A GIS-based landslide susceptibility evaluation using bivariate and multivariate statistical analyses

Bivariate and multivariate statistical analyses were used to predict the spatial distribution of landslides in the Cuyahoga River watershed, northeastern Ohio, U.S.A. The relationship between landslides and various instability factors contributing to their occurrence was evaluated using a Geographic Information System (GIS) based investigation. A landslide inventory map was prepared using landslide locations identified from aerial photographs, field checks, and existing literature. Instability factors such as slope angle, soil type, soil erodibility, soil liquidity index, landcover pattern, precipitation, and proximity to stream, responsible for the occurrence of landslides, were imported as raster data layers in ArcGIS, and ranked using a numerical scale corresponding to the physical conditions of the region. In order to investigate the role of each instability factor in controlling the spatial distribution of landslides, both bivariate and multivariate models were used to analyze the digital dataset. The logistic regression approach was used in the multivariate model analysis. Both models helped produce landslide susceptibility maps and the suitability of each model was evaluated by the area under the curve method, and by comparing the maps with the known landslide locations. The multivariate logistic regression model was found to be the better model in predicting landslide susceptibility of this area. The logistic regression model produced a landslide susceptibility map at a scale of 1:24,000 that classified susceptibility into four categories: low, moderate, high, and very high. The results also indicated that slope angle, proximity to stream, soil erodibility, and soil type were statistically significant in controlling the slope movement.     

Landslide susceptibility mapping using machine learning algorithms and comparison of their performance at Abha Basin,Asir Region,Saudi Arabia

The current study aimed at evaluating the capabilities of seven advanced machine learning techniques(MLTs),including,Support Vector Machine(SVM),Random Forest(RF),Multivariate Adaptive Regression Spline(MARS),Artificial Neural Network(ANN),Quadratic Discriminant Analysis(QDA),Linear Discriminant Analysis(LDA),and Naive Bayes(NB),for landslide susceptibility modeling and comparison of their performances.Coupling machine learning algorithms with spatial data types for landslide susceptibility mapping is a vitally important issue.This study was carried out using GIS and R open source software at Abha Basin,Asir Region,Saudi Arabia.First,a total of 243 landslide locations were identified at Abha Basin to prepare the landslide inventory map using different data sources.All the landslide areas were randomly separated into two groups with a ratio of 70%for training and 30%for validating purposes.Twelve landslide-variables were generated for landslide susceptibility modeling,which include altitude,lithology,distance to faults,normalized difference vegetation index(NDVI),landuse/landcover(LULC),distance to roads,slope angle,distance to streams,profile curvature,plan curvature,slope length(LS),and slope-aspect.The area under curve(AUC-ROC)approach has been applied to evaluate,validate,and compare the MLTs performance.The results indicated that AUC values for seven MLTs range from 89.0%for QDA to 95.1%for RF.Our findings showed that the RF(AUC=95.1%)and LDA(AUC=941.7%)have produced the best performances in comparison to other MLTs.The outcome of this study and the landslide susceptibility maps would be useful for environmental protection.     

GIS-based landslide susceptibility modeling: A comparison between fuzzy multi-criteria and machine learning algorithms

Hazards and disasters have always negative impacts on the way of life.Landslide is an overwhelming natural as well as man-made disaster that causes loss of natural resources and human properties throughout theworld.The present study aimed to assess and compare the prediction efficiency of different models in landslide susceptibility in the Kysuca river basin,Slovakia.In this regard,the fuzzy decision-making trial and evaluation laboratory combining with the analytic network process(FDEMATEL-ANP),Na?ve Bayes(NB)classifier,and random forest(RF)classifier were considered.Initially,a landslide inventory map was produced with 2000 landslide and nonlandslide points by randomly dividedwith a ratio of 70%:30%for training and testing,respectively.The geospatial database for assessing the landslide susceptibility was generated with the help of 16 landslide conditioning factors by allowing for topographical,hydrological,lithological,and land cover factors.The ReliefF methodwas considered for determining the significance of selected conditioning factors and inclusion in the model building.Consequently,the landslide susceptibility maps(LSMs)were generated using the FDEMATEL-ANP,Na?ve Bayes(NB)classifier,and random forest(RF)classifier models.Finally,the area under curve(AUC)and different arithmetic evaluation were used for validating and comparing the results and models.The results revealed that random forest(RF)classifier is a promising and optimum model for landslide susceptibility in the study area with a very high value of area under curve(AUC=0.954),lower value of mean absolute error(MAE=0.1238)and root mean square error(RMSE=0.2555),and higher value of Kappa index(K=0.8435)and overall accuracy(OAC=92.2%).     

Urban flood susceptibility analysis using a GIS-based multi-criteria analysis framework

Natural Hazards - Pluvial flooding is a common type of natural hazard caused by rainfall events with high intensity and short duration, which may lead to substantial property damages,...     

Landslide susceptibility mapping using GIS-based multi-criteria decision analysis,support vector machines,and logistic regression

Identification of landslides and production of landslide susceptibility maps are crucial steps that can help planners, local administrations, and decision makers in disaster planning. Accuracy of the landslide susceptibility maps is important for reducing the losses of life and property. Models used for landslide susceptibility mapping require a combination of various factors describing features of the terrain and meteorological conditions. Many algorithms have been developed and applied in the literature to increase the accuracy of landslide susceptibility maps. In recent years, geographic information system-based multi-criteria decision analyses (MCDA) and support vector regression (SVR) have been successfully applied in the production of landslide susceptibility maps. In this study, the MCDA and SVR methods were employed to assess the shallow landslide susceptibility of Trabzon province (NE Turkey) using lithology, slope, land cover, aspect, topographic wetness index, drainage density, slope length, elevation, and distance to road as input data. Performances of the methods were compared with that of widely used logistic regression model using ROC and success rate curves. Results showed that the MCDA and SVR outperformed the conventional logistic regression method in the mapping of shallow landslides. Therefore, multi-criteria decision method and support vector regression were employed to determine potential landslide zones in the study area.     

Site response assessment of an urban extension site using microtremor measurements,Ahud Rufeidah,Abha District,Southwest Saudi Arabia

Arabian Journal of Geosciences - Microtremor horizontal-to-vertical spectral ratio (HVSR) method has been conducted at 33 sites in Ahud Rufeidah urban expansion zone in order to assess the...     

GIS-based landslide susceptibility mapping using bivariate statistical analysis in Devrek (Zonguldak-Turkey)

Devrek town with increasing population is located in a hillslope area where some landslides exist. Therefore, landslide susceptibility map of the area is required. The purpose of this study was to generate a landslide susceptibility map using a bivariate statistical index and evaluate and compare the results of the statistical analysis conducted with three different approaches in seed cell concept resulting in different data sets in Geographical Information Systems (GIS) based landslide susceptibility mapping applied to the Devrek region. The data sets are created from the seed cells of (a) crowns and flanks, (b) only crowns, and (c) only flanks of the landslides by using ten different causative parameters of the study area. To increase the data dependency of the analysis, all parameter maps are classified into equal frequency classes based directly on the percentile divisions of each corresponding seed cell data set. The resultant maps of the landslide susceptibility analysis indicate that all data sets produce fairly acceptable results. In each data set analysis, elevation, lithology, slope, aspect, and drainage density parameters are found to be the most contributing factors in landslide occurrences. The results of the three data sets are compared using Seed Cell Area Indexes (SCAI). This comparison shows that the crown data set produces the most accurate and successful landslide susceptibility map of the study area.     

Assessment of shallow landslide susceptibility using the transient infiltration flow model and GIS-based probabilistic approach

This study proposes a probabilistic analysis method for modeling rainfall-induced shallow landslide susceptibility by combining a transient infiltration flow model and Monte Carlo simulations. The spatiotemporal change in pore water pressure over time caused by rainfall infiltration is one of the most important factors causing landslides. Therefore, the transient infiltration hydrogeological model was adopted to estimate the pore water pressure within the hill slope and to analyze landslide susceptibility. In addition, because of the inherent uncertainty and variability caused by complex geological conditions and the limited number of available soil samples over a large area, this study utilized probabilistic analysis based on Monte Carlo simulations to account for the variability in the input parameters. The analysis was performed in a geographic information system (GIS) environment because GIS can deal efficiently with a large volume of spatial data. To evaluate its effectiveness, the proposed analysis method was applied to a study area that had experienced a large number of landslides in July 2006. For the susceptibility analysis, a spatial database of input parameters and a landslide inventory map were constructed in a GIS environment. The results of the landslide susceptibility assessment were compared with the landslide inventory, and the proposed approach demonstrated good predictive performance. In addition, the probabilistic method exhibited better performance than the deterministic alternative. Thus, analysis methods that account for uncertainties in input parameters are more appropriate for analysis of an extensive area, for which uncertainties may significantly affect the predictions because of the large area and limited data.     

GIS-based landslide susceptibility for Arsin-Yomra (Trabzon,North Turkey) region

The purpose of this study is to assess the susceptibility of landslides around Yomra and Arsin towns near Trabzon, in northeast of Turkey, using a geographical information system (GIS). Landslide inventory of the area was made by detailed field surveys and the analyses of the topographical map. The landslide triggering factors are considered to be slope angle, slope aspect, distance from drainage, distance from roads and the weathered lithological units, which were called as “geotechnical units” in the study. Idrisi and ArcGIS packages manipulated all the collected data. Logistic regression (LR) and weighted linear combination (WLC) statistical methods were used to create a landslide susceptibility map for the study area. The results were assessed within the scope of two different points: (a) effectiveness of the methods used and (b) effectiveness of the environmental casual parameters influencing the landslides. The results showed that the WLC model is more suitable than the LR model. Regarding the casual parameters, geotechnical units and slopes were found to be the most important variables for estimating the landslide susceptibility in the study area.     

Generation of a landslide risk index map for Cuba using spatial multi-criteria evaluation

This paper explains the procedure for the generation of a landslide risk index map at national level in Cuba, using a semi-quantitative model with ten indicator maps and a cell size of 90 × 90 m. The model was designed and implemented using spatial multi-criteria evaluation techniques in a GIS system. Each indicator was processed, analysed and standardised according to its contribution to hazard and vulnerability. The indicators were weighted using direct, pairwise comparison and rank-ordering weighting methods, and weights were combined to obtain the final landslide risk index map. The results were analysed per physiographic region and administrative units at provincial and municipal levels. The Sierra Maestra mountain system was found to have the largest concentration of high landslide risk index values while the Nipe–Cristal–Baracoa system has the highest absolute values, although they are more dispersed. The results obtained allow designing an appropriated landslide risk mitigation plan at national level and to link the information to the national hurricane early warning system, allowing also warning and evacuation for landslide-prone areas.     

Magnetic and seismic refraction survey for site investigation of an urban expansion site in Abha District,Southwest Saudi Arabia

Arabian Journal of Geosciences - Ground magnetic and seismic refraction survey is carried out on an urban extension site in the southwest of Ahud Rufeidah town, southwest Saudi Arabia. The purpose...     

GIS-based assessment of landslide susceptibility on the base of the Weights-of-Evidence model

The major scope of the study is the assessment of landslide susceptibility of Flysch areas including the Penninic Klippen in the Vienna Forest (Lower Austria) by means of Geographical Information System (GIS)-based modelling. A statistical/probabilistic method, referred to as Weights-of-Evidence (WofE), is applied in a GIS environment in order to derive quantitative spatial information on the predisposition to landslides. While previous research in this area concentrated on local geomorphological, pedological and slope stability analyses, the present study is carried out at a regional level. The results of the modelling emphasise the relevance of clay shale zones within the Flysch formations for the occurrence of landslides. Moreover, the distribution of mass movements is closely connected to the fault system and nappe boundaries. An increased frequency of landslides is observed in the proximity to drainage lines, which can change to torrential conditions after heavy rainfall. Furthermore, landslide susceptibility is enhanced on N-W facing slopes, which are exposed to the prevailing direction of wind and rainfall. Both of the latter geofactors indirectly show the major importance of the hydrological conditions, in particular, of precipitation and surface runoff, for the occurrence of mass movements in the study area. Model performance was checked with an independent validation set of landslides, which are not used in the model. An area of 15% of the susceptibility map, classified as highly susceptible, “predicted” 40% of the landslides.     

Performance evaluation of ensemble learning techniques for landslide susceptibility mapping at the Jinping county,Southwest China

Natural Hazards - The objective of this study is to investigate different ensemble learning techniques namely Bagging, Boosting, and Stacking for LSM at the Jinping county, Southwest China. Two...     

GIS-based multi-criteria earthquake hazards evaluation using analytic hierarchy process for a nuclear power plant site,west Alexandria,Egypt

Nuclear power plants are designed to prevent the hazardous effects of the earthquakes and any external events to keep the safety of the plant. Ninety-one shallow seismic refraction profiles were performed to determine shear wave velocity of the engineering layers at the site of El Dabaa area that is situated to the northern coastline of Egypt for seismic hazard microzonation evaluation according to hazard index values. A microzonation is a procedure of delineating an area into individual zones having different ranks of numerous seismic hazards. This will aid in classifying areas of high seismic risk which is vigorous for industrial design of nuclear structures. The site response analysis requires the characterization of subsurface materials considering local subsurface profiles of the site. Site classification of the area under investigation was undertaken using P- and S-waves and available borehole data. The studied nuclear power plant site has been characterized as per NEHRP site classification using an average velocity of transverse wave (V _s ³⁰ ) of depth 30 m which acquired from seismic survey. This site was categorized into two site classes: the major one is “site class B,” and the minor one is “site class A.” The attenuation coefficient, the damping ratio and the liquefaction potential are geotechnical parameters which were derived from P- and S-waves, and have their major effects on the seismic hazard contribution. 1D ground response analysis was carried out in the places of seismic profiles inside the site for estimating the amount of ground quaking using peak ground acceleration (PGA), site amplification, predominant frequency and spectral accelerations on the surface of ground by the DEEPSOIL software package. Seven factors (criteria) deliberated to assess the earthquake hazard index map are: (1) the peak ground acceleration at the bedrock, (2) the amplification of the site, (3) the liquefaction potential, (4) the main frequency of the earthquake signal, (5) the average V _s of the first 30 m from the ground surface, (6) the depth to the groundwater and (7) the depth to the bedrock. These features were exemplified in normalized maps after uniting them to 0–1 scores according to some criteria by the minimum and maximum values as linear scaling points. Multi-criteria evaluation is an application of multi-criteria decision analysis theory that used for developing a seismic hazard index map for a nuclear power plant site at El Dabaa area in ArcGIS 10.1 software. Two models of decision making were used in this work for seismic hazard microzonation. The analytic hierarchy process model was applied to conduct the relative weights of the criteria by pairwise comparison using Expert Choice Software. An earthquake hazard index map was combined using Weighted Linear Combination model of the raster weighted overlay tool of ArcGIS 10.1. The results indicated that most of the study site of the nuclear power plant is a region of low to moderate hazard; its values are ranging between 0.2 and 0.4.     

GIS-based landslide susceptibility zonation for roadside slope repair and maintenance in the Himalayan region

Roadside slope failure is a common problem in the Himalayan region as road construction activities disturb natural slopes. Therefore, landslide susceptibility zonation is necessary for roadside slope disaster management and planning development activities. In this study, we consider a 53-kin section of a major highway in Nepal where road services are suspended for several days in the monsoon season every year. A number of methods have been used for landslide susceptibility zonation. We employed a bivariate statistical approach for this study. Relevant thematic layer maps represent- ing various factors （e.g., slope, aspect, land use, lithology, drainage density, proximity to stream and proximity to road） that are related to landslide activity, have been prepared using Geographic Information System （GIS） techniques. A total of 277 landslides （covering a total of 29.90 km2） of various dimensions have been identified in the area. A landslide susceptibility map was prepared by overlaying a landslide inventory map with various parameter maps segmented into various relevant classes. The landslide susceptibility index was seg- mented into five zones, viz. very low, low, moderate, high and very high susceptibility. Landslide susceptibility zonation maps are useful tools for the efficient planning and management of roadside slope repair and maintenance tasks in the Himalayan region.     

Comparative evaluation of landslide susceptibility in Minamata area, Japan

Landslides are unpredictable; however, the susceptibility of landslide occurrence can be assessed using qualitative and quantitative methods based on the technology of the Geographic Information Systems (GIS). A map of landslide inventory was obtained from the previous work in the Minamata area, the interpretation from aerial photographs taken in 1999 and 2002. A total of 160 landslides was identified in four periods. Following the construction of geospatial databases, including lithology, topography, soil deposits, land use, etc., the study documents the relationship between landslide hazard and the factors that affect the occurrence of landslides. Different methods, namely the logistic regression analysis and the information value model, were then adopted to produce susceptibility maps of landslide occurrence. After the application of each method, two resultant maps categorize the four classes of susceptibility as high, medium, low and very low. Both of them generated acceptable results as both classify the majority of the cells with landslide occurrence in high or medium susceptibility classes, which could be believed to be a success. By combining the hazard maps generated from both methods, the susceptibility was classified as high–medium and low–very low levels, in which the classification of high susceptibility level covers 6.5% of the area, while the areas predicted to be unstable, which are 50.5% of the total area, are classified as the low susceptibility level. However, comparing the results from both the approaches, 43% of the areas were misclassified, either from high–medium to low–very low or low–very low to high–medium classes. Due to the misclassification, 8% and 3.28% of all the areas, which should be stable or free of landsliding, were evaluated as high–medium susceptibility using the logistic regression analysis and the information value model, respectively. Moreover, in the case of the class rank change from high–medium susceptibility to low–very low, 35% and 39.72% of all mapping areas were predicted as stable using both the approaches, respectively, but in these areas landslides were likely to occur or were actually recognized.