Effectiveness of visually analyzing LiDAR DTM derivatives for earth and debris slide inventory mapping for statistical susceptibility modeling

Landslide inventories are the most important data source for landslide process, susceptibility, hazard, and risk analyses. The objective of this study was to identify an effective method for mapping a landslide inventory for a large study area (19,186 km²) from Light Detection and Ranging (LiDAR) digital terrain model (DTM) derivatives. This inventory should in particular be optimized for statistical susceptibility modeling of earth and debris slides. We compared the mapping of a representative set of landslide bodies with polygons (earth and debris slides, earth flows, complex landslides, and areas with slides) and a substantially complete set of earth and debris slide main scarps with points by visual interpretation of LiDAR DTM derivatives. The effectiveness of the two mapping methods was estimated by evaluating the requirements on an inventory used for statistical susceptibility modeling and their fulfillment by our mapped inventories. The resulting landslide inventories improved the knowledge on landslide events in the study area and outlined the heterogeneity of the study area with respect to landslide susceptibility. The obtained effectiveness estimate demonstrated that none of our mapped inventories are perfect for statistical landslide susceptibility modeling. However, opposed to mapping polygons, mapping earth and debris slides with a point in the main scarp were most effective for statistical susceptibility modeling within large study areas. Therefore, earth and debris slides were mapped with points in the main scarp in entire Lower Austria. The advantages, drawbacks, and effectiveness of landslide mapping on the basis of LiDAR DTM derivatives compared to other imagery and techniques were discussed.     

Influence of the sediment delivery ratio index on the analysis of silting and break risk in the Plasencia reservoir (Central System,Spain)

The random forest method was used to generate susceptibility maps for debris flows, rock slides, and active layer detachment slides in the Donjek River area within the Yukon Alaska Highway Corridor, based on an inventory of landslides compiled by the Geological Survey of Canada in collaboration with the Yukon Geological Survey. The aim of this study is to develop data-driven landslide susceptibility models which can provide information on risk assessment to existing and planned infrastructure. The factors contributing to slope failure used in the models include slope angle, slope aspect, plan and profile curvatures, bedrock geology, surficial geology, proximity to faults, permafrost distribution, vegetation distribution, wetness index, and proximity to drainage system. A total of 83 debris flow deposits, 181 active layer detachment slides, and 104 rock slides were compiled in the landslide inventory. The samples representing the landslide free zones were randomly selected. The ratio of landslide/landslide free zones was set to 1:1 and 1:2 to examine the results of different sample ratios on the classification. Two-thirds of the samples for each landslide type were used in the classification, and the remaining 1/3 were used to evaluate the results. In addition to the classification maps, probability maps were also created, which served as the susceptibility maps for debris flows, rock slides, and active layer detachment slides. Success and prediction rate curves created to evaluate the performance of the resulting models indicate a high performance of the random forest in landslide susceptibility modelling.     

Landslide risk analysis in the area North of Lisbon (Portugal): evaluation of direct and indirect costs resulting from a motorway disruption by slope movements

A risk analysis is developed for a test site located in the area north of Lisbon using a scenario of a temporary interruption of the motorway A9 due to a landslide of rotational or translational type. Landslide susceptibility is assessed at the regional scale independently for rotational and translational slides, comparing the landslide distribution with a set of assumed independent landslide predisposing factors. Susceptibility models are validated and classified through the computation of prediction rate curves based on the temporal partition of the landslide data sets. Landslide hazard maps are based on a scenario of future landslide occurrence for the next 27 years. These maps allow the definition of two critical areas on the motorway A9 with regards to landslide susceptibility. Direct costs associated with both critical spots are assessed taking into account the probable affected area of the motorway, and the reconstruction costs. Indirect costs derived from the traffic interruption are evaluated considering the alternatives paths to the motorway, and include costs resulting from: (1) additional fuel consumption; (2) decrease in tollgate income; and (3) loss of productive time. Results show that indirect costs may be 24 to 43 times higher than direct costs, assuming a temporary interruption of the motorway for 6 months.     

Lanslide hydrogeological susceptibility of Maierato (Vibo Valentia, Southern Italy)

A large landslide occurred at Maierato (Vibo Valencia District), Southern Italy, on 15 February 2010, when rapid failure was produced after several days of preliminary movements. The landslide can be classified as a rotational slide with flowing of the mass. It occurred within a larger deep-seated gravitational movement area and was preconditioned for failure by the intrinsic geological weakness of the area. Actually, the in situ survey showed the presence of several ancient movement surfaces all around the urban area. The landslide-triggering factor was the increase in the groundwater flow, consequent to a period of heavy and prolonged rainfall. The aim of the paper is to explain the mechanism of occurrence of the February 2010 composite landslide, in order to assess the landslide hydrogeological susceptibility in the whole urban area of Maierato. For this reason, the present paper deals with: (1) identification of the landslide mechanism and triggering factors (2) slope stability back-analysis using a finite-difference-based shear strength reduction method, and (3) 3D groundwater flow modelling extended to the whole urban area both in pre- and post-failure conditions. The results show that the February 2010 composite landslide was triggered by a water table increase of about 15 m uphill the landslide scarp. This hydrogeological condition could be reached after the period of heavy and prolonged rainfall preceding the landslide event. Finally, based on the groundwater modelling in post-failure condition, a landslide hydrogeological susceptibility map was drawn for the all urban area of Maierato, showing the presence of extended areas exposed to hazard.     

Landslide susceptibility mapping using a modified decision tree classifier in the Xanthi Perfection,Greece

The objective of this study was to validate the outcomes of a modified decision tree classifier by comparing the produced landslide susceptibility map and the actual landslide occurrence, in an area of intensive landslide manifestation, in Xanthi Perfection, Greece. The values that concerned eight landslide conditioning factors for 163 landslides and 163 non-landslide locations were extracted by using advanced spatial GIS functions. Lithological units, elevation, slope angle, slope aspect, distance from tectonic features, distance from hydrographic network, distance from geological boundaries and distance from road network were among the eight landslide conditioning factors that were included in the landslide database used in the training phase. In the present study, landslide and non-landslide locations were randomly divided into two subsets: 80 % of the data (260 instances) were used for training and 20 % of the data (66 instances) for validating the developed classifier. The outcome of the decision tree classifier was a set of rules that expressed the relationship between landslide conditioning factors and the actual landslide occurrence. The landslide susceptibility belief values were obtained by applying a statistical method, the certainty factor method, and by measuring the belief in each rule that the decision tree classifier produced, transforming the discrete type of result into a continuous value that enabled the generation of a landslide susceptibility belief map. In total, four landslide susceptibility maps were produced using the certainty factor method, the Iterative Dichotomizer version 3 algorithm, the J48 algorithm and the modified Iterative Dichotomizer version 3 model in order to evaluate the performance of the developed classifier. The validation results showed that area under the ROC curves for the models varied from 0.7936 to 0.8397 for success rate curve and 0.7766 to 0.8035 for prediction rate curves, respectively. The success rate and prediction curves showed that the modified Iterative Dichotomizer version 3 model had a slightly higher performance with 0.8397 and 0.8035, respectively. From the outcomes of the study, it was induced that the developed modified decision tree classifier could be efficiently used for landslide susceptibility analysis and in general might be used for classification and estimation purposes in spatial predictive models.     

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 %).     

Landslide hazard and risk mapping at catchment scale in the Arno River basin

We present the methodologies adopted and the outcomes obtained in the analysis of landslide risk in the basin of the Arno River (Central Italy) in the framework of a project sponsored by the Basin Authority of the Arno River, started in the year 2002 and completed at the beginning of 2005. In particular, a complete set of methods and applications for the assessment of landslide susceptibility and risk are described and discussed. A new landslide inventory of the whole area was realized, using conventional (aerial-photo interpretation and field surveys) and non-conventional methods (e.g. remote sensing techniques such as DInSAR and PS-InSAR). The great majority of the mapped mass movements are rotational slides (75%), solifluctions and other shallow slow movements (17%) and flows (5%), while soil slips, and other rapid landslides, seem less frequent everywhere within the basin. The relationships between landslide characteristics and environmental factors have been assessed through statistical analysis. As expected, the results show a strong control of land cover, lithology and morphology on landslide occurrence. The landslide frequency-size distribution shows a typical scaling behaviour already underlined in other landslide inventories worldwide. The assessment of landslide hazard in terms of probability of occurrence in a given time, based for mapped landslides on direct and indirect observations of the state of activity and recurrence time, has been extended to landslide-free areas through the application of statistical methods implemented in an artificial neural network (ANN). Unique conditions units (UCU) were defined by the map overlay of landslide preparatory factors (lithology, land cover, slope gradient, slope curvature and upslope contributing area) and afterwards used to construct a series of model vectors for the training and test of the ANN. Various different ANNs were selected throughout the basin, until each UCU was assigned a degree of membership to a susceptibility and a hazard class. Model validation confirms that prediction results are very good, with an average percentage of correctly recognized mass movements of about 85%. The analysis also revealed the existence of a large number of unmapped mass movements, thus contributing to the completeness of the final inventory. Temporal hazard was estimated via the translation of state of activity in recurrence time and hence probability of occurrence. The following intersection of hazard values with vulnerability and exposure figures, obtained by reclassification of digital vector mapping at 1:10,000 scale, lead to the definition of risk values for each terrain unit for different periods of time into the future. The final results of the research are now undergoing a process of integration and implementation within land planning and risk prevention policies and practices at local and national level.     

Application of weights-of-evidence and certainty factor models and their comparison in landslide susceptibility mapping at Haraz watershed, Iran

The main goal of this study was to investigate the application of the weights-of-evidence and certainty factor approaches for producing landslide susceptibility maps of a landslide-prone area (Haraz) in Iran. For this purpose, the input layers of the landslide conditioning factors were prepared in the first stage. The landslide conditioning factors considered for the study area were slope gradient, slope aspect, altitude, lithology, land use, distance from streams, distance from roads, distance from faults, topographic wetness index, stream power index, stream transport index and plan curvature. For validation of the produced landslide susceptibility maps, the results of the analyses were compared with the field-verified landslide locations. Additionally, the receiver operating characteristic curves for all the landslide susceptibility models were constructed and the areas under the curves were calculated. The landslide locations were used to validate results of the landslide susceptibility maps. The verification results showed that the weights-of-evidence model (79.87%) performed better than certainty factor (72.02%) model with a standard error of 0.0663 and 0.0756, respectively. According to the results of the area under curve evaluation, the map produced by weights-of-evidence exhibits satisfactory properties.     

The effect of the sampling strategies on the landslide susceptibility mapping by conditional probability and artificial neural networks

This study presented herein compares the effect of the sampling strategies by means of landslide inventory on the landslide susceptibility mapping. The conditional probability (CP) and artificial neural networks (ANN) models were applied in Sebinkarahisar (Giresun–Turkey). Digital elevation model was first constructed using a geographical information system software and parameter maps affecting the slope stability such as geology, faults, drainage system, topographical elevation, slope angle, slope aspect, topographic wetness index, stream power index and normalized difference vegetation index were considered. In the last stage of the analyses, landslide susceptibility maps were produced applying different sampling strategies such as; scarp, seed cell and point. The maps elaborated were then compared by means of their validations. Scarp sampling strategy gave the best results than the point, whereas the scarp and seed cell methods can be evaluated relatively similar. Comparison of the landslide susceptibility maps with known landslide locations indicated that the higher accuracy was obtained for ANN model using the scarp sampling strategy. The results obtained in this study also showed that the CP model can be used as a simple tool in assessment of the landslide susceptibility, because input process, calculations and output process are very simple and can be readily understood.     

Use of GIS-based fuzzy logic relations and its cross application to produce landslide susceptibility maps in three test areas in Malaysia

Landslides are one of the most frequent and common natural hazards in Malaysia. Preparation of landslide susceptibility maps is one of the first and most important steps in the landslide hazard mitigation. However, due to complex nature of landslides, producing a reliable susceptibility map is not easy. For this reason, a number of different approaches have been used, including direct and indirect heuristic approaches, deterministic, probabilistic, statistical, and data mining approaches. Moreover, these landslides can be systematically assessed and mapped through a traditional mapping framework using geoinformation technologies. Since the early 1990s, several mathematical models have been developed and applied to landslide hazard mapping using geographic information system (GIS). Among various approaches, fuzzy logic relation for mapping landslide susceptibility is one of the techniques that allows to describe the role of each predisposing factor (landslide-conditioning parameters) and their optimal combination. This paper presents a new attempt at landslide susceptibility mapping using fuzzy logic relations and their cross application of membership values to three study areas in Malaysia using a GIS. The possibility of capturing the judgment and the modeling of conditioning factors are the main advantages of using fuzzy logic. These models are capable to capture the conditioning factors directly affecting the landslides and also the inter-relationship among them. In the first stage of the study, a landslide inventory was complied for each of the three study areas using both field surveys and airphoto studies. Using total 12 topographic and lithological variables, landslide susceptibility models were developed using the fuzzy logic approach. Then the landslide inventory and the parameter maps were analyzed together using the fuzzy relations and the landslide susceptibility maps produced. Finally, the prediction performance of the susceptibility maps was checked by considering field-verified landslide locations in the studied areas. Further, the susceptibility maps were validated using the receiver-operating characteristics (ROC) success rate curves. The ROC curve technique is based on plotting model sensitivity—true positive fraction values calculated for different threshold values versus model specificity—true negative fraction values on a graph. The ROC curves were calculated for the landslide susceptibility maps obtained from the application and cross application of fuzzy logic relations. Qualitatively, the produced landslide susceptibility maps showed greater than 82% landslide susceptibility in all nine cases. The results indicated that, when compared with the landslide susceptibility maps, the landslides identified in the study areas were found to be located in the very high and high susceptibility zones. This shows that as far as the performance of the fuzzy logic relation approach is concerned, the results appeared to be quite satisfactory, the zones determined on the map being zones of relative susceptibility.     

Modeling debris flow initiation and run-out in recently burned areas using data-driven methods

In the framework of the landslide susceptibility assessment, the maps produced should include not only the landslide initiation areas, but also those areas potentially affected by the traveling mobilized material. To achieve this purpose, the susceptibility analysis must be separated in two distinct components: (1) The first one, which is also the most discussed in the literature, deals with the susceptibility to failure, and (2) the second component refers to the run-out modeling using the initiation areas as an input. Therefore, in this research we present a debris flow susceptibility assessment in a recently burned area in a mountain zone in central Portugal. The modeling of debris flow initiation areas is performed using two statistical methods: a bivariate (information value) and a multivariate (logistic regression). The independent validation of the results generated areas under the receiver operating characteristic curves between 0.91 and 0.98. The slope angle, plan curvature, soil thickness and lithology proved to be the most relevant predisposing factors for the debris flow initiation in recently burned areas. The run-out is simulated by applying two different methods: the empirical model Flow Path Assessment of Gravitational Hazards at a Regional Scale (Flow-R) and the hydrological algorithm D-infinity downslope influence (DI). The run-out modeling of the 36 initiation areas included in the debris flow inventory delivered a true positive rate of 83.5% for Flow-R and 80.5% for DI, reflecting a good performance of both models. Finally, the susceptibility map for the entire basin including both the initiation and the run-out areas in a scenario of a recent wildfire was produced by combining the four models mentioned above.     

A GIS-based approach for gully erosion susceptibility modelling: a test in Sicily, Italy

The aim of this study is to analyze the susceptibility conditions to gully erosion phenomena in the Magazzolo River basin and to test a method that allows for driving the factors selection. The study area is one of the largest (225 km²) watershed of southern Sicily and it is mostly characterized by gentle slopes carved into clayey and evaporitic sediments, except for the northern sector where carbonatic rocks give rise to steep slopes. In order to obtain a quantitative evaluation of gully erosion susceptibility, statistical relationships between the spatial distributions of gullies affecting the area and a set of twelve environmental variables were analyzed. Stereoscopic analysis of aerial photographs dated 2000, and field surveys carried out in 2006, allowed us to map about a thousand landforms produced by linear water erosion processes, classifiable as ephemeral and permanent gullies. The linear density of the gullies, computed on each of the factors classes, was assumed as the function expressing the susceptibility level of the latter. A 40-m digital elevation model (DEM) prepared from 1:10,000-scale topographic maps was used to compute the values of nine topographic attributes (primary: slope, aspect, plan curvature, profile curvature, general curvature, tangential curvature; secondary: stream power index; topographic wetness index; LS-USLE factor); from available thematic maps and field checks three other physical attributes (lithology, soil texture, land use) were derived. For each of these variables, a 40-m grid layer was generated, reclassifying the topographic variables according to their standard deviation values. In order to evaluate the controlling role of the selected predictive variables, one-variable susceptibility models, based on the spatial relationships between each single factor and gullies, were produced and submitted to a validation procedure. The latter was carried out by evaluating the predictive performance of models trained on one half of the landform archive and tested on the other. Large differences of accuracy were verified by computing geometric indexes of the validation curves (prediction and success rate curves; ROC curves) drawn for each one-variable model; in particular, soil texture, general curvature and aspect demonstrated a weak or a null influence on the spatial distribution of gullies within the studied area, while, on the contrary, tangential curvature, stream power index and plan curvature showed high predictive skills. Hence, predictive models were produced on a multi-variable basis, by variously combining the one-variable models. The validation of the multi-variables models, which generally indicated quite satisfactory results, were used as a sensitivity analysis tool to evaluate differences in the prediction results produced by changing the set of combined physical attributes. The sensitivity analysis pointed out that by increasing the number of combined environmental variables, an improvement of the susceptibility assessment is produced; this is true with the exception of adding to the multi-variables models a variable, as slope aspect, not correlated to the target variable. The addition of this attribute produces effects on the validation curves that are not distinguishable from noise and, as a consequence, the slope aspect was excluded from the final multi-variables model used to draw the gully erosion susceptibility map of the Magazzolo River basin. In conclusion, the research showed that the validation of one-variable models can be used as a tool for selecting factors to be combined to prepare the best performing multi-variables gully erosion susceptibility model.     

GIS-based frequency ratio and index of entropy models for landslide susceptibility assessment in the Caspian forest,northern Iran

This study presents a landslide susceptibility assessment for the Caspian forest using frequency ratio and index of entropy models within geographical information system. First, the landslide locations were identified in the study area from interpretation of aerial photographs and multiple field surveys. 72 cases (70 %) out of 103 detected landslides were randomly selected for modeling, and the remaining 31 (30 %) cases were used for the model validation. The landslide-conditioning factors, including slope degree, slope aspect, altitude, lithology, rainfall, distance to faults, distance to streams, plan curvature, topographic wetness index, stream power index, sediment transport index, normalized difference vegetation index (NDVI), forest plant community, crown density, and timber volume, were extracted from the spatial database. Using these factors, landslide susceptibility and weights of each factor were analyzed by frequency ratio and index of entropy models. Results showed that the high and very high susceptibility classes cover nearly 50 % of the study area. For verification, the receiver operating characteristic (ROC) curves were drawn and the areas under the curve (AUC) calculated. The verification results revealed that the index of entropy model (AUC = 75.59 %) is slightly better in prediction than frequency ratio model (AUC = 72.68 %). The interpretation of the susceptibility map indicated that NDVI, altitude, and rainfall play major roles in landslide occurrence and distribution in the study area. The landslide susceptibility maps produced from this study could assist planners and engineers for reorganizing and planning of future road construction and timber harvesting operations.     

National-scale data-driven rainfall induced landslide susceptibility mapping for China by accounting for incomplete landslide data

China is one of the countries where landslides caused the most fatalities in the last decades.The threat that landslide disasters pose to people might even be greater in the future,due to climate change and the increasing urbanization of mountainous areas.A reliable national-scale rainfall induced landslide suscep-tibility model is therefore of great relevance in order to identify regions more and less prone to landslid-ing as well as to develop suitable risk mitigating strategies.However,relying on imperfect landslide data is inevitable when modelling landslide susceptibility for such a large research area.The purpose of this study is to investigate the influence of incomplete landslide data on national scale statistical landslide susceptibility modeling for China.In this context,it is aimed to explore the benefit of mixed effects mod-elling to counterbalance associated bias propagations.Six influencing factors including lithology,slope,soil moisture index,mean annual precipitation,land use and geological environment regions were selected based on an initial exploratory data analysis.Three sets of influencing variables were designed to represent different solutions to deal with spatially incomplete landslide information:Set 1(disregards the presence of incomplete landslide information),Set 2(excludes factors related to the incompleteness of landslide data),Set 3(accounts for factors related to the incompleteness via random effects).The vari-able sets were then introduced in a generalized additive model(GAM:Set 1 and Set 2)and a generalized additive mixed effect model(GAMM:Set 3)to establish three national-scale statistical landslide suscep-tibility models:models 1,2 and 3.The models were evaluated using the area under the receiver operating characteristics curve(AUROC)given by spatially explicit and non-spatial cross-validation.The spatial pre-diction pattern produced by the models were also investigated.The results show that the landslide inven-tory incompleteness had a substantial impact on the outcomes of the statistical landslide susceptibility models.The cross-validation results provided evidence that the three established models performed well to predict model-independent landslide information with median AUROCs ranging from 0.8 to 0.9.However,although Model 1 reached the highest AUROCs within non-spatial cross-validation(median of 0.9),it was not associated with the most plausible representation of landslide susceptibility.The Model 1 modelling results were inconsistent with geomorphological process knowledge and reflected a large extent the underlying data bias.The Model 2 susceptibility maps provided a less biased picture of landslide susceptibility.However,a lower predicted likelihood of landslide occurrence still existed in areas known to be underrepresented in terms of landslide data(e.g.,the Kuenlun Mountains in the northern Tibetan Plateau).The non-linear mixed-effects model(Model 3)reduced the impact of these biases best by introducing bias-describing variables as random effects.Among the three models,Model 3 was selected as the best national-scale susceptibility model for China as it produced the most plausible portray of rainfall induced landslide susceptibility and the highest spatially explicit predictive perfor-mance(median AUROC of spatial cross validation 0.84)compared to the other two models(median AUROCs of 0.81 and 0.79,respectively).We conclude that ignoring landslide inventory-based incomplete-ness can entail misleading modelling results and that the application of non-linear mixed-effect models can reduce the propagation of such biases into the final results for very large areas.     

Application and validation of bivariate GIS-based landslide susceptibility assessment for the Vitravo river catchment (Calabria,south Italy)

The Calabria (Southern Italy) region is characterized by many geological hazards among which landslides, due to the geological, geomorphological, and climatic characteristics, constitute one of the major cause of significant and widespread damage. The present work aims to exploit a bivariate statistics-based approach for drafting a landslide susceptibility map in a specific scenario of the region (the Vitravo River catchment) to provide a useful and easy tool for future land planning. Landslides have been detected through air-photo interpretation and field surveys, by identifying both the landslide detachment zones (LDZ) and landslide bodies; a geospatial database of predisposing factors has been constructed using the ESRI ArcView 3.2 GIS. The landslide susceptibility has been assessed by computing the weighting values (Wi) for each class of the predisposing factors (lithology, proximity to fault and drainage line, land use, slope angle, aspect, plan curvature), thus evaluating the distribution of the landslide detachment zones within each class. The extracted predisposing factors maps have then been re-classified on the basis of the calculated weighting values (Wi) and by means of overlay processes. Finally, the landslide susceptibility map has been considered by five classes. It has been determined that a high percentage (61%) of the study area is characterized by a high to very high degree of susceptibility; clay and marly lithologies, and slope exceeding 20° in inclination would be much prone to landsliding. Furthermore, in order to ascertain the proposed landslide susceptibility estimate, a validation procedure has been carried out, by splitting the landslide detachment zones into two groups: a training and a validation set. By means of the training set, the susceptibility map has first been produced; then, it has been compared with the validation set. As a result, a great majority of LDZ-validation set (85%) would be located in highly and very highly susceptible areas. The predictive power of the model is considered reliable, since more than 50% of the LDZ fall into 20% of the most susceptible areas. The reliability of the susceptibility map is also suggested by computing the SCAI index, true positive and false positive rates; nevertheless, the most susceptible areas are overestimated. As a whole, the results indicate that landslide susceptibility assessment based on a bivariate statistics-based method in a GIS environment may be useful for land planning policy, especially when considering its cost/benefit ratio and the need of using an easy tool.     

A comparative study of sequential minimal optimization-based support vector machines,vote feature intervals,and logistic regression in landslide susceptibility assessment using GIS

Landslide susceptibility assessment using GIS has been done for part of Uttarakhand region of Himalaya (India) with the objective of comparing the predictive capability of three different machine learning methods, namely sequential minimal optimization-based support vector machines (SMOSVM), vote feature intervals (VFI), and logistic regression (LR) for spatial prediction of landslide occurrence. Out of these three methods, the SMOSVM and VFI are state-of-the-art methods for binary classification problems but have not been applied for landslide prediction, whereas the LR is known as a popular method for landslide susceptibility assessment. In the study, a total of 430 historical landslide polygons and 11 landslide affecting factors such as slope angle, slope aspect, elevation, curvature, lithology, soil, land cover, distance to roads, distance to rivers, distance to lineaments, and rainfall were selected for landslide analysis. For validation and comparison, statistical index-based methods and the receiver operating characteristic curve have been used. Analysis results show that all these models have good performance for landslide spatial prediction but the SMOSVM model has the highest predictive capability, followed by the VFI model, and the LR model, respectively. Thus, SMOSVM is a better model for landslide prediction and can be used for landslide susceptibility mapping of landslide-prone areas.     

Short-term geomorphological evolution of the Poggio Baldi landslide upper scarp via 3D change detection

On 19 March 2010, a 4 million m³ landslide occurred at Poggio Baldi, a small village in the Santa Sofia municipality, central Apennines (Forlì-Cesena, Italy). The landslide caused severe damages to some homes and obstructed both the SS310 national road and the Bidente river. The Poggio Baldi landslide arose in the “Marnoso-Arenacea Romagnola” formation composed of a pelitic-arenaceous turbiditic sequence. The landslide was classified as a rotational landslide, evolving into a partially confined flow-like landslide and causing the reactivation of the deposit of a previous landslide that took place in 1914. This paper reports a study of the phenomena currently occurring on the 100-m high main scarp of this landslide complex. The aim of the study was to assess ground changes that occurred on the upper scarp from 2015 to 2018 and to infer a preliminary evolutionary model capable of supporting short-term landslide scenarios. For this purpose, multi-station terrestrial laser scanner surveys were performed in 2015, 2016, 2017, and 2018. Additionally, an unmanned aerial vehicle three-dimensional photogrammetric survey was carried out in 2016. Analyses of the three-dimensional digital models of the main scarp made it possible to carry out several exhaustive multi-temporal investigations and to derive a detailed three-dimensional change detection scheme for it. The results showed an active geomorphological evolution of the rock scarp area due to frequent rockfalls and topples (of the order of a few m³), with significant local volume changes (a few thousand m³/year) and with potential implications for the long-term evolution of the entire slope.

     

Landslide susceptibility mapping by binary logistic regression, analytical hierarchy process, and statistical index models and assessment of their performances

The current research presents a detailed landslide susceptibility mapping study by binary logistic regression, analytical hierarchy process, and statistical index models and an assessment of their performances. The study area covers the north of Tehran metropolitan, Iran. When conducting the study, in the first stage, a landslide inventory map with a total of 528 landslide locations was compiled from various sources such as aerial photographs, satellite images, and field surveys. Then, the landslide inventory was randomly split into a testing dataset 70 % (370 landslide locations) for training the models, and the remaining 30 % (158 landslides locations) was used for validation purpose. Twelve landslide conditioning factors such as slope degree, slope aspect, altitude, plan curvature, normalized difference vegetation index, land use, lithology, distance from rivers, distance from roads, distance from faults, stream power index, and slope-length were considered during the present study. Subsequently, landslide susceptibility maps were produced using binary logistic regression (BLR), analytical hierarchy process (AHP), and statistical index (SI) models in ArcGIS. The validation dataset, which was not used in the modeling process, was considered to validate the landslide susceptibility maps using the receiver operating characteristic curves and frequency ratio plot. The validation results showed that the area under the curve (AUC) for three mentioned models vary from 0.7570 to 0.8520 $ ({\text{AUC}}_{\text{AHP}} = 75.70\;\% ,\;{\text{AUC}}_{\text{SI}} = 80.37\;\% ,\;{\text{and}}\;{\text{AUC}}_{\text{BLR}} = 85.20\;\% ) $ ( AUC AHP = 75.70 % , AUC SI = 80.37 % , and AUC BLR = 85.20 % ) . Also, plot of the frequency ratio for the four landslide susceptibility classes of the three landslide susceptibility models was validated our results. Hence, it is concluded that the binary logistic regression model employed in this study showed reasonably good accuracy in predicting the landslide susceptibility of study area. Meanwhile, the results obtained in this study also showed that the statistical index model can be used as a simple tool in the assessment of landslide susceptibility when a sufficient number of data are obtained.     

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.