A novel ensemble approach of bivariate statistical-based logistic model tree classifier for landslide susceptibility assessment

Abstract

This study addresses landslide susceptibility mapping (LSM) using a novel ensemble approach of using a bivariate statistical method (weights of evidence [WoE] and evidential belief function [EBF])-based logistic model tree (LMT) classifier. The performance and prediction capability of the ensemble models were assessed using the area under the ROC curve (AUROC), standard error, 95% confidence intervals and significance level P. Model performance analyses indicated that the AUROC values of the WoE–LMT ensemble model using the training and validation data-sets were 86.02 and 85.9%, respectively, whereas those of the EBF–LMT ensemble model were 88.2 and 87.8%, respectively. On the other hand, the AUC curves for the four landslide susceptibility maps indicated that the AUC values of the ensemble models of WoE–LMT (85.11 and 83.98%) and EBF–LMT (86.21 and 85.23%) could improve the performance and prediction accuracy of single WoE (84.23 and 82.46%) and EBF (85.39 and 81.33%) models for the training and validation data-sets.     

Application of frequency ratio,weights of evidence and evidential belief function models in landslide susceptibility mapping

The landslide hazard occurred in Taibai County has the characteristics of the typical landslides in mountain hinterland. The slopes mainly consist of residual sediments and locate along the highway. Most of them are in the less stable state and in high risk during rainfall in flood season especially. The main purpose of this paper is to produce landslide susceptibility maps for Taibai County (China). In the first stage, a landslide inventory map and the input layers of the landslide conditioning factors were prepared in the geographic information system supported by field investigations and remote sensing data. The landslides conditioning factors considered for the study area were slope angle, altitude, slope aspect, plan curvature, profile curvature, distance to faults, distance to rivers, distance to roads, normalized difference vegetation index, lithological unit, rainfall and land use. Subsequently, the thematic data layers of conditioning factors were integrated by frequency ratio (FR), weights of evidence (WOE) and evidential belief function (EBF) models. As a result, landslide susceptibility maps were obtained. In order to compare the predictive ability of these three models, a validation procedure was conducted. The curves of cumulative area percentage of ordered index values vs. the cumulative percentage of landslide numbers were plotted and the values of area under the curve (AUC) were calculated. The predictive ability was characterized by the AUC values and it indicates that all these models considered have relatively similar and high accuracies. The success rate of FR, WOE and EBF models was 0.9161, 0.9132 and 0.9129, while the prediction rate of the three models was 0.9061, 0.9052 and 0.9007, respectively. Considering the accuracy and simplicity comprehensively, the FR model is the optimum method. These landslide susceptibility maps can be used for preliminary land use planning and hazard mitigation purpose.     

Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province,Iran

Flood is one of the most devastating natural disasters with socio-economic and environmental consequences. Thus, comprehensive flood management is essential to reduce the flood effects on human lives and livelihoods. The main goal of this study was to investigate the application of the frequency ratio (FR) and weights-of-evidence (WofE) models for flood susceptibility mapping in the Golestan Province, Iran. At first, a flood inventory map was prepared using Iranian Water Resources Department and extensive field surveys. In total, 144 flood locations were identified in the study area. Of these, 101 (70%) floods were randomly selected as training data and the remaining 43 (30%) cases were used for the validation purposes. In the next step, flood conditioning factors such as lithology, land-use, distance from rivers, soil texture, slope angle, slope aspect, plan curvature, topographic wetness index (TWI) and altitude were prepared from the spatial database. Subsequently, the receiver operating characteristic (ROC) curves were drawn for produced flood susceptibility maps and the area under the curves (AUCs) was computed. The final results indicated that the FR (AUC = 76.47%) and WofE (AUC = 74.74%) models have almost similar and reasonable results. Therefore, these flood susceptibility maps can be useful for researchers and planner in flood mitigation strategies.     

Spatial prediction of landslide susceptibility by combining evidential belief function,logistic regression and logistic model tree

Abstract

In this study, we introduced novel hybrid of evidence believe function (EBF) with logistic regression (EBF-LR) and logistic model tree (EBF-LMT) for landslide susceptibility modelling. Fourteen conditioning factors were selected, including slope aspect, elevation, slope angle, profile curvature, plan curvature, topographic wetness index (TWI), stream sediment transport index (STI), stream power index (SPI), distance to rivers, distance to faults, distance to roads, lithology, normalized difference vegetation index (NDVI), and land use. The importance of factors was assessed using correlation attribute evaluation method. Finally, the performance of three models was evaluated using the area under the curve (AUC). The validation process indicated that the EBF-LMT model acquired the highest AUC for the training (84.7%) and validation (76.5%) datasets, followed by EBF-LR and EBF models. Our result also confirmed that combination of a decision tree-logistic regression-based algorithm with a bivariate statistical model lead to enhance the prediction power of individual landslide models.     

Landslide susceptibility assessment using evidential belief function,certainty factor and frequency ratio model at Baxie River basin,NW China

This study evaluates and compares landslide susceptibility maps of the Baxie River basin, Gansu Province, China, using three models: evidential belief function (EBF), certainty factor (CF) and frequency ratio (FR). First, a landslide inventory map is constructed from satellite image interpretation and extensive field data. Second, the study area is partitioned into 17,142 slope units, and modelled using nine landslide influence parameters: elevation, slope angle, slope aspect, relief amplitude, cutting depth, gully density, lithology, normalized difference vegetation index and distance to roads. Finally, landslide susceptibility maps are presented based on EBF, CF and FR models and validated using area under curve (AUC) analysis. The success rates of the EBF, CF and FR models are 0.8038, 0.7924 and 0.8088, respectively, while the prediction rates of the three models are 0.8056, 0.7922 and 0.7989, respectively. The result of this study can be reliably used in land use management and planning.     

A GIS-based comparative study of Dempster-Shafer,logistic regression and artificial neural network models for landslide susceptibility mapping

The main aim of present study is to compare three GIS-based models, namely Dempster–Shafer (DS), logistic regression (LR) and artificial neural network (ANN) models for landslide susceptibility mapping in the Shangzhou District of Shangluo City, Shaanxi Province, China. At First, landslide locations were identified by aerial photographs and supported by field surveys, and a total of 145 landslide locations were mapped in the study area. Subsequently, the landslide inventory was randomly divided into two parts (70/30) using Hawths Tools in ArcGIS 10.0 for training and validation purposes, respectively. In the present study, 14 landslide conditioning factors such as altitude, slope angle, slope aspect, topographic wetness index, sediment transport index, stream power index, plan curvature, profile curvature, lithology, rainfall, distance to rivers, distance to roads, distance to faults and normalized different vegetation index were used to detect the most susceptible areas. In the next step, landslide susceptible areas were mapped using the DS, LR and ANN models based on landslide conditioning factors. Finally, the accuracies of the landslide susceptibility maps produced from the three models were verified using the area under the curve (AUC). The validation results showed that the landslide susceptibility map generated by the ANN model has the highest training accuracy (73.19%), followed by the LR model (71.37%), and the DS model (66.42%). Similarly, the AUC plot for prediction accuracy presents that ANN model has the highest accuracy (69.62%), followed by the LR model (68.94%), and the DS model (61.39%). According to the validation results of the AUC curves, the map produced by these models exhibits the satisfactory properties.     

Application of GIS-based data-driven models for groundwater potential mapping in Kuhdasht region of Iran

Water shortage and population growth in Iran rapidly diminish groundwater supplies. Thus, finding the techniques such as GIS that can be used as powerful tools in groundwater management, and predicting groundwater potential is required. The main objective of this study is to evaluate the efficiency of the statistical index (SI), frequency ratio (FR) weights of evidence (WoE) and evidential belief function (EBF) models for groundwater potential mapping at Kuhdasht region, Lorestan province, Iran. For this purpose, 12 groundwater influencing factors were considered in this investigation. From 171 available wells in the study area, 114 wells (67%) and 57 wells (33%) were used based on random selection in SI, FR, WoE and EBF models as training and validation data-sets, respectively. The area under the ROC curve (AUC) for SI, FR, WoE and EBF models was calculated as 91.8, 91, 93.6 and 93.3%, respectively. These curve values indicated that all four models have reasonably good accuracy in spatially predicting groundwater potential in this area.     

Rainfall-induced landslide susceptibility assessment at the Chongren area (China) using frequency ratio,certainty factor,and index of entropy

The main objective of the study was to evaluate and compare the overall performance of three methods, frequency ratio (FR), certainty factor (CF) and index of entropy (IOE), for rainfall-induced landslide susceptibility mapping at the Chongren area (China) using geographic information system and remote sensing. First, a landslide inventory map for the study area was constructed from field surveys and interpretations of aerial photographs. Second, 15 landslide-related factors such as elevation, slope, aspect, plan curvature, profile curvature, stream power index, sediment transport index, topographic wetness index, distance to faults, distance to rivers, distance to roads, landuse, NDVI, lithology and rainfall were prepared for the landslide susceptibility modelling. Using these data, three landslide susceptibility models were constructed using FR, CF and IOE. Finally, these models were validated and compared using known landslide locations and the receiver operating characteristics curve. The result shows that all the models perform well on both the training and validation data. The area under the curve showed that the goodness-of-fit with the training data is 79.12, 80.34 and 80.42% for FR, CF and IOE whereas the prediction power is 80.14, 81.58 and 81.73%, for FR, CF and IOE, respectively. The result of this study may be useful for local government management and land use planning.     

Effects of Landslide Sampling Strategies on the Prediction Skill of Landslide Susceptibility Modelings

In this study, landslide susceptibility assessments were achieved using logistic regression, in a 523 km² area around the Eastern Mediterranean region of Southern Turkey. In reliable landslide susceptibility modeling, among others, an appropriate landslide sampling technique is always essential. In susceptibility assessments, two different random selection methods, ranging 78–83% for the train and 17–22% validation set in landslide affected areas, were applied. For the first, the landslides were selected based on their identity numbers considering the whole polygon while in the second, random grid cells of equal size of the former one was selected in any part of the landslides. Three random selections for the landslide free grid cells of equal proportion were also applied for each of the landslide affected data set. Among the landslide preparatory factors; geology, landform classification, land use, elevation, slope, plan curvature, profile curvature, slope length factor, solar radiation, stream power index, slope second derivate, topographic wetness index, heat load index, mean slope, slope position, roughness, dissection, surface relief ratio, linear aspect, slope/aspect ratio have been considered. The results showed that the susceptibility maps produced using the random selections considering the entire landslide polygons have higher performances by means of success and prediction rates.     

Evaluation and comparison of LogitBoost Ensemble,Fisher’s Linear Discriminant Analysis,logistic regression and support vector machines methods for landslide susceptibility mapping

The purpose of this study was to investigate and compare the capabilities of four machine learning methods namely LogitBoost Ensemble (LBE), Fisher’s Linear Discriminate Analysis (FLDA), Logistic Regression (LR) and Support Vector Machines (SVM) to select the best method for landslide susceptibility mapping. A part of landslide prone area of Tehri Garhwal district of Uttarakhand state, India, was selected as a case study. Validation of models was carried out using statistical analysis, the chi square test and the Receiver Operating Characteristic (ROC) curve. Result analysis shows that the LBE has the highest prediction ability (AUC = 0.972) for landslide susceptibility mapping, followed by the SVM (0.945), the LR (0.873) and the FLDA (0.870), respectively. Therefore, the LBE is the best and a promising method in comparison to other three models for landslide susceptibility mapping.     

Improving the reliability of landslide susceptibility mapping through spatial uncertainty analysis: a case study of Al Hoceima,Northern Morocco

This paper aims at providing an answer as to whether generalization obtained with data-driven modelling can be used to gauge the plausibility of the physically based (PB) model’s prediction. Two statistical models namely; Weight of Evidence (WofE) and Logistic Regression (LR), and a PB model using the infinite slope assumptions were evaluated and compared with respect to their abilities to predict susceptible areas to shallow landslides at the 1:10.000 urban scale. Threshold-dependent performance metrics showed that the three methods produced statistically comparable results in terms of success and prediction rates. However, with the Area Under the receiver operator Curve (AUC), statistical models are more accurate (88.7 and 84.6% for LR and WofE, respectively) than the PB model (only 69.8%). Nevertheless, in such data-sparse situation, the usual approaches for validation, i.e. comparing observed with predicted data, are insufficient, formal uncertainty analysis (UA) is a means for evaluating the validity and reliability of the model. We then refitted the PB model using a stochastic modification of the infinite slope stability model input scheme using Monte Carlo (MC) method backed with sensitivity analysis (SA). For statistical models, we used an informal Student t-test for estimating the certainty of the predicted probability (PP) at each location. Both modelling outputs independently show a high validity; and whereas the level of confidence in LR and WofE models remained the same after performance re-evaluation, the accuracy of the PB model showed an improvement (AUC = 72%). This result is reasonable and provides a further validation of PB model. So, in urban slope analysis, where PB diagnostic is necessary, statistical and PB modelling may play equally supportive roles in landslide hazard assessment.     

Spatial distribution and susceptibility analyses of pre-earthquake and coseismic landslides related to the Ms 6.5 earthquake of 2014 in Ludian,Yunan, China

On 3 August 2014, an earthquake struck Ludian County, Yunnan Province, China, which has caused a large number of coseismic landslides. Visual interpretation permitted 284 and 1053 landslides before and after the event to be mapped, respectively. This work attempted to analyse these two kinds of landslides. Conditioning factors, such as slope angle, aspect, curvature, elevation, distance from drainages, intensity and lithology, and the index of Landslide Number Density (LND) were used to describe the spatial distribution of these landslides. Then, the pre-earthquake and coseismic landslide susceptibility maps were produced using the information value model. The areas under curve are 84.73 and 77.05%, for the pre-earthquake and coseismic landslides, respectively. The results show that the LND values as well as the information values of coseismic landslides are larger than those of the pre-earthquake case. This also indicates that this Ludian earthquake has a relatively larger ability to trigger landslides.     

Landslide susceptibility mapping using random forest and boosted tree models in Pyeong-Chang,Korea

Landslides susceptibility maps were constructed in the Pyeong-Chang area, Korea, using the Random Forest and Boosted Tree models. Landslide locations were randomly selected in a 50/50 ratio for training and validation of the models. Seventeen landslide-related factors were extracted and constructed in a spatial database. The relationships between the observed landslide locations and these factors were identified by using the two models. The models were used to generate a landslide susceptibility map and the importance of the factors was calculated. Finally, the landslide susceptibility maps were validated. Finally, landslide susceptibility maps were generated. For the Random Forest model, the validation accuracy in regression and classification algorithms showed 79.34 and 79.18%, respectively, and for the Boosted Tree model, these were 84.87 and 85.98%, respectively. The two models showed satisfactory accuracies, and the Boosted Tree model showed better results than the Random Forest model.     

A comparative study on groundwater spring potential analysis based on statistical index,index of entropy and certainty factors models

The main aim of this study is to generate groundwater spring potential maps for the Ningtiaota area (China) using three statistical models namely statistical index (SI), index of entropy (IOE) and certainty factors (CF) models. Firstly, 66 spring locations were identified by field surveys, out of which, 46 (70%) spring locations were randomly selected for training the models and the rest 20 (30%) spring locations were used for validation. Secondly, 12 spring influencing factors, namely slope angle, slope aspect, altitude, profile curvature, plan curvature, sediment transport index, stream power index, topographic wetness index, distance to roads, distance to streams, lithology and normalized difference vegetation index (NDVI) were derived from the spatial database. Subsequently, using the mentioned factors and the three models, groundwater spring potential values were calculated and the results were plotted in ArcGIS 10.0. Finally, the area under the curve was used to validate groundwater spring potential maps. The results showed that the IOE model, with the highest success rate of 0.9126 and the highest prediction rate of 0.9051, showed the preferable performance in this study. The results of this study may be helpful for planners and engineers in groundwater resource management and other similar watersheds.     

Using InfoVal method and GIS techniques for the spatial modelling of landslide susceptibility in the upper catchment of river Meenachil in Kerala

A GIS-based statistical methodology for landslide susceptibility zonation is described and its application to a study area in the Western Ghats of Kerala (India) is presented. The study area was approximately 218.44 km² and 129 landslides were identified in this area. The environmental attributes used for the landslide susceptibility analysis include geomorphology, slope, aspect, slope length, plan curvature, profile curvature, elevation, drainage density, distance from drainages, lineament density, distance from lineaments and land use. The quantitative relationship between landslides and factors affecting landslides are established by the data driven-Information Value (InfoVal) — method. By applying and integrating the InfoVal weights using ArcGIS software, a continuous scale of numerical indices (susceptibility index) is obtained with which the study area is divided into five classes of landslide susceptibility. In order to validate the results of the susceptibility analysis, a success rate curve was prepared. The map obtained shows that a great majority of the landslides (74.42%) identified in the field were located in susceptible and highly susceptible zones (27.29%). The area ratio calculated by the area under curve (AUC) method shows a prediction accuracy of 80.45%. The area having a high scale of susceptibility lies on side slope plateaus and denudational hills with high slopes where drainage density is relatively low and terrain modification is relatively intense.     

Remote Sensing and GIS Based Landslide Susceptibility Assessment using Binary Logistic Regression Model: A Case Study in the Ganeshganga Watershed, Himalayas

A comprehensive Landslide Susceptibility Zonation (LSZ) map is sought for adopting any landslide preventive and mitigation measures. In the present study, LSZ map of landslide prone Ganeshganga watershed (known for Patalganga Landslide) has been generated using a binary logistic regression (BLR) model. Relevant thematic layers pertaining to the causative factors for landslide occurrences, such as slope, aspect, relative relief, lithology, tectonic structures, lineaments, land use and land cover, distance to drainage, drainage density and anthropogenic factors like distance to road, have been generated using remote sensing images, field survey, ancillary data and GIS techniques. The coefficients of the causative factors retained by the BLR model along with the constant have been used to construct the landslide susceptibility map of the study area, which has further been categorized into four landslide susceptibility zones from high to very low. The resultant landslide susceptibility map was validated using receiver operator characteristic (ROC) curve analysis showing an accuracy of 95.2 % for an independent set of test samples. The result also showed a strong agreement between distribution of existing landslides and predicted landslide susceptibility zones.     

Delineation of groundwater potential zones using remote sensing and GIS-based data-driven models

The rapid increase in human population has increased the groundwater resources demand for drinking, agricultural and industrial purposes. The main purpose of this study is to produce groundwater potential map (GPM) using weights-of-evidence (WOE) and evidential belief function (EBF) models based on geographic information system in the Azna Plain, Lorestan Province, Iran. A total number of 370 groundwater wells with discharge more than 10 m³s^?1were considered and out of them, 256 (70%) were randomly selected for training purpose, while the remaining114 (30%) were used for validating the model. In next step, the effective factors on the groundwater potential such as altitude, slope aspect, slope angle, curvature, distance from rivers, drainage density, topographic wetness index, fault distance, fault density, lithology and land use were derived from the spatial geodatabases. Subsequently, the GPM was produced using WOE and EBF models. Finally, the validation of the GPMs was carried out using areas under the ROC curve (AUC). Results showed that the GPM prepared using WOE model has the success rate of 73.62%. Similarly, the AUC plot showed 76.21% prediction accuracy for the EBF model which means both the models performed fairly good predication accuracy. The GPMs are useful sources for planners and engineers in water resource management, land use planning and hazard mitigation purpose.     

Assessment of a data-driven evidential belief function model and GIS for groundwater potential mapping in the Koohrang Watershed,Iran

The objective of this study is to produce groundwater potential map (GPM) and its performance assessment using a data-driven evidential belief function (EBF) model. This study was carried out in the Koohrang Watershed, Chaharmahal-e-Bakhtiari Province, Iran. It’s conducted in three main stages such as data preparation, groundwater potential mapping using EBF and validation of constructed model using receiver operating characteristic (ROC) curve. At first, 864 groundwater data were collected from spring locations; out of that, 605 (70%) locations were selected for training/model building and the remaining 259 (30%) cases were used for the model validation. In the next step, 12 effective factors such as altitude, slope aspect, slope degree, slopelength (LS), topographic wetness index (TWI), plan curvature, land use, lithology, distance from rivers, drainage density, distance from faults and fault density were extracted from the spatial database. Subsequently, GPM was prepared using EBF model in ArcGIS environment. Finally, the ROC curve and area under the curves (AUC) were drawn for verification purposes. The validation of results showed that the AUC for EBF model is 81.72%. In general, this result can be helpful for planners and engineers in water resource management and land-use planning.     

Multi-hazard assessment using machine learning and remote sensing in the North Central region of Vietnam

Natural hazards constitute a diverse category and are unevenly distributed in time and space. This hinders predictive efforts, leading to significant impacts on human life and economies. Multi-hazard prediction is vital for any natural hazard risk management plan. The main objective of this study was the development of a multi-hazard susceptibility mapping framework, by combining two natural hazards—flooding and landslides—in the North Central region of Vietnam. This was accomplished using support vector machines, random forest, and AdaBoost. The input data consisted of 4591 flood points, 1315 landslide points, and 13 conditioning factors, split into training (70%), and testing (30%) datasets. The accuracy of the models' predictions was evaluated using the statistical indices root mean square error, area under curve (AUC), mean absolute error, and coefficient of determination. All proposed models were good at predicting multi-hazard susceptibility, with AUC values over 0.95. Among them, the AUC value for the support vector machine model was 0.98 and 0.99 for landslide and flood, respectively. For the random forest model, these values were 0.98 and 0.98, and for AdaBoost, they were 0.99 and 0.99. The multi-hazard maps were built by combining the landslide and flood susceptibility maps. The results showed that approximately 60% of the study area was affected by landslides, 30% by flood, and 8% by both hazards. These results illustrate how North Central is one of the regions of Vietnam that is most severely affected by natural hazards, particularly flooding, and landslides. The proposed models adapt to evaluate multi-hazard susceptibility at different scales, although expert intervention is also required, to optimize the algorithms. Multi-hazard maps can provide a valuable point of reference for decision makers in sustainable land-use planning and infrastructure development in regions faced with multiple hazards, and to prevent and reduce more effectively the frequency of floods and landslides and their damage to human life and property.     

Landslide susceptibility mapping of a catchment area using frequency ratio,fuzzy logic and multivariate logistic regression approaches

Geospatial database creation for landslide susceptibility mapping is often an almost inhibitive activity. This has been the reason that for quite some time landslide susceptibility analysis was modelled on the basis of spatially related factors. This paper presents the use of frequency ratio, fuzzy logic and multivariate regression models for landslide susceptibility mapping on Cameron catchment area, Malaysia, using a Geographic Information System (GIS) and remote sensing data. Landslide locations were identified in the study area from the interpretation of aerial photographs, high resolution satellite images, inventory reports and field surveys. Topographical, geological data and satellite images were collected, processed, and constructed into a spatial database using GIS and image processing tools. There were nine factors considered for landslide susceptibility mapping and the frequency ratio coefficient for each factor was computed. The factors chosen that influence landslide occurrence were: topographic slope, topographic aspect, topographic curvature and distance from drainage, all from the topographic database; lithology and distance from lineament, taken from the geologic database; land cover from TM satellite image; the vegetation index value from Landsat satellite images; and precipitation distribution from meteorological data. Using these factors the fuzzy membership values were calculated. Then fuzzy operators were applied to the fuzzy membership values for landslide susceptibility mapping. Further, multivariate logistic regression model was applied for the landslide susceptibility. Finally, the results of the analyses were verified using the landslide location data and compared with the frequency ratio, fuzzy logic and multivariate logistic regression models. The validation results showed that the frequency ratio model (accuracy is 89%) is better in prediction than fuzzy logic (accuracy is 84%) and logistic regression (accuracy is 85%) models. Results show that, among the fuzzy operators, in the case with “gamma” operator (λ = 0.9) showed the best accuracy (84%) while the case with “or” operator showed the worst accuracy (69%).