Quantitative landslide susceptibility mapping at Pemalang area,Indonesia

For quantitative landslide susceptibility mapping, this study applied and verified a frequency ratio, logistic regression, and artificial neural network models to Pemalang area, Indonesia, using a Geographic Information System (GIS). Landslide locations were identified in the study area from interpretation of aerial photographs, satellite imagery, and field surveys; a spatial database was constructed from topographic and geological maps. The factors that influence landslide occurrence, such as slope gradient, slope aspect, curvature of topography, and distance from stream, were calculated from the topographic database. Lithology was extracted and calculated from geologic database. Using these factors, landslide susceptibility indexes were calculated by frequency ratio, logistic regression, and artificial neural network models. Then the landslide susceptibility maps were verified and compared with known landslide locations. The logistic regression model (accuracy 87.36%) had higher prediction accuracy than the frequency ratio (85.60%) and artificial neural network (81.70%) models. The models can be used to reduce hazards associated with landslides and to land-use planning.     

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.     

Multivariate models for landslide hazard evaluation

As part of a long-term project aimed at a better understanding of the geological and geomorphological factors that control slope instability phenomena in Southern Italy, multivariate models for assessing landslide incidence hazard were developed and tested in two Calabrian sample areas characterized by different geological-geomorphological conditions. Discriminant analysis, based on a large set of mappable geological and geomorphical variables, is able to discriminate rather successfully between stable and unstable areas or slope units. Multiple regression analysis has also proved to be a useful tool in predicting actual and potential landslide hazard. Consequently, geomathematical models may provide a feasible approach to environmental hazard assessment, particularly when applied within the framework of a wider multidisciplinary project for land evaluation and planning.     

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.     

基于GIS与WOE-BP模型的滑坡易发性评价

区域滑坡易发性研究对地质灾害风险管理具有重要意义.以往研究中,将多元统计模型与机器学习方法相结合用于滑坡易发性评价的研究较少.以三峡库区万州区为例,首先选取9种指标因子（坡度、坡向、剖面曲率、地表纹理、地层岩性、斜坡结构、地质构造、水系分布及土地利用类型）作为滑坡易发性评价指标.基于证据权模型（weights of evidence,WOE）计算得到的对比度和滑坡面积比与分级面积比的相对大小,对各指标因子进行状态分级;再利用粒子群法优化的BP神经网络模型（PSO-BP）得到各指标因子权重.综合两种模型确定的状态分级权重和指标因子权重（WOE-BP）计算滑坡易发性指数（landslide susceptibility index,LSI）,基于GIS平台得到全区滑坡易发性分区图.结果表明:水系、地层岩性和地质构造是影响万州区滑坡发育的主要指标因子;WOE-BP模型的预测精度为80.8%,优于WOE模型的73.1%和BP神经网络模型的71.6%,可为定量计算指标因子权重和优化滑坡易发性评价提供有效途径.      

Landslide susceptibility assessment in the İzmir (West Anatolia,Turkey) city center and its near vicinity by the logistic regression method

A landslide susceptibility assessment for İzmir city (Western Turkey), which is the third biggest city of Turkey, was performed by a logistic regression method. A database of landslide characteristics was prepared using detailed field surveys. The major landslides in the study area are generally observed in the field, dominated by weathered volcanics, and 39.63% of the total landslide area is in this unit. The parameters of lithology, slope gradient, slope aspect, distance to drainage, distance to roads and distance to fault lines were used as variables in the logistic regression analysis. The effect of each parameter on landslide occurrence was assessed from the corresponding coefficients that appear in the logistic regression function. On the basis of the obtained coefficients, lithology plays the most important role in determining landslide occurrence and distribution. Slope gradient has a more significant effect than the other geomorphological parameters, such as slope aspect and distance to drainage. Using a predicted map of probability, the study area was classified into five categories of landslide susceptibility: very low, low, moderate, high and very high. Whereas 49.65% of the total study area has very low susceptibility, very high susceptibility zones make up 11.69% of the area.     

Ensemble-based landslide susceptibility maps in Jinbu area, Korea

Ensemble techniques were developed, applied and validated for the analysis of landslide susceptibility in Jinbu area, Korea using the geographic information system (GIS). Landslide-occurrence areas were detected in the study by interpreting aerial photographs and field survey data. Landslide locations were randomly selected in a 70/30 ratio for training and validation of the models, respectively. Topography, geology, soil and forest databases were also constructed. Maps relevant to landslide occurrence were assembled in a spatial database. Using the constructed spatial database, 17 landslide-related factors were extracted. The relationships between the detected landslide locations and the factors were identified and quantified by frequency ratio, weight of evidence, logistic regression and artificial neural network models and their ensemble models. The relationships were used as factor ratings in the overlay analysis to create landslide susceptibility indexes and maps. Then, the four landslide susceptibility maps were used as new input factors and integrated using the frequency ratio, weight of evidence, logistic regression and artificial neural network models as ensemble methods to make better susceptibility maps. All of the susceptibility maps were validated by comparison with known landslide locations that were not used directly in the analysis. As the result, the ensemble-based landslide susceptibility map that used the new landslide-related input factor maps showed better accuracy (87.11% in frequency ratio, 83.14% in weight of evidence, 87.79% in logistic regression and 84.54% in artificial neural network) than the individual landslide susceptibility maps (84.94% in frequency ratio, 82.82% in weight of evidence, 87.72% in logistic regression and 81.44% in artificial neural network). All accuracy assessments showed overall satisfactory agreement of more than 80%. The ensemble model was found to be more effective in terms of prediction accuracy than the individual model.     

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.     

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.     

基于不同模型的赣南地区小型削方滑坡易发性评价对比分析

赣南地区滑坡灾害点多、面广、规模小,具有群发性和突发性的特点,90%以上的滑坡是因人工切坡导致的。为研究赣南地区小型削方滑坡对易发性评价模型的适用性,以赣州市于都县银坑镇为例,基于野外地质调查成果,并利用地理探测器,选取坡度、坡体结构、岩组、断层、道路、植被等6个评价指标,分别选用信息量模型、人工神经网络模型、决策树模型和逻辑回归模型开展易发性评价。结果表明：信息量、人工神经网络、决策树和逻辑回归等模型得到的AUC值分别为0.800、0.708、0.672和0.586,信息量模型所得的易发性结果与研究区滑坡实际分布情况较吻合,高易发区和中易发区滑坡占比近80%。信息量模型较其他三个模型,更适合于赣南地区小型削方滑坡易发性评价,评价结果对该地区地质灾害易发性评价模型选取提供了参考与借鉴。     

基于不同耦合模型的县域滑坡易发性评价对比分析

为有效预测县域滑坡发生的空间概率,探索不同统计学耦合模型滑坡易发性定量评价结果的合理性和精度,以四川省普格县为研究对象。选取坡度、坡向、高程、工程地质岩组、断层和斜坡结构等6项孕灾因子作为评价指标体系,基于信息量模型（I）、确定性系数模型（CF）、证据权模型（WF）、频率比模型（FR）分别与逻辑回归模型（LR）耦合开展滑坡易发性评价。结果表明:各耦合模型评价结果和易发程度区划均是合理的,极高易发区主要分布于则木河、黑水河河谷两侧斜坡带,面积介于129.04～183.43 km2（占比6.77%～9.62%）,各模型评价精度依次为WF-LR模型（AUC=0.869）>I-LR模型（AUC=0.868）>CF-LR模型（AUC=0.866）>NFR-LR模型（AUC=0.858）。研究成果可为川西南山区县域滑坡易发性定量评估提供重要参考。     

Comparing data-driven landslide susceptibility models based on participatory landslide inventory mapping in Purwosari area,Yogyakarta, Java

There are different approaches and techniques for landslide susceptibility mapping. However, no agreement has been reached in both the procedure and the use of specific controlling factors employed in the landslide susceptibility mapping. Each model has its own assumption, and the result may differ from place to place. Different landslide controlling factors and the completeness of landslide inventory may also affect the different result. Incomplete landslide inventory may produce significance error in the interpretation of the relationship between landslide and controlling factor. Comparing landslide susceptibility models using complete inventory is essential in order to identify the most realistic landslide susceptibility approach applied typically in the tropical region Indonesia. Purwosari area, Java, which has total 182 landslides occurred from 1979 to 2011, was selected as study area to evaluate three data-driven landslide susceptibility models, i.e., weight of evidence, logistic regression, and artificial neural network. Landslide in the study area is usually affected by rainfall and anthropogenic activities. The landslide typology consists of shallow translational and rotational slide. The elevation, slope, aspect, plan curvature, profile curvature, stream power index, topographic wetness index, distance to river, land use, and distance to road were selected as landslide controlling factors for the analysis. Considering the accuracy and the precision evaluations, the weight of evidence represents considerably the most realistic prediction capacities (79%) when comparing with the logistic regression (72%) and artificial neural network (71%). The linear model shows more powerful result than the nonlinear models because it fits to the area where complete landslide inventory is available, the landscape is not varied, and the occurence of landslide is evenly distributed to the class of controlling factor.     

Landslides in Sado Island of Japan: Part II. GIS-based susceptibility mapping with comparisons of results from two methods and verifications

Slope instability research and susceptibility mapping is a fundamental component of hazard management and an important basis for provision of measures aimed at decreasing the risk of living with landslides. On this basis, this paper presents the result of a comprehensive study on slope stability analyses and landslide susceptibility mapping carried out in part of Sado Island of Japan. Various types of landslides occurred in the island throughout history. Little is known about the triggering factors and severity of old landslides, but for many of the recent slope failures, the slope characteristics and stratigraphy are such that ground surfaces retain water perennially and landslides occur when additional moisture is induced during rainfall and snowmelt. A range of methods are available in literature for preparation of landslide susceptibility maps. In this study we used two methods namely, the analytical hierarchy process (AHP) and logistic regression, to produce and later compare two susceptibility maps. AHP is a semi-qualitative method, which involves a matrix-based pair-wise comparison of the contribution of different factors for landsliding. Logistic regression on the other hand promotes a multivariate statistical analysis with an objective to find the best-fitting model that describes the relationship between the presence or absence of landslides (dependent variable) and a set of causal factors (independent parameters). Elevation, lithology and slope gradient were casual factors in this study. The determinations of factor weights by AHP and logistic regression were preceded by the calculation of class weights (landslide densities) based on bivariate statistical analyses (BSA). The differences between the AHP derived susceptibility map and the logistic regression counterpart are relatively minor when broad-based classifications are considered. However, with an increase in the number of susceptibility classes, the logistic regression map gave more details but the one derived by AHP failed to do so. The reason is that the majority of pixels in the AHP map have high values, and an increase in the number of classes gives little change in the spatial distribution of susceptibility zones in the middle. To verify the practicality of the two susceptibility maps, both of them were compared with a landslide activity map containing 18 active landslide zones. The outcome was that the active landslide zones do not completely fit into the very high susceptibility class of both maps for various reasons. But 70% of these landslide zones fall into the high and very high susceptibility zones of the AHP map while this is 63% in the case of logistic regression. This indicates that despite the skewed distribution of susceptibility indices, the AHP map was better to capture the reality on the ground than the logistic regression equivalent.     

Landslide susceptibility mapping: A comparison of logistic regression and neural networks methods in a medium scale study, Hendek region (Turkey)

Landslide susceptibility mapping is one of the most critical issues in Turkey. At present, geotechnical models appear to be useful only in areas of limited extent, because it is difficult to collect geotechnical data with appropriate resolution over larger regions. In addition, many of the physical variables that are necessary for running these models are not usually available, and their acquisition is often very costly. Conversely, statistical approaches are currently pursued to assess landslide hazard over large regions. However, these approaches cannot effectively model complicated landslide hazard problems, since there is a non-linear relationship between nature-based problems and their triggering factors. Most of the statistical methods are distribution-based and cannot handle multisource data that are commonly collected from nature. In this respect, logistic regression and neural networks provide the potential to overcome drawbacks and to satisfy more rigorous landslide susceptibility mapping requirements. In the Hendek region of Turkey, a segment of natural gas pipeline was damaged due to landslide. Re-routing of the pipeline is planned but it requires preparation of landslide susceptibility map. For this purpose, logistic regression analysis and neural networks are applied to prepare landslide susceptibility map of the problematic segment of the pipeline. At the end, comparative analysis is conducted on the strengths and weaknesses of both techniques. Based on the higher percentages of landslide bodies predicted in very high and high landslide susceptibility zones, and compatibility between field observations and the important factors obtained in the analyses, the result found by neural network is more realistic.     

Landslide susceptibility mapping in the Damrei Romel area, Cambodia using frequency ratio and logistic regression models

This study applied, tested and compared a probability model, a frequency ratio and statistical model, a logistic regression to Damre Romel area, Cambodia, using a geographic information system. For landslide susceptibility mapping, landslide locations were identified in the study area from interpretation of aerial photographs and field surveys, and a spatial database was constructed from topographic maps, geology and land cover. The factors that influence landslide occurrence, such as slope, aspect, curvature and distance from drainage were calculated from the topographic database. Lithology and distance from lineament were extracted and calculated from the geology database. Land cover was classified from Landsat TM satellite imagery. The relationship between the factors and the landslides was calculated using frequency ratio and logistic regression models. The relationships, frequency ratio and logistic regression coefficient were overlaid to make landslide susceptibility map. Then the landslide susceptibility map was compared with known landslide locations and tested. As the result, the frequency ratio model (86.97%) and the logistic regression (86.37%) had high and similar prediction accuracy. The landslide susceptibility map can be used to reduce hazards associated with landslides and to land cover planning.     

Landslide susceptibility assessment in Apulian Southern Apennine: heuristic vs. statistical methods

In this paper, a bivariate-heuristic model (modified Stevenson’s method) and two multivariate statistical procedures (discriminant analysis and logistic regression) were used in order to assess and map landslide susceptibility in the north-western side of Daunia region (Apulia, Southern Italy). The whole Daunia region is characterized by complex and composite landslides, which are located on clayey slopes, near urban centers, affecting structures and infrastructures. The high predisposition to landsliding of the Daunia hillslopes is related to the very poor strength properties of clayey formations. The comparative analysis of landslide susceptibility using different methods, on the same test site and with the same inventory map allowed understanding the dependence of the results from the dataset and the capability of models under different levels of use, from expert to simple operator. By comparing the performance of the three models through the success rate curves, it emerges that the simple modified Stevenson’s method produces reliable outcomes, comparable with those deriving from more complex multivariate statistical models. This result is related to the characteristics of clayey slopes, in which the landslide occurrence is so much controlled by the poor strength properties of the clayey formations that the multivariate analysis of a large set of morphometric, geological and land-use variables results to be somehow superfluous. This suggests that, for clayey slopes, a simple, easy-to-manage bivariate-heuristic model based on expert opinion can be used with reliable results.     

Landslide susceptibility analysis and its verification using likelihood ratio, logistic regression, and artificial neural network models: case study of Youngin, Korea

The likelihood ratio, logistic regression, and artificial neural networks models are applied and verified for analysis of landslide susceptibility in Youngin, Korea, using the geographic information system. From a spatial database containing such data as landslide location, topography, soil, forest, geology, and land use, the 14 landslide-related factors were calculated or extracted. Using these factors, landslide susceptibility indexes were calculated by likelihood ratio, logistic regression, and artificial neural network models. Before the calculation, the study area was divided into two sides (west and east) of equal area, for verification of the models. Thus, the west side was used to assess the landslide susceptibility, and the east side was used to verify the derived susceptibility. The results of the landslide susceptibility analysis were verified using success and prediction rates. The verification results showed satisfactory agreement between the susceptibility map and the existing data on landslide locations.     

Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models

This paper summarizes findings of landslide hazard analysis on Penang Island, Malaysia, using frequency ratio, logistic regression, and artificial neural network models with the aid of GIS tools and remote sensing data. Landslide locations were identified and an inventory map was constructed by trained geomorphologists using photo-interpretation from archived aerial photographs supported by field surveys. A SPOT 5 satellite pan sharpened image acquired in January 2005 was used for land-cover classification supported by a topographic map. The above digitally processed images were subsequently combined in a GIS with ancillary data, for example topographical (slope, aspect, curvature, drainage), geological (litho types and lineaments), soil types, and normalized difference vegetation index (NDVI) data, and used to construct a spatial database using GIS and image processing. Three landslide hazard maps were constructed on the basis of landslide inventories and thematic layers, using frequency ratio, logistic regression, and artificial neural network models. Further, each thematic layer’s weight was determined by the back-propagation training method and landslide hazard indices were calculated using the trained back-propagation weights. The results of the analysis were verified and compared using the landslide location data and the accuracy observed was 86.41, 89.59, and 83.55% for frequency ratio, logistic regression, and artificial neural network models, respectively. On the basis of the higher percentages of landslide bodies predicted in very highly hazardous and highly hazardous zones, the results obtained by use of the logistic regression model were slightly more accurate than those from the other models used for landslide hazard analysis. The results from the neural network model suggest the effect of topographic slope is the highest and most important factor with weightage value (1.0), which is more than twice that of the other factors, followed by the NDVI (0.52), and then precipitation (0.42). Further, the results revealed that distance from lineament has the lowest weightage, with a value of 0. This shows that in the study area, fault lines and structural features do not contribute much to landslide triggering.     

基于集成学习与径向基神经网络耦合模型的三峡库区滑坡易发性评价

准确的滑坡易发性评价结果是滑坡风险评价的重要基础.为提升滑坡易发性评价精度,以三峡库区龙驹坝为例,选取坡度等10个因子构建滑坡易发性评价指标体系,应用频率比方法定量分析各指标与滑坡发育的关系.在此基础上,随机选取70%/30%的滑坡数据作为训练/测试样本,应用径向基神经网络和Adaboost集成学习耦合模型(RBNN-Adaboost),径向基神经网络和逻辑回归模型分别开展易发性评价.结果显示:水系距离、坡度等是滑坡发育的主控因素;RBNN-Adaboost耦合模型的预测精度最高(0.820),优于RBNN模型和LR模型的0.781和0.748.Adaboost集成算法能进一步提升模型的预测性能,所提出的耦合模型结合了两者的优点,具有更强的预测能力,是一种可靠的滑坡易发性评价模型.