Spatial Prediction Of Landslide Susceptibility Research Articles

Spatial prediction of landslide susceptibility using data mining-based kernel logistic regression, naive Bayes and RBFNetwork models for the Long County area (China)

The main goal of this study is to assess and compare three advanced machine learning techniques, namely, kernel logistic regression (KLR), naive Bayes (NB), and radial basis function network (RBFNetwork) models for landslide susceptibility modeling in Long County, China. First, a total of 171 landslide locations were identified within the study area using historical reports, aerial photographs, and extensive field surveys. All the landslides were randomly separated into two parts with a ratio of 70/30 for training and validation purposes. Second, 12 landslide conditioning factors were prepared for landslide susceptibility modeling, including slope aspect, slope angle, plan curvature, profile curvature, elevation, distance to faults, distance to rivers, distance to roads, lithology, NDVI (normalized difference vegetation index), land use, and rainfall. Third, the correlations between the conditioning factors and the occurrence of landslides were analyzed using normalized frequency ratios. A multicollinearity analysis of the landslide conditioning factors was carried out using tolerances and variance inflation factor (VIF) methods. Feature selection was performed using the chi-squared statistic with a 10-fold cross-validation technique to assess the predictive capabilities of the landslide conditioning factors. Then, the landslide conditioning factors with null predictive ability were excluded in order to optimize the landslide models. Finally, the trained KLR, NB, and RBFNetwork models were used to construct landslide susceptibility maps. The receiver operating characteristics (ROC) curve, the area under the curve (AUC), and several statistical measures, such as accuracy (ACC), F-measure, mean absolute error (MAE), and root mean squared error (RMSE), were used for the assessment, validation, and comparison of the resulting models in order to choose the best model in this study. The validation results show that all three models exhibit reasonably good performance, and the KLR model exhibits the most stable and best performance. The KLR model, which has a success rate of 0.847 and a prediction rate of 0.749, is a promising technique for landslide susceptibility mapping. Given the outcomes of the study, all three models could be used efficiently for landslide susceptibility analysis.

A novel hybrid integration model using support vector machines and random subspace for weather-triggered landslide susceptibility assessment in the Wuning area (China)

This study proposed a hybrid modeling approach using two methods, support vector machines and random subspace, to create a novel model named random subspace-based support vector machines (RSSVM) for assessing landslide susceptibility. The newly developed model was then tested in the Wuning area, China, to produce a landslide susceptibility map. With the purpose of achieving the objective of the study, a spatial dataset was initially constructed that includes a landslide inventory map consisting of 445 landslide regions. Then, various landslide-influencing factors were defined, including slope angle, aspect, altitude, topographic wetness index, stream power index, sediment transport index, soil, lithology, normalized difference vegetation index, land use, rainfall, distance to roads, distance to rivers, and distance to faults. Next, the result of the RSSVM model was validated using statistical index-based evaluations and the receiver operating characteristic curve approach. Then, to evaluate the performance of the suggested RSSVM model, a comparison analysis was performed to other existing approaches such as artificial neural network, Naïve Bayes (NB) and support vector machine (SVM). In general, the performance of the RSSVM model was better than the other models for spatial prediction of landslide susceptibility. The AUC results of the applied models are as follows: RSSVM (AUC = 0.857), followed by MLP (AUC = 0.823), SVM (AUC = 0.814) and NB (AUC = 0.783). The present study indicates that RSSVM can be used for landslide susceptibility evaluation, and the results are very useful for local governments and people living in the Wuning area.

Spatial prediction of landslide susceptibility using an adaptive neuro-fuzzy inference system combined with frequency ratio, generalized additive model, and support vector machine techniques

The spatial prediction of landslide susceptibility is an important prerequisite for the analysis of landslide hazards and risks in any area. This research uses three data mining techniques, such as an adaptive neuro-fuzzy inference system combined with frequency ratio (ANFIS-FR), a generalized additive model (GAM), and a support vector machine (SVM), for landslide susceptibility mapping in Hanyuan County, China. In the first step, in accordance with a review of the previous literature, twelve conditioning factors, including slope aspect, altitude, slope angle, topographic wetness index (TWI), plan curvature, profile curvature, distance to rivers, distance to faults, distance to roads, land use, normalized difference vegetation index (NDVI), and lithology, were selected. In the second step, a collinearity test and correlation analysis between the conditioning factors and landslides were applied. In the third step, we used three advanced methods, namely, ANFIS-FR, GAM, and SVM, for landslide susceptibility modeling. Subsequently, the results of their accuracy were validated using a receiver operating characteristic curve. The results showed that all three models have good prediction capabilities, while the SVM model has the highest prediction rate of 0.875, followed by the ANFIS-FR and GAM models with prediction rates of 0.851 and 0.846, respectively. Thus, the landslide susceptibility maps produced in the study area can be applied for management of hazards and risks in landslide-prone Hanyuan County.

A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility

The main purpose of the present study is to use three state-of-the-art data mining techniques, namely, logistic model tree (LMT), random forest (RF), and classification and regression tree (CART) models, to map landslide susceptibility. Long County was selected as the study area. First, a landslide inventory map was constructed using history reports, interpretation of aerial photographs, and extensive field surveys. A total of 171 landslide locations were identified in the study area. Twelve landslide-related parameters were considered for landslide susceptibility mapping, including slope angle, slope aspect, plan curvature, profile curvature, altitude, NDVI, land use, distance to faults, distance to roads, distance to rivers, lithology, and rainfall. The 171 landslides were randomly separated into two groups with a 70/30 ratio for training and validation purposes, and different ratios of non-landslides to landslides grid cells were used to obtain the highest classification accuracy. The linear support vector machine algorithm (LSVM) was used to evaluate the predictive capability of the 12 landslide conditioning factors. Second, LMT, RF, and CART models were constructed using training data. Finally, the applied models were validated and compared using receiver operating characteristics (ROC), and predictive accuracy (ACC) methods. Overall, all three models exhibit reasonably good performances; the RF model exhibits the highest predictive capability compared with the LMT and CART models. The RF model, with a success rate of 0.837 and a prediction rate of 0.781, is a promising technique for landslide susceptibility mapping. Therefore, these three models are useful tools for spatial prediction of landslide susceptibility.

Spatial prediction of landslide susceptibility using integrated frequency ratio with entropy and support vector machines by different kernel functions

The main purpose of the present study is to compare the prediction capability of frequency ratio (FR), index of entropy (IOE), and support vector machines with four kernel functions (LN-SVM, PL-SVM, RBF-SVM, and Sig-SVM) for landslide susceptibility mapping at Long County, China. For this purpose, a total of 171 landslide locations were collected from historical landslide reports, interpretation of satellite images, and field survey data. These landslides were separated into two parts (70/30): 120 landslides were randomly selected for training the models, and the remaining 51 landslides were used for validation purpose. Eleven landslide-related parameters were selected to produce landslide susceptibility maps, including slope aspect, slope angle, plan curvature, profile curvature, altitude, NDVI, land use, distance to faults, distance to roads, distance to rivers, and lithology. The landslide susceptibility maps were produced by FR, IOE, and SVM models, and these maps were validated and compared using area under the curve method. The results show that the RBF-SVM model has the best performance for this study area, while the success rate is 82.51 % and prediction rate is 77.83 %. For the other models, the results are as follows: the PL-SVM model (success rate is 82.44 %; prediction rate is 75.71 %), the FR model (success rate is 79.79 %; prediction rate 75.42 %), the LN-SVM model (success rate is 79.76 %; prediction rate is 74.76 %), the IOE model (success rate is 78.29 %; prediction rate is 74.01 %), and the Sig-SVM model (success rate is 75.22 %; prediction rate is 73.75 %). The results of this study are useful for land-use decision makers, landslide risk assessment and management study in this region, and other similar areas.

The spatial prediction of landslide susceptibility applying artificial neural network and logistic regression models: A case study of Inje, Korea

AbstractThe aim of this study is to predict landslide susceptibility caused using the spatial analysis by the application of a statistical methodology based on the GIS. Logistic regression models along with artificial neutral network were applied and validated to analyze landslide susceptibility in Inje, Korea. Landslide occurrence area in the study were identified based on interpretations of optical remote sensing data (Aerial photographs) followed by field surveys. A spatial database considering forest, geophysical, soil and topographic data, was built on the study area using the Geographical Information System (GIS). These factors were analysed using artificial neural network (ANN) and logistic regression models to generate a landslide susceptibility map. The study validates the landslide susceptibility map by comparing them with landslide occurrence areas. The locations of landslide occurrence were divided randomly into a training set (50%) and a test set (50%). A training set analyse the landslide susceptibility map using the artificial network along with logistic regression models, and a test set was retained to validate the prediction map. The validation results revealed that the artificial neural network model (with an accuracy of 80.10%) was better at predicting landslides than the logistic regression model (with an accuracy of 77.05%). Of the weights used in the artificial neural network model, ‘slope’ yielded the highest weight value (1.330), and ‘aspect’ yielded the lowest value (1.000). This research applied two statistical analysis methods in a GIS and compared their results. Based on the findings, we were able to derive a more effective method for analyzing landslide susceptibility.

Spatial prediction of landslide susceptibility in parts of Garhwal Himalaya, India, using the weight of evidence modelling.

Garhwal Himalaya in northern India has emerged as one of the most prominent hot spots of landslide occurrences in the Himalaya mainly due to geological causes related to mountain building processes, steep topography and frequent occurrences of extreme precipitation events. As this region has many pilgrimage and tourist centres, it is visited by hundreds of thousands of people every year, and in the recent past, there has been rapid development to provide adequate roads and building infrastructure. Additionally, attempts are also made to harness hydropower by constructing tunnels, dams and reservoirs and thus altering vulnerable slopes at many places. As a result, the overall risk due to landslide hazards has increased many folds and, therefore, an attempt was made to assess landslide susceptibility using 'Weights of Evidence (WofE)', a well-known bivariate statistical modelling technique implemented in a much improved way using remote sensing and Geographic Information System. This methodology has dual advantage as it demonstrates how to derive critical parameters related to geology, geomorphology, slope, land use and most importantly temporal landslide distribution in one of the data scarce region of the world. Secondly, it allows to experiment with various combination of parameters to assess their cumulative effect on landslides. In total, 15 parameters related to geology, geomorphology, terrain, hydrology and anthropogenic factors and 2 different landslide inventories (prior to 2007 and 2008-2011) were prepared from high-resolution Indian remote sensing satellite data (Cartosat-1 and Resourcesat-1) and were validated by field investigation. Several combinations of parameters were carried out using WofE modelling, and finally using best combination of eight parameters, 76.5 % of overall landslides were predicted in 24 % of the total area susceptible to landslide occurrences. The study has highlighted that using such methodology landslide susceptibility assessment can be carried out in vast stretches of Himalaya in short time in order to assess the impact of development as well as climate change/variability. The resultant map can play a critical role in selecting areas for remedial measures for slope stabilisation as well planning for future development of the region.

Spatial prediction of landslide susceptibility using a decision tree approach: a case study of the Pyeongchang area, Korea

A decision tree approach was applied and validated for analysis of landslide susceptibility using a geographic information system (GIS). The study area was the Pyeongchang area in Gangwon Province, Korea, where many landslides occurred in 2006 and where the 2018 Winter Olympics are to be held. Spatial data, such as landslides, topography, and geology, were detected, collected, and compiled in a database using remote sensing and GIS. The 3994 recorded landslide locations were randomly split 50/50 for training and validation of the models. A decision tree model, which is a type of data-mining classification model, was applied and decision trees were constructed using the chi-squared (χ2) automatic interaction detector (CHAID) and the quick, unbiased, and efficient statistical tree (QUEST) algorithms. Also, as a reference, a frequency-ratio model was applied using the same database. The relationships between the detected landslide locations and their factors were identified and quantified by frequency-ratio and decision tree models. The relationships were used as factor ratings in the overlay analysis to create landslide susceptibility indices and maps. Then, the resulting landslide-susceptibility maps were validated using area-under-the-curve (AUC) analysis with the landslide area data that had not been used for training the model. The decision tree models using the CHAID and QUEST algorithms had accuracies of 81.56% and 80.91%, respectively, which were somewhat better than the results for the frequency-ratio model (80.15%). These results indicate that decision tree models using the CHAID and QUEST algorithms can be useful for landslide susceptibility analysis.

Landslide susceptibility mapping at Vaz Watershed (Iran) using an artificial neural network model: a comparison between multilayer perceptron (MLP) and radial basic function (RBF) algorithms

Landslide susceptibility and hazard assessments are the most important steps in landslide risk mapping. The main objective of this study was to investigate and compare the results of two artificial neural network (ANN) algorithms, i.e., multilayer perceptron (MLP) and radial basic function (RBF) for spatial prediction of landslide susceptibility in Vaz Watershed, Iran. At first, landslide locations were identified by aerial photographs and field surveys, and a total of 136 landside locations were constructed from various sources. Then the landslide inventory map was randomly split into a training dataset 70 % (95 landslide locations) for training the ANN model and the remaining 30 % (41 landslides locations) was used for validation purpose. Nine landslide conditioning factors such as slope, slope aspect, altitude, land use, lithology, distance from rivers, distance from roads, distance from faults, and rainfall were constructed in geographical information system. In this study, both MLP and RBF algorithms were used in artificial neural network model. The results showed that MLP with Broyden–Fletcher–Goldfarb–Shanno learning algorithm is more efficient than RBF in landslide susceptibility mapping for the study area. Finally the landslide susceptibility maps were validated using the validation data (i.e., 30 % landslide location data that was not used during the model construction) using area under the curve (AUC) method. The success rate curve showed that the area under the curve for RBF and MLP was 0.9085 (90.85 %) and 0.9193 (91.93 %) accuracy, respectively. Similarly, the validation result showed that the area under the curve for MLP and RBF models were 0.881 (88.1 %) and 0.8724 (87.24 %), respectively. The results of this study showed that landslide susceptibility mapping in the Vaz Watershed of Iran using the ANN approach is viable and can be used for land use planning.

Discussion on “Combining landslide susceptibility maps obtained from frequency ratio, logistic regression, and artificial neural network models using ASTER images and GIS” by Choi et al. (2012), Engineering Geology, 124, 12–23

The spatial prediction of landslide susceptibility is an important prerequisite for the analysis of landslide hazards and risks in any area. This research uses three data mining techniques, such as an adaptive neuro-fuzzy inference system combined with frequency ratio (ANFIS-FR), a generalized additive model (GAM), and a support vector machine (SVM), for landslide susceptibility mapping in Hanyuan County, China. In the first step, in accordance with a review of the previous literature, twelve conditioning factors, including slope aspect, altitude, slope angle, topographic wetness index (TWI), plan curvature, profile curvature, distance to rivers, distance to faults, distance to roads, land use, normalized difference vegetation index (NDVI), and lithology, were selected. In the second step, a collinearity test and correlation analysis between the conditioning factors and landslides were applied. In the third step, we used three advanced methods, namely, ANFIS-FR, GAM, and SVM, for landslide susceptibility modeling. Subsequently, the results of their accuracy were validated using a receiver operating characteristic curve. The results showed that all three models have good prediction capabilities, while the SVM model has the highest prediction rate of 0.875, followed by the ANFIS-FR and GAM models with prediction rates of 0.851 and 0.846, respectively. Thus, the landslide susceptibility maps produced in the study area can be applied for management of hazards and risks in landslide-prone Hanyuan County.

GIS-based spatial prediction of landslide susceptibility using logistic regression model

In the present study, logistic regression analysis has been used to create a landslide hazard map for Sajarood basin, Northern Iran. At first, an inventory map of 95 landslides was used to produce a dependent variable, a value of 0 for absence and 1 for presence of landslides. The effect of causative parameters on landslide occurrence was assessed by the corresponding coefficient that appears in the logistic regression function. The interpretation of the coefficients shows that the road network plays the major role in determining landslide occurrence. Elevation, slope curvature, rainfall and distance to fault were excluded from the final analysis, because these variables do not significantly add to the predictive power of the logistic regression. After running the final probability function into Arc/view 3.2 software, a landslide susceptibility map has been produced. The accuracy assessment shows an overall accuracy of the landslide susceptibility map to be 85.3%. An area of 53.01% is found to be located in a very low, 18.33% in low, 20.96% in moderate and 7.7% in high-risk regions. The proposed susceptibility map was tested using –2LL, Cox and Snell R 2, Nagelkerk R 2 and Roc procedure, and it is found to be very reliable.