Shallow Landslide Susceptibility Mapping Research Articles

A holistic approach of remote sensing, GIS, and machine learning for shallow landslide susceptibility mapping in Gaganbawada region of Western Ghats, India

A holistic approach of remote sensing, GIS, and machine learning for shallow landslide susceptibility mapping in Gaganbawada region of Western Ghats, India

A modular framework for FAIR shallow landslide susceptibility mapping based on machine learning

AbstractMachine learning has grown in popularity in the past few years for susceptibility and hazard mapping tasks. Necessary steps for the generation of a susceptibility or hazard map are repeatedly implemented in new studies. We present a Random Forest classifier-based landslide susceptibility and hazard mapping framework to facilitate future mapping studies using machine learning. The framework, as a piece of software, follows the FAIR paradigm, and hence is set up as a transparent, reproducible and modularly extensible workflow. It contains pre-implemented steps from conceptualisation to map generation, such as the generation of input datasets. The framework can be applied to different areas of interest using different environmental features and is also flexible in terms of the desired scale and resolution of the final map. To demonstrate the functionality and validity of the framework, and to explore the challenges and limitations of Random Forest-based susceptibility and hazard mapping, we apply the framework to a test case. This test case conveys the influence of the training dataset on the generated susceptibility maps in terms of feature combination, influence of non-landslide instances and representativeness of the training data with respect to the area of interest. A comparison of the test case results with the literature shows that the framework works reliably. Furthermore, the results obtained in this study complement the findings of previous studies that demonstrate the sensitivity of the training process to the training data, particularly in terms of its representativeness.

A Novel Heterogeneous Ensemble Framework Based on Machine Learning Models for Shallow Landslide Susceptibility Mapping

Landslides are devastating natural disasters that seriously threaten human life and property. Landslide susceptibility mapping (LSM) plays a key role in landslide hazard management. Machine learning (ML) models are widely used in LSM but suffer from limitations such as overfitting and unreliable accuracy. To improve the classification performance of a single machine learning (ML) model, this study selects logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient boosting decision tree (GBDT), and proposes a novel heterogeneous ensemble framework based on Bayesian optimization (BO), namely, stratified weighted averaging (SWA), to test its applicability in a typical landslide area in Yanbian Prefecture, China. Firstly, a dataset consisting of 1531 historical landslides was collected from field investigations and historical records, and a spatial database containing 16 predisposing factors was established. The dataset was divided into a training set and a test set in a ratio of 7:3. The results showed that SWA effectively improved the Accuracy, AUC, and robustness of the model compared to a single ML model. The SWA achieved the best classification results (Accuracy = 91.39% and AUC = 0.967). To verify the generalization ability of SWA, we selected published landslide datasets from Yanshan country and Yongxin country in China for testing. SWA also performed well, with an AUC of 0.871 and 0.860, respectively. As indicated by shapely values (SVs), Normalized Difference Vegetation Index (NDVI) is the factor that has the greatest impact on landslide occurrence. The landslide susceptibility maps obtained from this study will provide an effective reference program for land use planning and disaster prevention and mitigation projects in Yanbian Prefecture, China.

Application of a Novel Hybrid Machine Learning Algorithm in Shallow Landslide Susceptibility Mapping in a Mountainous Area

Landslides can be a major challenge in mountainous areas that are influenced by climate and landscape changes. In this study, we propose a hybrid machine learning model based on a rotation forest (RoF) meta classifier and a random forest (RF) decision tree classifier called RoFRF for landslide prediction in a mountainous area near Kamyaran city, Kurdistan Province, Iran. We used 118 landslide locations and 25 conditioning factors from which their predictive usefulness was measured using the chi-square technique in a 10-fold cross-validation analysis. We used the sensitivity, specificity, accuracy, F1-measure, Kappa, and area under the receiver operating characteristic curve (AUC) to validate the performance of the proposed model compared to the Artificial Neural Network (ANN), Logistic Model Tree (LMT), Best First Tree (BFT), and RF models. The validation results demonstrated that the landslide susceptibility map produced by the hybrid model had the highest goodness-of-fit (AUC = 0.953) and higher prediction accuracy (AUC = 0.919) compared to the benchmark models. The hybrid RoFRF model proposed in this study can be used as a robust predictive model for landslide susceptibility mapping in the mountainous regions around the world.

Ensemble Conditioning Factor Selection with Markov Chain Framework for Shallow Landslide Susceptibility Mapping in Lake Sapanca Basin and its Vicinity, Turkey

Ensemble Conditioning Factor Selection with Markov Chain Framework for Shallow Landslide Susceptibility Mapping in Lake Sapanca Basin and its Vicinity, Turkey

Shared Blocks-Based Ensemble Deep Learning for Shallow Landslide Susceptibility Mapping

Natural disaster impact assessment is of the utmost significance for post-disaster recovery, environmental protection, and hazard mitigation plans. With their recent usage in landslide susceptibility mapping, deep learning (DL) architectures have proven their efficiency in many scientific studies. However, some restrictions, including insufficient model variance and limited generalization capabilities, have been reported in the literature. To overcome these restrictions, ensembling DL models has often been preferred as a practical solution. In this study, an ensemble DL architecture, based on shared blocks, was proposed to improve the prediction capability of individual DL models. For this purpose, three DL models, namely Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM), together with their ensemble form (CNN–RNN–LSTM) were utilized to model landslide susceptibility in Trabzon province, Turkey. The proposed DL architecture produced the highest modeling performance of 0.93, followed by CNN (0.92), RNN (0.91), and LSTM (0.86). Findings proved that the proposed model excelled the performance of the DL models by up to 7% in terms of overall accuracy, which was also confirmed by the Wilcoxon signed-rank test. The area under curve analysis also showed a significant improvement (~4%) in susceptibility map accuracy by the proposed strategy.

Modeling Shallow Landslide Susceptibility and Assessment of the Relative Importance of Predisposing Factors, through a GIS-Based Statistical Analysis

Shallow landslides are destructive hazards and play an important role in landscape processes. The purpose of this paper is to evaluate the shallow landslide susceptibility and to investigate which predisposing factors control the spatial distribution of the collected instability phenomena. The GIS-based logistic regression model and jackknife test were respectively employed to achieve the scopes. The studied area falls in the Mesima basin, located in the southern Calabria (Italy). The research was based mainly on geomorphological study using both interpretation of Google Earth images and field surveys. Thus, 1511 shallow landslides were mapped and 18 predisposing factors (lithology, distance to faults, fault density, land use, soil texture, soil bulk density, soil erodibility, distance to streams, drainage density, elevation, slope gradient, slope aspect, local relief, plan curvature, profile curvature, TPI, TWI, and SPI) were recognized as influencing the shallow landslide susceptibility. The 70% of the collected shallow landslides were randomly divided into a training data set to build susceptibility model and the remaining 30% were used to validate the newly built model. The logistic regression model calculated the landslide probability of each pixel in the study area and produced the susceptibility map. Four classification methods were tested and compared between them, so the most reliable classification system was employed to the shallow landslide susceptibility map construction. In the susceptibility map, five classes were recognized as following: very low, low, moderate, high, and very high susceptibility. About 26.1% of the study area falls in high and very high susceptible classes and most of the landslides mapped (82.4%) occur in these classes. The accuracy of the predictive model was evaluated by using the ROC (receiver operating characteristics) curve approach, which showed an area under the curve (AUC) of 0.93, proving the excellent forecasting ability of the susceptibility model. The predisposing factors importance evaluation, using the jackknife test, revealed that slope gradient, TWI, soil texture and lithology were the most important factors; whereas, SPI, fault density and profile curvature have a least importance. According to these results, we conclude that the shallow landslide susceptibility map can be use as valuable tool both for land-use planning and for management and mitigation of the shallow landslide risk in the study area.

A refinement analysis of the shallow landslides susceptibility at regional scale supported by GIS-aided geo-database

Intense rainfall events often produce a great number of shallow landslides events, which in many cases can hits large areas or an entire regional territory. These slope instabilities cause damage to many roads, buildings, and infrastructures and often human loss. In these conditions, it is useful to refine shallow landslides susceptibility maps at regional scale progressively more reliable and efficacy. To take the highlighted goal it is opportune to promote the use of a circular approach that can considers knowledge (data, methods, models, solutions, etc.) constantly upgraded. To achieve this aims we propose a method that introduces structurally in a possible circular approach (progressive better results with constantly upgraded knowledge) the use of a comprehensive geo-database of shallow landslide events and related implemented through a collection and analysis of numerous sources, including published inventory maps, scientific literature, technical reports and newspapers, integrated by a multi-temporal interpretation of remote sensing images and several field surveys. The method is applied referring to the Calabria region, which is largely affected by this landslide category. The refined geo-database realized includes 22,028 shallow landslides, occurred between 1951 and 2017. The relationship between spatial pattern of the shallow landslides and the analyzed predisposing factors (lithological units, fault density, land use, drainage density, slope gradient, TWI, SPI and LS) showed that the high values of slope gradient, LS factor and drainage density, coupled to low values of TWI, displayed a strong control on the shallow landslide occurrence. The efficacy of the geo-database realization proves their usefulness in order to estimate and validate shallow landslide susceptibility map, which was optimally obtained applied a simple bivariate statistical method. The susceptibility map was classified into five classes and about 26% of the study area falls in high and very high susceptible classes and most of the shallow landslides mapped (76%) occur in the same classes. The AUC value of the prediction rate curve was 0.81, indicating a good prediction capability of the susceptibility map. The interaction between shallow landslide susceptibility map and road network map highlighted that the 20% of the roadways of the region area falls in high and very high susceptible areas, whereas was observed that the high (58.4%) and very high (65.6%) susceptibility classes are mainly distributed within cover materials from weathered crystalline rocks. The results obtained in this study indicate that the proposed method can concur to promote a circular approach and support with efficacy a progressive refinement of regional shallow landslide susceptibility map, from 2008 to now, that may be useful tool for national and/or local authorities to manage land use and civil protection planning, and for hazard and risk assessment from regional to slope scale.

Application and comparison of different ensemble learning machines combining with a novel sampling strategy for shallow landslide susceptibility mapping

The existence of shallow landslide brings huge threats to the human lives and economic development, as the Lang County, Southeastern Tibet prone to landslide. Landslide susceptibility mapping (LSM) is considered as the key for the prevention of hazard. The primary goal of the present study is to assess and compare four models: classification and regression tree, gradient boosting decision tree (GBDT), adaptive boosting-decision tree and random forest for the performance of landslide susceptibility modeling. Firstly, a landslide inventory map consisting of 229 historical shallow landslide locations was prepared and the same number of non-landslide points was determined by k-means clustering. Secondly, 12 conditioning factors were considered in the landslide susceptibility modeling. The prediction performance of the four models were estimated by fivefold cross validation and relative operating characteristic curve (ROC), area under the ROC curve (AUC) and statistical measures. The results showed that the GBDT performed best in the training and validation dataset, with the highest prediction capability (AUC = 0.986 and 0.940), highest accuracy value (95.3% and 88.1%) and highest kappa index (0.904 and 0.772), respectively. Therefore, the GBDT was considered to be the most suitable model and applied to the whole study area for LSM. The results of this study also demonstrate that the performance can be enhanced with the use of ensemble learning. The sampling strategy of non-landslide points can be improved by combining with clustering analysis which are more reasonable.

Rainfall-Induced Shallow Landslide Susceptibility Mapping at Two Adjacent Catchments Using Advanced Machine Learning Algorithms

Landslides impact on human activities and socio-economic development, especially in mountainous areas. This study focuses on the comparison of the prediction capability of advanced machine learning techniques for the rainfall-induced shallow landslide susceptibility of Deokjeokri catchment and Karisanri catchment in South Korea. The influencing factors for landslides, i.e., topographic, hydrologic, soil, forest, and geologic factors, are prepared from various sources based on availability, and a multicollinearity test is also performed to select relevant causative factors. The landslide inventory maps of both catchments are obtained from historical information, aerial photographs and performed field surveys. In this study, Deokjeokri catchment is considered as a training area and Karisanri catchment as a testing area. The landslide inventories contain 748 landslide points in training and 219 points in testing areas. Three landslide susceptibility maps using machine learning models, i.e., Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN), are prepared and compared. The outcomes of the analyses are validated using the landslide inventory data. A receiver operating characteristic curve (ROC) method is used to verify the results of the models. The results of this study show that the training accuracy of RF is 0.756 and the testing accuracy is 0.703. Similarly, the training accuracy of XGBoost is 0.757 and testing accuracy is 0.74. The prediction of DNN revealed acceptable agreement between the susceptibility map and the existing landslides, with a training accuracy of 0.855 and testing accuracy of 0.802. The results showed that the DNN model achieved lower prediction error and higher accuracy results than other models for shallow landslide modeling in the study area.

Comparison of Support Vector Machine, Bayesian Logistic Regression, and Alternating Decision Tree Algorithms for Shallow Landslide Susceptibility Mapping along a Mountainous Road in the West of Iran

This paper aims to apply and compare the performance of the three machine learning algorithms–support vector machine (SVM), bayesian logistic regression (BLR), and alternating decision tree (ADTree)–to map landslide susceptibility along the mountainous road of the Salavat Abad saddle, Kurdistan province, Iran. We identified 66 shallow landslide locations, based on field surveys, by recording the locations of the landslides by a global position System (GPS), Google Earth imagery and black-and-white aerial photographs (scale 1: 20,000) and 19 landslide conditioning factors, then tested these factors using the information gain ratio (IGR) technique. We checked the validity of the models using statistical metrics, including sensitivity, specificity, accuracy, kappa, root mean square error (RMSE), and area under the receiver operating characteristic curve (AUC). We found that, although all three machine learning algorithms yielded excellent performance, the SVM algorithm (AUC = 0.984) slightly outperformed the BLR (AUC = 0.980), and ADTree (AUC = 0.977) algorithms. We observed that not only all three algorithms are useful and effective tools for identifying shallow landslide-prone areas but also the BLR algorithm can be used such as the SVM algorithm as a soft computing benchmark algorithm to check the performance of the models in future.

Shallow landslide susceptibility mapping: A comparison between classification and regression tree and reduced error pruning tree algorithms

Shallow landslides through land degrading not only lead to threat the properly and life of human but they also may produce huge ecosystem damages. The aim of this study was to compare the performance of two decision tree machine learning algorithms including classification and regression tree (CART) and reduced error pruning tree (REPTree) for shallow landslide susceptibility mapping in Bijar, Kurdistan province, Iran. We first used 20 conditioning factors and then they were tested by information gain ratio (IGR) technique to select the most important ones. We then constructed a geodatabase based on the selected factors along with a total of 111 landslide locations with a ratio of 80/20 (for calibration/validation). The performance of the models was checked by the true positive rate (TP Rate), false positive rate (FP Rate), precision, recall, F1-Measure, Kappa, mean absolute error, and area under the receiver operatic curve (AUC). Results of IGR specified that the slope angle and TWI had the most contribution to shallow landslide occurrence in the study area. Moreover, results concluded that although these models had a high goodness-of-fit and prediction accuracy, the CART model (AUC=0.856) outperformed the REPTree model (AUC=0.837). Therefore, the CART model can be used as a promising tool and also as a base classifier to hybrid with optimization algorithms and Meta classifiers for spatial prediction of shallow landslide-prone areas.

Shallow Landslide Susceptibility Mapping by Random Forest Base Classifier and Its Ensembles in a Semi-Arid Region of Iran

We generated high-quality shallow landslide susceptibility maps for Bijar County, Kurdistan Province, Iran, using Random Forest (RAF), an ensemble computational intelligence method and three meta classifiers—Bagging (BA, BA-RAF), Random Subspace (RS, RS-RAF), and Rotation Forest (RF, RF-RAF). Modeling and validation were done on 111 shallow landslide locations using 20 conditioning factors tested by the Information Gain Ratio (IGR) technique. We assessed model performance with statistically based indexes, including sensitivity, specificity, accuracy, kappa, root mean square error (RMSE), and area under the receiver operatic characteristic curve (AUC). All four machine learning models that we tested yielded excellent goodness-of-fit and prediction accuracy, but the RF-RAF ensemble model (AUC = 0.936) outperformed the BA-RAF, RS-RAF (AUC = 0.907), and RAF (AUC = 0.812) models. The results also show that the Random Forest model significantly improved the predictive capability of the RAF-based classifier and, therefore, can be considered as a useful and an effective tool in regional shallow landslide susceptibility mapping.

Shallow Landslide Susceptibility Models Based on Artificial Neural Networks Considering the Factor Selection Method and Various Non-Linear Activation Functions

Landslide susceptibility mapping is well recognized as an essential element in supporting decision-making activities for preventing and mitigating landslide hazards as it provides information regarding locations where landslides are most likely to occur. The main purpose of this study is to produce a landslide susceptibility map of Mt. Umyeon in Korea using an artificial neural network (ANN) involving the factor selection method and various non-linear activation functions. A total of 151 historical landslide events and 20 predisposing factors consisting of Geographic Information System (GIS)-based morphological, hydrological, geological, and land cover datasets were constructed with a resolution of 5 x 5 m. The collected datasets were applied to information gain ratio analysis to confirm the predictive power and multicollinearity diagnosis to ensure the correlation of independence among the landslide predisposing factors. The best 11 predisposing factors that were selected in this study were randomly divided into a 70:30 ratio for training and validation datasets, which were used to produce ANN-based landslide susceptibility models. The ANN model used in this study had a multi-layer perceptron (MLP) structure consisting of an input layer, one hidden layer, and an output layer. In the output layer, the logistic sigmoid function was used to represent the result value within the range of 0 to 1, and six non-linear activation functions were used for the hidden layer. The performance of the landslide susceptibility models was evaluated using the receiver operating characteristic curve, Kappa index, and five statistical indices (sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV)) with the training dataset. In addition, the landslide susceptibility models were validated using the aforementioned measures with the validation dataset and were compared using the Friedman test to check the significant differences among the six developed models. The optimal number of neurons was determined based on the aforementioned performance evaluation and validation results. Overall, the model with the best performance was the MLP model with the logistic sigmoid activation function in the output layer and the hyperbolic tangent sigmoid activation function with five neurons in the hidden layer. The validation results of the best model showed a sensitivity of 82.61%, specificity of 78.26%, accuracy of 80.43%, PPV of 79.17%, NPV of 81.82%, a Kappa index of 0.609, and AUC of 0.879. The results of this study highlight the effectiveness of selecting an optimal MLP model structure for shallow landslide susceptibility mapping using an appropriate predisposing factor section method.

Effectiveness assessment of Keras based deep learning with different robust optimization algorithms for shallow landslide susceptibility mapping at tropical area

This research aims at investigating the capability of Keras’s deep learning models with three robust optimization algorithms (stochastic gradient descent, root mean square propagation, and adaptive moment optimization) and two-loss functions for spatial modeling of landslide hazard at a regional scale. Shallow landslides at the Ha Long area (Vietnam) were selected as a case study. For this regard, set of ten influencing factors (slope, aspect, curvature, topographic wetness index, landuse, distance to road, distance to river, soil type, distance to fault, and lithology) and 193 landslide polygons were prepared to construct a Geographic Information System (GIS) database for the study area. Using the collected database, the DNN with its potential of realizing complex functional mapping hidden in the data is used to generalize a decision boundary that separates the learning space into two distinct categories: landslide (a positive class) and non-landslide (a negative class). Experimental results point out that the utilized the Keras’s deep learning model with the Adam optimization and the mean squared error lost function is the best with the prediction performance of 84.0%. The performance is better than those of the employed benchmark approaches of random forest, J48 decision tree, classification tree, and logistic model tree. We conclude that the Keras’s deep learning model is a new tool for shallow susceptibility mapping at landslide-prone areas.

Shallow Landslide Susceptibility Mapping in Sochi Ski-Jump Area Using GIS and Numerical Modelling

The mountainous region of Greater Sochi, including the Olympic ski-jump complex area, located in the northern Caucasus, is always subjected to landslides. The weathered mudstone of low strength and potential high-intensity earthquakes are considered as the crucial factors causing slope instability in the ski-jump complex area. This study aims to conduct a seismic slope instability map of the area. A slope map was derived from a digital elevation model (DEM) and calculated using ArcGIS. The numerical modelling of slope stability with various slope angles was conducted using Geostudio. The Spencer method was applied to calculate the slope safety factors (Fs). The pseudostatic analysis was used to compute Fs considering seismic effect. A good correlation between Fs and slope angle was found. Combining these data, sets slope instability maps were achieved. Newmark displacement maps were also drawn according to empirical regression equations. The result shows that the static safety factor map corresponds to the existing slope instability locations in a shallow landslide inventory map. The seismic safety factor maps and Newmark displacement maps may be applied to predict potential landslides of the study area in the case of earthquake occurrence.

Novel GIS Based Machine Learning Algorithms for Shallow Landslide Susceptibility Mapping.

The main objective of this research was to introduce a novel machine learning algorithm of alternating decision tree (ADTree) based on the multiboost (MB), bagging (BA), rotation forest (RF) and random subspace (RS) ensemble algorithms under two scenarios of different sample sizes and raster resolutions for spatial prediction of shallow landslides around Bijar City, Kurdistan Province, Iran. The evaluation of modeling process was checked by some statistical measures and area under the receiver operating characteristic curve (AUROC). Results show that, for combination of sample sizes of 60%/40% and 70%/30% with a raster resolution of 10 m, the RS model, while, for 80%/20% and 90%/10% with a raster resolution of 20 m, the MB model obtained a high goodness-of-fit and prediction accuracy. The RS-ADTree and MB-ADTree ensemble models outperformed the ADTree model in two scenarios. Overall, MB-ADTree in sample size of 80%/20% with a resolution of 20 m (area under the curve (AUC) = 0.942) and sample size of 60%/40% with a resolution of 10 m (AUC = 0.845) had the highest and lowest prediction accuracy, respectively. The findings confirm that the newly proposed models are very promising alternative tools to assist planners and decision makers in the task of managing landslide prone areas.

Landslide susceptibility assessment by TRIGRS in a frequently affected shallow instability area

Landslide susceptibility assessment over large areas is considered a preliminary step for the planning or design of the most appropriate risk mitigation measures. The use of physically based models is considered a useful tool for landslide susceptibility assessment. Sometimes, using the available geotechnical input data, physically based models can be used to assess landslide susceptibility to obtain a susceptibility map which allows the expert to identify areas where detailed in situ investigations and laboratory tests should be carried out. In this context, the paper proposes a methodology based on the use of TRIGRS to assess landslide susceptibility in an area of about 1 km2 frequently affected by shallow phenomena in weathered gneiss. Owing to the fact that these materials are extremely complex to characterize from a mechanical and hydraulic point of view, the methodology starts with the collection and analysis of the geotechnical data available for weathered gneiss outcropping in the study area. These data are combined with the data provided by scientific literature on soils similar, for genesis and stress history, to those of the studied area. Through the application of TRIGRS, the data are combined in order to obtain the values of parameters that better analyze shallow landslide source areas. Subsequently, using the abovementioned values, several susceptibility maps are obtained. Finally, the most representative shallow landslide susceptibility map for the area is chosen by means of the error index (EI), the true positive fraction (TPF), and the forecasting index (FI). The success of the best map is confirmed by the high value of the area under the receiver operator characteristic curve (AUC) that demonstrates a good level of forecasting ability.

Application of GIS-Based Back Propagation Artificial Neural Networks and Logistic Regression for shallow Landslide Susceptibility Mapping in South China-Take Meijiang River Basin as an Example

Introduction: In this study, artificial neural network (ANN) model and logistic regression were applied to analyze susceptibility and identify the main controlling factors of landslide in Meijiang River Basin of Southern China. Methods: Methods: Eleven variables such as altitude, slope angle, slope aspect, topographic relief, distance to fault, rock-type, soil-type, land-use type, NDVI, maximum rainfall intensity, distance to river were employed as landslide conditioning factors in landslide susceptibility mapping. Both landsliding and non-landsliding samples were needed as training data for ANN model. 384 landslides and 380 non-landsliding point with no recorded landslides according to field investigation and survey data were chosen as sample data of ANN model. And ROC curve was applied to calculate the prediction accuracy. Results: The validation results showed that prediction accuracy rate of 82.6% exists between the susceptibility map and the location of the initial 384 landsliding samples. However, logistic regression analysis showed that the average correct classification percentage was 75.4%. The prediction results of ANN model in high sensitive zone is more accurate than the logistic regression model. Conclusion: Therefore, the ANN model is valid when assessing the susceptibility. The main controlling factors were identified from the eleven factors by ANN model. The slope, rock and land use type appeared to be the main controlling factors in landslide formation process in Southern China.

A data-driven approach for landslide susceptibility mapping: a case study of Shennongjia Forestry District, China

The main purpose of this study was to establish a data-driven approach and assess its potential for shallow landslide susceptibility mapping of the Shennongjia Forestry District, China. For the data processing, Fisher segmenting was used for the classification of topographical factors (gradient, relief amplitude, plan curvature, and normalized difference vegetation index) and the improved Otsu method was used to determine the buffer length thresholds of the locational factors (proximity to roads, rivers and faults). The computations show that these two objective methods help to avoid the uncertainty caused by the subjective judgments and the obtained thresholds are more consistent with actual conditions. Considering the different data types, the locational and topographical factors were evaluated by fuzzy comprehensive evaluation while the geological factors were evaluated by frequency index, and then the three separate evaluations were combined using radar chart analysis. The validation result shows that the susceptibility map based on a data-driven approach has a high accuracy of prediction and this approach will be salutary for risk mitigation and land-use management in mountainous regions.