Landslide Susceptibility Analysis Research Articles

LANDSLIDE SUSCEPTIBILITY ASSESSMENT OF THE CITY OF KARLOVAC USING THE BIVARIATE STATISTICAL ANALYSIS

A preliminary landslide susceptibility analysis on a regional scale of 1:100 000 using bivariate statistics was conducted for the City of Karlovac. The City administration compiled landslide inventory used in the analysis based on recorded landslides from 2014 to 2019 that caused significant damage to buildings or infrastructures. Analyses included 17 geofactors relevant to landslide occurrence and classified them into four groups: geomorphological (elevation, slope gradient, slope orientation, terrain curvature, terrain roughness), geological (lithology-rock type, proximity to geological contacts, proximity to faults), hydrological (proximity to drainage network, proximity to springs, proximity to temporary, permanent and to all streams, topographic wetness) and anthropogenic (proximity to traffic infrastructure, land cover using two classifications). Five scenarios were defined using a different combination of geofactors weighted by the Weights-of Evidence (WoE) method, resulting in five different landslide susceptibility maps. The best landslide susceptibility map was selected upon the results of a ROC curve analysis, which was used to obtain success and prediction rates of each scenario. The novelty in the presented research is that a limited amount of thematic data and an incomplete landslide inventory map allows for the production of a preliminary landslide susceptibility map for usage in spatial planning. Also, this study provides a discussion regarding the used method, geofactors, defined scenarios and reliability of the results. The final preliminary landslide susceptibility map was derived using ten geofactors, which satisfied the pairwise CI test, and it is classified in four zones: low landslide susceptibility (57.05% of the area), medium landslide susceptibility (20.63% of the area), high landslide susceptibility (13.28% of the area), and very high landslide susceptibility (9.03% of the area), and has a success rate of 94% and a prediction rate of 93% making it a highly accurate source of preliminary information for the study area.

Dynamic Landslide Susceptibility Analysis that Combines Rainfall Period, Rainfall, and Geospatial Information

Dynamic Landslide Susceptibility Analysis that Combines Rainfall Period, Rainfall, and Geospatial Information

Landslide Susceptibility Analysis by Applying TRIGRS to a Reliable Geotechnical Slope Model

This paper presents the results of a research aimed at analysing the susceptibility to shallow landslides of a study area in the Calabria region (Southern Italy). These shallow landslides, which in some cases evolve as debris flows, periodically affect the study area, causing damage to structures and infrastructure. The involved soils come from the weathering of gneissic rocks and cover about 60% of the study area. To fulfil the goal of the research, the Transient Rainfall Infiltration and Grid-based Slope-Stability (TRIGRS) model was first used, assuming input data (including physical and mechanical parameters of soils) provided by the scientific literature. Then, the preliminary results obtained were used to properly locate in situ investigations that included sampling. Geotechnical laboratory tests allowed characterising the investigated soils, and related parameters were used as new input data of the TRIGRS model. The generated shallow landslide susceptibility scenario showed a good predictive capability based on the adoption of a cutoff-independent performance technique.

Review on the Geomorphological Approaches to the Landslide Susceptibility Analysis in Rwanda

Review on the Geomorphological Approaches to the Landslide Susceptibility Analysis in Rwanda

Comparison of landslide susceptibility models and their robustness analysis: a case study from the NW Himalayas, Pakistan

Machine learning methods are considered as most effective approaches to accomplish landslide susceptibility analysis around the globe. Landslide susceptibility maps (LSMs) have been frequently executed by statistical models in NW Himalaya. However, the comparison and applications of the statistical models with modern machine learning techniques has not been fully explored in this region. Hence, this study aims to compare the predicted performance of statistical and popular machine learning models to explore robust landslide prediction model in the landslide-prone area of NW Himalaya and investigate the compensations and limitations of these models to grasp a more precise and consistent result. This study presented machine learning approaches based on the artificial neural network (ANN), support vector machine (SVM) and logistic regression (LR) and the statistical methods based on the frequency ratio (FR), information value (InfoV) and weight of evidence (WoE). For this purpose, first an inventory map of 1507 landslides was prepared and randomly divided into training (70%) and testing (30%) dataset. Furthermore, 12 landslide conditioning factors (LCFs) were extracted from geospatial dataset to prepare thematic layers in ArcGIS. Thereafter, factor analysis was performed to eliminate colinear and least important variables which can mislead the results. The results showed that all selected LCFs are noncolinear and have significant contribution on landslides initiation, however, lithology, slope angle, annual rainfall and landuse were most influential factors. For modeling purpose, landslide inventory was correlated against all LCFs and trained into six models to produce respective LSMs. Finally, the performance of produced LSM models was validated and compared through area under receiver operating characteristic curve (AUROC), Accuracy, Recall, F 1-score and Cohen’s Kappa coefficients to assess the robustness of employed models. The results exhibit that the performance scores of machine learning models were considerably superior than statistical models. While, the AUROC values based on validation dataset indicate that LR (0.89) has better prediction ability followed by SVM (0.86), ANN (0.84), FR (0.83), InfoV (0.82) and WoE (0.81) in this study. Therefore, it is reasoned out that the machine learning methods are more reliable in generating adequate LSMs. However, the LR is recommended as most efficient model for predicting landslide susceptible zones in study region and thus can be considered as robust model for landslide susceptibility assessment in similar geo-environmental regimes.

Landslide Susceptibility Mapping in the Vrancea-Buzău Seismic Region, Southeast Romania

This study presents the results of a landslide susceptibility analysis applied to the Vrancea-Buzău seismogenic region in the Carpathian Mountains, Romania. The target area is affected by a large diversity of landslide processes. Slopes are made-up of various types of rocks, climatic conditions can be classified as wet, and the area is a seismically active one. All this contributes to the observed high landslide hazard. The paper analyses the spatial component of the landslide hazard affecting the target area, the regional landslide susceptibility. First, an existing landslide inventory was completed to cover a wider area for the landslide susceptibility analysis. Second, two types of methods are applied, a purely statistical technique, based on correlations between landslide occurrence and local conditions, as well as the simplified spatial process-based Newmark Displacement analysis. Landslide susceptibility maps have been produced by applying both methods, the second one also allowing us to simulate different scenarios, based on various soil saturation rates and seismic inputs. Furthermore, landslide susceptibility was computed both for the landslide source and runout zones—the first providing information about areas where landslides are preferentially triggered and the second indicating where landslides preferentially move along the slope and accumulate. The analysis showed that any of the different methods applied produces reliable maps of landslide susceptibility. However, uncertainties were also outlined as validation is insufficient, especially in the northern area, where only a few landslides could be mapped due to the intense vegetation cover.

Geological hazards of the Gerecse Hills (Hungary)

ABSTRACT Landslides and related mass movement processes actively pose a threat in the Gerecse Hills (Hungary, Transdanubian Range) by endangering residential and agricultural areas. Several closed or abandoned mining sites and waste deposits are also located in the area. Most of these sites have not been fully remediated, which makes their surroundings dangerous and unsuitable for other use. A multi-hazard map (1: 60,000) was prepared about the geological hazard sources of the Gerecse by collecting and synthetizing data from individual thematic maps and databases. The aim of the map is to provide a comprehensive look at the different but often-interrelated hazard sources of the area. The thematic content of the map consists of three main parts: the result of a statistical landslide susceptibility analysis marking the most landslide-prone slopes, the documented slope failure events, and the areas of hazardous mining sites and their waste deposits.

FRMOD, a Python tool for statistical landslide susceptibility assessment

Abstract. Locating landslide-prone slopes is important, as landslides often threaten life or property where they occur. There is an abundance of statistical methods in the literature for estimating susceptibility to landslides, i.e., the likelihood of landslide occurrence based on the analyzed conditions. Still, there is a lack of readily available GIS tools for landslide susceptibility analysis, making it hard to reproduce or compare the results of different susceptibility assessments. The FRMOD is a Python-based tool for conducting landslide susceptibility analysis with the frequency ratio method. The frequency ratio method yields susceptibility estimates by comparing the frequency distributions of a set of variables from the sample landslide areas to the distributions for the whole study area. The estimates show the level of similarity to the sample landslides. The two main inputs of the tool are the raster grids of the analyzed continuous (e.g., elevation, slope) and thematic (e.g., lithology) variables and the mask grid that marks the landslide and the non-landslide areas. The analysis is performed with cross-validation to measure the predictive performance of the model. Data computed during the analysis is stored along the final susceptibility estimates and the supplementary statistics. The script reads and writes GDAL-compatible rasters, while the statistics can be saved as text files. Basic plotting functionalities for the grids and the statistics are also built-in to quicken the evaluation of the results. FRMOD enables the swift testing of different analysis setups and to apply the same analysis method for different areas with relative ease.

Landslide Susceptibility Analysis by Type of Cultural Heritage Site Using Ensemble Model: Case Study of the Chungcheong Region of South Korea

Landslide Susceptibility Analysis by Type of Cultural Heritage Site Using Ensemble Model: Case Study of the Chungcheong Region of South Korea

Entropy-Based Hybrid Integration of Random Forest and Support Vector Machine for Landslide Susceptibility Analysis

Landslide susceptibility mapping is a crucial step in comprehensive landslide risk management. The purpose of the present study is to analyze the landslide susceptibility of Mandi district, Himachal Pradesh, India, based on optimum feature selection and hybrid integration of the Shannon entropy (SE) model with random forest (RF) and support vector machine (SVM) models. An inventory of 1723 rainfall-induced landslides was generated and randomly selected for training (1199; 70%) and validation (524; 30%) purposes. A set of 14 relevant factors was selected and checked for multicollinearity. These factors were first ranked using Information Gain and Chi-square feature ranking algorithms. Furthermore, Wilcoxon Signed Rank Test and One-Sample T-Test were applied to check their statistical significance. An optimum subset of 11 landslide causative factors was then used for generating landslide susceptibility maps (LSM) using hybrid SE-RF and SE-SVM models. These LSM’s were validated and compared using receiver operating characteristic (ROC) curves and performance matrices. The SE-RF performed better with training and validation accuracies of 96.93% and 88.94%, respectively, compared with the SE-SVM model with training and validation accuracies of 94.05% and 82.4%, respectively. The prediction matrices also confirmed that the SE-RF model is better and is recommended for the landslide susceptibility analysis of similar mountainous regions worldwide.

Landslide Susceptibility Mapping by Comparing GIS-Based Bivariate Methods: A Focus on the Geomorphological Implication of the Statistical Results

Landslide susceptibility is one of the main topics of geomorphological risk studies. Unfortunately, many of these studies applied an exclusively statistical approach with little coherence with the geomorphodynamic models, resulting in susceptibility maps that are difficult to read. Even if many different models have been developed, those based on statistical techniques applied to slope units (SUs) are among the most promising. SU segmentation divides terrain into homogenous domains and approximates the morphodynamic response of the slope to landslides. This paper presents a landslide susceptibility (LS) analysis at the catchment scale for a key area based on the comparison of two GIS-based bivariate statistical methods using the landslide index (LI) approach. A new simple and reproducible method for delineating SUs is defined with an original GIS-based terrain segmentation based on hydrography. For the first time, the morphometric slope index (MSI) was tested as a predisposing factor for landslides. Beyond the purely statistic values, the susceptibility maps obtained have strong geomorphological significance and highlight the areas with the greatest propensity to landslides. We demonstrate the efficiency of the SU segmentation method and the potential of the proposed statistical methods to perform landslide susceptibility mapping (LSM).

Performance assessment of artificial neural network using chi-square and backward elimination feature selection methods for landslide susceptibility analysis

Performance assessment of artificial neural network using chi-square and backward elimination feature selection methods for landslide susceptibility analysis

Correction to: Using hybrid artificial intelligence approach based on a neuro‑fuzzy system and evolutionary algorithms for modeling landslide susceptibility in East Azerbaijan Province, Iran

Landslide susceptibility analysis is beneficial information for a wide range of applications, including land use management plans. The present attempt has shed light on an efficient landslide susceptibility mapping framework that involves an adaptive neural-fuzzy inference system (ANFIS), which incorporates three metaheuristic methods including grey wolf optimization (GWO), particle swarm optimization (PSO), and shuffled frog leaping algorithm (SFLA) in the East Azerbaijan of Iran. To achieve this goal, 10 landslide occurrence-related influencing factors were pondered. A sum of 766 locations with landslide potentiality was recognized in the context of the study, and the Pearson correlation technique utilized in order to select the influencing factors in landslide models. The association between landslides and conditioning factors was also evaluated using a probability certainty factor (PCF) model. In the next phase, three data mining techniques were united with the ANFIS model, comprising ANFIS-grey wolf algorithm (ANFIS-GW), ANFIS-particle swarm optimization (ANFIS-PSO), and ANFIS-shuffled frog leaping algorithm (ANFIS-SFLA), were structured by the training dataset. Lastly, the receiver operating characteristic (ROC) and statistical procedures were utilized with the aim of validating and contrasting the predictive capability of the models. The findings of the study in terms of the Pearson correlation technique method for the importance ranking of conditioning factors in the context area uncovered that slope, aspect, normalized difference vegetation index (NDVI), and elevation have the highest impact on the occurrence of the landslide. All in all, the ANFIS-PSO model had high performance on both the training (RMSE = 0.288, MAE = 0.069, AUC = 0.89) and validation dataset (RMSE = 0.309, MAE = 0.097, AUC = 0.89), after which, the ANFIS-GWO model and the ANFIS-SFLA model demonstrated the second and third rates. Besides, the study revealed that benefiting the optimization algorithm with the proper selection of the techniques could facilitate landslide susceptibility modeling.

Extracting the Topographic Features as a Pragmatic Survey for Landslide Susceptibility Analysis

Landslide susceptibility mapping in the mountainous area has become crucial for taking any precautions and imperative for any disaster management. As safety factor is currently widely used to indicate the ratio of strength to stress in a unit column, it lacks what matters to the disaster response unit – the probability in which a landslide can occur in a place. A value of safety factor shows whether a unit column will fail (SF >1) but does not lead to which unit column will be prioritized for monitoring and prevention measures. Therefore, unit slopes are generated based on the watersheds to part the study area. Before evaluating the landslide movement, and types, slope analyses is required. Several references of slope classification are chosen to gain the descriptive characteristics of a certain unit column and its correlation to other topography parameters. This research paper is a step before limit equilibrium analysis where the ratio of strength-to-stress calculation cannot disregard the slope behavior and soil thickness.

Machine learning driven landslide susceptibility prediction for the Uttarkashi region of Uttarakhand in India

ABSTRACT A landslip is derived from nature and sometimes caused by human activities that endanger humanity and habitation. This work focuses on landslide behaviour for sustainable landslide mitigation and susceptibility analysis. The current research aims to evaluate three state-of-the-art machine learning techniques including, Random Forest (RF), Backpropagation Neural Network (BPNN), and Bayesian Network (BN), to predict the landslide susceptibility for the Uttarakashi district, Uttarakhand (India). For this purpose, a total of 554 landslide locations and eleven influencing factors were integrated to construct a landslide susceptibility map. The landslide inventory data were separated into training and testing sets. The receiver operating characteristic (ROC) with other statistical metrics, including sensitivity, specificity, precision, recall, and accuracy, was applied to compare the performance of machine learning techniques. The results indicated that the area under the curve (AUC) value for the RF model (AUC=0.89) is high. Furthermore, our findings showed that the RF model performs the best among all the other models with the highest training and testing accuracy, 96% and 86%, respectively. The final landslide susceptibility map is grouped into three classes, i.e. Low, Moderate, and High. The study outcome would provide support to disaster management officials in effective decision-making to prioritise necessary actions.

Retrospective evaluation of landslide susceptibility maps and review of validation practice

Despite the widespread application of landslide susceptibility analyses, there is hardly any information about whether or not the occurrence of recent landslide events was correctly predicted by the relevant susceptibility maps. Hence, the objective of this study is to evaluate four landslide susceptibility maps retrospectively in a landslide-prone area of the Swabian Alb (Germany). The predictive performance of each susceptibility map is evaluated based on a landslide event triggered by heavy rainfalls in the year 2013. The retrospective evaluation revealed significant variations in the predictive accuracy of the analyzed studies. Both completely erroneous as well as very precise predictions were observed. These differences are less attributed to the applied statistical method and more to the quality and comprehensiveness of the used input data. Furthermore, a literature review of 50 peer-reviewed articles showed that most landslide susceptibility analyses achieve very high validation scores. 73% of the analyzed studies achieved an area under curve (AUC) value of at least 80%. These high validation scores, however, do not reflect the high uncertainty in statistical susceptibility analysis. Thus, the quality assessment of landslide susceptibility maps should not only comprise an index-based, quantitative validation, but also an additional qualitative plausibility check considering local geomorphological characteristics and local landslide mechanisms. Finally, the proposed retrospective evaluation approach cannot only help to assess the quality of susceptibility maps and demonstrate the reliability of such statistical methods, but also identify issues that will enable the susceptibility maps to be improved in the future.

Quantitative Assessment of Landslide Risk Based on Susceptibility Mapping Using Random Forest and GeoDetector

This study aims to evaluate risk and discover the distribution law for landslides, so as to enrich landslide prevention theory and method. It first selected Fengjie County in the Three Gorges Reservoir Area as the study area. The work involved developing a landslide risk map using hazard and vulnerability maps utilizing landslide dataset from 2001 to 2016. The landslide dataset was built from historical records, satellite images and extensive field surveys. Firstly, under four primary conditioning factors (i.e., topographic factors, geological factors, meteorological and hydrological factors and vegetation factors), 19 dominant factors were selected from 25 secondary conditioning factors based on the GeoDetector to form an evaluation factor library for the LSM. Subsequently, the random forest model (RF) was used to analyze landslide susceptibility. Then, the landslide hazard map was generated based on the landslide susceptibility mapping (LSM) for the study region. Thereafter, landslide vulnerability assessment was conducted using key elements (economic, material, community) and the weights were provided based on expert judgment. Finally, when risk equals vulnerability multiplied by hazard, the region was categorized as very low, low, medium, high and very high risk level. The results showed that most landslides distribute on both sides of the reservoir bank and the primary and secondary tributaries in the study area, which showed a spatial distribution pattern of more north than south. Elevation, lithology and groundwater type are the main factors affecting landslides. Fengjie County landslide risk level is mostly low (accounting for 73.71% of the study area), but a small part is high and very high risk level (accounting for 2.5%). The overall risk level shows the spatial distribution characteristics of high risk in the central and eastern urban areas and low risk in the southern and northern high-altitude areas. Secondly, it is necessary to strictly control the key risk areas, and carry out prevention and control zoning management according to local conditions. The study is conducted for a specific region but can be extended to other areas around the investigated area. The developed landslide risk map can be considered by relevant government officials for the smooth implementation of management at the regional scale.

Analysis of Landslide Susceptibility Using Deep Neural Network

Landslides in Korea are caused by various factors, such as topographic characteristics, geology, and climate change, and they cause significant damage to property and human life. It is necessary to analyze landslide susceptibility to identify the location of landslide occurrence precisely and respond to the risk of landslides. In this study, the probability of landslide occurrence was calculated through a landslide sensitivity analysis using a deep neural network based on eight conditioning factors and 26 landslide data. In addition, verification was performed using the ROC method. The landslide susceptibility obtained using a deep neural network showed a success rate of 70% and a prediction rate of 81.7%, indicating that the prediction rate was 11.7% higher than the success rate. In addition, a landslide susceptibility map for estimating the probability of landslide occurrence was plotted using the geometric spacing method. The chi-square test results indicated that the landslide susceptibility map obtained in this study was statistically significant. The location of landslides can be identified more accurately using the proposed method.

Combined analysis of landslide susceptibility and soil water dynamics in a metropolitan area, northeast Brazil

Landslide susceptibility and water balance in the soil, in the community of Lagoa Encantada, Recife Metropolitan Area, Brazil, were assessed using the computational models SINMAP and HYDRUS-1D. The SINMAP input parameters were the physical and hydrodynamic characteristics of the soil, evidence of landslides and the DEM; and for the HYDRUS-1D model, the hydraulic parameters of the soil. For both programs, simulations were also carried out, based on the rain recorded in the area. The soil was classified using the Unified Soil Classification System (USCS). To assess infiltration processes that cause landslides, HYDRUS-1D was used, under the same scenarios simulated by the SINMAP model and also in the evaluation of the infiltrated volume, in real landslides. The SINMAP results (susceptibility maps) show a 71% increase in the susceptible area (SI < 1; SI = stability index) between the two precipitation scenarios, and are consistent with evidence of landslides. The HYDRUS-1D results complement SINMAP results and suggest that infiltration values for simulated scenarios were similar to those of real landslides. It is concluded that it is possible to map areas of greater instability and to predict possible landslides in different precipitation scenarios, by quantitatively assessing the infiltrated volume that contributes to the destabilization of the soil.

Influence of DEM spatial resolution on the susceptibility mapping with SHALSTAB in the Rio Garcia hydrographic basin, municipality of Blumenau/SC / Influência de la resolución espacial del MDE en la cartografía de susceptibilidad con SHALSTAB en la cuenca hidrográfica del Río García, municipio de Blumenau/SC

In translational landslide susceptibility analysis with SHALSTAB (Shallow Landsliding Stability Model), the resolution of the digital elevation model (DSM) is determinant for defining the type of mapping generated (preliminary or not). In this study, in order to verify the influence of the SDM scale on the SHALSTAB stability classes, susceptibility maps were prepared at two scales: 1:50,000 and 1:10,000. The study area was the Garcia River watershed, belonging to the municipality of Blumenau, Santa Catarina, affected by landslides in the 2008 catastrophe, which enabled the validation of the simulations with the scars mapped in the field. Thus, the influence of scale on the distribution of the model's stability classes and on its performance was verified. SHALSTAB performed better at the 1:10,000 scale, predicting 70% of the instabilities in a percentage of unstable area approximately three times smaller than at the 1,50,000 scale.