A comparison of logistic regression-based models of susceptibility to landslides in western Colorado,USA

The Paonia-McClure Pass area of Colorado has been recognized as a region highly susceptible to mass movement. Because of the dynamic nature of this landscape, accurate methods are needed to predict susceptibility to movement of these slopes. The area was evaluated by coupling a geographic information system (GIS) with logistic regression methods to assess susceptibility to landslides. We mapped 735 shallow landslides in the area. Seventeen factors, as predictor variables of landslides, were mapped from aerial photographs, available public data archives, ETM + satellite data, published literature, and frequent field surveys. A logistic regression model was run using landslides as the dependent factor and landslide-causing factors as independent factors (covariates). Landslide data were sampled from the landslide masses, landslide scarps, center of mass of the landslides, and center of scarp of the landslides, and an equal amount of data were collected from areas void of discernible mass movement. Models of susceptibility to landslides for each sampling technique were developed first. Second, landslides were classified as debris flows, debris slides, rock slides, and soil slides and then models of susceptibility to landslides were created for each type of landslide. The prediction accuracies of each model were compared using the Receiver Operating Characteristic (ROC) curve technique. The model, using samples from landslide scarps, has the highest prediction accuracy (85 %), and the model, using samples from landslide mass centers, has the lowest prediction accuracy (83 %) among the models developed from the four techniques of data sampling. Likewise, the model developed for debris slides has the highest prediction accuracy (92 %), and the model developed for soil slides has the lowest prediction accuracy (83 %) among the four types of landslides. Furthermore, prediction from a model developed by combining the four models of the four types of landslides (86 %) is better than the prediction from a model developed by using all landslides together (85 %).     

A distributed hydrological–geotechnical model using satellite-derived rainfall estimates for shallow landslide prediction system at a catchment scale

This paper describes the potential applicability of a hydrological–geotechnical modeling system using satellite-based rainfall estimates for a shallow landslide prediction system. The physically based distributed model has been developed by integrating a grid-based distributed kinematic wave rainfall-runoff model with an infinite slope stability approach. The model was forced by the satellite-based near real-time half-hourly CMORPH global rainfall product prepared by NOAA-CPC. The method combines the following two model outputs necessary for identifying where and when shallow landslides may potentially occur in the catchment: (1) the time-invariant spatial distribution of areas susceptible to slope instability map, for which the river catchment is divided into stability classes according to the critical relative soil saturation; this output is designed to portray the effect of quasi-static land surface variables and soil strength properties on slope instability and (2) a produced map linked with spatiotemporally varying hydrologic properties to provide a time-varying estimate of susceptibility to slope movement in response to rainfall. The proposed hydrological model predicts the dynamic of soil saturation in each grid element. The stored water in each grid element is then used for updating the relative soil saturation and analyzing the slope stability. A grid of slope is defined to be unstable when the relative soil saturation becomes higher than the critical level and is the basis for issuing a shallow landslide warning. The method was applied to past landslides in the upper Citarum River catchment (2,310 km²), Indonesia; the resulting time-invariant landslide susceptibility map shows good agreement with the spatial patterns of documented historical landslides (1985–2008). Application of the model to two recent shallow landslides shows that the model can successfully predict the effect of rainfall movement and intensity on the spatiotemporal dynamic of hydrological variables that trigger shallow landslides. Several hours before the landslides, the model predicted unstable conditions in some grids over and near the grids at which the actual shallow landslides occurred. Overall, the results demonstrate the potential applicability of the modeling system for shallow landslide disaster predictions and warnings.     

Assessment of rainfall-induced shallow landslides in Phetchabun and Krabi provinces,Thailand

Shallow landslides are a common type of rainfall-induced landslide, and various methods are currently used to predict their occurrence on a regional scale. Physically based models, such as the shallow landslide instability prediction (SLIP) model, have many advantages because these models can assess the hazards of shallow landslides dynamically, based on physical stability equations that consider rainfall as a triggering factor. The main objective of this research is to test the SLIP model’s potential to predict shallow landslide hazards in Thailand. To achieve this goal, the SLIP model was applied to two massive landslide events in Thailand. The results predicted by the SLIP model for the two study areas are outlined, and the model prediction capabilities were evaluated using the receiver operating characteristic plot. The Phetchabun results showed that the western part of the catchment had the lowest factor of safety (F _S) value, whereas the Krabi results showed that the slopes surrounding the peak of Khao Panom Mountain had the lowest F _S value, explaining the highest potentials for shallow landslides in each area. The SLIP model showed good performance: The global accuracies were 0.828 for the Phetchabun area and 0.824 for the Krabi area. The SLIP model predicted the daily time-varying percentage of unstable areas over the analyzed periods. The SLIP model simulated a negligible percentage of unstable areas over all considered periods, except for expected dates, suggesting that the prediction capability is reasonably accurate.     

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.     

Landslide susceptibility mapping using rough sets and back-propagation neural networks in the Three Gorges, China

In the Three Gorges of China, there are frequent landslides, and the potential risk of landslides is tremendous. An efficient and accurate method of generating landslide susceptibility maps is very important to mitigate the loss of lives and properties caused by these landslides. This paper presents landslide susceptibility mapping on the Zigui-Badong of the Three Gorges, using rough sets and back-propagation neural networks (BPNNs). Landslide locations were obtained from a landslide inventory map, supported by field surveys. Twenty-two landslide-related factors were extracted from the 1:10,000-scale topographic maps, 1:50,000-scale geological maps, Landsat ETM + satellite images with a spatial resolution of 28.5 m, and HJ-A satellite images with a spatial resolution of 30 m. Twelve key environmental factors were selected as independent variables using the rough set and correlation coefficient analysis, including elevation, slope, profile curvature, catchment aspect, catchment height, distance from drainage, engineering rock group, distance from faults, slope structure, land cover, topographic wetness index, and normalized difference vegetation index. The initial, three-layered, and four-layered BPNN were trained and then used to map landslide susceptibility, respectively. To evaluate the models, the susceptibility maps were validated by comparing with the existing landslide locations according to the area under the curve. The four-layered BPNN outperforms the other two models with the best accuracy of 91.53 %. Approximately 91.37 % of landslides were classified as high and very high landslide-prone areas. The validation results show sufficient agreement between the obtained susceptibility maps and the existing landslide locations.     

A simplified three-dimensional shallow landslide susceptibility framework considering topography and seismicity

Shallow landslides are a prevalent concern in mountainous or hilly regions that can result in severe societal, economic, and environmental impacts. The challenge is further compounded as the size and location of a potential slide is often unknown. This study presents a generalized approach for the evaluation of regional shallow landslide susceptibility using an existing shallow landslide inventory, remote sensing data, and various geotechnical scenarios. The three-dimensional limit equilibrium model derived in this study uses a raster-based approach that uniquely integrates tree root reinforcement, earth pressure boundary forces, and pseudo-static seismic accelerations. Contributions of this methodology include the back-calculation of soil strength from a landslide inventory, sensitivity analyses regarding landslide size-pixel size relationships, and the determination of shallow landslide susceptibility for a landscape or infrastructure considering various root, water, and seismic conditions using lidar bare-earth DEMs as a topographic input. Using a distribution of inventoried landslide points and random points in non-landslide locales, the proposed methodology demonstrated reasonable correlation between regions of high landslide susceptibility and observed shallow landslides within a 150-km² region of the Oregon Coast Range when the water-height ratio was 0.5. The method may be improved by considering spatial hydrologic conditions and geology more explicitly.     

Landslide detection and susceptibility mapping using LiDAR and an artificial neural network approach: a case study in the Cuyahoga Valley National Park,Ohio

The purpose of this study was to detect shallow landslides using hillshade maps derived from light detection and ranging (LiDAR)-based digital elevation model (DEM) derivatives. The landslide susceptibility mapping used an artificial neural network (ANN) approach and backpropagation method that was tested in the northern portion of the Cuyahoga Valley National Park (CVNP) located in northeast Ohio. The relationship between landslides and predictor attributes, which describe landform classes using slope, profile and plan curvatures, upslope drainage area, annual solar radiation, and wetness index, was extracted from LiDAR-based DEM using geographic information system (GIS). The approach presented in this paper required a training study area for the development of the susceptibility model and a validation study area to test the model. The results from the validation showed that within the very high susceptibility class, a total of 42.6 % of known landslides that were associated with 1.56 % of total area were correctly predicted. In contrast, the very low susceptibility class that represented 82.68 % of the total area was associated with 1.20 % of known landslides. The results suggest that the majority of the known landslides occur within a small portion of the study area, consistent with field investigation and other studies. Sample probabilistic maps of landslide susceptibility potential and other products from this approach are summarized and presented for visualization to help park officials in effective management and planning.     

A test of transferability for landslides susceptibility models under extreme climatic events: application to the Messina 2009 disaster

A model building strategy is tested to assess the susceptibility for extreme climatic events driven shallow landslides. In fact, extreme climatic inputs such as storms typically are very local phenomena in the Mediterranean areas, so that with the exception of recently stricken areas, the landslide inventories which are required to train any stochastic model are actually unavailable. A solution is here proposed, consisting in training a susceptibility model in a source catchment, which was implemented by applying the binary logistic regression technique, and exporting its predicting function (selected predictors regressed coefficients) in a target catchment to predict its landslide distribution. To test the method, we exploit the disaster that occurred in the Messina area (southern Italy) on 1 October 2009 where, following a 250-mm/8-h storm, approximately two thousand debris flow/debris avalanches landslides in an area of 21 km² triggered, killing 37 people and injuring more than 100, and causing 0.5 M € worth of structural damage. The debris flows and debris avalanches phenomena involved the thin weathered mantle of the Varisican low to high-grade metamorphic rocks that outcrop in the eastern slopes of the Peloritani Mounts. Two 10-km²-wide stream catchments, which are located inside the storm core area, were exploited: susceptibility models trained in the Briga catchment were tested when exported to predict the landslides distribution in the Giampilieri catchment. The prediction performance (based on goodness of fit, prediction skill, accuracy and precision assessment) of the exported model was then compared with that of a model prepared in the Giampilieri catchment exploiting its landslide inventory. The results demonstrate that the landslide scenario observed in the Giampilieri catchment can be predicted with the same high performance without knowing its landslide distribution: we obtained, in fact, a very poor decrease in predictive performance when comparing the exported model to the native random partition-based model.     

Relative effect method of landslide susceptibility zonation in weathered granite soil: a case study in Deokjeok-ri Creek,South Korea

The objective of this study was to produce and evaluate a landslide susceptibility map for weathered granite soils in Deokjeok-ri Creek, South Korea. The relative effect (RE) method was used to determine the relationship between landslide causative factors (CFs) and landslide occurrence. To determine the effect of CFs on landslides, data layers of aspect, elevation, slope, internal relief, curvature, distance to drainage, drainage density, stream power index, sediment transport index, topographic wetness index, soil drainage character, soil type, soil depth, forest type, timber age, and geology were analyzed in a geographical information system (GIS) environment. A GIS-based landslide inventory map of 748 landslide locations was prepared using data from previous reports, aerial photographic interpretation, and extensive field work. A RE model was generated from a training set consisting of 673 randomly selected landslides in the inventory map, with the remaining 75 landslides used for validation of the susceptibility map. The results of the analysis were verified using the landslide location data. According to the analysis, the RE model had a success rate of 86.3 % and a predictive accuracy of 88.6 %. The validation results showed satisfactory agreement between the susceptibility map and the existing data on landslide locations. The results of this study can therefore be used to mitigate landslide-induced hazards and to plan land use.     

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.     

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.     

基于TRIGRS模型的浅层滑坡稳定性分析

采用基于网格的瞬态降雨入渗(TRIGRS)模型,以滑坡灾害频发的陕南安康市东部巴山东段白河县为研究区,探讨模型适用性及不同降雨条件下边坡稳定性空间分布规律。根据中国土壤分布图并结合已有研究,选取模拟所需的水土力学参数。将模拟所得研究区稳定性分布图与实际滑坡目录对比分析进行TRIGRS模型精度评估,分别模拟连阴雨和短时间强降雨两种降雨情景,探讨研究区边坡稳定性空间分布规律,结果表明:1)TRIGRS模型在模拟预测降雨诱发型浅层滑坡时,结合受试者特征ROC曲线进行精度评估,曲线下面积为0.752,说明此模型在白河县进行滑坡模拟时具有一定的合理性与准确性,能反应该地区滑坡灾害的空间分布特征;2)连阴雨情景模拟下,极不稳定区域主要集中在北部低山地貌区,以冷水镇和麻虎镇为主,随降雨历时增加向东部和南部增多,西部仓上镇、西营镇和双丰镇的极不稳定区域面积较少,能承受长时间连续性降雨。短时间强降雨对边坡稳定性的影响更为直接,极不稳定区域随降雨强度增大而增加,以冷水镇和麻虎镇为主要防范区域。结合地形分析,极陡峭区域边坡稳定性最差,无法承受持续性降雨和高强度降雨,较陡峭区域更易受到降雨历时和降雨强度的影响,而平缓区域则能承受长时间及高强度的降雨;3)TRIGRS模型根据不同降雨条件预测易发生滑坡灾害的区域,为滑坡实时预报警系统提供了新的可能方法。     

Landslide Susceptibility Mapping Using Fuzzy Logic System and Its Influences on Mainlines in Lashgarak Region,Tehran, Iran

Landslide susceptibility mapping is among the useful tools applied in disaster management and planning development activities in mountainous areas. The susceptibility maps prepared in this research provide valuable information for landslide hazard management in Lashgarak region of Tehran. This study was conducted to, first, prepare landslide susceptibility maps for Lashgarak region and evaluate landslide effect on mainlines and, second, to analyze the main factors affecting landslide hazard increase in the study area in order to propose efficient strategies for landslide hazard mitigation. A GIS-based multi-criteria decision analysis model (fuzzy logic) is used in the present work for scientific evaluation of landslide susceptible areas in Lashgarak region. To this end, ArcGIS, PCIGeomatica, and IDIRISI software packages were used. Eight information layers were selected for information analysis: ground strength class, slope angle, terrain roughness, normalized difference moisture index, normalized difference vegetation index, distance from fault, distance from the river, and distance from the road. Next, eight different scenarios were created to determine landslide susceptibility of the study area using different operators (intersection (AND), union (OR), algebraic sum (SUM), multiplication (PRODUCT), and different fuzzy gamma values) of fuzzy overlay approach. After that, the performance of various fuzzy operators in landslide susceptibility mapping was empirically compared. The results revealed the excellent consistency of landslide susceptibility map prepared using the fuzzy union (OR) operator with landslide distribution map in the study area. Eventually, the accuracy of landslide susceptibility map prepared using the fuzzy union (OR) operator was evaluated using the frequency ratio diagram. The results showed that frequency values of the landslides gradually increase from “low susceptibility” to high “susceptibility” as 88.34% of the landslides are categorized into two “high” and “very high” susceptibility classes, implying the satisfactory consistency between the landslide susceptibility map prepared using fuzzy union (OR) operator and landslide distribution map.     

Use of fuzzy relations to produce landslide susceptibility map of a landslide prone area (West Black Sea Region, Turkey)

Preparation of landslide susceptibility maps is important for engineering geologists and geomorphologists. However, due to complex nature of landslides, producing a reliable susceptibility map is not easy. For this reason, many procedures have been used to produce such maps. In this study, a new attempt is tried to produce landslide susceptibility map of a part of West Black Sea Region of Turkey. To obtain the fuzzy relations for producing the susceptibility map, a landslide inventory database is compiled by both field surveys and airphoto studies. A total of 266 landslides are identified in the study area, and dominant mode of failure is rotational slide while the other mode of failures are soil flow and shallow translational slide. The landslide inventory and the parameter maps are analyzed together using a computer program (FULLSA) developed in this study. The computer program utilizes the fuzzy relations and produces the landslide susceptibility map automatically. According to this map, 9.6% of the study area is classified as very high susceptibility, 10.3% as high susceptibility, 8.9% as moderate susceptibility, 27.5% as low susceptibility and 43.8% as very low susceptibility or nonsusceptible areas. The prediction performance of the susceptibility map is checked by considering actual landslides in the study area. For this purpose, strength of the relation (r_ij) and the root mean square error (RMSE) values are calculated as 0.867 and 0.284, respectively. These values show that the produced landslide susceptibility map in the present study has a sufficient reliability. It is believed that the approach employed in this study mainly prevents the subjectivity sourced from the parameter selection and provides a support to improve the landslide susceptibility mapping studies.     

Do landslides follow landslides? Insights in path dependency from a multi-temporal landslide inventory

Landslides are a major category of natural disasters, causing loss of lives, livelihoods and property. The critical roles played by triggering (such as extreme rainfall and earthquakes), and intrinsic factors (such as slope steepness, soil properties and lithology) have previously successfully been recognized and quantified using a variety of qualitative, quantitative and hybrid methods in a wide range of study sites. However, available data typically do not allow to investigate the effect that earlier landslides have on intrinsic factors and hence on follow-up landslides. Therefore, existing methods cannot account for the potentially complex susceptibility changes caused by landslide events. In this study, we used a substantially different alternative approach to shed light on the potential effect of earlier landslides using a multi-temporal dataset of landslide occurrence containing 17 time slices. Spatial overlap and the time interval between landslides play key roles in our work. We quantified the degree to which landslides preferentially occur in locations where landslides occurred previously, how long such an effect is noticeable, and how landslides are spatially associated over time. We also investigated whether overlap with previous landslides causes differences in landslide geometric properties. We found that overlap among landslides demonstrates a clear legacy effect (path dependency) that has influence on the landslide affected area. Landslides appear to cause greater susceptibility for follow-up landslides over a period of about 10  years. Follow-up landslides are on average larger and rounder than landslides that do not follow earlier slides. The effect of earlier landslides on follow-up landslides has implications for understanding of the landslides evolution and the assessment of landslide susceptibility.     

Effects of degree of saturation on shallow landslides triggered by rainfall

The empirical rainfall threshold concept and the physical-based model are two commonly used approaches for the assessment of shallow landslides triggered by rainfall. To investigate in detail the rainfall-triggered shallow landslides, many physical-based models coupling the infinite slope stability analysis with the rainfall infiltration modeling in variably saturated soil were developed. However, in those physical-based shallow landslide models, the unit weight and the unsaturated shear strength were assumed constant rather than depending on the degree of saturation. In this study, the effects of the unit weight and the unsaturated shear strength as function of degree of saturation on rainfall-triggered shallow landslides are examined. Several designed scenarios and a real case scenario are used to conduct the examinations. The results show that not only the occurrence of shallow landslides but also the failure depth and the time to failure could be misassessed if the influences of degree of saturation on the unit weight and the unsaturated shear strength are neglected.     

A Comparative Study of Least Square Support Vector Machines and Multiclass Alternating Decision Trees for Spatial Prediction of Rainfall-Induced Landslides in a Tropical Cyclones Area

The objective of this study is to explore and compare the least square support vector machine (LSSVM) and multiclass alternating decision tree (MADT) techniques for the spatial prediction of landslides. The Luc Yen district in Yen Bai province (Vietnam) has been selected as a case study. LSSVM and MADT are effective machine learning techniques of classification applied in other fields but not in the field of landslide hazard assessment. For this, Landslide inventory map was first constructed with 95 landslide locations identified from aerial photos and verified from field investigations. These landslide locations were then divided randomly into two parts for training (70 % locations) and validation (30 % locations) processes. Secondly, landslide affecting factors such as slope, aspect, elevation, curvature, lithology, land use, distance to roads, distance to faults, distance to rivers, and rainfall were selected and applied for landslide susceptibility assessment. Subsequently, the LSSVM and MADT models were built to assess the landslide susceptibility in the study area using training dataset. Finally, receiver operating characteristic curve and statistical index-based evaluations techniques were employed to validate the predictive capability of these models. As a result, both the LSSVM and MADT models have high performance for spatial prediction of landslides in the study area. Out of these, the MADT model (AUC = 0.853) outperforms the LSSVM model (AUC = 0.803). From the landslide study of Luc Yen district in Yen Bai province (Vietnam), it can be conclude that the LSSVM and MADT models can be applied in other areas of world also for and spatial prediction. Landslide susceptibility maps obtained from this study may be helpful in planning, decision making for natural hazard management of the areas susceptible to landslide hazards.     

Tier-based approaches for landslide susceptibility assessment in Europe

In the framework of the European Soil Thematic Strategy and the associated proposal of a Framework Directive on the protection and sustainable use of soil, landslides were recognised as a soil threat requiring specific strategies for priority area identification, spatial hazard assessment and management. This contribution outlines the general specifications for nested, Tier-based geographical landslide zonings at small spatial scales to identify priority areas susceptible to landslides (Tier 1) and to perform quantitative susceptibility evaluations within these (Tier 2). A heuristic, synoptic-scale Tier 1 assessment exploiting a reduced set of geoenvironmental factors derived from common pan-European data sources is proposed for the European Union and adjacent countries. Evaluation of the susceptibility estimate with national-level landslide inventory data suggests that a zonation of Europe according to, e.g. morphology and climate, and performing separate susceptibility assessments per zone could give more reliable results. To improve the Tier 1 assessment, a geomorphological terrain zoning and landslide typology differentiation are then applied for France. A multivariate landslide susceptibility assessment using additional information on landslide conditioning and triggering factors, together with a historical catalogue of landslides, is proposed for Tier 2 analysis. An approach is tested for priority areas in Italy using small administrative mapping units, allowing for relating socioeconomic census data with landslide susceptibility, which is mandatory for decision making regarding the adoption of landslide prevention and mitigation measures. The paper concludes with recommendations on further work to harmonise European landslide susceptibility assessments in the context of the European Soil Thematic Strategy.     

Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines,artificial neural networks,kernel logistic regression,and logistic model tree

Preparation of landslide susceptibility maps is considered as the first important step in landslide risk assessments, but these maps are accepted as an end product that can be used for land use planning. The main objective of this study is to explore some new state-of-the-art sophisticated machine learning techniques and introduce a framework for training and validation of shallow landslide susceptibility models by using the latest statistical methods. The Son La hydropower basin (Vietnam) was selected as a case study. First, a landslide inventory map was constructed using the historical landslide locations from two national projects in Vietnam. A total of 12 landslide conditioning factors were then constructed from various data sources. Landslide locations were randomly split into a ratio of 70:30 for training and validating the models. To choose the best subset of conditioning factors, predictive ability of the factors were assessed using the Information Gain Ratio with 10-fold cross-validation technique. Factors with null predictive ability were removed to optimize the models. Subsequently, five landslide models were built using support vector machines (SVM), multi-layer perceptron neural networks (MLP Neural Nets), radial basis function neural networks (RBF Neural Nets), kernel logistic regression (KLR), and logistic model trees (LMT). The resulting models were validated and compared using the receive operating characteristic (ROC), Kappa index, and several statistical evaluation measures. Additionally, Friedman and Wilcoxon signed-rank tests were applied to confirm significant statistical differences among the five machine learning models employed in this study. Overall, the MLP Neural Nets model has the highest prediction capability (90.2 %), followed by the SVM model (88.7 %) and the KLR model (87.9 %), the RBF Neural Nets model (87.1 %), and the LMT model (86.1 %). Results revealed that both the KLR and the LMT models showed promising methods for shallow landslide susceptibility mapping. The result from this study demonstrates the benefit of selecting the optimal machine learning techniques with proper conditioning selection method in shallow landslide susceptibility mapping.     

Medium-scale hazard mapping for shallow landslide initiation: the Buyukkoy catchment area (Cayeli, Rize, Turkey)

The main purpose of this study is to develop a new hazard evaluation technique considering the current limitations, particularly for shallow landslides. For this purpose, the Buyukkoy catchment area, located in the East Black Sea Region in the east of Rize province and the south of Cayeli district, was selected as the study area. The investigations were executed in four different stages. These were (1) preparation of a temporal shallow landslide inventory of the study area, (2) assessment of conditioning factors in the catchment, (3) susceptibility analyses and (4) hazard evaluations and mapping. A total of 251 shallow landslides in the period of 1955–2007 were recognised using different data sources. A ‘Sampling Circle’ approach was proposed to define shallow landslide initiation in the mapping units in susceptibility evaluations. To accomplish the susceptibility analyses, the method of artificial neural networks was implemented. According to the performance analyses conducted using the training and testing datasets, the prediction and generalisation capacities of the models were found to be very high. To transform the susceptibility values into hazard rates, a new approach with a new equation was developed, taking into account the behaviour of the responsible triggering factor over time in the study area. In the proposed equation, the threshold value of the triggering factor and the recurrence interval are the independent variables. This unique property of the suggested equation allows the execution of more flexible and more dynamic hazard assessments. Finally, using the proposed technique, shallow landslide initiation hazard maps of the Buyukkoy catchment area for the return periods of 1, 2, 5, 10, 50 and 100 years were produced.