed decisions for future geohazard prevention and mitigation. Furthermore, they will prove valuable and be useful for other regions with similar geological characteristics features.

Mapping Post-Earthquake Landslide Susceptibility Using U-Net, VGG-16, VGG-19, and Metaheuristic Algorithms

Landslides are among the most frequent secondary disasters caused by earthquakes in areas prone to seismic activity. Given the necessity of assessing the current seismic conditions for ensuring the safety of life and infrastructure, there is a rising demand worldwide to recognize the extent of landslides and map their susceptibility. This study involved two stages: First, the regions prone to earthquake-induced landslides were detected, and the data were used to train deep learning (DL) models and generate landslide susceptibility maps. The application of DL models was expected to improve the outcomes in both stages. Landslide inventory was extracted from Sentinel-2 data by using U-Net, VGG-16, and VGG-19 algorithms. Because VGG-16 produced the most accurate inventory locations, the corresponding results were used in the landslide susceptibility detection stage. In the second stage, landslide susceptibility maps were generated. From the total measured landslide locations (63,360 cells), 70% of the locations were used for training the DL models (i.e., convolutional neural network [CNN], CNN-imperialist competitive algorithm, and CNN-gray wolf optimizer [GWO]), and the remaining 30% were used for validation. The earthquake-induced landslide conditioning factors included the elevation, slope, plan curvature, valley depth, topographic wetness index, land cover, rainfall, distance to rivers, and distance to roads. The reliability of the generated susceptibility maps was evaluated using the area under the receiver operating characteristic curve (AUROC) and root mean square error (RMSE). The CNN-GWO model (AUROC = 0.84 and RMSE = 0.284) outperformed the other methods and can thus be used in similar applications. The results demonstrated the efficiency of applying DL in the natural hazard domain. The CNN-GWO predicted that approximately 38% of the total area consisted of high and very high susceptibility regions, mainly concentrated in areas with steep slopes and high levels of rainfall and soil wetness. These outcomes contribute to an enhanced understanding of DL application in the natural hazard domain. Moreover, using the knowledge of areas highly susceptible to landslides, officials can actively adopt steps to reduce the potential impact of landslides and ensure the sustainable management of natural resources.

Investigation of Landslide Susceptibility Decision Mechanisms in Different Ensemble-Based Machine Learning Models with Various Types of Factor Data

Machine learning (ML)-based methods of landslide susceptibility assessment primarily focus on two dimensions: accuracy and complexity. The complexity is not only influenced by specific model frameworks but also by the type and complexity of the modeling data. Therefore, considering the impact of factor data types on the model’s decision-making mechanism holds significant importance in assessing regional landslide characteristics and conducting landslide risk warnings given the achievement of good predictive performance for landslide susceptibility using excellent ML methods. The decision-making mechanism of landslide susceptibility models coupled with different types of factor data in machine learning methods was explained in this study by utilizing the Shapley Additive exPlanations (SHAP) method. Furthermore, a comparative analysis was carried out to examine the differential effects of diverse data types for identical factors on model predictions. The study area selected was Cenxi, Guangxi, where a geographic spatial database was constructed by combining 23 landslide conditioning factors with 214 landslide samples from the region. Initially, the factors were standardized using five conditional probability models, frequency ratio (FR), information value (IV), certainty factor (CF), evidential belief function (EBF), and weights of evidence (WOE), based on the spatial arrangement of landslides. This led to the formation of six types of factor databases using the initial data. Subsequently, two ensemble-based ML methods, random forest (RF) and XGBoost, were utilized to build models for predicting landslide susceptibility. Various evaluation metrics were employed to compare the predictive capabilities of different models and determined the optimal model. Simultaneously, the analysis was conducted using the interpretable SHAP method for intrinsic decision-making mechanisms of different ensemble-based ML models, with a specific focus on explaining and comparing the differential impacts of different types of factor data on prediction results. The results of the study illustrated that the XGBoost-CF model constructed with CF values of factors not only exhibited the best predictive accuracy and stability but also yielded more reasonable results for landslide susceptibility zoning, and was thus identified as the optimal model. The global interpretation results revealed that slope was the most crucial factor influencing landslides, and its interaction with other factors in the study area collectively contributed to landslide occurrences. The differences in the internal decision-making mechanisms of models based on different data types for the same factors primarily manifested in the extent of influence on prediction results and the dependency of factors, providing an explanation for the performance of standardized data in ML models and the reasons behind the higher predictive performance of coupled models based on conditional probability models and ML methods. Through comprehensive analysis of the local interpretation results from different models analyzing the same sample with different sample characteristics, the reasons for model prediction errors can be summarized, thereby providing a reference framework for constructing more accurate and rational landslide susceptibility models and facilitating landslide warning and management.

Comparison study of a landslide-event hazard mapping using a multi-approach of fuzzy logic, TRIGRS model, and support vector machine in a data-scarce Andes Mountain region

Landslides are a significant global hazard, especially prevalent in regions with high rainfall, active tectonic processes, and rugged topography, such as the Colombian Andean region. Therefore, it is crucial to identify areas prone to landslides in order to protect human lives and mitigate the adverse impacts on national economies, especially in developing countries situated in tropical and mountainous regions. Assessing landslide hazard and susceptibility is a fundamental step in comprehending the fundamental characteristics of slopes susceptible to failure, particularly under extreme rainfall conditions. Various researchers have devised methods and techniques to assess and map landslides, employing heuristic, statistical, and deterministic approaches. This study carried out a geographic information system-based approach for shallow landslides, with the objective to compare different methods for a landslide-event hazard mapping using the landslide records on May 18, 2015, triggered by a rainstorm in the La Liboriana basin (Colombia). In the first place, a fuzzy logic gamma model was applied using landslide conditioning factors. Then, the deterministic model TRIGRS was applied to assess shallow landslides. Finally, a support vector machine (SVM) model was used to obtain an intermediate scale solution. All models consider the rainfall that triggered the aforementioned landslide event. The results indicated that the SVM (radial basis function) model permits to obtain a better performance (AUC = 0.95) in landslide hazard zonation rather than quantitative heuristic fuzzy gamma model (AUC = 0.86) and the deterministic TRIGRS model (AUC = 0.60), obtaining best accurate at predicting the landslide hazard in the study area.

Modeling landslide susceptibility based on convolutional neural network coupling with metaheuristic optimization algorithms

ABSTRACT Landslides are one of the most common geological hazards worldwide, especially in Sichuan Province (Southwest China). The current study's main purposes are to explore the potential applications of convolutional neural networks (CNN) hybrid ensemble metaheuristic optimization algorithms, namely beluga whale optimization (BWO) and coati optimization algorithm (COA), for landslide susceptibility mapping in Sichuan Province (China). For this aim, fourteen landslide conditioning factors were compiled in a spatial database. The effectiveness of the conditioning factors in the development of the landslide predictive model was quantified using the linear support vector machine model. The receiver operating characteristic (ROC) curve (AUC), the root mean square error, and six statistical indices were used to test and compare the three resultant models. For the training dataset, the AUC values of the CNN-COA, CNN-BWO and CNN models were 0.946, 0.937 and 0.855, respectively. In terms of the validation dataset, the CNN-COA model exhibited a higher AUC value of 0.919, while the AUC values of the CNN-BWO and CNN models were 0.906 and 0.805, respectively. The results indicate that the CNN-COA model, followed by the CNN-BWO model, and the CNN model, offers the best overall performance for landslide susceptibility analysis.