A comparison of the GIS based landslide susceptibility assessment methods: multivariate versus bivariate

The purpose of this study is to evaluate and to compare the results of multivariate (logical regression) and bivariate (landslide susceptibility) methods in Geographical Information System (GIS) based landslide susceptibility assessment procedures. In order to achieve this goal the Asarsuyu catchment in NW Turkey was selected as a test zone because of its well-known landslide occurrences interfering with the E-5 highway mountain pass.Two methods were applied to the test zone and two separate susceptibility maps were produced. Following this a two-fold comparison scheme was implemented. Both methods were compared by the Seed Cell Area Indexes (SCAI) and by the spatial locations of the resultant susceptibility pixels.It was found that both of the methods converge in 80% of the area; however, the weighting algorithm in the bivariate technique (landslide susceptibility method) had some severe deficiencies, as the resultant hazard classes in overweighed areas did not converge with the factual landslide inventory map. The result of the multivariate technique (logical regression) was more sensitive to the different local features of the test zone and it resulted in more accurate and homogeneous susceptibility maps.     

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.     

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.     

Flood susceptibility mapping using integrated bivariate and multivariate statistical models

Flooding can have catastrophic effects on human lives and livelihoods and thus comprehensive flood management is needed. Such management requires information on the hydrologic, geotechnical, environmental, social, and economic aspects of flooding. The number of flood events that took place in Busan, South Korea, in 2009 exceeded the normal situation for that city. Mapping the susceptible areas helps us to understand flood trends and can aid in appropriate planning and flood prevention. In this study, a combination of bivariate probability analysis and multivariate logistic regression was used to produce flood susceptibility maps of Busan City. The main aim of this research was to overcome the weakness of logistic regression regarding bivariate probability capabilities. A flood inventory map with a total of 160 flood locations was extracted from various sources. Then, the flood inventory was randomly split into a testing dataset 70 % for training the models and the remaining 30 %, which was used for validation. Independent variables datasets included the rainfall, digital elevation model, slope, curvature, geology, green farmland, rivers, slope, soil drainage, soil effect, soil texture, stream power index, timber age, timber density, timber diameter, and timber type. The impact of each independent variable on flooding was evaluated by analyzing each independent variable with the dependent flood layer. The validation dataset, which was not used for model generation, was used to evaluate the flood susceptibility map using the prediction rate method. The results of the accuracy assessment showed a success rate of 92.7 % and a prediction rate of 82.3 %.     

Comparing predictive capability of statistical and deterministic methods for landslide susceptibility mapping: a case study in the northern Apennines (Reggio Emilia Province, Italy)

Statistical and deterministic methods are widely used in geographic information system based landslide susceptibility mapping. This paper compares the predictive capability of three different models, namely the Weight of Evidence, the Fuzzy Logic and SHALSTAB, for producing shallow earth slide susceptibility maps, to be included as informative layers in land use planning at a local level. The test site is an area of about 450 km² in the northern Apennines of Italy where, in April 2004, rainfall combined with snowmelt triggered hundreds of shallow earth slides that damaged roads and other infrastructure. An inventory of the landslides triggered by the event was obtained from interpretation of aerial photos dating back to May 2004. The pre-existence of mapped landslides was then checked using earlier aerial photo coverage. All the predictive models were run on the same set of geo-environmental causal factors: soil type, soil thickness, land cover, possibility of deep drainage through the bedrock, slope angle, and upslope contributing area. Model performance was assessed using a threshold-independent approach (the ROC plot). Results show that global accuracy is as high as 0.77 for both statistical models, while it is only 0.56 for SHALSTAB. Besides the limited quality of input data over large areas, the relatively poorer performance of the deterministic model maybe also due to the simplified assumptions behind the hydrological component (steady-state slope parallel flow), which can be considered unsuitable for describing the hydrologic behavior of clay slopes, that are widespread in the study area.     

Validation and evaluation of two multivariate statistical models for predictive shallow landslide susceptibility mapping of the Eastern Pyrenees (Spain)

This paper deals with the quality of two multivariate statistical models based on the Geographical Information System for shallow landslide susceptibility assessment in a test area at La Pobla de Lillet (Eastern Pyrenees, Spain). The quality, which was guaranteed by a rigorous methodology based on a suitable diagnosis, validation, and evaluation of the models, ensured a reliable contrast of the final susceptibility maps. This enables us to transfer the best results to the end user. Landslide susceptibility models were carried out by logistic regression and discriminant analysis of the significant conditioning factors related to the characteristics of the slope and the upslope contributing area captured from the digital elevation model and landslide distribution. The explanatory variables were tested (KS test, principal components and one-way and T-test) to select the most statistically significant ones before being introduced into the logistic and discriminant analyses. Accuracy statistics and the receiver operating characteristic curve used for diagnosis and validation showed similar prediction skills and a good fit to the data with more than 85% of unfailed cells properly classified for the two models. The evaluation of the study area and the correlation function (R ² = 0.83) between the models revealed that the discriminant model overestimated the susceptibility of the most stable zones with respect to the logistic model. Different methods of producing susceptibility maps showed marked differences in matching the models. Substantial spatial agreement (Kappa = 0.741) between binary maps produced by the standard cut-off value descended moderately (Kappa = 0.540) as a result of superimposing maps with five susceptibility levels defined by landslide percentage. Despite the fact that the two statistical models are similar in assessing susceptibility in the study area, the implications for hazard and risk management can be different because of the conservative nature of the discriminant model.     

Improvement of statistical landslide susceptibility mapping by using spatial and global regression methods in the case of More and Romsdal (Norway)

Statistical models are one of the most preferred methods among many landslide susceptibility assessment methods. As landslide occurrences and influencing factors have spatial variations, global models like neural network or logistic regression (LR) ignore spatial dependence or autocorrelation characteristics of data between the observations in susceptibility assessment. However, to assess the probability of landslide within a specified period of time and within a given area, it is important to understand the spatial correlation between landslide occurrences and influencing factors. By including these relations, the predictive ability of the developed model increases. In this respect, spatial regression (SR) and geographically weighted regression (GWR) techniques, which consider spatial variability in the parameters, are proposed in this study for landslide hazard assessment to provide better realistic representations of landslide susceptibility. The proposed model was implemented to a case study area from More and Romsdal region of Norway. Topographic (morphometric) parameters (slope angle, slope aspect, curvature, plan, and profile curvatures), geological parameters (geological formations, tectonic uplift, and lineaments), land cover parameter (vegetation coverage), and triggering factor (precipitation) were considered as landslide influencing factors. These influencing factors together with past rock avalanche inventory in the study region were considered to obtain landslide susceptibility maps by using SR and LR models. The comparisons of susceptibility maps obtained from SR and LR show that SR models have higher predictive performance. In addition, the performances of SR and LR models at the local scale were investigated by finding the differences between GWR and SR and GWR and LR maps. These maps which can be named as comparison maps help to understand how the models estimate the coefficients at local scale. In this way, the regions where SR and LR models over or under estimate the landslide hazard potential were identified.     

Geomorphology and landslide susceptibility assessment using GIS and bivariate statistics: a case study in southern Italy

In this article, the results of a study aimed to assess the landslide susceptibility in the Calaggio Torrent basin (Campanian Apennines, southern Italy) are presented. The landslide susceptibility has been assessed using two bivariate-statistics-based methods in a GIS environment. In the first method, widely used in the existing literature, weighting values (Wi) have been calculated for each class of the selected causal factors (lithology, land-use, slope angle and aspect) taking into account the landslide density (detachment zones + landslide body) within each class. In the second method, which is a modification of the first method, only the landslide detachment zone (LDZ) density has been taken into account to calculate the weighting values. This latter method is probably characterized by a major geomorphological coherence. In fact, differently from the landslide bodies, LDZ must necessarily occur in geoenvironmental classes prone to failure. Thus, the calculated Wi seem to be more reliable in estimating the propensity of a given class to generate failure. The thematic maps have been reclassified on the basis of the calculated Wi and then overlaid, with the purpose to produce landslide susceptibility maps. The used methods converge both in indicating that most part of the study area is characterized by a high–very high landslide susceptibility and in the location and extent of the low-susceptible areas. However, an increase of both the high–very high and moderate–high susceptible areas occurs in using the second method. Both the produced susceptibility maps have been compared with the geomorphological map, highlighting an excellent coherence which is higher using method-2. In both methods, the percentage of each susceptibility class affected by landslides increases with the degree of susceptibility, as expected. However, the percentage at issue in the lowest susceptibility class obtained using method-2, even if low, is higher than that obtained using method-1. This suggests that method-2, notwithstanding its major geomorphological coherence, probably still needs further refinements.     

A comparative study on the landslide susceptibility mapping using logistic regression and statistical index models

The logistic regression and statistical index models are applied and verified for landslide susceptibility mapping in Daguan County, Yunnan Province, China, by means of the geographic information system (GIS). A detailed landslide inventory map was prepared by literatures, aerial photographs, and supported by field works. Fifteen landslide-conditioning factors were considered: slope angle, slope aspect, curvature, plan curvature, profile curvature, altitude, STI, SPI, and TWI were derived from digital elevation model; NDVI was extracted from Landsat ETM7; rainfall was obtained from local rainfall data; distance to faults, distance to roads, and distance to rivers were created from a 1:25,000 scale topographic map; the lithology was extracted from geological map. Using these factors, the landslide susceptibility maps were prepared by LR and SI models. The accuracy of the results was verified by using existing landslide locations. The statistical index model had a predictive rate of 81.02%, which is more accurate prediction in comparison with logistic regression model (80.29%). The models can be used to land-use planning in the study area.     

机器学习及其相关算法综述

机器学习已经在滑坡易发性评价中大量应用且取得了较好的表现,但在进行大区域评价时,仍存在数据库样本需求量大,算力要求高;影响因素分级机械化,未考虑其与滑坡机理的相关性等情况。为减少数据库样本需求,本文提出了构建包含3种坡体状态的滑坡的数据库：已经发生过失稳的坡体、正处于失稳状态的坡体、失稳概率小的坡体,该数据库可以在数值上划分出临界值,便于模型更准确地识别滑坡,较大幅度地减小了数据量。针对影响因素分级机械化的问题,提出了基于频数分布图、累计曲线及其导数图的数理统计方式,更精细地描述因数与滑坡易发性的关系。以新疆滑坡灾害为例,验证了“包含3种坡体状态的数据库”与“基于数理统计的描述方法”的适用性,获得了新疆滑坡灾害易发性分区图。结果表明与传统数据库对比,在不明显改变精度的前提下,减少了90%以上的样本量;基于数理统计的描述方法可以绘制出更加细致的滑坡危险性分区图;活动性断裂和地形起伏度对新疆滑坡易发性起到重要的控制作用。     

Evaluation and comparison of GIS based landslide susceptibility mapping procedures in Kulekhani watershed, Nepal

The goal of this paper is to evaluate and compare the consistency of GIS-based heuristic and bivariate landslide susceptibility mapping techniques in the Himalayan region, taking the Kulekhani watershed of central Nepal as an example. For this purpose, a heuristic and two statistical bivariate landslide susceptibility mapping methods are applied, and three separate landslide susceptibility zonation maps are produced. The maps are compared using three approaches: landslide density analysis, success rate analysis, and agreed area analysis. A comparison of the values obtained from landslide density analysis and the curves of success rate analysis indicate that the two bivariate methods produce almost identical results, whereas the map produced with the heuristic method differs significantly from the others. On the other hand, the agreed area analysis highlights significant spatial differences in the maps obtained from the three methods. Although the three approaches evaluate the consistency of susceptibility maps, only the agreed area analysis is capable of spatially comparing them. Hence, this approach proves to be more suitable for spatially and quantitatively evaluating the consistency of various landslide susceptibility zonation maps.     

Evaluation of the consistency of landslide susceptibility mapping: a case study from the Kankai watershed in east Nepal

GIS-based landslide susceptibility maps for the Kankai watershed in east Nepal are developed using the frequency ratio method and the multiple linear regression technique. The maps are derived from comparing observed landslides with possible causative factors: slope angle, slope aspect, slope curvature, relative relief, distance from drainage, land use, geology, distance from faults and mean annual rainfall. The consistency of the maps is evaluated using landslide density analysis, success rate analysis and spatially agreed area approach. The first two analyses produce almost identical quantitative results, whereas the last approach is able to reveal spatial differences between the maps and also to improve predictions in the agreed high landslide-susceptible area.     

PFR model and GiT for landslide susceptibility mapping: a case study from Central Alborz, Iran

In northern parts of Iran such as the Alborz Mountain belt, frequent landslides occur due to a combination of climate and geologic conditions with high tectonic activities. This results in millions of dollars of financial damages annually excluding casualties and unrecoverable resources. This paper evaluates the landslide susceptible areas in Central Alborz using the probabilistic frequency ratio (PFR) model and Geo-information Technology (GiT). The landslide location map in this study has been generated based on image elements interpreted from IRS satellite data and field observations. The display, manipulation and analysis have been carried out to evaluate layers such as geology, geomorphology, soil, slope, aspect, land use, distance from faults, lineaments, roads and drainages. The validation group of actual landslides and relative operation curve method has been used to increase the accuracy of the final landslide susceptibility map. The area under the curve evaluates how well the method predicts landslides. The results showed a satisfactory agreement of 91% between prepared susceptibility map and existing data on landslide locations.     

A statistical approach to landslide risk modelling at basin scale: from landslide susceptibility to quantitative risk assessment

A procedure for landslide risk assessment is presented. The underlying hypothesis is that statistical relationships between past landslide occurrences and conditioning variables can be used to develop landslide susceptibility, hazard and risk models. The latter require also data on past damages. Landslides occurred during the last 50 years and subsequent damages were analysed. Landslide susceptibility models were obtained by means of Spatial Data Analysis techniques and independently validated. Scenarios defined on the basis of past landslide frequency and magnitude were used to transform susceptibility into quantitative hazard models. To assess vulnerability, a detailed inventory of exposed elements (infrastructures, buildings, land resources) was carried out. Vulnerability values (0–1) were obtained by comparing damages experienced in the past by each type of element with its actual value. Quantitative risk models, with a monetary meaning, were obtained for each element by integrating landslide hazard and vulnerability models. Landslide risk models showing the expected losses for the next 50 years were thus obtained for the different scenarios. Risk values obtained are not precise predictions of future losses but rather a means to identify areas where damages are likely to be greater and require priority for mitigation actions.     

Innovative landslide susceptibility mapping supported by geomorphon and geographical detector methods

Landslides are among the most common and dangerous natural hazards in mountainous regions that can cause damage to properties and loss of lives. Landslide susceptibility mapping (LSM) is a critical tool for preventing or mitigating the negative impacts of landslides. Although many previous studies have employed various statistical methods to produce quantitative maps of the landslide susceptibility index (LSI) based on inventories of past landslides and contributing factors, they are mostly ad hoc to a specific area and their success has been hindered by the lack of a methodology that could produce the right mapping units at proper scale and by the lack of a general framework for objectively accounting for the differing contribution of various preparatory factors. This paper addresses these issues by integrating the geomorphon and geographical detector methods into LSM to improve its performance. The geomorphon method, an innovative pattern recognition approach for identifying landform elements based on the line of sight concept, is adapted to delineate ridge lines and valley lines to form slope units at self-adjusted spatial scale suitable for LSM. The geographical detector method, a spatial variance analysis method, is integrated to objectively assign the weights of contributing factors for LSM. Applying the new integrated approach to I-Lan, Taiwan produced very significant improvement in LSI mapping performance than a previous model, especially in highly susceptible areas. The new method offers a general framework for better mapping landslide susceptibility and mitigating its negative impacts.     

Development of hybrid wavelet packet-statistical models (WP-SM) for landslide susceptibility mapping

Landslides are recognized as one of the most important natural hazards in many areas throughout the world. Producing landslide susceptibility maps have received particular attention from a wide range of scientists. The main objective of this study was to produce landslide susceptibility maps using hybrid wavelet packet-statistical models (WP-SM). In the first step, landslide susceptibility maps were produced using single artificial neural network (ANN), support vector machine (SVM), maximum entropy (MaxEnt), and generalized linear model (GLM). In the next step, the input maps were preprocessed using different mother wavelets in different levels. Then, the hybrid models were developed using the wavelet-based preprocessed maps. Results showed that the wavelet packet transform can be effectively used to produce precise landslide susceptibility maps. It was shown that wavelet packet transform significantly enhanced the ability of the single statistical models. The kappa coefficients were increased from 0.829 to 0.941, 0.846 to 0.978, 0.744 to 0.829, and 0.735 to 0.817 in hybrid ANN, SVM, MaxEnt, and GLM, respectively. The best wavelet transform was performed using bior1.5 with a three-level decomposition. It was also recognized that MaxEnt and GLM produced approximately poor results. However, SVM performed better than the other three models both in single and hybrid forms. ANN also outperformed MaxEnt and GLM models. Spatial distribution of the susceptible area is consistent with the observed landslide distribution pattern particularly in maps obtained from the hybrid models. The produced maps showed that the general pattern of susceptible area intensively followed the pattern of roads and sensitive geological formations.     

基于XGBoost模型的三峡库区燕山乡滑坡易发性评价与区划

滑坡易发性评价是精细化滑坡灾害风险评价的基础。为了提升滑坡易发性评价模型的精度和稳健性,以三峡库区万州区燕山乡为例,选取工程地质岩组、堆积层厚度等九个影响因子构建滑坡易发性评价指标体系,应用信息量模型定量分析滑坡发育与指标之间的关系。在此基础上,随机选取70%/30%的滑坡样本作为训练/验证数据集,应用极致梯度提升模型(extreme gradient boosting, XGBoost)开展易发性评价。随后从模型预测精度和模型稳定性两方面将其与决策树模型(decision tree, DT)和梯度提升树模型(gradient boosting decision tree, GBDT)进行对比。结果表明：研究区堆积层滑坡主要受长江水系、堆积层厚度和工程地质岩组影响。XGBoost模型具有最高的准确率(94.3%)和预测精度(97.3%)。在模型稳定性验证中,平均预测精度最高(97.3%),优于DT(91.3%)和GBDT(95.7%),模型标准差和变异系数均为0.01,低于其余两种模型。XGBoost在区域滑坡易发性评价与制图中得到了可靠的结果,为滑坡灾害空间预测提供了新的技术支撑。