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.     

Accounting for spatial patterns of multiple geological data sets in geological thematic mapping using GIS-based spatial analysis

This paper presents a Geographic Information System (GIS)-based spatial analysis scheme to account for spatial patterns and association in geological thematic mapping with multiple geological data sets. The multi-buffer zone analysis, the main part of the present study, was addressed to reveal the spatial pattern around geological source primitives and statistical analysis based on a contingency table was performed to extract information for the assessment of an integrated layer. Mineral potential mapping using multiple geological data sets from Ogdong in Korea was carried out to illustrate application of this methodology. The results obtained from the case study indicated that some geochemical elements and residual magnetic anomaly dominantly affected spatial patterns of the mineral potential map in the study area and the dominant classes of input data layers were also extracted. This information on spatial patterns of multiple geological data sets around mines could be used as effective evidences for the interpretation of the integrated layer within GIS.     

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,...     

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.     

Flood risk perceptions and spatial multi-criteria analysis: an exploratory research for hazard mitigation

The conventional method of risk analysis (with risk as a product of probability and consequences) does not allow for a pluralistic approach that includes the various risk perceptions of stakeholders or lay people within a given social system. This article introduces a methodology that combines the virtues of three different methods: the quantifiable conventional approach to risk; the taxonomic analysis of perceived risk; and the analytical framework of a spatial multi-criteria analysis. This combination of methods is applied to the case study ‘Ebro Delta’ in Spain as part of the European sixth framework project ‘Floodsite’. First, a typology for flood hazards is developed based on individual and/or stakeholders’ judgements. Awareness, worry and preparedness are the three characteristics that typify a community to reflect various levels of ignorance, perceived security, perceived control or desired risk reduction. Applying ‘worry’ as the central characteristic, a trade-off is hypothesized between Worry and the benefits groups in society receive from a risky situation. Second, this trade-off is applied in Spatial Multi-Criteria Analysis (SMCA). MCA is the vehicle that often accompanies participatory processes, where governmental bodies have to decide on issues in which local stakeholders have a say. By using risk perception-scores as weights in a standard MCA procedure a new decision framework for risk assessment is developed. Finally, the case of sea-level rise in the Ebro Delta in Spain serves as an illustration of the applied methodology. Risk perception information has been collected with help of an on-site survey. Risk perception enters the multi-criteria analysis as complementary weights for the criteria risk and benefit. The results of the survey are applied to a set of scenarios representing both sea-level rise and land subsidence for a time span of 50 years. Land use alternatives have been presented to stakeholders in order to provide the regional decision maker with societal preferences for handling risk. Even with limited resources a characteristic ‘risk profile’ could be drawn that enables the decision maker to develop a suitable land use policy.     

Landslide susceptibility zonation mapping using logistic regression and its validation in Hashtchin Region,northwest of Iran

Landslide susceptibility zonation mapping assists researchers greatly to understand the spatial distribution of slope failure probability in a region. Being extremely useful in reducing landslide hazards, such maps could simply be produced using both qualitative and quantitative methods. In the present study, a multivariate statistical method called ‘logistic regression’ was used to assess landslide susceptibility in Hashtchin region, situated in west of Alborz Mountainsnorthwest of Iran. In this study, two independent variables, categorical (predictor) and continuous, were drawn on together in the model. To identify the region’s landslides use was made of aerial photographs, field studies and topographic maps. To prepare the database of factors affecting the region’s landslides and to determine landslide zones, geographic information system (GIS) was used. Using such information, landslide susceptibility modeling was accomplished. The data related to factors causing landslides were extracted as independent variables in each cell (in 50 m×50 m cells). Then, the whole data were input into the SPSS, Version 18. The prepared database was later analyzed using logistic regression, the forward stepwise method and based on maximum likelihood estimation. Regression equation was determined using obtained constants and coefficients and the landslide susceptibility of the area in grid-cells (pixels) was computed between 0 and 0.9954. The Receiver Operating Characteristic (ROC) curve was used to assess the accuracy of the logistic regression model. The predicting ability of the model was 84.1% given the area under ROC curve. Finally, the degree of success of landslide susceptibility zonation mapping was estimated to be 79%.     

基于ANN和GIS耦合模型的场地地震液化势评价系统研究

采用组件式GIS (COMGIS)技术开发了结合BP神经网络分析模型的场地地震液化势评价系统,调用水平成层土地震反应分析程序SHAKE91实现设定地震下地震动影响场的模拟。在VB下调用Matlab神经网络工具箱来完成场地地震液化势评价模型在COMGIS系统中的模块化;利用GIS技术对评价结果,即液化势等级进行空间复合,给出场地潜在的地层液化势空间分布图。研究表明,SHAKE91应用程序在系统菜单下可直接调用,实现地震动影响场计算的模块化;BP神经网络技术应用于场地地震液化势评价中能达到较为理想的效果;系统的GIS空间分析功能可使评价结果与场地信息进行空间匹配,实现目标场地潜在地震液化势的快速评估。     

Automatic detection of earthquake-induced ground failure effects through Faster R-CNN deep learning-based object detection using satellite images

Natural Hazards - The seismically induced ground failure is defined as any earthquake-generated process that leads to deformations within a soil medium, which in turn results in permanent...     

Predictive landslide susceptibility mapping using spatial information in the Pechabun area of Thailand

For predictive landslide susceptibility mapping, this study applied and verified probability model, the frequency ratio and statistical model, logistic regression at Pechabun, Thailand, using a geographic information system (GIS) and remote sensing. Landslide locations were identified in the study area from interpretation of aerial photographs and field surveys, and maps of the topography, geology and land cover were constructed to spatial database. The factors that influence landslide occurrence, such as slope gradient, slope aspect and curvature of topography and distance from drainage were calculated from the topographic database. Lithology and distance from fault were extracted and calculated from the geology database. Land cover was classified from Landsat TM satellite image. The frequency ratio and logistic regression coefficient were overlaid for landslide susceptibility mapping as each factor’s ratings. Then the landslide susceptibility map was verified and compared using the existing landslide location. As the verification results, the frequency ratio model showed 76.39% and logistic regression model showed 70.42% in prediction accuracy. The method can be used to reduce hazards associated with landslides and to plan land cover.     

Landslide susceptibility zonation mapping and its validation in part of Garhwal Lesser Himalaya, India, using binary logistic regression analysis and receiver operating characteristic curve method

A landslide susceptibility zonation (LSZ) map helps to understand the spatial distribution of slope failure probability in an area and hence it is useful for effective landslide hazard mitigation measures. Such maps can be generated using qualitative or quantitative approaches. The present study is an attempt to utilise a multivariate statistical method called binary logistic regression (BLR) analysis for LSZ mapping in part of the Garhwal Lesser Himalaya, India, lying close to the Main Boundary Thrust (MBT). This method gives the freedom to use categorical and continuous predictor variables together in a regression analysis. Geographic Information System has been used for preparing the database on causal factors of slope instability and landslide locations as well as for carrying out the spatial modelling of landslide susceptibility. A forward stepwise logistic regression analysis using maximum likelihood estimation method has been used in the regression. The constant and the coefficients of the predictor variables retained by the regression model have been used to calculate the probability of slope failure for the entire study area. The predictive logistic regression model has been validated by receiver operating characteristic curve analysis, which has given 91.7% accuracy for the developed BLR model.     

GIS-based hazard mapping and zonation of debris flows in Xiaojiang Basin,southwestern China

Debris flow sites were identified at 140 locations in the Xiaojiang Basin in Yunnan province, southwestern China. Their spatial distribution and catchment characteristics are described in detail on the basis of previous research, air photo interpretation, field investigation and mapping using Geographical Information Systems (GIS). Using a statistical approach, a quantitative model of hazards assessment and zonation was developed through synthesis analysis of basin areas, gradients, and the relative reliefs of these debris flow sites. In terms of debris flow hazard assessment, areas within the Xiaojiang Basin can be classified as severe, heavy and light hazard regions.     

Back analysis of landslide susceptibility zonation mapping for the 2005 Kashmir earthquake: an assessment of the reliability of susceptibility zoning maps

The October 2005 earthquake triggered several thousand landslides in the Lesser Himalaya of Kashmir in northern Pakistan and India. Analyses of ASTER satellite imagery from 2001 were compared with a study undertaken in 2005; the results show the extent and nature of pre- and co-/post-seismic landsliding. Within a designated study area of ~2,250 km², the number of landslides increased from 369 in 2001 to 2,252 in October 2005. Assuming a balanced baseline landsliding frequency over the 4 years, most of the new landslides were likely triggered by the 2005 earthquake and its aftershocks. These landslides mainly happened in specific geologic formations, along faults, rivers and roads, and in shrubland/grassland and agricultural land. Preliminary results from repeat photographs from 2005 and 2006 after the snowmelt season reveal that much of the ongoing landsliding occurred along rivers and roads, and the extensive earthquake-induced fissuring. Although the susceptibility zoning success rate for 2001 was low, many of the co-/post-seismic landsliding in 2005 occurred in areas that had been defined as being potentially dangerous on the 2001 map. While most of the area in 2001 was (very) highly susceptible to future landsliding, most of the area in 2005 was only moderate to low susceptible, that is, most of the landsliding in 2005 actually occurred in the potentially dangerous areas on the 2001 map. This study supports the view that although susceptibility zoning maps represent a powerful tool in natural hazard management, caution is needed when developing and using such maps.     

建筑物地基不均匀震陷有限元时程分析方法

根据建筑物不均匀震陷发生机制,提出了建筑物不均匀震陷二维有限元分析方法。采用了不规则荷载下土的残余应变模型及土体逐步软化模型,考虑了土、结构及地震动波形对不均匀震陷的协同作用效果,实现了对建筑物不均匀震陷的时程分析,并通过大型振动台试验对方法的可靠度进行了检验。     

Earthquake hazard zonation of Sikkim Himalaya using a GIS platform

An earthquake hazard zonation map of Sikkim Himalaya is prepared using eight thematic layers namely Geology (GE), Soil Site Class (SO), Slope (SL), Landslide (LS), Rock Outcrop (RO), Frequency–Wavenumber (F–K) simulated Peak Ground Acceleration (PGA), Predominant Frequency (PF), and Site Response (SR) at predominant frequencies using Geographic Information System (GIS). This necessitates a large scale seismicity analysis for seismic source zone classification and estimation of maximum earthquake magnitude or maximum credible earthquake to be used as a scenario earthquake for a deterministic or quasi-probabilistic seismic scenario generation. The International Seismological Center (ISC) and Global Centroid Moment Tensor (GCMT) catalogues have been used in the present analysis. Combining b-value, fractal correlation dimension (Dc) of the epicenters and the underlying tectonic framework, four seismic source zones are classified in the northeast Indian region. Maximum Earthquake of M _W 8.3 is estimated for the Eastern Himalayan Zone (EHZ) and is used to generate the seismic scenario of the region. The Geohazard map is obtained through the integration of the geological and geomorphological themes namely GE, SO, SL, LS, and RO following a pair-wise comparison in an Analytical Hierarchy Process (AHP). Detail analysis of SR at all the recording stations by receiver function technique is performed using 80 significant events recorded by the Sikkim Strong Motion Array (SSMA). The ground motion synthesis is performed using F–K integration and the corresponding PGA has been estimated using random vibration theory (RVT). Testing for earthquakes of magnitude greater than M _W 5, a few cases presented here, establishes the efficacy and robustness of the F–K simulation algorithm. The geohazard coverage is overlaid and sequentially integrated with PGA, PF, and SR vector layers, in order to evolve the ultimate earthquake hazard microzonation coverage of the territory. Earthquake Hazard Index (EHI) quantitatively classifies the terrain into six hazard levels, while five classes could be identified following the Bureau of Indian Standards (BIS) PGA nomenclature for the seismic zonation of India. EHI is found to vary between 0.15 to 0.83 quantitatively classifying the terrain into six hazard levels as “Low” corresponding to BIS Zone II, “Moderate” corresponding to BIS Zone III, “Moderately High” belonging to BIS Zone IV, “High” corresponding to BIS Zone V(A), “Very High” and “Severe” with new BIS zones to Zone V(B) and V(C) respectively.