Landslide Influencing Factors Research Articles

A landslide susceptibility assessment method considering the similarity of geographic environments based on graph neural network

Landslide susceptibility assessment (LSA) is vital for landslide mitigation and management. Existing LSA methods only consider local environmental characteristics associated with landslides, while neglecting the characteristics of remote yet interconnected geographic environments. In addition, the datasets for landslide samples do not consider the equilibrium among various geographic environmental characteristics. Ultimately, the landslide susceptibility mapping (LSM) generated is unreliable. We propose an LSA method based on the similarity of geographic environments and the equilibrium of landslide samples. We selected the Bailong River Basin (BRB) as the study area. Our proposed LSA method has four steps: (1) We constructed slope units using the curvature watershed method (CWM) based on the digital elevation model (DEM) to generate geographic nodes and selected 12 landslide influencing factors (LIFs) through multicollinearity analysis to extract geographic node features. (2) We constructed an association graph of geographic environment similarity constraints based on geographic node features using the cosine similarity method to correlate landslide and geographical environments. (3) We constructed sample datasets for an equal number of landslide and non-landslides based on various geographic environments. (4) We constructed a graph neural network (GNN) model based on the association graph to predict the susceptibility of unknown geographic nodes, obtaining a reliable LSM. Compared with random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) models, our proposed model framework outperforms in the LSA. The area under the receiver operating characteristic curve (AUC) values improved by 6.2%, 5.7%, and 1.8%, respectively. Specifically, our model can predict landslides across space in areas with few samples. Our proposed model offers an effective approach and essential technical support for landslide disaster investigation and prevention.

A python system for regional landslide susceptibility assessment by integrating machine learning models and its application

Landslide susceptibility assessment is considered the first step in landslide risk assessment, but current studies mostly rely on GIS platforms or other software for data preprocessing. The modeling process is relatively complicated and multi-models cannot be integrated. With regard to this issue, this study develops a Python system for automatic assessment of regional landslide susceptibility. The Python system implements landslide susceptibility assessment through three modules: geographic data processing, machine learning modeling and result evaluation analysis. For geographic data processing, ten landslide influencing factors can be used to construct an evaluation factor dataset and reclassify the thematic maps based on the frequency ratio method. Four built-in machine learning models (logistic regression (LR), multi-layer perceptron (MLP), support vector machine (SVM) and extreme gradient boosting (XGBoost)) are integrated into the system to complete susceptibility modeling and calculation. Additionally, receiver operating characteristic (ROC) curves can be automatically generated to evaluate the accuracy. The system was then applied into Lantian County in Shaanxi Province as a demonstration example. The results show that the areas under the ROC curve (AUC) of the four models are 0.838 (LR)、0.882 (SVM)、0.809 (MLP) and 0.812 (XGBoost), respectively, indicating that the SVM model was the most suitable model for landslide susceptibility assessment in Lantian County in the Loess Plateau of China. The system has now been made open source on Github, which can effectively improve the efficiency of regional landslide susceptibility assessment, especially provide tools for data processing and modeling for non-professionals.

Landslide susceptibility assessment in Western Henan Province based on a comparison of conventional and ensemble machine learning

Landslide is a serious natural disaster next only to earthquake and flood, which will cause a great threat to people’s lives and property safety. The traditional research of landslide disaster based on experience driving or statistical model and its assessment results are subjective , difficult to quantify, and no pertinence. As a new research method for landslide susceptibility assessment, machine learning can greatly improve the landslide susceptibility model’s accuracy by constructing statistical models. Taking Western Henan for example, the study selected 16 landslide influencing factors such as topography, geological environment, hydrological conditions, and human activities. And 11 landslide factors with the most significant influence on the landslide were selected by the recursive feature elimination (RFE) method. There are five machine learning methods (Support Vector Machines (SVM), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Linear Discriminant Analysis (LDA)) were used to construct the spatial distribution model of landslide susceptibility. The models were evaluated by the receiver operating characteristic curve and statistical index. After analysis and comparison, the XGBoost model (AUC 0.8759) performed the best and was suitable for dealing with regression problems. The model had a high adaptability to landslide data. According to the landslide susceptibility map of the five models, the overall distribution can be observed. The extremely high and high susceptibility areas are distributed in the Funiu Mountain range in the southwest, the Xiaoshan Mountain range in the west, and the Yellow River basin in the north. These areas have large terrain fluctuations, complicated geological structural environments and frequent human engineering activities. The extremely high and highly prone areas were 12043.3 km² and 3087.45 km², accounting for 47.61% and 12.20% of the total area of the study area, respectively. Our study reflects the distribution of landslide susceptibility in western Henan Province, which provides a scientific basis for regional disaster warning, prediction, and resource protection. The study has important practical significance for subsequent landslide disaster management.

Landslide Recognition from Multi-Feature Remote Sensing Data Based on Improved Transformers

Efficient and accurate landslide recognition is crucial for disaster prevention and post-disaster rescue efforts. However, compared to machine learning, deep learning approaches currently face challenges such as long model runtimes and inefficiency. To tackle these challenges, we proposed a novel knowledge distillation network based on Swin-Transformer (Distilled Swin-Transformer, DST) for landslide recognition. We created a new landslide sample database and combined nine landslide influencing factors (LIFs) with remote sensing images (RSIs) to evaluate the performance of DST. Our approach was tested in Zigui County, Hubei Province, China, and our quantitative evaluation showed that the combined RSIs with LIFs improved the performance of the landslide recognition model. Specifically, our model achieved an Overall Accuracy (OA), Precision, Recall, F1-Score (F1), and Kappa that were 0.8381%, 0.6988%, 0.9334%, 0.8301%, and 0.0125 higher, respectively, than when using only RSIs. Compared with the results of other neural networks, namely ResNet50, Swin-Transformer, and DeiT, our proposed deep learning model achieves the best OA (98.1717%), Precision (98.1672%), Recall (98.1667%), F1 (98.1615%), and Kappa (0.9766). DST has the lowest number of FLOPs, which is crucial for improving computational efficiency, especially in landslide recognition applications after geological disasters. Our model requires only 2.83 GFLOPs, which is the lowest among the four models and is 1.8242 GFLOPs, 1.741 GFLOPs, and 2.0284 GFLOPs less than ResNet, Swin, and DeiT, respectively. The proposed method has good applicability in rapid recognition scenarios after geological disasters.

Ensemble of fuzzy-analytical hierarchy process in landslide susceptibility modeling from a humid tropical region of Western Ghats, Southern India.

The western flanks of the Western Ghats are one of the major landslide hotspots in India. Recent rainfall triggered landslide incidents in this humid tropical region necessitating the accurate and reliable landslide susceptibility mapping (LSM) of selected parts of Western Ghats for hazard mitigation. In this study, a GIS-coupled fuzzy Multi-Criteria Decision Making (MCDM) technique is used to evaluate the landslide-susceptible zones in a highland segment of the Southern Western Ghats. Fuzzy numbers specified the relative weights of nine landslide influencing factors that were established and delineated using the ArcGIS, and the pairwise comparison of these fuzzy numbers in the Analytical hierarchy process (AHP) system resulted in standardized causative factor weights. Thereafter, the normalized weights are assigned to corresponding thematic layers, and finally, a landslide susceptibility map is generated. The model is validated using the area under the curve values (AUC) and F1 scores. The result reveals that about 27% of the study area is classified as highly susceptible zones followed by 24% area in moderately susceptible zone, 33% in low susceptible, and 16% in a very low susceptible area. Also, the study shows that the plateau scarps in the Western Ghats are highly susceptible to the occurrence of landslides. Moreover, the predictive accuracy estimated by the AUC scores (79%) and F1 scores (85%) shows that the LSM map is trustworthy for future hazard mitigation and land use planning in the study area.

Landslide Susceptibility Mapping Using LiDAR Data: A Case Study of Khao Yai National Park, Thailand

Landslide is the natural problem occur worldwide due to its geological features, climatic characteristics and human activities. With the help of a geographic information system (GIS) and the Analytic Hierarchical Process (AHP) method, this research attempts to develop a map of landslide susceptibility. During the present investigation, a total of ten landslide influencing factors including elevation, slope, curvature, aspect, topographic wetness index (TWI), land cover, lithology, precipitation, distance to the road and drainage, were examined for the present analysis. Using AHP, weights were applied to each factor. The weight over lay approach was used to create the landslide susceptibility map, which was then divided into five classes. According to the research findings of the susceptibility classes, 19.97% of the research 's area was highly susceptible, followed by 61.65% of low susceptible, 17.33% of moderate susceptible, 0.94% of high susceptible, and 0.12% of very high susceptible. The areas with extremely high landslide susceptibility are adjacent to a road system and have a steep slope. The amount of mean annual rainfall is high and lithology belonging to the Jurassic metasediments. The findings for this map showing the research area's vulnerability to landslides in Khao Yai National Park are useful for planners and decision-makers for slope management and future development projects in the area.

An Ensemble Approach of Feature Selection and Machine Learning Models for Regional Landslide Susceptibility Mapping in the Arid Mountainous Terrain of Southern Peru

This study evaluates the utility of the ensemble framework of feature selection and machine learning (ML) models for regional landslide susceptibility mapping (LSM) in the arid climatic condition of southern Peru. A historical landslide inventory and 24 different landslide influencing factors (LIFs) were prepared using remotely sensed and auxiliary datasets. The LIFs were evaluated using multi-collinearity statistics and their relative importance was measured to select the most discriminative LIFs using the ensemble feature selection method, which was developed using Chi-square, gain ratio, and relief-F methods. We evaluated the performance of ten different ML algorithms (linear discriminant analysis, mixture discriminant analysis, bagged cart, boosted logistic regression, k-nearest neighbors, artificial neural network, support vector machine, random forest, rotation forest, and C5.0) using different accuracy statistics (sensitivity, specificity, area under curve (AUC), and overall accuracy (OA)). We used suitable combinations of individual ML models to develop different ensemble ML models and evaluated their performance in LSM. We assessed the impact of LIFs on ML performance. Among all individual ML models, the k-nearest neighbors (sensitivity = 0.72, specificity = 0.82, AUC = 0.86, OA = 78%) and artificial neural network (sensitivity = 0.71, specificity = 0.85, AUC = 0.87, OA = 79%) algorithms showed the best performance using the top five LIFs, while random forest, rotation forest, and C5.0 (sensitivity = 0.76–0.81, specificity = 0.87, AUC = 0.90–0.93, OA = 82–84%) outperformed other models when developed using all twenty-four LIFs. Among ensemble models, the ensemble of k-nearest neighbors and rotation forest, k-nearest neighbors and artificial neural network, and artificial neural network and rotation forest outperformed other models (sensitivity = 0.72–0.73, specificity = 0.83–0.84, AUC = 0.86, OA = 79%) using the top five LIFs. The landslide susceptibility maps derived using these models indicate that ~2–3% and ~10–12% of the total study area fall within the “very high” and “high” susceptibility. The obtained susceptibility maps can be efficiently used to prioritize landslide mitigation activities.

Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model

The spatial heterogeneity of landslide influencing factors is the main reason for the poor generalizability of the susceptibility evaluation model. This study aimed to construct a comprehensive explanatory framework for landslide susceptibility evaluation models based on the SHAP (SHapley Additive explanation)-XGBoost (eXtreme Gradient Boosting) algorithm, analyze the regional characteristics and spatial heterogeneity of landslide influencing factors, and discuss the heterogeneity of the generalizability of the models under different landscapes. Firstly, we selected different regions in typical mountainous hilly region and constructed a geospatial database containing 12 landslide influencing factors such as elevation, annual average rainfall, slope, lithology, and NDVI through field surveys, satellite images, and a literature review. Subsequently, the landslide susceptibility evaluation model was constructed based on the XGBoost algorithm and spatial database, and the prediction results of the landslide susceptibility evaluation model were explained based on regional topography, geology, and hydrology using the SHAP algorithm. Finally, the model was generalized and applied to regions with both similar and very different topography, geology, meteorology, and vegetation, to explore the spatial heterogeneity of the generalizability of the model. The following conclusions were drawn: the spatial distribution of landslides is heterogeneous and complex, and the contribution of each influencing factor on the occurrence of landslides has obvious regional characteristics and spatial heterogeneity. The generalizability of the landslide susceptibility evaluation model is spatially heterogeneous and has better generalizability to regions with similar regional characteristics. Further explanation of the XGBoost landslide susceptibility evaluation model using the SHAP method allows quantitative analysis of the differences in how much various factors contribute to disasters due to spatial heterogeneity, from the perspective of global and local evaluation units. In summary, the integrated explanatory framework based on the SHAP-XGBoost model can quantify the contribution of influencing factors on landslide occurrence at both global and local levels, which is conducive to the construction and improvement of the influencing factor system of landslide susceptibility in different regions. It can also provide a reference for predicting potential landslide hazard-prone areas and for Explainable Artificial Intelligence (XAI) research.

Landslide susceptibility assessment through TrAdaBoost transfer learning models using two landslide inventories

The prediction performance of conventional landslide susceptibility (LS) models is generally limited by the size of samples in the landslide inventory, as unsatisfying performance may be yielded with landslide samples less than certain thresholds. Increasing landslide samples is the most reliable approach for solving this problem, but it can be expensive, time-consuming, and even unable to conduct. In this study, a novel method is presented that improves the performance of the LS models using the TrAdaBoost transfer learning algorithm. The proposed method transfers useful knowledge from one landslide inventory to another to improve the performance of LS models through which the effort to recollect landslide data is reduced. A database involving 373 historical landslide locations and 5 landslide influencing factors (LIFs, the slope angle, slope aspect, altitude, lithology, and curvature) in the study area (Zigui Basin, China) and 4,120 historical landslide locations and the corresponding LIFs in the source area (Wenchuan-Yingxiu area, China) were used for demonstration. The frequency ratio method was used to tackle problems of feature dissimilarities of LIFs between the study area and the source area. And then, with these quantified influencing factors as inputs, the three TrAdaBoost models (with decision trees (DT), support vector machine (SVM), and random forest (RF) as basic learners, namely TrAdaBoost-DT, TrAdaBoost-SVM, and TrAdaBoost-RF, respectively), and three conventional machine learning models (DT, SVM, RF) were adopted for showing the performance of the TrAdaBoost in improving the LS models. The area under the receiver operating characteristic curve (AUC) and the existing landslides were used to evaluate the performance of the LS models. The calculated results show that the AUC values of the DT, SVM, RF, TrAdaBoost-DT, TrAdaBoost-SVM, and TrAdaBoost-RF are 0.73, 0.82, 0.83, 0.80, 0.85, and 0.85, respectively; the landslide prediction accuracies of these models are 69%, 77%, 71%, 74%, 87% and 75%, respectively. Compared to the aforementioned results, when using the landslide inventory in the Wenchuan-Yingxiu area, the AUCs of the DT, SVM and RF increase by 0.07, 0.03 and 0.02, respectively, and the landslide prediction accuracies increase by 5%, 10% and 4%, respectively. The results of this study present that in the uncomplete landslide inventory environment, using the TrAdaBoost model to improve the performance of LS models is promising due to its low costs and the great improvement to LS models.

Earthquake-Induced Landslide Susceptibility Assessment Using a Novel Model Based on Gradient Boosting Machine Learning and Class Balancing Methods

Predicting the susceptibility of a specific part of a landslide (SSPL) involves predicting the likelihood that the part of the landslide (e.g., the entire landslide, the source area, or the scarp) will form in a given area. When predicting SSPL, the landslide samples are far less than the non-landslide samples. This class imbalance makes it difficult to predict the SSPL. This paper proposes an advanced artificial intelligence (AI) model based on the dice-cross entropy (DCE) loss function and XGBoost (XGBDCE) or Light Gradient Boosting Machine (LGBDCE) to ameliorate the class imbalance in the SSPL prediction. We select the earthquake-induced landslides from the 2018 Hokkaido earthquake as a case study to evaluate our proposed method. First, six different datasets with 24 landslide influencing factors and 10,422 samples of a specific part of the landslides are established using remote sensing and geographic information system technologies. Then, based on each of the six datasets, four landslide susceptibility algorithms (XGB, LGB, random-forest (RF) and linear discriminant analysis (LDA)) and four class balancing methods (non-balance (NB), equal-quantity sampling (EQS), inverse landslide-frequency weighting (ILW), and DCE loss) are applied to predict the SSPL. The results show that the non-balanced method underestimates landslide susceptibility, and the ILW or EQS methods overestimate the landslide susceptibility, while the DCE loss method produces more balanced results. The prediction performance of the XGBDCE (average area under the receiver operating characteristic curve (0.970) surpasses that of RF (0.956), LGB (0.962), and LDA (0.921). Our proposed methods produce more unbiased and precise results than the existing models, and have a great potential to produce accurate general (e.g., predicting the entire landslide) and detailed (e.g., combining the prediction of the landslide source area with the landslide run-out modeling) landslide susceptibility assessments, which can be further applied to landslide hazard and risk assessments.

Mapping Landslide Sensitivity Based on Machine Learning: A Case Study in Ankang City, Shaanxi Province, China

The main purpose of this research is to apply the logistic regression (LR) model, the support vector machine (SVM) model based on radial basis function, the random forest (RF) model, and the coupled model of the whale optimization algorithm (WOA) and genetic algorithm (GA) with RF, to make landslide susceptibility mapping for the Ankang City of Shaanxi Province, China. To this end, a landslide inventory map consisting of 4278 identified landslides is randomly divided into training and test landslides in a ratio of 7 : 3. The 15 landslide influencing factors are selected as follows: slope aspect, slope degree, elevation, terrain curvature, plane curvature, profile curvature, surface roughness, distance to faults, distance to roads, landform, lithology, distance to rivers, rainfall, stream power index (SPI), and normalized difference vegetation index (NDVI), and the potential multicollinearity problem among these factors is detected by Pearson correlation coefficient (PCC), variance inflation factor (VIF), and tolerance (TOL). We evaluate the performance of the model separately by statistical training and test dataset metrics, including sensitivity, specificity, accuracy, kappa, mean absolute error (MSE), root mean square error (RMSE), and area under the receiver operating characteristic curve. The training success rates of LR, SVM, RF, WOA-RF, and GA-RF models are 0.7546, 0.8317, 0.8561, 0.8804, and 0.8957; the testing success rates are 0.7551, 0.8375, 0.8395, 0.8348, and 0.85007. The results show that the GA significantly improves the predictive power of the RF model. This study provides a scientific reference for disaster prevention and control in this area and its surrounding areas.

GIS-based landslide susceptibility mapping using frequency ratio and index of entropy models for She County of Anhui Province, China

Abstract Landslides caused countless economic and casualty losses in China, especially in mountainous and hilly areas. Landslide susceptibility mapping is an important approach and tool for landslide disaster prevention and control. This study presents a landslide susceptibility assessment using frequency ratio (FR) and index of entropy (IOE) models within a geographical information system for She County in the mountainous region of South Anhui, China. First, the landslide locations were ascertained in the study area using historical landslide records, aerial photographs, and multiple field surveys. In all, 502 landslides were identified and randomly divided into two groups as training (70%) and validation (30%) datasets. Additionally, the landslide-influencing factors, including slope angle, slope aspect, curvature, landform, lithology, distance to faults, distance to roads, distance to rivers, rainfall, and normalized difference vegetation index, were selected and their relative importance and weights were determined by FR and IOE models. The results show that the very high and high susceptibility classes cover nearly 50% of the study area. Finally, the comprehensive performance of the two models was validated and compared using receiver operating characteristic curves. The results demonstrated that the IOE model with the area under the curve (AUC) of 0.802, which is slightly better in prediction than the FR model (AUC = 0.786). The interpretation of the susceptibility map indicated that landform, slope degree, and distance to rivers plays a major role in landslide occurrence and distribution. The research results can be used for preliminary land use planning and hazard mitigation purposes.

A Data-Driven Model for Spatial Shallow Landslide Probability of Occurrence Due to a Typhoon in Ningguo City, Anhui Province, China

From 9 to 11 August 2019, the southeast coastal areas of China were hit by Typhoon Lekima, which caused a large number of shallow landslides. The typhoon resulted in a maximum rainfall of 402 mm during 3 days in Ningguo City. In this study, satellite images were acquired before and after the rainfall and visual interpretation was used to identify 414 shallow landslides in Ningguo City, and a complete database of shallow landslides caused by the typhoon-induced rainfall in Ningguo City was created. Nine landslide-influencing factors were selected—elevation, slope, aspect, strata, distance to faults, distance to rivers, distance to roads, normalized vegetation difference index, and rainfall—and the relationships between the rainfall-induced landslide distribution and the influencing factors were analyzed. The Bayesian probability method was combined with a logistic regression model to establish a landslide probability map for the study area. The real probabilities of landslide occurrence in the study area under five different rainfall conditions were calculated, and probability maps of landslide occurrence were drawn. The results of this study provide a reference for disaster prevention and reduction of typhoon rainstorm landslides in the southeast coastal areas of China and a future basis for decision making by the Ningguo government departments before a typhoon rainstorm occurs.

A Comparative Assessment of Machine Learning Models for Landslide Susceptibility Mapping in the Rugged Terrain of Northern Pakistan

This study investigated the performances of different techniques, including random forest (RF), support vector machine (SVM), maximum entropy (maxENT), gradient-boosting machine (GBM), and logistic regression (LR), for landslide susceptibility mapping (LSM) in the rugged terrain of northern Pakistan. Initially, a landslide inventory of 200 samples was produced along with an additional 200 samples indicating nonlandslide areas and divided into training (70%) and validation (30%) groups using a stratified loop-based random sampling approach. Then, a geospatial database of 12 possible landslide influencing factors (LIFs) was generated, including elevation, slope, aspect, topographic wetness index (TWI), topographic position index (TPI), distance to drainage, distance to fault, distance to road, normalized difference vegetation index (NDVI), rainfall, land cover/land use (LCLU), and a geological map of the study area. None of the LIFs were redundant for the modeling, as indicated by the multicollinearity test (tolerance > 0.1) and information gain ratio (IGR > 0). We extended the evaluation measures of each algorithm from area-under-the-curve (AUC) analysis to the calculation of performance overall (POA) with the help of precision, recall, F1 score, accuracy (ACC), and Matthew’s correlation coefficient (MCC). The results showed that the SVM was the most promising model (AUC = 0.969, POA = 2669) for the LSM, followed by RF (AUC = 0.967, POA = 2656), GBM (AUC = 0.967, POA = 2623), maxENT (AUC = 0.872, POA = 1761), and LR (AUC = 0.836, POA = 1299). It is important to note that the SVM, RF, and GBM were the top performers, with almost similar accuracy. Thus, each of these could be equally effective for LSM and can be used for risk reduction and mitigation measures in the rugged terrain of Pakistan and other regions with similar topography.

Landslide Susceptibility Mapping using Frequency Ratio, a case study of Vythiriblock in Wayanad, the northern part of Kerala, India

Landslides are common and disastrous events in India's Western Ghats during the rainy season and various factors influence the occurrence of landslides. The present research aims to establish landslide susceptibility zones to control landslide hazards and risk effectively. Landslides occurred in the entire area of the Wayanad district. The study was carried out in vythiri taluk to do detailed surveys using remote sensing and GIS, GPS and field investigation. A total of 162 landslide locations are used to develop a landslide susceptibility map of this area. Landslide susceptibility map of this area was done by using the frequency ratio (FR) model. The landslide susceptibility map is based on factors that affect directly or indirectly land subsidence process. There are twelve landslide influencing factors taken for this study: Slope, Aspect, Land use/land cover, Rainfall, Vegetation, Soil, Distance to lineament, Distance to the road, Elevation, Curvature, Geomorphology and Lithology. The resulting landslide susceptibility map shows that 3.6 % of the region is in a low susceptible zone, 40.5 % is in a moderate susceptible zone, 49 % is in a high susceptible zone and 6.9 % is in a very high susceptible zone to landslides. According to this model, the area under the curve (AUC) for the success rate is 75.3 %. This study would support the relevant authorities in identifying potential risks in particular parts which could be used for landslide mitigation activities as construction development in the region increases.

LANDSLIDE SUSCEPTIBILITY MAPPING ALONG NATIONAL HIGHWAY-6, HOA BINH PROVINCE, VIETNAM USING FREQUENCY RATIO MODEL AND GIS

The landslide has happened quite frequently on National Highway 6 (NH6) and causes damage to both property and life every year. Whereas, detailed landslide susceptibility maps are rarely available on this road. The application of the Frequency Ratio (FR) method and GIS allows for faster, cheaper, more efficient and easily updated landslide susceptibility area determination. This paper presents a landslide susceptibility map along NH6 by using the FR method and GIS. The input data layers include eight main factors that cause landslides, which have collected from various sources. The FR value for each class was calculated based on the spatial relationships between the landslide inventory and landslide influencing factors, then integrated into the GIS environment to produce a landslide susceptibility map. This map was classified into five levels, including very low, low, moderate, high and very high. The validation result of the frequency ratio model is fairly good (AUC = 0.738). The developed landslide susceptibility map can help organizers and decision-makers give early warning to people who have lived along this route and improve the planning of construction and land-use change.

GIS-Based Soft Computing Models for Landslide Susceptibility Mapping: A Case Study of Pithoragarh District, Uttarakhand State, India

The main objective of the study was to investigate performance of three soft computing models: Naïve Bayes (NB), Multilayer Perceptron (MLP) neural network classifier, and Alternating Decision Tree (ADT) in landslide susceptibility mapping of Pithoragarh District of Uttarakhand State, India. For this purpose, data of 91 past landslide locations and ten landslide influencing factors, namely, slope degree, curvature, aspect, land cover, slope forming materials (SFM), elevation, distance to rivers, geomorphology, overburden depth, and distance to roads were considered in the models study. Thematic maps of the Geological Survey of India (GSI), Google Earth images, and Aster Digital Elevation Model (DEM) were used for the development of landslide susceptibility maps in the Geographic Information System (GIS) environment. Landslide locations data was divided into a 70 : 30 ratio for the training (70%) and testing/validation (30%) of the three models. Standard statistical measures, namely, Positive Predicted Values (PPV), Negative Predicted Values (NPV), Sensitivity, Specificity, Mean Absolute Error (MAE), Root Mean Squire Error (RMSE), and Area under the ROC Curve (AUC) were used for the evaluation of the models. All the three soft computing models used in this study have shown good performance in the accurate development of landslide susceptibility maps, but performance of the ADT and MLP is better than NB. Therefore, these models can be used for the construction of accurate landslide susceptibility maps in other landslide-prone areas also.

Application of Bayesian Hyperparameter Optimized Random Forest and XGBoost Model for Landslide Susceptibility Mapping

Landslides are widely distributed worldwide and often result in tremendous casualties and economic losses, especially in the Loess Plateau of China. Taking Wuqi County in the hinterland of the Loess Plateau as the research area, using Bayesian hyperparameters to optimize random forest and extreme gradient boosting decision trees model for landslide susceptibility mapping, and the two optimized models are compared. In addition, 14 landslide influencing factors are selected, and 734 landslides are obtained according to field investigation and reports from literals. The landslides were randomly divided into training data (70%) and validation data (30%). The hyperparameters of the random forest and extreme gradient boosting decision tree models were optimized using a Bayesian algorithm, and then the optimal hyperparameters are selected for landslide susceptibility mapping. Both models were evaluated and compared using the receiver operating characteristic curve and confusion matrix. The results show that the AUC validation data of the Bayesian optimized random forest and extreme gradient boosting decision tree model are 0.88 and 0.86, respectively, which showed an improvement of 4 and 3%, indicating that the prediction performance of the two models has been improved. However, the random forest model has a higher predictive ability than the extreme gradient boosting decision tree model. Thus, hyperparameter optimization is of great significance in the improvement of the prediction accuracy of the model. Therefore, the optimized model can generate a high-quality landslide susceptibility map.

Landslide susceptibility zonation method based on C5.0 decision tree and K-means cluster algorithms to improve the efficiency of risk management

Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation. This study presents a machine learning approach based on the C5.0 decision tree (DT) model and the K-means cluster algorithm to produce a regional landslide susceptibility map. Yanchang County, a typical landslide-prone area located in northwestern China, was taken as the area of interest to introduce the proposed application procedure. A landslide inventory containing 82 landslides was prepared and subsequently randomly partitioned into two subsets: training data (70% landslide pixels) and validation data (30% landslide pixels). Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model. Susceptibility zonation was implemented according to the cut-off values calculated by the K-means cluster algorithm. The validation results of the model performance analysis showed that the AUC (area under the receiver operating characteristic (ROC) curve) of the proposed model was the highest, reaching 0.88, compared with traditional models (support vector machine (SVM) = 0.85, Bayesian network (BN) = 0.81, frequency ratio (FR) = 0.75, weight of evidence (WOE) = 0.76). The landslide frequency ratio and frequency density of the high susceptibility zones were 6.76/km2 and 0.88/km2, respectively, which were much higher than those of the low susceptibility zones. The top 20% interval of landslide occurrence probability contained 89% of the historical landslides but only accounted for 10.3% of the total area. Our results indicate that the distribution of high susceptibility zones was more focused without containing more “stable” pixels. Therefore, the obtained susceptibility map is suitable for application to landslide risk management practices.

Landslide Hazard Analysis Using a Multilayered Approach Based on Various Input Data Configurations

Landslide is a natural disaster that occurs mostly in hill areas. Landslide hazard mapping is used to classify the prone areas to mitigate the risk of landslide hazards. This paper aims to compare spatial landslide prediction performance using an artificial neural network (ANN) model based on different data input configurations, different numbers of hidden neurons, and two types of normalization techniques on the data set of Penang Island, Malaysia. The data set involves twelve landslide influencing factors in which five factors are in continuous values, while the remaining seven are in categorical/discrete values. These factors are considered in three different configurations, i.e., original (OR), frequency ratio (FR), and mixed-type (MT) data, which act as an input to train the ANN model separately. A significant effect on the final output is the number of hidden neurons in the hidden layer. In addition, three data configurations are processed using two different normalization methods, i.e., mean-standard deviation (Mean-SD) and Min-Max. The landslide causative data often consist of correlated information caused by overlapping of input instances. Therefore, the principal component analysis (PCA) technique is used to eliminate the correlated information. The area under the receiver of characteristics (ROC) curve, i.e., AUC is also applied to verify the produced landslide hazard maps. The best result of AUC for both Mean-SD and Min-Max with PCA schemes are 96.72% and 96.38%, respectively. The results show that Mean-SD with PCA of MT data configuration yields the best validation accuracy, AUC, and lowest AIC at 100 number of hidden neurons. MT data configuration with the Mean-SD normalization and PCA scheme is more robust and stable in the MLP model's training for landslide prediction. 
 Keywords: Landslide; ANN; Hidden Neurons; Normalization; PCA; ROC; Hazard map
 
 Copyright (c) 2021 Geosfera Indonesia and Department of Geography Education, University of Jember
 This work is licensed under a Creative Commons Attribution-Share A like 4.0 International License