Model For Landslide Susceptibility Mapping Research Articles

Co-seismic landslide susceptibility mapping for the Luding earthquake area based on heterogeneous ensemble machine learning models

ABSTRACT Considering the complexity of landslide susceptibility mapping (LSM) at the municipal-scale, it is difficult for the assumption space of a single machine learning (ML) algorithm to fully and accurately reflect the intrinsic correlation between the landslide influencing factors and the actual catastrophic events under all scenarios. This study addresses this by integrating three heterogeneous ensemble learning (HEL) algorithms(Bagging, Blending, and Stacking) with four ML models (Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), and Backpropagation-Neural Network (BPNN)), to construct 27 HEL LSM models, and to realize optimization and selection of the models and algorithms through the comparative analysis of the results of the LSM and the accuracy of the prediction of the individual models. The final results indicate that the Bagging and Blending HEL algorithms fail to enhance model prediction accuracy effectively. In contrast, the Stacking HEL algorithm significantly improves model prediction accuracy (with an accuracy increase of over 1.4% and AUC values above 0.95). The Stacking (GBDT-XGBoost) model had the highest prediction accuracy (AUC = 0.964) and thus was selected as the optimal LSM model. This study's modeling and mapping results are intended to serve as a reference for geohazard prevention and sustainability studies in related cities.

Landslide susceptibility mapping using modified frequancy ratio method in Correb area, South Wollo, North-Western Ethiopia

Correb area in Mekdela Woreda, South-Wollo Zone, North-Western Ethiopia is one of the most landslide affected region. The primary aim of this study was to assess the landslide susceptibility of the area and create a landslide susceptibility map. A bivariate statistical frequency ratio model was used to accomplish this goal. Using fieldwork and Google Earth picture interpretation, a map of landslides was made. A total of 524 landslides were identified and then classified in to training landslide (75%) for model development and validation landslide (25%) for model validation. Eight landslide causative factors slope, aspect, elevation, distance to drainage, distance to spring, slope material, distance to lineament, and vegetation cover were integrated with training landslides in order to determine frequency ratio value(weight) for each class of landslide causative factors. Furthermore, each causative factor’s prediction rate or weight was established. Relative frequency values were allocated to the appropriate factor classes and prediction rate values were allocated to the appropriate causative factors and summed using a raster calculator algorithm in order to produce the landslide susceptibility map. The final landslide susceptibility map revealed that 27.54% (31.52 km2) of the study area falls under very low susceptible, 30.35% (34.74 km2) low susceptible, 21.36% (24.44 km2) moderate susceptible, 14.74% (16.88 km2) high susceptible, and the rest 6.01% (6.88 km2) as very high susceptible. This shows that more than 20% of the area has probability and risk of landslide while about 80% has relatively low probability and risk of this natural hazard. The performance of modified frequency ratio model for landslide susceptibility mapping was validated using simply overlay, relative landslide density index, and receiver operating characteristics curve. Both training and validation landslides were rare in the very low and low susceptibility classes and strongly concentrated in the high and very high susceptibility classes, according to validation using simple overlay and the relative landslide density index. The implemented model performed exceptionally well, as seen by the receiver operating characteristics curve, which showed 82.6% success rate and an 83.1% prediction rate. In general, the model produced reasonable accuracy. The resultant map would be useful for general land use planning, site selection, and landslide prevention and mitigation programs.

A Unique Conditions Model for Landslide Susceptibility Mapping

Several methods and approaches have been proposed to assess landslide susceptibility. The likelihood of landslides occurring can be determined by applying statistical models to historical landslides, taking into account controlling factors. Popular methods for predicting the probability of landslides are weights-of-evidence and logistic regression. We discuss the assumptions and interpretations of these methods, the relationships between them, and their strengths and weaknesses in case of categorical factors. Of particular interest is the conditional independence of the controlling factors and its effect on model bias. To avoid lack of conditional independence of factors and model bias, we present a unique conditions model that is always unbiased. To illustrate the theoretical developments, a practical application is given using observed landslides and geo-environmental factors from a previous study. The unique conditions model appears superior to the other models.

Regional-scale spatiotemporal landslide probability assessment through machine learning and potential applications for operational warning systems: a case study in Kvam (Norway)

The use of machine learning models for landslide susceptibility mapping is widespread but limited to spatial prediction. The potential of employing these techniques in spatiotemporal landslide forecasting remains largely unexplored. To address this gap, this study introduces an innovative dynamic (i.e., space–time-dependent) application of the random forest algorithm for evaluating landslide hazard (i.e., spatiotemporal probability of landslide occurrence). An area in Norway has been chosen as the case study because of the availability of a comprehensive, spatially, and temporally explicit rainfall-induced landslide inventory. The applied methodology is based on the inclusion of dynamic variables, such as cumulative rainfall, snowmelt, and their seasonal variability, as model inputs, together with traditional static parameters such as lithology and morphologic attributes. In this study, the variables’ importance was assessed and used to interpret the model decisions and to verify that they align with the physical mechanism responsible for landslide triggering. The algorithm, once trained and tested against landslide and non-landslide data sampled over space and time, produced a model predictor that was subsequently applied to the entire study area at different times: before, during, and after specific landslide events. For each selected day, a specific and space–time-dependent landslide hazard map was generated, then validated against field data. This study overcomes the traditional static applications of machine learning and demonstrates the applicability of a novel model aimed at spatiotemporal landslide probability assessment, with perspectives of applications to early warning systems.

Interpretable Landslide Susceptibility Evaluation Based on Model Optimization

Machine learning (ML) is increasingly utilized in Landslide Susceptibility Mapping (LSM), though challenges remain in interpreting the predictions of ML models. To reveal the response relationship between landslide susceptibility and evaluation factors, an interpretability model was constructed to analyze how the results of the ML model are realized. This study focuses on Zhenba County in Shaanxi Province, China, employing both Random Forest (RF) and Support Vector Machine (SVM) to develop LSM models optimized through Random Search (RS). To enhance interpretability, the study incorporates techniques such as Partial Dependence Plot (PDP), Local Interpretable Model-Agnostic Explanations (LIMEs), and Shapley Additive Explanations (SHAP). The RS-optimized RF model demonstrated superior performance, achieving an Area Under the Curve (AUC) of 0.965. The interpretability model identified the NDVI and distance from road as important factors influencing landslides occurrence. NDVI plays a positive role in the occurrence of landslides in this region, and the landslide-prone areas are within 500 m from the road. These analyses indicate the importance of improved hyperparameter selection in enhancing model accuracy and performance. The interpretability model provides valuable insights into LSM, facilitating a deeper understanding of landslide formation mechanisms and guiding the formulation of effective prevention and control strategies.

Utilization of Frequency Ratio and Logistic Regression Model for Landslide Susceptibility Mapping in Bogor Area

Java Island holds the highest record of landslide events in Indonesia. In 2021, the Bogor area, consisting of the city and regency of Bogor, recorded the highest number of landslides. These events further impact the fatalities, damage, and loss to society. Landslide mitigation should be considered to reduce the risk caused by landslide hazards. In this regard, a landslide susceptibility analysis is one of the fundamental steps in mitigation measures that can support policymakers in response to landslide disaster risk reduction. The location of landslide possibilities can be identified by mapping landslide susceptibility. Therefore, this study aims to produce a landslide susceptibility map (LSM) using a statistical frequency ratio method and logistic regression. The number of landslide inventories used in the model is about 822 events. To apply the model, the present study evaluates 13 influencing factors consisting of elevation, slope angle, slope aspect, slope curvature, Topographic Wetness Index (TWI), distance to river, lithological, distance to fault, soil type, annual rainfall, Normalized Difference Vegetation Index (NDVI), land use land cover (LULC), and road distance. The model performance is further evaluated using Area Under the ROC Curve (AUC). The frequency ratio (FR) and logistic regression (LR) models produce satisfactory results and have high predictions of future landslide occurrences with a score of 0.8317 and 0.8817, respectively.

An information quantity and machine learning integrated model for landslide susceptibility mapping in Jiuzhaigou, China

An information quantity and machine learning integrated model for landslide susceptibility mapping in Jiuzhaigou, China

Game-theoretic optimization of landslide susceptibility mapping: a comparative study between Bayesian-optimized basic neural network and new generation neural network models.

Landslide susceptibility mapping is essential for reducing the risk of landslides and ensuring the safety of people and infrastructure in landslide-prone areas. However, little research has been done on the development of well-optimized Elman neural networks (ENN), deep neural networks (DNN), and artificial neural networks (ANN) for robust landslide susceptibility mapping (LSM). Additionally, there is a research gap regarding the use of Bayesian optimization and the derivation of SHapley Additive exPlanations (SHAP) values from optimized models. Therefore, this study aims to optimize DNN, ENN, and ANN models using Bayesian optimization for landslide susceptibility mapping and derive SHAP values from these optimized models. The LSM models have been validated using the receiver operating characteristics curve, confusion matrix, and other twelve error matrices. The study used six machine learning-based feature selection techniques to identify the most important variables for predicting landslide susceptibility. The decision tree, random forest, and bagging feature selection models showed that slope, elevation, DFR, annual rainfall, LD, DD, RD, and LULC are influential variables, while geology and soil texture have less influence. The DNN model outperformed the other two models, covering 7839.54 km2 under the very low landslide susceptibility zone and 3613.44 km2 under the very high landslide susceptibility zone. The DNN model is better suited for generating landslide susceptibility maps, as it can classify areas with higher accuracy. The model identified several key factors that contribute to the initiation of landslides, including high elevation, built-up and agricultural land use, less vegetation, aspect (north and northwest), soil depth less than 140 cm, high rainfall, high lineament density, and a low distance from roads. The study's findings can help stakeholders make informed decisions to reduce the risk of landslides and ensure the safety of people and infrastructure in landslide-prone areas.

Optimizing landslide susceptibility mapping using machine learning and geospatial techniques

Landslides present a substantial risk to human lives, the environment, and infrastructure. Consequently, it is crucial to highlight the regions prone to future landslides by examining the correlation between past landslides and various geo-environmental factors. This study aims to investigate the optimal data selection and machine learning model, or ensemble technique, for evaluating the vulnerability of areas to landslides and determining the most accurate approach. To attain our objectives, we considered two different scenarios for selecting landslide-free random points (a slope threshold and a buffer-based approach) and performed a comparative analysis of five machine learning models for landslide susceptibility mapping, namely: Support Vector Machine (SVM), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The study area for this research is an area in Polk County in Western North Carolina that has experienced fatal landslides, leading to casualties and significant damage to infrastructure, properties, and road networks. The model construction process involves the utilization of a dataset comprising 1215 historical landslide occurrences and 1215 non-landslide points. We integrated a total of fourteen geospatial data layers, consisting of topographic variables, soil data, geological data, and land cover attributes. We use various metrics to assess the models' performance, including accuracy, F1-score, Kappa score, and AUC-ROC. In addition, we used the seeded-cell area index (SCAI) to evaluate map consistency. The ensemble of the five models using Weighted Average produces outstanding results, with an AUC-ROC of 99.4% for the slope threshold scenario and 91.8% for the buffer-based scenario. Our findings emphasize the significant impact of non-landslide random sampling on model performance in landslide susceptibility mapping. Furthermore, by optimally identifying landslide-prone regions and hotspots that need urgent risk management and land use planning, our study demonstrates the effectiveness of machine learning models in analyzing landslide susceptibility and providing valuable insights for informed decision-making and disaster risk reduction initiatives.

Study on the influence of input variables on the supervised machine learning model for landslide susceptibility mapping

Study on the influence of input variables on the supervised machine learning model for landslide susceptibility mapping

Integration of multi-criteria decision analysis and statistical models for landslide susceptibility mapping in the western Algiers Province (Algeria) using GIS techniques and remote sensing data

Integration of multi-criteria decision analysis and statistical models for landslide susceptibility mapping in the western Algiers Province (Algeria) using GIS techniques and remote sensing data

Comparison of different open‐source Digital Elevation Models for landslide susceptibility mapping

AbstractIn this study, the application of open‐source digital elevation model (DEM) is explored for regional landslide susceptibility mapping (LSM), and the potential impact of different DEM choices on the mapping accuracy is also examined. With the advancements in remote sensing technology, an increasing number of global open‐source DEMs have been available, with improvement in the accuracy. However, the latest released data are rarely evaluated in LSM research. In this paper, DEM‐based factors, including elevation, aspect, slope, plan curvature and profile curvature, were generated from seven open‐source DEMs, including Advanced Spaceborne Thermal Emission and Reflection (ASTER) V2, ASTERV3, ALOS World 3D‐30 m (AW3D30), Copernicus DEM 30 m (COP) Forest and Buildings removed Copernicus DEM (FABDEM), NASADEM, and Shuttle Radar Topography Mission (SRTM). DEM‐based factors were coupled with the distance to road, distance to river, land use, lithology, rain and normalized difference vegetation index (NDVI). The significant difference between DEMs is determined by comparing the area proportion. Slope, plane curvature and profile curvature are found to have a maximum difference of 15%–20%. Then, K‐Nearest Neighbours (KNN) and Random Forest (RF) were used to predict landslide susceptibility with two sampling methods, namely, 70% for training and 30% for testing (S1); 67% for training and 33% for testing (S2). For KNN with S1, the prediction rate is range from 0.8299 to 0.8701, with a difference of 0.0402. The difference of prediction rate is decreased to 0.0207 for S2 and 0.0258 for RF. COP has the highest prediction rate of 0.8701, 0.9254 and 0.9461 for KNN with S1 and RF with S1 and S2, respectively. ASTERV2 is the worst with prediction rate of 0.8897 and 0.8996 for KNN with S2 and RF with S1, respectively. The research result provides valuable insights for the selection of open‐source DEMs in future LSM.

Landslide susceptibility mapping (LSM) based on different boosting and hyperparameter optimization algorithms: A case of Wanzhou District, China

Boosting algorithms have been widely utilized in the development of landslide susceptibility mapping (LSM) studies. However, these algorithms possess distinct computational strategies and hyperparameters, making it challenging to propose an ideal LSM model. To investigate the impact of different boosting algorithms and hyperparameter optimization algorithms on LSM, this study constructed a geospatial database comprising 12 conditioning factors, such as elevation, stratum, and annual average rainfall. The XGBoost (XGB), LightGBM (LGBM), and CatBoost (CB) algorithms were employed to construct the LSM model. Furthermore, the Bayesian optimization (BO), particle swarm optimization (PSO), and Hyperband optimization (HO) algorithms were applied to optimizing the LSM model. The boosting algorithms exhibited varying performances, with CB demonstrating the highest precision, followed by LGBM, and XGB showing poorer precision. Additionally, the hyperparameter optimization algorithms displayed different performances, with HO outperforming PSO and BO showing poorer performance. The HO-CB model achieved the highest precision, boasting an accuracy of 0.764, an F1-score of 0.777, an area under the curve (AUC) value of 0.837 for the training set, and an AUC value of 0.863 for the test set. The model was interpreted using SHapley Additive exPlanations (SHAP), revealing that slope, curvature, topographic wetness index (TWI), degree of relief, and elevation significantly influenced landslides in the study area. This study offers a scientific reference for LSM and disaster prevention research. This study examines the utilization of various boosting algorithms and hyperparameter optimization algorithms in Wanzhou District. It proposes the HO-CB-SHAP framework as an effective approach to accurately forecast landslide disasters and interpret LSM models. However, limitations exist concerning the generalizability of the model and the data processing, which require further exploration in subsequent studies.

Improving pixel-based regional landslide susceptibility mapping

Regional landslide susceptibility mapping (LSM) is essential for risk mitigation. While deep learning algorithms are increasingly used in LSM, their extensive parameters and scarce labels (limited landslide records) pose training challenges. In contrast, classical statistical algorithms, with typically fewer parameters, are less likely to overfit, easier to train, and offer greater interpretability. Additionally, integrating physics-based and data-driven approaches can potentially improve LSM. This paper makes several contributions to enhance the practicality, interpretability, and cross-regional generalization ability of regional LSM models: (1) Two new hybrid models, composed of data-driven and physics-based modules, are proposed and compared. Hybrid Model I combines the infinite slope stability analysis (ISSA) with logistic regression, a classical statistical algorithm. Hybrid Model II integrates ISSA with a convolutional neural network, a representative of deep learning techniques. The physics-based module constructs a new explanatory factor with higher nonlinearity and reduces prediction uncertainty caused by incomplete landslide inventory by pre-selecting non-landslide samples. The data-driven module captures the relation between explanatory factors and landslide inventory. (2) A step-wise deletion process is proposed to assess the importance of explanatory factors and identify the minimum necessary factors required to maintain satisfactory model performance. (3) Single-pixel and local-area samples are compared to understand the effect of pixel spatial neighborhood. (4) The impact of nonlinearity in data-driven algorithms on hybrid model performance is explored. Typical landslide-prone regions in the Three Gorges Reservoir, China, are used as the study area. The results show that, in the testing region, by using local-area samples to account for pixel spatial neighborhoods, Hybrid Model I achieves roughly a 4.2% increase in the AUC. Furthermore, models with 30 m resolution land-cover data surpass those using 1000 m resolution data, showing a 5.5% improvement in AUC. The optimal set of explanatory factors includes elevation, land-cover type, and safety factor. These findings reveal the key elements to enhance regional LSM, offering valuable insights for LSM practices.

Comparative analysis of frequency ratio, information value, and analytical hierarchy process statistical models for landslide susceptibility mapping in Kashmir Himalayas

Comparative analysis of frequency ratio, information value, and analytical hierarchy process statistical models for landslide susceptibility mapping in Kashmir Himalayas

Refined Landslide Susceptibility Mapping by Integrating the SHAP-CatBoost Model and InSAR Observations: A Case Study of Lishui, Southern China

Landslide susceptibility mapping based on static influence factors often exhibits issues of low accuracy and classification errors. To enhance the accuracy of susceptibility mapping, this study proposes a refined approach that integrates categorical boosting (CatBoost) with small baseline subset interferometric synthetic-aperture radar (SBAS-InSAR) results, achieving more precise and detailed susceptibility mapping. We utilized optical remote sensing images, the information value (IV) model, and fourteen influencing factors (elevation, slope, aspect, roughness, profile curvature, plane curvature, lithology, distance to faults, land use type, normalized difference vegetation index (NDVI), topographic wetness index (TWI), distance to rivers, distance to roads, and annual precipitation) to establish the IV-CatBoost landslide susceptibility mapping method. Subsequently, the Sentinel-1A ascending data from January 2021 to March 2023 were utilized to derive the deformation rates within the city of Lishui in the southern region of China. Based on the outcomes derived from IV-CatBoost and SBAS-InSAR, a discernment matrix was formulated to rectify inaccuracies in the partitioned regions, leading to the creation of a refined information value CatBoost integration (IVCI) landslide susceptibility mapping model. In the end, we utilized optical remote sensing interpretations alongside surface deformations obtained from SBAS-InSAR to cross-verify the excellence and accuracy of IVCI. Research findings indicate a distinct enhancement in susceptibility levels across 165,784 grids (149.20 km2) following the integration of SBAS-InSAR correction. The enhanced susceptibility classes and the spectral characteristics of remote sensing images closely correspond to the trends of SBAS-InSAR cumulative deformation, reflecting a high level of consistency with field-based conditions. These improved classifications effectively enhance the refinement of landslide susceptibility mapping. The refined susceptibility mapping approach proposed in this paper effectively enhances landslide prediction accuracy, providing valuable technical reference for landslide hazard prevention and control in the Lishui region.

Deep Learning and Machine Learning Models for Landslide Susceptibility Mapping with Remote Sensing Data

Karakoram Highway (KKH) is an international route connecting South Asia with Central Asia and China that holds socio-economic and strategic significance. However, KKH has extreme geological conditions that make it prone and vulnerable to natural disasters, primarily landslides, posing a threat to its routine activities. In this context, the study provides an updated inventory of landslides in the area with precisely measured slope deformation (Vslope), utilizing the SBAS-InSAR (small baseline subset interferometric synthetic aperture radar) and PS-InSAR (persistent scatterer interferometric synthetic aperture radar) technology. By processing Sentinel-1 data from June 2021 to June 2023, utilizing the InSAR technique, a total of 571 landslides were identified and classified based on government reports and field investigations. A total of 24 new prospective landslides were identified, and some existing landslides were redefined. This updated landslide inventory was then utilized to create a landslide susceptibility model, which investigated the link between landslide occurrences and the causal variables. Deep learning (DL) and machine learning (ML) models, including convolutional neural networks (CNN 2D), recurrent neural networks (RNNs), random forest (RF), and extreme gradient boosting (XGBoost), are employed. The inventory was split into 70% for training and 30% for testing the models, and fifteen landslide causative factors were used for the susceptibility mapping. To compare the accuracy of the models, the area under the curve (AUC) of the receiver operating characteristic (ROC) was used. The CNN 2D technique demonstrated superior performance in creating the landslide susceptibility map (LSM) for KKH. The enhanced LSM provides a prospective modeling approach for hazard prevention and serves as a conceptual reference for routine management of the KKH for risk assessment and mitigation.

Landslide susceptibility mapping and management in Western Serbia: an analysis of ANFIS- and SVM-based hybrid models

Landslide susceptibility mapping (LSM) is essential for land-use planning, as it helps to identify areas at risk of landslides and enables effective prevention measures to be taken. Various statistical and machine learning (ML) models are used in LSM, including SVM and ANFIS, which have shown promising results. However, determining which model performs better remains a key challenge. To address this issue, this paper aims to compare six hybrid models constructed with two well-known and powerful ML models, namely SVM and ANFIS, and three meta-heuristic algorithms, namely Genetic Algorithm (GA), Differential Evolution (DE), and Cultural Algorithm (CA), for LSM in a case study in western Serbia. In the process of building the models, 359 landslide sites and 14 determinants were used. The accuracy of the models was evaluated using several indexes, including Root Mean-Squared Error (RMSE), coefficient of determination (R2), and Area under the Receiver Operating Characteristic Curve (AUROC). The modeling results showed that the SVM-GA model has the highest accuracy (AUROC = 0.78) in predicting landslide incidence, followed by the ANFIS-GA (AUROC = 0.775), SVM-CA (AUROC = 0.773), ANFIS-DE (AUROC = 0.771), SVM-DE (AUROC = 0.76), and ANFIS-CA (AUROC = 0.65) models in validation phase. Therefore, the study suggested that SVM-based hybrid models are more accurate than ANFIS-based models for LSM, and thus, modelers may use SVM-based hybrid models for such applications. This study provides valuable insights into identifying the most appropriate and effective models for LSM, which can help to mitigate the risks associated with landslides and ensure sustainable land-use practices.

Identifying the essential influencing factors of landslide susceptibility models based on hybrid-optimized machine learning with different grid resolutions: a case of Sino-Pakistani Karakorum Highway.

This study attempts to explore the essential influencing factors of landslides and explores the effects of different datasets on landslide susceptibility mapping (LSM) at six grid resolutions (i.e., 10 m, 30 m, 300 m, 1000 m, 2000 m, and 3000 m). Firstly, the geospatial dataset of 21 influencing factors was extracted from 1847 historical landslide InSAR (Interferometric Synthetic Aperture Radar) points, which were taken as a sample for the Sino-Pakistani Karakorum Highway. Secondly, Spearman correlation coefficient (SCC), random forest feature selection (RFFS), and their combinations (SCC-RFFS) were selected at different grid resolutions to identify the essential influencing factors from the 21 original factors. A random division into training set (70%) and test set (30%) was performed. Then, the LSM models for the original influencing factors and the selected influencing factors were constructed separately using machine learning models. Finally, the reasonableness of the essential influencing factors was verified by comparing the accuracy of the models under different grid resolutions. The results show that (1) relief degree of land surface (RDLS), SPI, and rainfall have significant effects on landslide occurrence. (2) The primary elements (i.e., RDLS, slop, rainfall) are less affected by the grid resolution, while the secondary elements (TWI) are more affected by the grid resolution. (3) At 30 m, the SCC-RFFS-RF model can get the highest landslide susceptibility model accuracy. The prediction will also provide scientific guidance for the allocation of land resources on a regional and global scale, and minimize the human and economic costs along the highway, while ensuring safe highway operations.

Development and assessment of a novel hybrid machine learning-based landslide susceptibility mapping model in the Darjeeling Himalayas

Development and assessment of a novel hybrid machine learning-based landslide susceptibility mapping model in the Darjeeling Himalayas