Assessment of Forest Road Networks for Landslide Susceptibility

A comparative study of composite kernels for landslide susceptibility mapping: A case study in Yongxin County, China

Landslide risk prevention requires the delineation of landslide-prone areas as accurately as possible. Therefore, selecting a method or a technique that is capable of providing the highest landslide prediction capability is highly important. The main objective of this study is to assess and compare the prediction capability of advanced machine learning methods for landslide susceptibility mapping in the Mila Basin (Algeria). First, a geospatial database was constructed from various sources. The database contains 1156 landslide polygons and 16 conditioning factors (altitude, slope, aspect, topographic wetness index (TWI), landforms, rainfall, lithology, stratigraphy, soil type, soil texture, landuse, depth to bedrock, bulk density, distance to faults, distance to hydrographic network, and distance to road networks). Subsequently, the database was randomly resampled into training sets and validation sets using 5 times repeated 10 k-folds cross-validations. Using the training and validation sets, five landslide susceptibility models were constructed, assessed, and compared using Random Forest (RF), Gradient Boosting Machine (GBM), Logistic Regression (LR), Artificial Neural Network (NNET), and Support Vector Machine (SVM). The prediction capability of the five landslide models was assessed and compared using the receiver operating characteristic (ROC) curve, the area under the ROC curves (AUC), overall accuracy (Acc), and kappa index. Additionally, Wilcoxon signed-rank tests were performed to confirm statistical significance in the differences among the five machine learning models employed in this study. The result showed that the GBM model has the highest prediction capability (AUC = 0.8967), followed by the RF model (AUC = 0.8957), the NNET model (AUC = 0.8882), the SVM model (AUC = 0.8818), and the LR model (AUC = 0.8575). Therefore, we concluded that GBM and RF are the most suitable for this study area and should be used to produce landslide susceptibility maps. These maps as a technical framework are used to develop countermeasures and regulatory policies to minimize landslide damages in the Mila Basin. This research demonstrated the benefit of selecting the best-advanced machine learning method for landslide susceptibility assessment.

A comprehensive landslide inventory and susceptibility maps are prerequisite for developing and implementing landslide mitigation strategies. Landslide susceptibility maps for the landslides prone regions in northern Pakistan are rarely available. The Hunza-Nagar valley in northern Pakistan is known for its frequent and devastating landslides. In this paper, we have developed a landslide inventory map for Hunza-Nagar valley by using the visual interpretation of the SPOT-5 satellite imagery and mapped a total of 172 landslides. The landslide inventory was subsequently divided into modelling and validation data sets. For the development of landslide susceptibility map seven discrete landslide causative factors were correlated with the landslide inventory map using weight of evidence and frequency ratio statistical models. Four different models of conditional independence were used for the selection of landslide causative factors. The produced landslides susceptibility maps were validated by the success rate and area under curves criteria. The prediction power of the models was also validated with the prediction rate curve. The validation results shows that the success rate curves of the weight of evidence and the frequency models are 82% and 79%, respectively. The prediction accuracy results obtained from this study are 84% for weight of evidence model and 80% for the frequency ratio model. Finally, the landslide susceptibility index maps were classified into five different varying susceptibility zones. The validation and prediction result indicates that the weight of evidence and frequency ratio model are reliable to produce an accurate landslide susceptibility map, which may be helpful for landslides management strategies.

Review on landslide susceptibility mapping using support vector machines

Landslides in Slovakia are followed by great economic loss and threat to human life. Therefore, implementation of landslides susceptibility models is essential in urban planning. The main purpose of this study is to investigate the possible applicability of Support Vector Machines (SVMs) in landslides susceptibility prediction. We have built a classification problem with two classes, landslides and stable areas, and applied SVMs algorithms in the districts Bytca, Kysucke Nove Mesto and Žilina. A spatial database of landslides areas and geologically stable areas from the State Geological Institute of Dionýz Stur were used to fit SVMs models. Four environmental input parameters, land use, lithology, aspect and slope were used to train support vector machines models. During the training phase, the primal objective was to find optimal sets of kernel parameters by grid search. The linear, polynomial and radial basis function kernels were computed. Together 534 models were trained and tested with LIBLINEAR and LIBSVM libraries. Models were evaluated by Accuracy parameter. Then the Receiver Operating Characteristic (ROC) and landslides susceptibility maps were produced for the best model for every kernel. The best predictive performance was gained by radial basis function kernel. This kernel has also the best generalization ability. The results showed that SVMs employed in the presented study gave promising results with more than 0.90 (the area under the ROC curve (AUC) prediction performance.

The main goal of this study is to produce a landslide susceptibility map in the Wanzhou section of the Three Gorges reservoir area (China) with a weighted gradient boosting decision tree (weighted GBDT) model. According to the current research on landslide susceptibility mapping (LSM), the GBDT method is rarely used in LSM. Furthermore, previous studies have rarely considered the imbalance of landslide samples and simply regarded the LSM problem as a binary classification problem. In this paper, we considered LSM as an imbalanced learning problem and obtained a better predictive model using the weighted GBDT method. The innovations of the article mainly include the following two points: introducing the GBDT model into the evaluation of landslide susceptibility; using the weighted GBDT method to deal with the problem of landslide sample imbalance. The logistic regression (LR) model and gradient boosting decision tree (GBDT) model were also used in the study to compare with the weighted GBDT model. Five kinds of data from different data source were used in the study: geology, topography, hydrology, land cover, and triggered factors (rainfall, earthquake, land use, etc.). Twenty nine environmental parameters and 233 landslides were used as input data. The receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC) value, and the recall value were used to estimate the quality of the weighted GBDT model, the GBDT model, and the LR model. The results showed that the GBDT model and the weighted GBDT model had a higher AUC value (0.977, 0.976) than the LR model (0.845); the weighted GBDT model had a little higher AUC value (0.977) than the GBDT model (0.976); and the weighted GBDT model had a higher recall value (0.823) than the GBDT model (0.426) and the LR model (0.004). The weighted GBDT method could be considered to have the best performance considering the AUC value and the recall value in landslide susceptibility mapping dealing with imbalanced landslide data.

Landslides are dangerous events that threaten both human life and property. This research presents a case study of Kaghan valley catchment, which is an area of frequent landslide activity. We aim to present a comparison between the bivariate Landslide Numerical Risk Factor (LNRF), Statistical Index (SI) and Information Value (InfV) statistical models to evaluate landslide susceptibility. A total of 1556 landslides were identified using earlier reports, field surveys, and GOOGLE Earth imagery. The abundance of landslides is primarily controlled by acute deformation caused by a major thrust fault system and proximity to Hazara Kashmir Syntaxis (HKS). A landslide inventory was randomly partitioned into two datasets. 70% (1106) of landslides were used as a training phase of the models, whereas 30% (450) as validation of the three models. A spatial database of 11 conditioning factors was produced consisting of slope, aspect, elevation, lithology, land use, Topographic Wetness Index (TWI), rainfall, Stream Power Index (SPI), distance to faults, rivers and streams. All the landslide susceptibility assessment parameters were obtained from different sources and different landslide susceptibility maps were prepared on the GIS software. Performance of the three models was validated through the Receiver operator Characteristics (ROC) through success and prediction rate curves. Results show that the area under the ROC curve (AUC) for InfV, LNRF and SI models are 70.95, 83.99 and 67.56 for success rate curves and 70.75, 83.99 and 67.85 for prediction rate curves, respectively. LNRF having the highest AUC value proved to be superior for generating regional scale landslide susceptibility maps.

The quality of “non-landslide’ samples data impacts the accuracy of geological hazard risk assessment. This research proposed a method to improve the performance of support vector machine (SVM) by perfecting the quality of ‘non-landslide’ samples in the landslide susceptibility evaluation model through fuzzy c-means (FCM) cluster to generate more reliable susceptibility maps. Firstly, three sample selection scenarios for ‘non-landslide’ samples include the following principles: 1) select randomly from low-slope areas (scenario-SS), 2) select randomly from areas with no hazards (scenario-RS), 3) obtain samples from the optimal FCM model (scenario-FCM), and then three sample scenarios are constructed with 10,193 landslide positive samples. Next, we have compared and evaluated the performance of three sample scenarios in the SVM models based on the statistical indicators such as the proportion of disaster points, density of disaster points precision, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC). Finally, The evaluation results show that the ‘non-landslide’ negative samples based on the FCM model are more reasonable. Furthermore, the hybrid method supported by SVM and FCM models exhibits the highest prediction efficiency. Scenario FCM produces an overall accuracy of approximately 89.7% (AUC), followed by scenario-SS (86.7%) and scenario-RS (85.6%).

Landslides are prevalent in the Western Ghats, and the incidences that happened in 2021 in the Koottickal area of the Kottayam district (Western Ghats) resulted in the loss of 10 lives. The objectives of this study are to assess the landslide susceptibility of the high-range local self-governments (LSGs) in the Kottayam district using the analytical hierarchy process (AHP) and fuzzy-AHP (F-AHP) models and to compare the performance of existing landslide susceptible maps. This area never witnessed any massive landslides of this dimension, which warrants the necessity of relooking into the existing landslide-susceptible models. For AHP and F-AHP modeling, ten conditioning factors were selected: slope, soil texture, land use/land cover (LULC), geomorphology, road buffer, lithology, and satellite image-derived indices such as the normalized difference road landslide index (NDRLI), the normalized difference water index (NDWI), the normalized burn ratio (NBR), and the soil-adjusted vegetation index (SAVI). The landslide-susceptible zones were categorized into three: low, moderate, and high. The validation of the maps created using the receiver operating characteristic (ROC) technique ascertained the performances of the AHP, F-AHP, and TISSA maps as excellent, with an area under the ROC curve (AUC) value above 0.80, and the NCESS map as acceptable, with an AUC value above 0.70. Though the difference is negligible, the map prepared using the TISSA model has better performance (AUC = 0.889) than the F-AHP (AUC = 0.872), AHP (AUC = 0.867), and NCESS (AUC = 0.789) models. The validation of maps employing other matrices such as accuracy, mean absolute error (MAE), and root mean square error (RMSE) also confirmed that the TISSA model (0.869, 0.226, and 0.122, respectively) has better performance, followed by the F-AHP (0.856, 0.243, and 0.147, respectively), AHP (0.855, 0.249, and 0.159, respectively), and NCESS (0.770, 0.309, and 0.177, respectively) models. The most landslide-inducing factors in this area that were identified through this study are slope, soil texture, LULC, geomorphology, and NDRLI. Koottickal, Poonjar-Thekkekara, Moonnilavu, Thalanad, and Koruthodu are the LSGs that are highly susceptible to landslides. The identification of landslide-susceptible areas using diversified techniques will aid decision-makers in identifying critical infrastructure at risk and alternate routes for emergency evacuation of people to safer terrain during an exigency.

A hybrid model considering spatial heterogeneity for landslide susceptibility mapping in Zhejiang Province, China

The objective of this study was to investigate whether computed tomography texture analysis can be used to differentiate papillary renal cell carcinoma (PRCC) subtypes. Sixty-two PRCC tumors were retrospectively evaluated, with 30 type 1 tumors and 32 type 2 tumors. Texture parameters quantified from three-phase contrast-enhanced CT images were compared with least absolute shrinkage and selection operator (LASSO) regression. Receiver operating characteristic (ROC) analysis was performed, and the area under the ROC curve (AUC) was calculated for each parameter. The selected texture parameters of each phase were used to generate support vector machine (SVM) classifiers. Decision curve analysis (DCA) of the classification was performed. The two texture parameters with the top two AUC values were - 333-7 Correlation (AUC = 0.772) and 45-7 Entropy (AUC = 0.753) in the corticomedullary phase, 333-4 Correlation (AUC = 0.832) and 45-7 Entropy (AUC = 0.841) in the nephrographic phase, and 135-7 Entropy (AUC = 0.858) and - 333-1 InformationMeasureCorr2 (AUC = 0.849) in the excretory phase. Entropy and Correlation have a high correlation with the two types of PRCC and are increased in type 2 PRCC. A model incorporating the texture parameters with the top two AUC values in each phase produced an AUC of 0.922 with an accuracy of 84% (sensitivity = 89% and specificity = 80%). The nephrographic-phase model and the model combining the texture parameters of the three phases can differentiate the two types with the largest net benefit. Computed tomography texture analysis can be used to distinguish type 2 PRCC from type 1 with high accuracy, which may be clinically important.

Earthquakes cause a huge number of landslides and alter the regional landslide risk distribution. As a result, after a significant earthquake, the landslide susceptibility maps (LSMs) must be updated. The study goal was to create seismic landslide susceptibility maps containing landslide causative variables which are adaptable to great changes in susceptibility after the Jiuzhaigou earthquake (MS 7.0) and to perform a rapid update of the LSM after the earthquake by means of the distributed scatterer interferometric synthetic aperture radar (DS-InSAR) technique. We selected the territory of Jiuzhaigou County (southwestern China) as the study region. Jiuzhaigou is a world-renowned natural heritage and tourist area of great human and ecological value. For landslide susceptibility mapping, we examined the applicability of three models (logistic regression, support vector machine, and random forest) for landslide susceptibility mapping and offered a strategy for updating seismic landslide susceptibility maps using DS-InSAR. First, using logistic regression, support vector machine, and random forest techniques, susceptibility models of seismic landslides were built for Jiuzhaigou based on twelve contributing variables. Second, we obtained the best model parameters by means of a Bayesian network and network search, while using five-fold cross-validation to validate the optimized model. According to the receiver operating characteristic curve (ROC), the SVM model and RF model had excellent prediction capability and strong robustness over large areas compared with the LR models. Third, the surface deformation in Jiuzhaigou was calculated using DS-InSAR technology, and the deformation data were adopted to update the landslide susceptibility model using the correction matrix. The correction of deformation data resulted in a susceptibility class transition in 4.87 percent of the research region. According to practical examples, this method of correcting LSMs for the continuous monitoring of surface deformation (DS-InSAR) was effective. Finally, we analyze the reasons for the change in the revised LSM and point out the help of ecological restoration in reducing landslide susceptibility. The results show that the integration of InSAR continuous monitoring not only improved the performance of the LSM model but also adapted it to track the evolution of future landslide susceptibility, including seismic and human activities.

An expert-based landslide susceptibility mapping (LSM) module developed for Netcad Architect Software

This paper assesses the potentiality of certainty factor models (CF) for the best suitable causative factors extraction for landslide susceptibility mapping in the Sado Island, Niigata Prefecture, Japan. To test the applicability of CF, a landslide inventory map provided by National Research Institute for Earth Science and Disaster Prevention (NIED) was split into two subsets: (i) 70% of the landslides in the inventory to be used for building the CF based model; (ii) 30% of the landslides to be used for the validation purpose. A spatial database with fifteen landslide causative factors was then constructed by processing ALOS satellite images, aerial photos, topographical and geological maps. CF model was then applied to select the best subset from the fifteen factors. Using all fifteen factors and the best subset factors, landslide susceptibility maps were produced using statistical index (SI) and logistic regression (LR) models. The susceptibility maps were validated and compared using landslide locations in the validation data. The prediction performance of two susceptibility maps was estimated using the Receiver Operating Characteristics (ROC). The result shows that the area under the ROC curve (AUC) for the LR model (AUC = 0.817) is slightly higher than those obtained from the SI model (AUC = 0.801). Further, it is noted that the SI and LR models using the best subset outperform the models using the fifteen original factors. Therefore, we conclude that the optimized factor model using CF is more accurate in predicting landslide susceptibility and obtaining a more homogeneous classification map. Our findings acknowledge that in the mountainous regions suffering from data scarcity, it is possible to select key factors related to landslide occurrence based on the CF models in a GIS platform. Hence, the development of a scenario for future planning of risk mitigation is achieved in an efficient manner.

The Himalayan region and hilly areas face severe challenges due to landslide occurrences during the rainy seasons in India, and the study area, i.e., the Rudraprayag district, is no exception. However, the landslide related database and research are still inadequate in these landslide-prone areas. The main purpose of this study is: (1) to prepare the multi-temporal landslide inventory map using geospatial platforms in the data-scarce environment; (2) to evaluate the landslide susceptibility map using weights of evidence (WoE) method in the Geographical Information System (GIS) environment at the district level; and (3) to provide a comprehensive understanding of recent developments, gaps, and future directions related to landslide inventory, susceptibility mapping, and risk assessment in the Indian context. Firstly, 293 landslides polygon were manually digitized using the BHUVAN (Indian earth observation visualization) and Google Earth® from 2011 to 2013. Secondly, a total of 14 landslide causative factors viz. geology, geomorphology, soil type, soil depth, slope angle, slope aspect, relative relief, distance to faults, distance to thrusts, distance to lineaments, distance to streams, distance to roads, land use/cover, and altitude zones were selected based on the previous study. Then, the WoE method was applied to assign the weights for each class of causative factors to obtain a landslide susceptibility map. Afterward, the final landslide susceptibility map was divided into five susceptibility classes (very high, high, medium, low, and very low classes). Later, the validation of the landslide susceptibility map was checked against randomly selected landslides using IDRISI SELVA 17.0 software. Our study results show that medium to very high landslide susceptibilities had occurred in the non-forest areas, mainly scrubland, pastureland, and barren land. The results show that medium to very high landslide susceptibilities areas are in the upper catchment areas of the Mandakini river and adjacent to the National Highways (107 and 07). The results also show that landslide susceptibility is high in high relative relief areas and shallow soil, near thrusts and faults, and on southeast, south, and west-facing steep slopes. The WoE method achieved a prediction accuracy of 85.7%, indicating good accuracy of the model. Thus, this landslide susceptibility map could help the local governments in landslide hazard mitigation, land use planning, and landscape protection.