Accuracy Of Landslide Susceptibility Mapping Research Articles

Analyzing the posterior predictive capability and usability of landslide susceptibility maps: a case of Kerala, India

AbstractLandslide susceptibility maps serve as the basis for hazard and risk assessment, as well as risk-informed land use planning at various spatial scales. Researchers create these maps aiming to fulfil a variety of purposes, including infrastructure planning and restrictive land use zoning. These applications require accurate and specific information to fulfil these purposes, as decisions based on these maps have the potential to cost lives and cause infrastructure damage. The usability of the maps depends on whether they provide the required information and their accuracy to be utilized for the intended purpose. Therefore, assessing the usability and predictive accuracy of landslide susceptibility maps is of paramount importance. Typically, the accuracy of the maps is evaluated using the same landslide inventory that was used to create the map, which does not actually test the predictive ability of the maps in future situations. In this study, we briefly reviewed the purposes of the map creation using literature and stakeholder interviews and assessed the accuracy of three landslide susceptibility maps in a posterior manner. We generated a multi-temporal landslide event inventory after the creation dates of these landslide susceptibility maps. We devised a method to evaluate classified maps by making use of Unique Conditions Units (UCUs) to compare the posteriorly predicted susceptibility classes and the new landslide occurrences. Interviews with stakeholders revealed a disconnection between the aims set forth by map producers and the specific needs of the end users. Our posterior assessment shows that overall predictions of the maps provide plausible results; however, their interpretations for different use cases make them less likely to be used. When comparing the maps using UCUs, landslide densities overlap between the different susceptibility classes, indicating low predictive performance of the maps. Direct comparison of all maps shows a low agreement between susceptibility classes, which pinpoints the uncertainties in data and methods used to create different maps. This study highlights the need for purpose-oriented landslide susceptibility mapping and posterior assessment of the predictive capabilities of these maps aiming to fulfil respective purposes.

Fuzzy Logic-Based Landslide Susceptibility Mapping in Earthquake-Prone Areas: A Case Study of the Mila Basin, Algeria

Abstract —This research focuses on analyzing landslides triggered by a moderate earthquake (Mw = 4.9) in the northeastern region of the Mila province, which resulted in significant damage and economic losses in the El Kherba district and Grarem Gouga city. Through an extensive field-based investigation, a comprehensive inventory of landslides has been compiled. To assess the susceptibility to landslides triggered by seismic activity, a GIS-based fuzzy logic model was employed. The model incorporates various input factors, such as lithology, slope angle, normalized difference vegetation index (NDVI), distance from rivers and roads, precipitation, and seismic hazard, which is shown on a map. The study compares the performance of different fuzzy operators and gamma values and determines that using fuzzy gamma operators with a gamma value of 0.8 yields a satisfactory consistency with the distribution of landslides. Moreover, incorporating the map of seismic hazard as a causative factor enhances the accuracy of landslide susceptibility mapping. This study underscores the utility of the fuzzy logic model in disaster management and the planning of development activities.

A Novel Dataset Replenishment Strategy Integrating Time-Series InSAR for Refined Landslide Susceptibility Mapping in Karst Regions

The accuracy of landslide susceptibility mapping is influenced by the quality of sample data, factor systems, and assessment methods. This study aims to enhance the representativeness and overall quality of the sample dataset through an effective sample expansion strategy, achieving greater precision and reliability in the landslide susceptibility model. An integrated interpretative framework for landslide susceptibility assessment is developed using the XGBoost-SHAP-PDP algorithm to deeply investigate the key contributing factors of landslides in karst areas. Firstly, 17 conditioning factors (e.g., surface deformation rate, land surface temperature, slope, lithology, and NDVI) were introduced based on field surveys, satellite imagery, and literature reviews, to construct a landslide susceptibility conditioning factor system in line with karst geomorphology characteristics. Secondly, a sample expansion strategy combining the frequency ratio (FR) with SBAS-InSAR interpretation results was proposed to optimize the landslide susceptibility assessment dataset. The XGBoost algorithm was then utilized to build the assessment model. Finally, the SHAP and PDP algorithms were applied to interpret the model, examining the primary contributing factors and their influence on landslides in karst areas from both global and single-factor perspectives. Results showed a significant improvement in model accuracy after sample expansion, with AUC values of 0.9579 and 0.9790 for the training and testing sets, respectively. The top three important factors were distance from mining sites, lithology, and NDVI, while land surface temperature, soil erosion modulus, and surface deformation rate also significantly contributed to landslide susceptibility. In summary, this paper provides an in-depth discussion of the effectiveness of LSM in predicting landslide occurrence in complex terrain environments. The reliability and accuracy of the landslide susceptibility assessment model were significantly improved by optimizing the sample dataset within the karst landscape region. In addition, the research results not only provide an essential reference for landslide prevention and control in the karst region of Southwest China and regional central engineering construction planning but also provide a scientific basis for the prevention and control of geologic hazards globally, showing a wide range of application prospects and practical significance.

Optimized landslide susceptibility prediction based on SBAS-InSAR: case study of the Jiuzhaigou Ms7.0 earthquake

Earthquake-induced landslides can cause severe surface damage and casualties, posing a serious threat to the overall ecological environment and social stability. Traditional landslide susceptibility prediction (LSP) techniques often suffer from low effectiveness and precision, necessitating the exploration of remote sensing technology. However, this research in this area is limited, and the development of high-performance prediction models remains a pressing scientific issue. This study focuses on the Ms7.0 earthquake in Jiuzhaigou on 8 August 2017. To investigate the optimal integration of remote sensing technology with traditional LSP techniques, the study applies collaborative factor analysis and contingency matrix methods to create four new coupling models (SVM-I, SVM-II, RF-I, RF-II), followed by a comprehensive performance evaluation of these models. The results indicate that the integration of SAR-derived surface deformation data significantly enhances the accuracy of Landslide Susceptibility Mapping (LSM). Comparing the model performance with the receiver operating characteristic curve and landslide density, the reliability and prediction performance of the RF-I model are outstanding, reflecting that the improved method based on the InSAR collaborative machine learning model with shape variables along the slope direction can optimize the accuracy of the LSM, and has better performance and robustness in earthquake landslide susceptibility evaluation.

A novel evolutionary combination of artificial intelligence algorithm and machine learning for landslide susceptibility mapping in the west of Iran.

Detecting and mapping landslides are crucial for effective risk management and planning. With the great progress achieved in applying optimized and hybrid methods, it is necessary to use them to increase the accuracy of landslide susceptibility maps. Therefore, this research aims to compare the accuracy of the novel evolutionary methods of landslide susceptibility mapping. To achieve this, a unique method that integrates two techniques from Machine Learning and Neural Networks with novel geomorphological indices is used to calculate the landslide susceptibility index (LSI). The study was conducted in western Azerbaijan, Iran, where landslides are frequent. Sixteen geology, environment, and geomorphology factors were evaluated, and 160 landslide events were analyzed, with a 30:70 ratio of testing to training data. Four Support Vector Machine (SVM) algorithms and Artificial Neural Network (ANN)-MLP were tested. The study outcomes reveal that utilizing the algorithms mentioned above results in over 80% of the study area being highly sensitive to large-scale movement events. Our analysis shows that the geological parameters, slope, elevation, and rainfall all play a significant role in the occurrence of landslides in this study area. These factors obtained 100%, 75.7%, 68%, and 66.3%, respectively. The predictive performance accuracy of the models, including SVM, ANN, and ROC algorithms, was evaluated using the test and train data. The AUC for ANN and each machine learning algorithm (Simple, Kernel, Kernel Gaussian, and Kernel Sigmoid) was 0.87% and 1, respectively. The Classification Matrix algorithm and Sensitivity, Accuracy, and Specificity variables were used to assess the models' efficacy for prediction purposes. Results indicate that machine learning algorithms are more effective than other methods for evaluating areas' sensitivity to landslide hazards. The Simple SVM and Kernel Sigmoid algorithms performed well, with a performance score of one, indicating high accuracy in predicting landslide-prone areas.

Effect of time-variant NDVI on landside susceptibility: A case study in Quang Ngai province, Vietnam

Abstract Normalized difference vegetation index (NDVI) is a conditioning factor that significantly affects slope stabilization, as the low vegetation coverage can create conducive conditions for landslide occurrence. In previous studies, NDVI was often calculated from long-term average NDVI maps or specific yearly NDVI maps. However, this approach is unsuitable due to the time-varying nature of these data, influenced by numerous factors, including human activities. To solve this problem, this study uses NDVI as a time-varying factor. NDVI maps are generated from Sentinel 2 and Landsat_8 imagery at the onset of each rainy season between 2015 and 2020 in the mountainous region of Quang Ngai Province. Moreover, the landslide events that occurred within this 5-year period (2016–2020), along with a set of conditioning factors, are utilized to develop landslide susceptibility models based on three algorithms: logistic regression, support vector machine, and extreme gradient boosting (XGBoost). The obtained results demonstrate that using time-varying NDVI shows superior performance compared to using only NDVI from 2015. The outcomes also indicate that XGBoost is the most effective model. Selecting suitable NDVI maps can improve the predictive accuracy of landslide susceptibility mapping.

Exploration and Comparison of the Effect of Conventional and Advanced Modeling Algorithms on Landslide Susceptibility Prediction: A Case Study from Yadong Country, Tibet

Shallow landslides pose serious threats to human existence and economic development, especially in the Himalayan areas. Landslide susceptibility mapping (LSM) is a proven way for minimizing the hazard and risk of landslides. Modeling as an essential step, various algorithms have been applied to LSM, but no consensus exists on which model is most suitable or best. In this study, information value (IV) and logistic regression (LR) were selected as representatives of the conventional algorithms, categorical boosting (CatBoost), and conventional neural networks (CNN) as the advanced algorithms, for LSM in Yadong County, and their performance was compared. To begin with, 496 historical landslide events were compiled into a landslide inventory map, followed by a list of 11 conditioning factors, forming a data set. Secondly, the data set was randomly divided into two parts, 80% of which was used for modeling and 20% for validation. Finally, the area under the curve (AUC) and statistical metrics were applied to validate and compare the performance of the models. The results showed that the CNN model performed the best (sensitivity = 79.38%, specificity = 91.00%, accuracy = 85.28%, and AUC = 0.908), while the LR model performed the worst (sensitivity = 79.38%, specificity = 76.00%, accuracy = 77.66%, and AUC = 0.838) and the CatBoost model performed better (sensitivity = 76.28%, specificity = 85.00%, accuracy = 80.81%, and AUC = 0.893). Moreover, the LSM constructed by the CNN model did a more reasonable prediction of the distribution of susceptible areas. As for feature selection, a more detailed analysis of conditioning factors was conducted, but the results were uncertain. The result analyzed by GI may be more reliable but fluctuates with the amount of data. The conclusion reveals that the accuracy of LSM can be further improved with the advancement of algorithms, by determining more representative features, which serve as a more effective guide for land use planning in the study area or other highlands where landslides are frequent.

The accuracy of landslide susceptibility map in the regional spatial plan with landslide event in Lima Puluh Kota Regency

Spatial plan is a reference in spatial development in Indonesia. One of the information displayed is landslides susceptibility area. Lima puluh kota regency in province of West Sumatra, which is located in the Bukit Barisan mountains, is a landslide-prone area, so that the regional spatial plan (RTRW) document contains a map of landslide susceptibility areas. This study evaluates the accuracy of the landslide susceptibility map contained in the regional spatial plan with landslide events in the regency until 2021, using the overlay method and then examining with the characteristics that affect it. The results of the study show that not all landslide events are in the locations indicated on the map in the spatial plan. It is necessary to improve the information on the landslide susceptibility map on a regional scale which has been based on the InaRisk map published by the BNPB (National Disaster Management Agency) on a small scale. In order to be more accurate with the causal factors, it is needed to improve the method of landslide susceptibility maps at the regional level. The methods that have been heuristic in nature need to be improved with statistical methods.

A comprehensive review of machine learning‐based methods in landslide susceptibility mapping

Landslide susceptibility mapping (LSM) has been widely used as an important reference for development and construction planning to mitigate the potential social‐eco impact caused by landslides. Originally, most of those maps were generated by the judgements of experts, which is time‐consuming and laborious, and whose accuracy is difficult to be quantified because of the subjective effects. With the development of machine learning algorithms and the methods of data collection, big data and artificial intelligence have now been popularized in this field, significantly improving mapping accuracy and efficiency. Various machine learning‐based methods, mainly including conventional machine learning, deep learning, and transfer learning have been applied and compared in LSM in different areas by previous researchers. Nevertheless, none of them can be effective in all cases. Although deep learning‐based methods were proven more accurate than conventional machine learning‐based methods in most data‐rich situations, the latter is sometimes more popularly used in LSM, as there is not that much data in this field to train a deep learning network perfectly. In a more rigorous situation when there is very limited data, transfer learning‐based approaches are applied by several researchers, which have contributed to improve the workability and the accuracy of LSM in data‐limited areas. Such technical explosion has promoted the application of landslide susceptibility maps, thus contributing to mitigating the social‐eco impact associated with landslides. This paper comprehensively reviews the whole process of generating landslide susceptibility maps based on machine learning methods, introduces and compares the commonly used machine learning methods, and discusses the topics for future research.

Reducing Local Correlations Among Causal Factor Classifications as a Strategy to Improve Landslide Susceptibility Mapping

A landslide susceptibility map (LSM) is the basis of hazard and risk assessment, guiding land planning and utilization, early warning of disaster, etc. Researchers are often overly keen on hybridizing state-of-the-art models or exploring new mathematical susceptibility models to improve the accuracy of the susceptibility map in terms of a receiver operator characteristic curve. Correlation analysis of the causal factors is a necessary routine process before susceptibility modeling to ensure that the overall correlation among all factors is low. However, this overall correlation analysis is insufficient to detect a high local correlation among the causal factor classes. The objective of this study is to answer three questions: 1) Is there a high correlation between causal factors in some parts locally? 2) Does it affect the accuracy of landslide susceptibility assessment? and 3) How can this influence be eliminated? To this aim, Wanzhou County was taken as the test site, where landslide susceptibility assessment based on 12 causal factors has been previously performed using the frequency ratio (FR) model and random forest (RF) model. In this work, we conducted a local spatial correlation analysis of the “altitude” and “rivers” factors and found a sizeable spatial overlap between altitude-class-1 and rivers-class-1. The “altitude” and “rivers” factors were reclassified, and then the FR model and RF model were used to reevaluate the susceptibility and analyze the accuracy loss caused by the local spatial correlation of the two factors. The results demonstrated that the accuracy of LSMs was markedly enhanced after reclassification of “altitude” and “rivers,” especially for the RF model–based LSM. This research shed new light on the local correlation of causal factors arising from a particular geomorphology and their impact on susceptibility.

Risk Factor Detection and Landslide Susceptibility Mapping Using Geo-Detector and Random Forest Models: The 2018 Hokkaido Eastern Iburi Earthquake

Landslide susceptibility mapping is an effective approach for landslide risk prevention and assessments. The occurrence of slope instability is highly correlated with intrinsic variables that contribute to the occurrence of landslides, such as geology, geomorphology, climate, hydrology, etc. However, feature selection of those conditioning factors to constitute datasets with optimal predictive capability effectively and accurately is still an open question. The present study aims to examine further the integration of the selected landslide conditioning factors with Q-statistic in Geo-detector for determining stratification and selection of landslide conditioning factors in landslide risk analysis as to ultimately optimize landslide susceptibility model prediction. The location chosen for the study was Atsuma Town, which suffered from landslides following the Eastern Iburi Earthquake in 2018 in Hokkaido, Japan. A total of 13 conditioning factors were obtained from different sources belonging to six categories: geology, geomorphology, seismology, hydrology, land cover/use and human activity; these were selected to generate the datasets for landslide susceptibility mapping. The original datasets of landslide conditioning factors were analyzed with Q-statistic in Geo-detector to examine their explanatory powers regarding the occurrence of landslides. A Random Forest (RF) model was adopted for landslide susceptibility mapping. Subsequently, four subsets, including the Manually delineated landslide Points with 9 features Dataset (MPD9), the Randomly delineated landslide Points with 9 features Dataset (RPD9), the Manually delineated landslide Points with 13 features Dataset (MPD13), and the Randomly delineated landslide Points with 13 features Dataset (RPD13), were selected by an analysis of Q-statistic for training and validating the Geo-detector-RF- integrated model. Overall, using dataset MPD9, the Geo-detector-RF-integrated model yielded the highest prediction accuracy (89.90%), followed by using dataset MPD13 (89.53%), dataset RPD13 (88.63%) and dataset RPD9 (87.07%), which implied that optimized conditioning factors can effectively improve the prediction accuracy of landslide susceptibility mapping.

GIS-based ensemble modelling of fuzzy system and bivariate statistics as a tool to improve the accuracy of landslide susceptibility mapping

The primary objective is to propose and verify an ensemble approach based on fuzzy system and bivariate statistics for landslide susceptibility assessment (LSA) at Azarshahr Chay Basin (Iran). In this regard, various integrations of fuzzy membership value (FMV), frequency ratio (FR), and information value (IV) with index of entropy (IOE) were investigated. Aerial photograph interpretations and substantial field checking were used to identify the landslide locations. Out of 75 identified landslides, 52 (≈70%) locations were utilized for the training of the models, whereas the remaining 23 (≈30%) cases were employed for the validation of the models. Fourteen landslide conditioning factors including altitude, slope aspect, slope degree, lithology, distance to fault, curvature, land use, distance to river, topographic position index (TPI), topographic wetness index (TWI), stream power index (SPI), normalized difference vegetation index (NDVI), distance to road, and rainfall were prepared and utilized during the analysis. The $$\mathrm{FMV}\_\mathrm{IOE}$$ , $$\mathrm{FR}\_\mathrm{IOE}$$ , and $$\mathrm{IV}\_\mathrm{IOE}$$ models were designed utilizing the dataset for training. Finally, to validate as well as to compare the model’s predictive abilities, the statistical measures of receiver operating characteristic (ROC), including sensitivity, accuracy, and specificity, were employed. The accuracy of 92.7, 92.5, and 91.8% of the models such as $$\mathrm{FMV}\_\mathrm{IOE}$$ , $$\mathrm{FR}\_\mathrm{IOE}$$ , and $$\mathrm{IV}\_\mathrm{IOE}$$ ensembles, respectively, was by the area under the receiver operating characteristic (AUROC) values developed from the ROC curve. For the validation dataset, the $$\mathrm{FMV}\_\mathrm{IOE}$$ model had the maximum sensitivity, accuracy, and specificity values of 95.7, 91.3, and 87.0%, respectively. Thus, the ensemble of FMV_IOE was introduced as a promising and premier approach that could be used for LSA in the study area. Also, IOE results indicated that altitude, lithology, and slope degree were main drivers of landslide occurrence. The results of the present research can be employed as a platform for appropriate basined management practices in order to plan the highly susceptible zones to landslide and hence minimize the expected losses.

The application of DInSAR and Bayesian statistics for the assessment of landslide susceptibility

The use of an inventory map of past landslide events in the derivation of susceptibility models is considered common practice. However, evidence of landslide activity may be lost due to various degrees of modification by subsequent landslides, erosional processes, vegetation growth and anthropic influences. The timely detection of active landslides can form an effective supplement to landslide records for improving the accuracy of landslide susceptibility maps. In this paper, we present a landslide susceptibility assessment carried out in a southwestern region of Cyprus using a synergy of differential interferometry and evidential statistics. A measurement of the vertical and horizontal displacements for the period 2016–2018 was done using the Small BAseline Subset multi-pass Differential Interferometric Synthetic Aperture Radar technique. Based on the results, a total of 8859 raster cells/pixels were classified as active landslides. The weight-of-evidence technique was applied to determine the weights of seven geomorphological and hydrological factors to landslide occurrence and compile a susceptibility model. The success and prediction rates of the derived model were calculated as 79.6% and 78.9%, respectively. The validation of the results against the existing landslide inventory indicates an 84% agreement with respect to the moderate and high landslide susceptibility zones. The proposed methodology can complement existing conventional landslide inventories as a means of providing updated landslide activity at frequent intervals and can provide valuable information regarding the distribution of landslides to support a detailed landslide assessment.

The Influence of Different Knowledge-Driven Methods on Landslide Susceptibility Mapping: A Case Study in the Changbai Mountain Area, Northeast China.

Landslides are one of the most frequent geomorphic hazards, and they often result in the loss of property and human life in the Changbai Mountain area (CMA), Northeast China. The objective of this study was to produce and compare landslide susceptibility maps for the CMA using an information content model (ICM) with three knowledge-driven methods (the artificial hierarchy process with the ICM (AHP-ICM), the entropy weight method with the ICM (EWM-ICM), and the rough set with the ICM (RS-ICM)) and to explore the influence of different knowledge-driven methods for a series of parameters on the accuracy of landslide susceptibility mapping (LSM). In this research, the landslide inventory data (145 landslides) were randomly divided into a training dataset: 70% (81 landslides) were used for training the models and 30% (35 landslides) were used for validation. In addition, 13 layers of landslide conditioning factors, namely, altitude, slope gradient, slope aspect, lithology, distance to faults, distance to roads, distance to rivers, annual precipitation, land type, normalized difference vegetation index (NDVI), topographic wetness index (TWI), plan curvature, and profile curvature, were taken as independent, causal predictors. Landslide susceptibility maps were developed using the ICM, RS-ICM, AHP-ICM, and EWM-ICM, in which weights were assigned to every conditioning factor. The resultant susceptibility was validated using the area under the ROC curve (AUC) method. The success accuracies of the landslide susceptibility maps produced by the ICM, RS-ICM, AHP-ICM, and EWM-ICM methods were 0.931, 0.939, 0.912, and 0.883, respectively, with prediction accuracy rates of 0.926, 0.927, 0.917, and 0.878 for the ICM, RS-ICM, AHP-ICM, and EWM-ICM, respectively. Hence, it can be concluded that the four models used in this study gave close results, with the RS-ICM exhibiting the best performance in landslide susceptibility mapping.

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.

Representing Landslides as Polygon (Areal) or Points? How Different Data Types Influence the Accuracy of Landslide Susceptibility Maps

In the literatures, discussions on the accuracy of different models for landslide analysis have been discussed widely. However, to date, arguments on the type of input data (landslides in the form of point or polygon) and how they affect the accuracy of these models can hardly be found. This study assesses how different types of data (point or polygon) applied to the same model influence the accuracy of the model in determining areas susceptible to landsliding. A total of 137 landslides was digitised as polygon (areal) units and then transformed into points; forming two separate datasets both representing the same landslides within the study area. These datasets were later separated into training and validation datasets. The polygon unit dataset uses the area density technique reported as percentage, while the point data uses the landslide density technique, as means of assigning weighting to landslide factor maps to generate the landslide susceptibility map that is based on the analytical hierarchy process (AHP) model. Both data groups show striking differences in terms of mapping accuracy for both training and validation datasets. The final landslide susceptibility map using area density (polygon) as input only has 48% (training) and 35% (validation) accuracy. The accuracy for the susceptibility map using the landslide density as input data achieved 89% and 82% for both training and validation datasets, respectively. This result showed that the selection of the type of data for landslide analysis can be critical in producing an acceptable level of accuracy for the landslide susceptibility map. The authors hope that the finding of this research will assist landslide investigators to determine the appropriateness of the type of landslide data because it will influence the accuracy of the final landslide potential map.

Landslide susceptibility map refinement using PSInSAR data

Abstract Landslide susceptibility maps (LSM) are commonly used by local authorities for land use management and planning activities, representing a valuable tool used to support decision makers in urban and infrastructural planning. The accuracy of a landslide susceptibility map is affected by false negative and false positive errors which can decrease the reliability of this useful product. In particular, false negative errors, are generally worse in terms of social and economic losses with respect to the losses associated with false positives. In this paper, we present a new technique to improve the accuracy of landslide susceptibility maps using Permanent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR) data. The proposed approach uses two different data sets acquired in ascending and descending geometry. The PS velocity measured along the line of sight is re-projected into a new velocity along the steepest slope direction ( V Slope ). Integration between the LSM and the ground deformation velocity map along the slope was performed using an empirical contingency matrix, which takes into account the average V Slope and the susceptibility degree obtained using the Random Forests algorithm. The Results show that the susceptibility degree increased in 56.41 km 2 of the study area. The combination of PSInSAR data and the landslide susceptibility map (LSM) improved the prediction reliability of slow moving landslides, which particularly affect urbanized areas. The use of this procedure can be easily applied in different areas where PSI data sets are available. This approach will help planning and decision-making authorities produce reliable landslide susceptibility maps, correcting some of the LSM errors.

Landslide susceptibility mapping by geographical information system-based multivariate statistical and deterministic models: in an artificial reservoir area at Northern Turkey

In Turkey, landslide phenomenon is one of the most important natural hazards. Due to landslide occurrence, several landforms and man-made structures are adversely affected and may cause many injuries and loss of life. In this context, landslide susceptibility assessment is an important task to determine susceptible areas to landslide occurrence. Especially, several dam reservoir areas in Turkey are threatened by landslide phenomena. For this reason, in this study, a dam reservoir area, located in the northern part of Turkey, was selected and investigated in the point of view of landslide susceptibility assessment. A landslide susceptibility assessment for Kurtun Dam reservoir area (Gumushane, North Turkey) was carried out by geographical information system (GIS)-based statistical and deterministic models. For this purpose, logistic regression (LR) and stability index mapping (SINMAP) methodologies were applied. In this context, eight contributing factors such as altitude, lithology, slope gradient, slope aspect, distance to drainage, distance to lineament, stream power index (SPI) and topographical wetness index (TWI) were considered. After assessment of these parameters by LR and SINMAP methods in a GIS environment, two landslide susceptibility maps were obtained. Then, the produced maps were analyzed for validation purpose. For this purpose, area under curvature (AUC) approach was used. At the end of this process, the AUC values of 0.73 and 0.65 were found for LR and SINMAP models, respectively. For the performance of the SINMAP model, statistical results produced by the model were also considered. In this context, landslide density of the stability index (SI) classes were taken into account, and it was determined that 89.5 % of the landslides fall into lower and upper threshold classes which almost correspond to moderate and high susceptibility classes. These two validation values indicate that the accuracy of landslide susceptibility maps is acceptable, and the maps are feasible for further natural hazard management affairs in the area.

A comparative study for landslide susceptibility mapping using GIS-based multi-criteria decision analysis (MCDA), logistic regression (LR) and association rule mining (ARM)

Landslide susceptibility mapping is one of the crucial stages of landslide hazard and risk assessment. Moreover, the susceptibility maps assist planners, local administrations, and decision makers in disaster planning. Various approaches have been applied in the literature to increase the accuracy of landslide susceptibility maps. The determination of suitable susceptibility mapping method plays critical role for obtaining required accuracy. In this study, the performances of three quantitative susceptibility mapping methods are evaluated. The logistic regression (LR) analysis is the typical example of statistical methods, while GIS-based multi-criteria decision analyses (MCDA) and association rule mining (ARM) are the examples of heuristic and data mining methods, respectively. The susceptibility maps based on the three methods are obtained for Şavşat in Artvin province (NE Turkey) where the region has intense landslides. The landslide influencing parameters for the study area are lithology, land use/land cover, soil type, erosion, altitude, slope, aspect, distance to drainage, soil depth, distance to fault, distance to road. The models for the three methods are then compared and evaluated by using pixel-based evaluation metrics. Results showed that ARM provides a higher quality percent (QP), whereas percent of damage detection (PDD) is higher for LR method. The lowest QP is obtained by GIS-based MCDA. It is found that LR and ARM methods are better than GIS-based MCDA in modeling the landslide susceptibility and they can be integrated to obtain better performance.

Effect of Landslide Factor Combinations on the Prediction Accuracy of Landslide Susceptibility Maps in the Blue Nile Gorge of Central Ethiopia

Database construction for landslide factors (slope, aspect, profile curvature, plan curvature, lithology, land use, distance from lineament & distance from river) and landslide inventory map is an important step in landslide susceptibility modelling. Using the frequency ratio model, the weights for each factor classes were calculated and assigned in GIS so as to add these factors and produce landslide susceptibility index maps based on mathematical combination theory. However, before combining them, their independence among each other should be ascertained. For this, the correlation matrix of logistic regression was applied and this showed that most of the correlations between factors were either absent or very insignificant suggesting that all landslide factors are independent. From a set of eight landslide factors, a total of 247 landslide susceptibility map combinations can be generated. However, for simplification, only 28 landslide susceptibility maps were chosen. Then the best landslide susceptibility map was selected based on high prediction accuracy. But, when there is similarity in the prediction accuracies of different combinations, the landslide susceptibility index difference values can be used as another selection criterion. Hence, the susceptibility map from a combination of all landslide factors except distance from river was found to be the best one. Among the 28 representative combinations, landslide susceptibility maps with the same prediction accuracy of 87.7% have been found in spite of their dissimilarity in their difference values. The combination, with a limited number of landslide factors and the highest prediction accuracy of 87.7%, was found from a combination of slope, lithology, land use and distance from lineament. In order to validate the prediction model, landslides were overlaid over the landslide susceptibility map and the number of landslides that fall into each susceptibility class was calculated. From this analysis 0.39%, 1.84%, 9.1%, 32.04% and 56.63% of the landslides fall in the very low, low, medium, high and very high landslide susceptibility classes respectively. Since 88.67% of the landslides fall in the high and very high susceptibility classes, the landslide susceptibility map can be considered reliable to predict future landslides.