A comparative study on the landslide susceptibility mapping using logistic regression and statistical index models

This study aimed to produce landslide susceptibility maps using frequency ratio (FR) and evidential belief function (EBF) models based on GIS for Gongliu County, China. For this purpose, a detailed landslide inventory map was prepared and 12 landslide conditioning factors were considered; these factors were as follows: slope angle, slope aspect, curvature, plan curvature, profile curvature, altitude, the normalized difference vegetation index, rainfall, the topographic wetness index (STI), distance from roads, distance from rivers, and lithology. The landslide inventory map was prepared from published sources and aerial photographs, supported by field work. A total of 233 landslides were identified and mapped in the study area. Out of which, 70 % landslides were applied for establishing the model and 30 % landslides were used to validate the model. GIS software was used to analyze landslide conditioning factors and to map landslide susceptibility. Landslide susceptibility maps were prepared using FR and EBF models based on ArcGIS 10.0 and classified into five susceptibility zones: very low, low, moderate, high, and very high. Finally, in order to validate the accuracy of the landslide susceptibility maps produced from two models, the area under curve approach was applied. The validation results showed that the maps using FR and EBF models have a success rate of 82.41 and 79.69 %, respectively. Similarly, the maps using FR and EBF models have a predictive rate of 77.26 and 68.79 %, respectively. Based on the results, both landslide susceptibility maps produced by the two models have a high accuracy and will be helpful for land-use planning in the study area.

Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat—Turkey)

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.

A study demonstrating the application of the weights-of-evidence model (a Bayesian probability model) to landslide susceptibility mapping using geographical remote sensing (GIS) in a tropical hilly area of Malaysia is presented. In the first stage, a landslide related spatial database was created. Seven landslide conditioning factors were considered for the susceptibility analysis. Using landslide location and a spatial database containing information such as topography, soil, lithology, land cover and lineament, the weights-of-evidence model was applied to calculate each relevant factor's rating for the Cameron Highlands area in Malaysia. The topographic database including information on slope angle, slope aspect, plan curvature and distance from drainage was developed from a digital elevation model (DEM); the lithology and the distance from the lineament were derived from the geological database; soil texture was derived from the soil database; land cover and normalized difference vegetation index (NDVI) information were extracted from Landsat Thematic Mapper (TM) satellite imagery. Tests of conditional independence were performed for the selection of landslide conditioning factors, allowing nine combinations in total. Finally, landslide susceptibility maps were constructed using the ratings of each landslide conditioning factor. The resultant susceptibility maps were validated using the receiver operating characteristics (ROCs) based area under curve (AUC) method. Landslide locations were used to validate the results of the landslide susceptibility map and the verification results showed 97% accuracy for model 5, which employed a combination of parameters. Plan curvature, distance from drainage, distance from lineament, lithology and land cover performed better than other combinations of landslide conditioning factors.

The main aim of this study was to apply and compare two GIS-based data mining models, namely support vector machine (SVM) by four kernel functions (linear-SVM, polynomial-SVM, radial basic function-SVM, and sigmoidal-SVM) and entropy models in landslide susceptibility mapping, in Shangzhou District, China. Initially, 145 landslide locations were mapped using early reports, aerial photographs, and supported by field surveys. Subsequently, landslides in the study area were divided randomly into training and validation datasets (70/30) using ArcGIS 10.0 software. In the current study, 14 landslide conditioning factors, namely, slope aspect, slope angle, profile curvature, plan curvature, altitude, topographic wetness index (TWI), stream power index (SPI), sediment transport index (STI), normalized difference vegetation index (NDVI), distance from roads, distance from rivers, distance from faults, rainfall, and lithology, were exploited to detect the most susceptible areas. In the next step, landslide susceptibility maps generated by four types of SVM or entropy models were produced. Finally, validation of the landslide susceptibility maps produced by different models was evaluated using receiver operating characteristics (ROC) curves. The results showed that the entropy model exhibited the highest success rate (0.7610), followed by polynomial-SVM (0.7526), the sigmoidal-SVM (0.7518), radial basic function-SVM (0.7446), and linear-SVM (0.7390) models. Similarly, the ROC plots also showed that the prediction rates gave almost similar results. The entropy model had the highest prediction rate (0.7599), followed by polynomial-SVM (0.7259), sigmoidal-SVM (0.7203), radial basic function-SVM (0.7149), and linear-SVM (0.7009) models. Hence, it can be concluded that the five models used in this study gave close results, with the entropy model exhibiting best performance in landslide susceptibility mapping.

GIS-based evaluation of landslide susceptibility using hybrid computational intelligence models

Chapter 9 - Landslide susceptibility modeling using a generalized linear model in a tropical river basin of the Southern Western Ghats, India

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.

The main objective of this study is to investigate potential application of frequency ratio (FR), weights of evidence (WoE), and statistical index (SI) models for landslide susceptibility mapping in a part of Mazandaran Province, Iran. First, a landslide inventory map was constructed from various sources. The landslide inventory map was then randomly divided in a ratio of 70/30 for training and validation of the models, respectively. Second, 13 landslide conditioning factors including slope degree, slope aspect, altitude, plan curvature, stream power index, topographic wetness index, sediment transport index, topographic roughness index, lithology, distance from streams, faults, roads, and land use type were prepared, and the relationships between these factors and the landslide inventory map were extracted by using the mentioned models. Subsequently, the multi-class weighted factors were used to generate landslide susceptibility maps. Finally, the susceptibility maps were verified and compared using several methods including receiver operating characteristic curve with the areas under the curve (AUC), landslide density, and spatially agreed area analyses. The success rate curve showed that the AUC for FR, WoE, and SI models was 81.51, 79.43, and 81.27, respectively. The prediction rate curve demonstrated that the AUC achieved by the three models was 80.44, 77.94, and 79.55, respectively. Although the sensitivity analysis using the FR model revealed that the modeling process was sensitive to input factors, the accuracy results suggest that the three models used in this study can be effective approaches for landslide susceptibility mapping in Mazandaran Province, and the resultant susceptibility maps are trustworthy for hazard mitigation strategies.

This article addresses the spatial analysis of landslide susceptibility in the Ardabil province of Iran. To this end, two well-known optimization algorithms, namely genetic algorithm (GA) and particle swarm optimization (PSO) are synthesized with an adaptive neuro-fuzzy inference system (ANFIS) to create the ensembles of GA-ANFIS and PSO-ANFIS. Besides, the statistical index (SI) model is also performed to be compared with the mentioned intelligent techniques. Fourteen landslide conditioning factors including elevation, slope aspect, land use, plan curvature, profile curvature, soil type, distance to river, distance to road, distance to fault, rainfall, slope degree, stream power index (SPI), topographic wetness index (TWI), and lithology were considered within the geographic information system (GIS). Out of 253 identified landslides, 177 points (70% of them) were randomly selected and used for the training phase, and the remaining 76 points (30% of them) were used to evaluate the accuracy of the SI, GA-ANFIS, and PSO-ANFIS models. Referring to the calculated area under the receiver operating characteristic curve (AUROC) index, the GA-ANFIS (AUROC = 0.914) and SI (AUROC = 0.821) showed the best performance, respectively in the training and testing phases. Notably, ANFIS-PSO emerged as the faster prediction method compared to the GA-ANFIS. Also, from spatial analysis, it was revealed that around 95%, 87%, and 97% of the training landslides, and 96%, 84%, and 76% of the testing landslides are located in hazardous areas.

This study was carried out on the hilly topographic area in Kundasang, Sabah. This area is known to be extremely prone to landslides that occurred either naturally or by human interference to natural slopes. Aerial photographs interpretation was conducted in order to identify landslide distributions across three assessment years (2012, 2009 and 1984). These datasets were classified into two landslides groups based on their occurrences; natural and artificial. A total of 362 naturally occurring landslides were identified and another 133 are artificial slope landslides. Physical parameters which include lithology, slope angle, slope aspect and soil series were analyzed with each landslide group to examine the different influence of these parameters on each of the group. From the analysis, the landslide density for the natural landslide group shows that more than 35° slope angle and slope aspect facing east and southwest are prone to landslides. In terms of geological materials, high landslide density is recorded in the phyllite, shale, siltstone and sandstone lithologies group and the Pinosuk, Kepayan and Trusmadi soil series. In contrast, for the artificial slope landslide, high landslide density is observed in the 25°-35° slope angle and similar density in every slope aspect classes. The geological materials however have similar landslide density across their factors’ classes. The landslide density technique was also used to generate the landslide susceptibility maps for both landslide conditions. Validation of the maps shows acceptable accuracy of 71% and 74%, respectively, for both natural and artificial slope landslide susceptibility maps and this shows that these maps can be used for future land use planning.

The current research presents landslide susceptibility mapping by frequency ratio (FR) and weights of evidence (WoE) models based on geographic information system (GIS) and an assessment of their performances for the Shangzhou District of Shangluo City, China. Firstly, landslide locations of the study area were detected using aerial photographs as well as by carrying outfield survey. Then, a total of 145 landslides were mapped out of which 101 (70 % landslide locations) were randomly selected for training the models, and the remaining 44 (30 % landslide locations) were used for validating the models. The following ten landslide conditioning factors, such as slope aspect, curvature, slope angle, elevation, distance to rivers, distance to faults, lithology, peak ground acceleration, distance to roads and precipitation, were considered in this study. Subsequently, landslide susceptibility maps were produced using FR and WoE models in ArcGIS 10.0 software. The validation of landslide susceptibility maps were carried out using areas under the curve. The validation results showed that the training accuracy were 0.7635 (76.35 %) and 0.7450 (74.50 %) for the FR and WoE models, with predictive accuracy 0.7395 (73.95 %) and 0.7102 (71.02 %), respectively, indicating that landslide susceptibility mapping using FR model is more accurate than WoE model for the study area.

The main purpose of this study is to apply three bivariate statistical models, namely weight of evidence (WoE), evidence belief function (EBF) and index of entropy (IoE), and their ensembles with logistic regression (LR) for landslide susceptibility mapping in Muchuan County, China. First, a landslide inventory map contained 279 landslides was obtained through the field investigation and interpretation of aerial photographs. Next, the landslides were randomly divided into two parts for training and validation with the ratio of 70/30. In addition, according to the regional geological environment characteristics, twelve landslide conditioning factors were selected, including altitude, plan curvature, profile curvature, slope angle, distance to roads, distance to rivers, topographic wetness index (TWI), normalized different vegetation index (NDVI), land use, soil, and lithology. Subsequently, the landslide susceptibility mapping was carried out by the above models. Eventually, the accuracy of this research was validated by the area under the receiver operating characteristic (ROC) curve and the results indicated that the landslide susceptibility map produced by EBF-LR model has the highest accuracy (0.826), followed by IoE-LR model (0.825), WoE-LR model (0.792), EBF model (0.791), IoE model (0.778), and WoE model (0.753). The results of this study can provide references of landslide prevention and land use planning for local government.

Intelligent data analytics approaches are popular in landslide susceptibility mapping. This chapter develops a random forest (RF) approach for spatial modeling of landslide susceptibility. A total number of 78 landslide locations are identified using field survey, 55 of which are randomly selected to model landslide susceptibility and remaining 23 locations considered for model validation. Twelve predictor variables are selected: elevation, slope percentage, slope aspect, plan curvature, profile curvature, distance from roads, distance from streams, distance from faults, lithological formations, land use, soil type, and topographic wetness index (TWI) to create an RF model for landslide susceptibility mapping. The results of RF model are evaluated using efficiency (E), true positive rate (TPR), false positive rate (FPR), true skill statistic (TSS), and area under receiver operating characteristic curve (AUC) in training and validation steps. RF model registered excellent goodness-of-fit with AUC = 93.6%, E = 0.887, TSS = 0.776, TPR = 0.905, FPR = 0.129, and predictive performance with AUC = 90.7%, E = 0.777, TSS = 0.559, TPR = 0.809, FPR = 0.25. Intelligent data analytic method, therefore, has a significant promise in tackling challenges of landslide susceptibility mapping in large regions, which may not have sufficient geotechnical data to employ a physically based method.

The accuracy of topographic indices derived from digital elevation models (DEMs) is of critical importance for eco-environment simulating and modeling based on DEMs. The objective of this study was to evaluate the accuracy of topographic indices derived from DEMs with different scales. Maps with scales of 1:10000, 1:50000, 1:100000, and 1:250000 were digitized and corresponding DEMs were produced using Arclnfo. Topographic indices including slope, aspect, profile curvature, and plan curvature were determined using the DEMs. Overall, certain topographic features were less perceptible on coarser DEMs than finer DEMs. Slope, profile and plan curvatures varied with the scales of the studied DEMs. Decreasing the scale of the studied DEMs produced lower slope gradients, narrower ranges in profile and plan curvatures. Further work will focus on the extraction and self-information of more other topographic indices and the scale impacts on different indices.