Produce Landslide Susceptibility Maps Research Articles

CO-SEISMIC LANDSLIDE BASED VALIDATION OF SUSCEPTIBILITY MAPPING AFTER KAHRAMANMARAS EARTHQUAKES (FEB 6, 2023) IN AMANOS MOUNTAINS

Abstract. The quality of landslide susceptibility maps is often assessed using a part of learning data that represents geographical and land use characteristics over a quasi-fixed time. However, when validated with multi-temporal landslide inventories, more realistic insights on the susceptibility maps can be obtained. In addition, extreme events may trigger landslides in regions which are not considered as landslide-prone. The February 6, 2023, Kahramanmaras Earthquakes (Mw 7.7 and Mw 7.6), also known as the disaster of the century, triggered numerous landslides. Amanos Mountains located in southern Türkiye were also within the earthquake-affected area and had a very small amount of inventory recorded in official databases. The aim of this study was to evaluate the performance of the random forest method for producing landslide susceptibility maps. The official inventory of General Directorate of Mineral Research and Exploration (MTA) was used for map production. The resulting susceptibility map was assessed using the co-seismic landslide inventory produced in the study. The model’s performance evaluated using a part of the learning data yielded high accuracy expressed with area under receiver operating characteristics curve (AUC), precision, and recall values and F1 score using (AUC = 97%, recall = 97%, precision = 96%, F1 = 98%). However, multi-temporal evaluation with co-seismic landslides showed that 80% of the landslide pixels with moderate, high, and very high susceptibility levels could be predicted with the model. The results suggest that special attention should be given to features underrepresented in the inventory, such as low altitudes and types of lithology.

Potential Factors of Landslide Recurrence in Uttaradit, Thailand: A Case Study in Laplae, Mueang Uttaradit, and Tha Pla Districts

Laplae, Mueang Uttaradit, and Tha Pla district, Uttaradit province, Thailand are considered as high potential landslide areas. Still, this disaster is difficult to address because of complex factors controlling its occurrence. Therefore, the prediction of the potential landslide area using a landslide susceptibility map has been able to accomplish as a great strategy for the disaster. A landslide susceptibility map was produced by the geographic information system (GIS) data. The methods were initially conducted by the selection of potential factors related to landslides, which were lithology, slope, aspect, plan curvature, profile curvature, distance to stream, land use, and rainfall. All factors were assigned coefficients weight, and analyses frequency ratio (FR). Then, the weighted variables have been combined and ranked into five different susceptibility levels, which were very low, low, medium, high, and very high. Finally, the produced landslide susceptibility map has been validated by the success rate and prediction rate. After the analysis, the high and the very high landslide susceptibility area were dominantly covered in the northern and northwest parts of the study area; and the factor of slope, land use, and lithology potentially caused the landslide risk indicated by high frequency ratio values. In addition, the produced landslide susceptibility map had high accuracy, about 90% of success rate and prediction rate, calculated from the area under the curve (AUC), this map would be beneficial for geological hazard management and land use planning. The landslide susceptibility map and the GIS-based methods can be applied to the regional area with additional benefits to well-being, society, and the environment.

Application and validation of AHP and FR methods for landslide susceptibility mapping around choke mountain, northwestern ethiopia

The present research was conducted around Choke Mountain, East Gojjam, Northwestern Ethiopia. This study aimed to apply and validate analytical hierarchy process (AHP) and frequency ratio (FR) Methods and produce landslide susceptibility maps of the area. At first, a landslide inventory map was produced with information on past and active landslide locations. To produce a susceptibility map, nine influencing factors including lithology, slope, elevation, distance to drainage, distance to road, profile curvature, plane curvature, NDVI, and aspect were determined and integrated into the ArcGIS platform. All these influencing factors were statistically analyzed to determine their relationship to past landslides. The landslide susceptibility maps generated in the GIS environment by the AHP and FR methods were classified into five susceptibility classes: very low, low, moderate, high, and very high. Accordingly, the AHP method showed that very high susceptibility zones and high susceptibility zones cover 9.8% and 19.3% of the area, respectively. Whereas, moderate, low, and very low susceptibility zones cover 26.1%, 28.0%, and 16.8% of the area, respectively. Similarly, the FR method showed that very high susceptibility zones and high susceptibility zones cover 12.2% and 22.5% of the area, respectively. Whereas, moderate, low, and very low susceptibility zones cover 27.6%, 24.2%, and 13.4% of the area, respectively. The final results were compared and validated using the area under the curve (AUC) method. According to the AUC graph, the AHP and FR methods had success rates of 85.8 and 82.0%, respectively, and prediction rates of 88.2 and 84.8%. According to the AUC validation results, the map obtained from the AHP method is more accurate than that obtained from the FR method. Thus, the validation of the landslide susceptibility map demonstrated that the methodologies used resulted in acceptable results. This type of map can be useful for damage and risk prevention management and land use planning.

Application of data‐driven techniques for landslide susceptibility prediction along an earthquake‐affected road section in Kashmir Himalaya

The interaction of seismic events with geo‐environmental conditions and anthropogenic activities may exacerbate the risk of landslide hazard in a mountainous region. As an example of this, the 2005 Kashmir earthquake triggered many shallow to deep slope failures, which were further intensified in the following years by human activities notably along road networks, posing a long‐term hazard. Hence, this study was planned to evaluate the effectiveness of landslide susceptibility prediction along an earthquake‐affected road section of Neelum Highway using six different data‐driven models. We applied analytical hierarchy process as a heuristic approach, weight of evidence and index of entropy as statistical models and multi‐layer perceptron, support vector machine and binary logistic regression (BLR) as machine learning models. Initially, 224 landslide locations were marked through field surveys to prepare a landslide inventory, which was further randomly divided into training (70%) and testing (30%) datasets. Then, 13 landslide causative factors (LCFs) were extracted from geospatial database and analysed by measuring collinearity among factors and assessing their contribution to landslide occurrence using different feature selection methods for inclusion in susceptibility modelling. Thereafter, six employed models were trained to produce landslide susceptibility maps of the investigated road section. Finally, the area under receiver operating characteristics (AU‐ROC) curve and various statistical measures were applied to validate and compare the performance of modelled landslide susceptibility. The results revealed that no collinearity issue exists among all 13 LCFs, and all six models exhibited satisfying performance in predicting landslide susceptibility of study area. However, BLR model has produced the most promising and optimum results as compared with other models with AU‐ROC (0.881), Matthew's correlation coefficient (0.609), Kappa coefficient (0.604), accuracy (0.797) and F‐score (0.787). The outcomes of this study can be used as pertinent guide for preventing and managing the landslide disaster risk along Neelum Highway and beyond.

Evaluation of Different Landslide Susceptibility Models for a Local Scale in the Chitral District, Northern Pakistan.

This work evaluates the performance of three machine learning (ML) techniques, namely logistic regression (LGR), linear regression (LR), and support vector machines (SVM), and two multi-criteria decision-making (MCDM) techniques, namely analytical hierarchy process (AHP) and the technique for order of preference by similarity to ideal solution (TOPSIS), for mapping landslide susceptibility in the Chitral district, northern Pakistan. Moreover, we create landslide inventory maps from LANDSAT-8 satellite images through the change vector analysis (CVA) change detection method. The change detection yields more than 500 landslide spots. After some manual post-processing correction, the landslide inventory spots are randomly split into two sets with a 70/30 ratio for training and validating the performance of the ML techniques. Sixteen topographical, hydrological, and geological landslide-related factors of the study area are prepared as GIS layers. They are used to produce landslide susceptibility maps (LSMs) with weighted overlay techniques using different weights of landslide-related factors. The accuracy assessment shows that the ML techniques outperform the MCDM methods, while SVM yields the highest accuracy of 88% for the resulting LSM.

Landslide Susceptibility Mapping Using Bivariate Statistical Models and GIS in Chattagram District, Bangladesh

Landslide is one of the most devastating hazards in Chattagram Dsitrict and has become a recurrent phenomenon in this region. This study attempts to produce Landslide Susceptibility Map (LSM) for Chattagram District of Bangladesh by using five GIS based bivariate statistical models, namely the Frequency Ratio (FR), Shanon’s Entropy (SE), Weight of Evidence (WofE), Information Value (IV) and Certainty Factor (CF). Landslide Inventory (2001–2017) of Chittagong Hilly Areas database was used to measure the relationship between the previous landslides with the landslide conditioning factors. SRTM DEM and Landsat satellite images were collected from USGS and the geological data were collected from GSB to produce the thematic layer of conditioning factors. Sixteen landslide conditioning factors of Slope Aspect, Slope Angle, Geology, Elevation, Plan Curvature, Profile Curvature, General Curvature, Topographic Wetness Index, Stream Power Index, Sediment Transport Index, Topographic Roughness Index, Distance to Stream, Distance to Anticline, Distance to Fault, Distance to Road and NDVI were used. The Area Under Curve (AUC) was used for validation of the LSMs. The predictive rate of AUC for FR, SE, WofE, IV and CF were 76.11%, 70.11%, 78.93%, 76.57% and 80.43% respectively. CF model indicates 15.04% of areas are highly susceptible to landslide. All the models showed that the high elevated areas are more susceptible to landslide where the low-lying river basin areas have a low probability of landslide occurrence. The findings of this research will contribute to land use planning, management and hazard mitigation of the CHT region.

Landslide Susceptibility Assessment using Open-Source Data in the Far Western Nepal Himalaya: Case Studies from Selected Local Level Units

This paper explores openly available geo-spatial and earth observatory data to understand landslide risk in data scarce rural areas of Nepal. It attempts to explore the application of open-source data and analytical models to inform future landslide research. The first step of this procedure starts from the review of global open datasets, literatures and case studies relevant to landslide research. The second step is followed by the case study in one of the mountainous municipalities of Nepal where we tested the identified open-source data and models to produce landslide susceptibility maps. Past studies and experiences show that the major potential sites of landslide in Nepal are highly concentrated in a geologically weak area such as the active fault regions, shear zones, axis of folds and unfavorable setting of lithology. Triggering factors like concentrated precipitation, frequent earthquake phenomenon and haphazard infrastructural development activities in the marginally stable mountain slopes have posed serious issues of landslides mostly through the geologically weak regions. In this context, openly available geo-spatial datasets can provide baseline information for exploring the landslide hazard scenario in the data scarce areas of Nepal. This research has used the available open-source data to produce a landslide susceptibility map of the Bithadchir Rural Municipality in Bajhang District and Budiganga Municipality in Bajura District of the Sudurpaschim Province of Nepal. We used qualitative analysis to evaluate the parameters and assess the susceptibility of landslide; the result was classified into five susceptibility zones: Very High, High, Moderate, Low, and Very Low. Slope and Aspect were identified to be the major determinants for the assessment. This approach is applicable, specifically, for the preliminary investigation in the data scarce region using open data sources. Furthermore, the result can be used to plan and prioritize effective disaster risk reduction strategies.

Application of the group method of data handling (GMDH) approach for landslide susceptibility zonation using readily available spatial covariates

Landslide susceptibility (LS) mapping is an essential tool for landslide risk assessment. This study aimed to provide a new approach with better performance for landslide mapping and adopting readily available variables. In addition, it investigates the capability of a state-of-the-art model developed using the group method of data handling (GMDH) to spatially model LS. Furthermore, hybridized models of GMDH were developed using different metaheuristic algorithms. The study area was the Bonghwa region of South Korea, for which an accurate landslide inventory dataset is available. We considered a total of 13 spatial covariates (altitude, slope, aspect, topographic wetness index, valley depth, plan curvature, profile curvature, distance from fault, distance from river, distance from road, land use, density of forest, and lithology were chosen as independent variables). Two benchmark models—random forest and boosted regression trees—were used to compare their results with the standalone GMDH and hybridized models. We compared model accuracy using the two most robust evaluation metrics, root mean square error (RMSE) and area under the receiver operating characteristic curve (AUROC). The validation results showed that hybridized models outperformed the standalone GMDH model. Moreover, the hybridized GMDH-PSO (AUC = 0.83, RMSE = 0.108), GMDH-IWO (AUC = 0.81, RMSE = 0.111), GMDH-BBO (AUC = 0.8; RMSE = 0.12), and GMDH-ICA (AUC = 0.8; RMSE = 0.117) had a better predictive performance than both RF and BRT. Therefore, the proposed approach could successfully produce landslide susceptibility maps using relatively few readily available variables and can be repeated in data-scarce regions.

Evaluation of the Effect of Hydroseeded Vegetation for Slope Reinforcement

A landslide is a significant environmental hazard that results in an enormous loss of lives and properties. Studies have revealed that rainfall, soil characteristics, and human errors, such as deforestation, are the leading causes of landslides, reducing soil water infiltration and increasing the water runoff of a slope. This paper introduces vegetation establishment as a low-cost, practical measure for slope reinforcement through the ground cover and the root of the vegetation. This study reveals the level of complexity of the terrain with regards to the evaluation of high and low stability areas and has produced a landslide susceptibility map. For this purpose, 12 conditioning factors, namely slope, aspect, elevation, curvature, hill shade, stream power index (SPI), topographic wetness index (TWI), terrain roughness index (TRI), distances to roads, distance to lakes, distance to trees, and build-up, were used through the analytic hierarchy process (AHP) model to produce landslide susceptibility map. Receiver operating characteristics (ROC) was used for validation of the results. The area under the curve (AUC) values obtained from the ROC method for the AHP model was 0.865. Four seed samples, namely ryegrass, rye corn, signal grass, and couch, were hydroseeded to determine the vegetation root and ground cover’s effectiveness on stabilization and reinforcement on a high-risk susceptible 65° slope between August and December 2020. The observed monthly vegetation root of couch grass gave the most acceptable result. With a spreading and creeping vegetation ground cover characteristic, ryegrass showed the most acceptable monthly result for vegetation ground cover effectiveness. The findings suggest that the selection of couch species over other species is justified based on landslide control benefits.

GIS-Based Landslide Susceptibility Mapping using Logistic Regression, Instability Index, and Support Vector Machine: Case Study of the Jingshan River, Taiwan

Many techniques have been developed to produce landslide susceptibility maps. However, mapping the spatial distribution of landslide susceptibility involves critical steps. This study evaluated susceptibility to the occurrence of shallow landslides in upstream areas of the Jingshan River, Taiwan, where heavy rainfall has resulted in increased landslide occurrence and reservoir sedimentation. The landslide susceptibility case study was conducted using logistic regression, an instability index method, and support vector machine (SVM). A selection procedure was first developed to identify the factors influencing landslide occurrence. Historical landslide data were used to assess the corresponding parameters of each model. The receiver operating characteristic curve was then used to evaluate the accuracy of model results. The results indicated that the instability index method underestimated landslide susceptibilities in areas near the river. The instability index method was highly affected by the classifications of model factors. Of the models, the SVR model was the most accurate regarding landslide susceptibility in the study area. Employing this framework, governments may implement suitable, cost-effective improvements to structural measures and land-use planning.

Spatial prediction of landslide susceptibility using projected storm rainfall and land use in Himalayan region

Landslide susceptibility assessment (LSA) is a method used to reduce landslide vulnerability defined as landslide spatial prediction with the help of associative factors. The goal of the analysis is to forecast potential (2040, 2060, 2080, and 2100 AC) rainfall and land use and land cover (LULC) with the aid of the CSIRO-MK3.6.0 General circulation models (GCMs) climatic model and the dynamic conversion of land use and its effects (Dyna-CLUE) model. The purpose of this work is to produce landslide susceptibility map (LSM) of potential cycles correlated with expected rainfall and LULC data utilizing the binary logistic regression (BLR) models in the Upper Rangit River basin of eastern Himalayan region, India. Including rainfall and LULC total nineteen factors have been incorporated, these are mainly topographical, hydrological, geological, and environmental factors. A total 671 landslide locations have been mapped which divided randomly as training (70%) and validation (30%) datasets of LSM. Current (2018) LSM was validated by 30% of landslide inventory location and the result of area under curve of receiver operating characteristic (ROC) indicated that the LSM has 92.4% and 89.6% of the success and prediction rate respectively. To demonstrate the accuracy of the BLR landslide susceptibility (LS) model, this model was used to generated future LSMs based on projected of rainfall and LULC. The result of projected representative concentration pathway (RCP)-based rainfall depicted that the increasing trend of rainfall in the future period and the moderate to very high LS zones has also increased from 2040 to 2100. This study will be used to further study of landslide hazard (LH) studies with climatic approaches, and will also contribute to regional planning and development of current and future Upper Rangit River basin.

Landslide susceptibility mapping using information value method in Jhelum Valley of the Himalayas

The geological and geographical conditions have made the Himalayas one of the regions most vulnerable to disasters. Northern Pakistan is made up of high-relief Himalayan mountains where landslides are the most frequently occurring catastrophic events. Floods, earthquakes, and landslides occur most often in this region, causing deaths and severe infrastructure damages. The studied area is experiencing significant landslide events triggered by destructive seismic activity, extreme seasonal rainfalls, and human activities. In this study, landslide susceptibility mapping is proposed using an integrated model of information value method by optimizing its capabilities and overcoming its limitations to enhance both precision and accuracy of the results. This approach quantifies and estimates the probability of landslide occurrence using statistical principles and techniques. Seven distinct landslide causative factors, including slope angle, distance to stream, drainage density, distance to road, land cover, normalized difference vegetation index, lithology, and distance to faults were evaluated to determine the areas at risk for future slope movements. A reliable landside inventory from a spatial database combined with ground-truthing field surveys was prepared for evaluating the relationship between the landslides and their causative factors. The accuracy and efficiency of the developed model are evaluated using sensitivity analysis of the receiver operator curve (ROC). The ROC-validated results showed an accuracy of 0.845 for model prediction rate and an accuracy of 0.837 for model success rate, indicating that the model is reliable to produce landslide susceptibility map. The results showed the reasonable efficiency of the applied method for assessing landslide susceptibility in the study area and applicable to other regions with similar geomorphological conditions.

Comparing classical statistic and machine learning models in landslide susceptibility mapping in Ardanuc (Artvin), Turkey

Landslide susceptibility maps provide crucial information that helps local authorities, public institutions, and land-use planners make the correct decisions when they are managing landslide-prone areas. In recent years, machine-learning techniques have become very popular for producing landslide susceptibility maps. This study aims to compare the performance of these machine learning models with the traditional statistical methods used to produce landslide susceptibility maps. The landslide susceptibility for Ardanuc, Turkey was evaluated using three models: logistic regression (LR), support vector machine (SVM), and random forest (RF). Ten parameters that are effective in landslide occurrence are used in this study. The accuracy and prediction capabilities of the models were assessed using both the receiver operating characteristic (ROC) curve and area under the curve (AUC) methods. According to the AUC method, the success rate of the LR, SVM, and RF models was 83.1%, 93.2%, and 98.3%, respectively. Further, the prediction rates were calculated as 82.9% (LR), 92.8% (SVM), and 97.7% (RF). According to the verification results, RF and SVM models outperformed the traditional LR model in terms of success and prediction rate. The RF model, however, performed better than the SVM model in terms of success and prediction rates. The landslide susceptibility maps produced as a result of this study can guide city planners, local administrators, and public institutions related to disaster management to prevent and reduce landslide hazards.

GIS-based landslide susceptibility mapping using hybrid MCDM models

Landslide susceptibility mapping plays an important role in integrated watershed management planning, especially in the field of land-use planning in landslide-prone areas. This study aims to evaluate the performance of widely used hybrid multi-criteria decision-making (MCDM) models including the integrated index method (IIM), AHP-TOPSIS, and AHP-VIKOR to produce landslide susceptibility maps (LSMs) in the Alamut watershed, Iran. Ten causal layers including slope angle, slope aspect, rainfall, lithology, altitude, land use, and the most common distance maps including distance to fault, distance to stream, and distance to road were used to produce LSMs. Meanwhile, the landslide distribution map was used to evaluate the accuracy of the produced LSMs. The weights of the causal factors were also calculated using the analytic hierarchy process (AHP) method based on the viewpoints of 14 experts. Finally, the quality sum (Qs) index as well as the receiver operating characteristic (ROC) curves were used to validate the performance of the MCDM models. The Qs values for AHP-TOPSIS, IIM, and AHP-VIKOR were calculated 0.355, 0.903, and 0.703, respectively. Therefore, IIM and AHP-VIKOR methods are more efficient than AHP-TOPSIS to create LSM. The area under the curve (AUC) values of the ROC curves for AHP-TOPSIS, IIM, and AHP-VIKOR were calculated 0.784, 0.853, and 0.844, respectively. Therefore, the accuracy of the MCDM models is acceptable for TOPSIS and excellent for IIM and AHP-VIKOR. In general, results of the performance assessment of MCDM models indicated the good performance of the models to produce LSMs, so that the IIM was introduced as the best model. Also, the performance of IIM and AHP-VIKOR are more than the AHP-TOPSIS model to produce LSMs. Overall, the application of the AHP method in combination with other MCDM models as a hybrid model to produce LSMs is recommended under the principles of group decision-making in AHP for land-use planning and landslide risk management.

Generating Landslide Susceptibility Map using Airborne Lidar Derived Parameters and Geological Mapping Factors for Canada Hill, Miri, Sarawak

Landslide Susceptibility Mapping using GIS software and remote sensing data have been conducted in several location involving geological and geomorphological sensitive at Canada Hill, Miri. The previous researcher has conducted quantitative analyses using different statistical methods with different parameters in the same study area. The mapping of landslides using high-resolution Airborne LiDAR data is a valuable effort. All of this play important role, in the analysis and development of landslide susceptibility map. High-resolution Airborne LiDAR data has the ability to penetrate thick forest cover and produce Digital Terrain Model. Using Digital Terrain Model, the landslide parameter can be generated and extracted. The main objective of this study was to produce landslide susceptibility map using the Probability Frequency Ratio Model method. This study involved the delineating of causative factors from Digital Terrain Model generated by Airborne LiDAR data as well as the data collected from the field. Apart from parameters derived from LiDAR, parameters from filed and site investigation were included into the mapping process. This study was different from the previous studies in the same area in terms of various analytical approaches and samples used. The results of the landslide susceptibility map were verified via randomly selected landslides samples using two different methods. The landslide susceptibility map produced is more refined and is able to predict more effectively compared to the existing map. The landslide susceptibility map produced in this study could be used for land use planning and management by decision makers and land use planners.

Landslide Susceptibility Mapping Using Statistical Methods along the Asian Highway, Bhutan

In areas prone to frequent landslides, the use of landslide susceptibility maps can greatly aid in the decision-making process of the socio-economic development plans of the area. Landslide susceptibility maps are generally developed using statistical methods and geographic information systems. In the present study, landslide susceptibility along road corridors was considered, since the anthropogenic impacts along a road in a mountainous country remain uniform and are mainly due to road construction. Therefore, we generated landslide susceptibility maps along 80.9 km of the Asian Highway (AH48) in Bhutan using the information value, weight of evidence, and logistic regression methods. These methods have been used independently by some researchers to produce landslide susceptibility maps, but no comparative analysis of these methods with a focus on road corridors is available. The factors contributing to landslides considered in the study are land cover, lithology, elevation, proximity to roads, drainage, and fault lines, aspect, and slope angle. The validation of the method performance was carried out by using the area under the curve of the receiver operating characteristic on training and control samples. The area under the curve values of the control samples were 0.883, 0.882, and 0.88 for the information value, weight of evidence, and logistic regression models, respectively, which indicates that all models were capable of producing reliable landslide susceptibility maps. In addition, when overlaid on the generated landslide susceptibility maps, 89.3%, 85.6%, and 72.2% of the control landslide samples were found to be in higher-susceptibility areas for the information value, weight of evidence, and logistic regression methods, respectively. From these findings, we conclude that the information value method has a better predictive performance than the other methods used in the present study. The landslide susceptibility maps produced in the study could be useful to road engineers in planning landslide prevention and mitigation works along the highway.

Comparative landslide spatial research based on various sample sizes and ratios in Penang Island, Malaysia

This paper aims to compare and develop the influence on different sample sizes and sample ratios when using machine learning (ML) models, i.e., support vector machine (SVM) and artificial neural network (ANN), to produce landslide susceptibility maps (LSMs) in Penang Island, Malaysia. At the same time, traditional statistical (TS) models are also considered to produce LSMs in this comparative research. The receiver operating characteristic (ROC) curve and recall metric are applied to evaluate the model’s performance. Based on the evaluation criteria, the ML model outperforms the TS models and the ML models trained using the datasets with larger sample size give a better performance. ML models, especially SVM models, have better performance when training with balanced datasets as well as the datasets of more landslide sample data. Kruskal-Wallis test and Mann-Whitney U test are applied to test the significance. The results indicate that sample size and sample ratio are essential factors when considering ML models to produce LSMs. The LSMs produced in this research can provide valid and useful information to the local authorities for landslide mitigation and prediction.

Landslide Detection and Susceptibility Modeling on Cameron Highlands (Malaysia): A Comparison between Random Forest, Logistic Regression and Logistic Model Tree Algorithms

We used remote sensing techniques and machine learning to detect and map landslides, and landslide susceptibility in the Cameron Highlands, Malaysia. We located 152 landslides using a combination of interferometry synthetic aperture radar (InSAR), Google Earth (GE), and field surveys. Of the total slide locations, 80% (122 landslides) were utilized for training the selected algorithms, and the remaining 20% (30 landslides) were applied for validation purposes. We employed 17 conditioning factors, including slope angle, aspect, elevation, curvature, profile curvature, stream power index (SPI), topographic wetness index (TWI), lithology, soil type, land cover, normalized difference vegetation index (NDVI), distance to river, distance to fault, distance to road, river density, fault density, and road density, which were produced from satellite imageries, geological map, soil maps, and a digital elevation model (DEM). We used these factors to produce landslide susceptibility maps using logistic regression (LR), logistic model tree (LMT), and random forest (RF) models. To assess prediction accuracy of the models we employed the following statistical measures: negative predictive value (NPV), sensitivity, positive predictive value (PPV), specificity, root-mean-squared error (RMSE), accuracy, and area under the receiver operating characteristic (ROC) curve (AUC). Our results indicated that the AUC was 92%, 90%, and 88% for the LMT, LR, and RF algorithms, respectively. To assess model performance, we also applied non-parametric statistical tests of Friedman and Wilcoxon, where the results revealed that there were no practical differences among the used models in the study area. While landslide mapping in tropical environment such as Cameron Highlands remains difficult, the remote sensing (RS) along with machine learning techniques, such as the LMT model, show promise for landslide susceptibility mapping in the study area.

Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest

Decision tree-based classifier ensemble methods are a machine learning (ML) technique that combines several tree models to produce an effective or optimum predictive model, and that allows well-predictive performance especially compared to a single model. Thus, selecting a proper ML algorithm help us to understand possible future occurrences by analyzing the past more accurate. The main purpose of this study is to produce landslide susceptibility map of the Ayancik district of Sinop province, situated in the Black Sea region of Turkey using three featured regression tree-based ensemble methods including gradient boosting machines (GBM), extreme gradient boosting (XGBoost), and random forest (RF). Fifteen landslide causative factors and 105 landslide locations occurred in the region were used. The landslide inventory map was randomly divided into training (70%) and testing (30%) dataset to construct the RF, XGBoost and GBM prediction models. Symmetrical uncertainty measure was utilized to determine the most important causative factors, and then the selected features were used to construct susceptibility prediction models. The performance of the ensemble models was validated using different accuracy metrics including Area under the curve (AUC), overall accuracy (OA), Root mean square error (RMSE), and Kappa coefficient. Also, the Wilcoxon signed-rank test was used to assess differences between optimum models. The accuracy results showed that the model of XgBoost_Opt model (the model created by optimum factor combination) has the highest prediction capability (OA = 0.8501 and AUC = 0.8976), followed by the RF_opt (OA = 0.8336 and AUC = 0.8860) and GBM_Opt (OA = 0.8244 and AUC = 0.8796). When the Wilcoxon sign-rank test results were analyzed, XgBoost_Opt model, which is the best subset combinations, were confirmed to be statistically significant considering other models. The results showed that, the XGBoost method according to optimum model achieved lower prediction error and higher accuracy results than the other ensemble methods.

Landslide susceptibility mapping along the upper Jinsha River, south-western China: a comparison of hydrological and curvature watershed methods for slope unit classification

The mapping unit is the smallest indivisible unit of landslide susceptibility mapping. The mapping unit considerably affects the effect of landslide susceptibility mapping. Among many mapping units, the slope unit is one of the most suitable units for landslide susceptibility mapping. The methods available for classifying slope unit are not uniform, and the dividing effects differ. In this study, the hydrological method and curvature watershed method were used to classify the slope units in the study area on the upper Jinsha River, south-western China. Lithology, slope angle, slope aspect, normalized difference vegetation index (NDVI), land cover, rainfall, curvature, distance-to-river, distance-to-fault, were selected as the landslide conditioning factors. Support vector machine were applied to the landslide susceptibility modeling. Statistical indexes, 5-flod cross validation, Kappa coefficient, and AUC values were introduced to validate the prediction accuracy of the landslide susceptibility model. By comparing the shape characteristics of slope units classified by the two methods, we found that the slope unit classified based on curvature watershed method has a uniform size, shape between circle and equilateral triangle, and small internal terrain variation. As for the mean prediction accuracy, Kappa coefficient and AUC values of landslide susceptibility model, in the training stage, were 81.62%, 63.23%, and 89.72%, respectively, for the hydrological method, while 84.26%, 68.51%, and 90.80%, respectively, for the curvature watershed method; in the testing stage, were 80.70%, 61.40%, and 88.08%, respectively, for the hydrological method, while 83.24%, 66.49%, and 88.96%, respectively, for the curvature watershed method, which means that the curvature watershed method is more effective to produce landslide susceptibility map of the study area.