Resulting Susceptibility Maps Research Articles

Understanding the mechanism of gully erosion in the alpine region through an interpretable machine learning approach

In the alpine region, climate warming has led to the retreat of glaciers, snow cover, and permafrost. This has intensified water cycling, soil erosion, and increased the occurrence of natural disasters in the alpine region. This study investigated the Lhasa River Basin in the southern Tibetan Plateau, serving as a representative case study of a typical alpine basin, with a specific focus on gully erosion. Based on field investigations and interpretation using high-resolution satellite remote sensing images, the Random Forest (RF) algorithm was applied to evaluate gully erosion susceptibility on watershed level. The Shapley Additive Interpretation method was then used to interpret the RF model and gain deeper insights into the influencing variables of gully erosion. The results showed that the RF model achieved an area under the receiver operating characteristic (AUC) accuracy of 0.99 and 0.98 for the training and testing datasets, respectively, indicating an outstanding performance of the model. The resulting susceptibility map based on the RF model shows that areas with moderate and higher levels of gully erosion susceptibility are covering 50 % of the basin. The model interpretation results indicated that elevation, slope, permafrost, rainstorm, silt loam topsoil, human activity, stream power, and vegetation were the explaining variables with the highest importance for gully erosion occurrence. Different variables are characterized by specific thresholds promoting gully erosion such as: i) elevations higher than 4950 m, ii) slopes steeper than 13.5°, iii) extreme rainstorms longer than 11 days per year, iv) silt loam topsoil, v) presence of permafrost, vi) stream power index higher than 1.2, and vii) normalized difference vegetation index (NDVI) lower than 0.25. Our findings provide the scientific basis to improve soil erosion control in such highly vulnerable alpine area.

Comparing Frequency Ratio and Analytical Hierarchy Models for Landslide Susceptibility in the Dharan Sub-Metropolitan Region of Eastern Nepal

This study compares the application of Frequency Ratio (FR) (statistical/quantitative) and Analytical Hierarchy Process (AHP) (heuristic/semi-quantitative) for landslide susceptibility analysis in Dharan Sub-Metropolitan Region of eastern Nepal. Nine different thematic layers including slope, aspect, curvature, geology, land use, distance to roads, distance to thrusts, topographic position index (TPI), and distance to streams were used for analysis. A landslide inventory map was prepared by identifying the landslides in recent Google Earth images, and it was then verified by field observations. The resulting susceptibility map with different susceptibility levels was validated using the Area Under the Curve (AUC) method, and the resulting AUC values were determined to be 78% for FR and 76.8% for AHP. Both methods offer a reliable strategy for landslide susceptibility mapping with a good prediction rate. The FR model enclosed 41%, 31%, 20%, 7% and 1% of the area as very low, low, moderate, high, and very high susceptibility, respectively, whereas AHP showed 21%, 24%, 27%, 21% and 7% of the area for the respective susceptibility levels. The specific zones identified within the range from very low to very high susceptibility provide valuable insights for local authorities, planners, and decision-makers, allowing them to identify areas susceptible to landslides and implement mitigation measures to aid in targeted risk management efforts.

Uncertainty Reduction in Flood Susceptibility Mapping Using Random Forest and eXtreme Gradient Boosting Algorithms in Two Tropical Desert Cities, Shibam and Marib, Yemen

Flooding is a natural disaster that coexists with human beings and causes severe loss of life and property worldwide. Although numerous studies for flood susceptibility modelling have been introduced, a notable gap has been the overlooked or reduced consideration of the uncertainty in the accuracy of the produced maps. Challenges such as limited data, uncertainty due to confidence bounds, and the overfitting problem are critical areas for improving accurate models. We focus on the uncertainty in susceptibility mapping, mainly when there is a significant variation in the predictive relevance of the predictor factors. It is also noted that the receiver operating characteristic (ROC) curve may not accurately depict the sensitivity of the resulting susceptibility map to overfitting. Therefore, reducing the overfitting problem was targeted to increase accuracy and improve processing time in flood prediction. This study created a spatial repository to test the models, containing data from historical flooding and twelve topographic and geo-environmental flood conditioning variables. Then, we applied random forest (RF) and extreme gradient boosting (XGB) algorithms to map flood susceptibility, incorporating a variable drop-off in the empirical loop function. The results showed that the drop-off loop function was a crucial method to resolve the model uncertainty associated with the conditioning factors of the susceptibility modelling and methods. The results showed that approximately 8.42% to 9.89% of Marib City and 9.93% to 15.69% of Shibam City areas were highly vulnerable to floods. Furthermore, this study significantly contributes to worldwide endeavors focused on reducing the hazards linked to natural disasters. The approaches used in this study can offer valuable insights and strategies for reducing natural disaster risks, particularly in Yemen.

Landslide Susceptibility Mapping of Chaliyar River Basin by Multivariate Statistical Model

Landslides were frequently observed in nature that can result in significant property damage and fatalities. Land management in landslide-prone areas can be aided by preparing a landslide susceptibility map. The landslide susceptibility of Chaliyar river basin was evaluated using the logistic regression (LR) technique. For this, an inventory map of 592 prior landslides was created using Landsat 8 OLI satellite imagery. The inventory of landslides was then randomly split into 30% and 70% for model training and validation respectively. Fifteen landslide causative factors viz., Slope, Aspect, Curvature, Relative Relief, TWI, Distance to Road, Distance to Streams, Distance to Lineaments, Land Use Land Cover, Drainage Density, Road Density, Lineament Density, Geomorphology, Soil Texture, NDVI were considered for landslide susceptibility modelling. Utilising a Receiver Operating Characteristics Curve (ROC) and Area Under Curve (AUC) value, the resulting susceptibility maps were validated. Analysis reveals that the validation stage of the LR model had a ROC-AUC value of 0.815. The study also demonstrates that slope, soil texture and LULC play a substantial role on the occurrence of landslides in the study area. The proposed landslide susceptibility model is appropriate, taking into account the ROC-AUC (0.815), and can be applied to future land use planning and landslide mitigation in the Chaliyar basin.

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

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

Predisposing Factors for Shallow Landslides in Alpine and Hilly/Apennines Environments: A Case Study from Piemonte, Italy

Landslides are the most common natural hazard in the Piemonte region (northwestern Italy). This study is focused on shallow landslides caused by the sliding of the surficial detrital-colluvial cover caused by rainfall and characterized by a sudden and fast evolution. This study investigates shallow landslide events compared with variables considered as main predisposing qualitative factors (lithology, pedology and land use) to obtain a zonation of shallow landslide susceptibility in a GIS environment. Additionally, wildfire occurrence is also evaluated as a further predisposing factor for shallow landslide initiation. The resulting susceptibility map shows a strong correlation between the first three variables and shallow landslide occurrence, while it shows a negligible, or very localized, relationship with wildfire occurrence. Through the intersection of the predisposing factors with the landslide data points, a map of homogeneous zones is obtained; each identified zone is characterized by uniform lithological, soil-type, and land-use characteristics. The shallow landslide density occurrence is computed for each zone, resulting in a four-range susceptibility map. The resulting susceptibility zones can be used to define and evaluate the hazard linked to shallow landslide events for civil protection and regional planning purposes.

Exploring available landslide inventories for susceptibility analysis in Gipuzkoa province (Spain)

Similar to many mountainous regions of the world, landslides are a recurrent geological hazard in the Gipuzkoa province (northern Spain) that commonly cause damage to communication infrastructure, such as roads and railways. This geomorphological process also threatens buildings and human beings, albeit to a lesser degree. Over time, different institutions and academic research groups have individually collected crucial information on historic and ancient landslides in this region, resulting in various landslide inventories. However, these inventories have not been collectively assessed, and their suitability for landslide susceptibility modelling projects has often been assumed without comprehensive evaluation. In this study, we propose a simplified method to explore, describe, and compare the various landslide inventories in a specific study area to assess their suitability for landslide susceptibility modelling. Additionally, we present the results of an illustrative experiment that demonstrates the direct effect of using different inventories in landslide susceptibility modelling through a data-driven approach. We found that out of the five digitally available inventories in the study area, only three provide sufficient guarantees to be used as input data for susceptibility modelling. Furthermore, we observed that each individual inventory exhibited inherent biases, which directly influenced the resulting susceptibility map. We believe that our proposed methods can be easily replicated in other study areas where multiple landslide inventory sources exist, and that our work will induce other researchers to conduct preliminary assessments of their inventories as a critical step prior to any landslide susceptibility modelling project.

GIS-based landslide susceptibility mapping in the Longmen Mountain area (China) using three different machine learning algorithms and their comparison.

Landslides are a common natural disaster, having severe socio-economic effects and posing immense threat to safety, such as loss of life at a global scale. Modeling and predicting the possibility of landslides are important in order to monitor and prevent their negative consequences. In this study, landslides are the primary research object. Further, the frequency ratio (FR) method was applied to the random forest (RF), support vector machine (SVM), and decision tree (DT) regression algorithms for landslide sensitivity assessment. It was also applied to landslide risk assessment mapping in the Longmen Mountain area. Therefore, taking into account the positive and negative sample balance, 7774 historical landslide points and 7774 non-landslide points were selected and divided them into training sets and test sets. The influence factors were selected and analyzed through multicollinearity analysis and the FR method. To improve the performance of the model and the accuracy of the findings, the individual environmental factors are normalized. Subsequently, the LSI (landslide susceptibility index), was obtained by calculating the frequency ratio. Following this, the RF, SVM, and DT were used to construct the model. The trained model calculates the landslide probability of each cell in the study area and generates the resultant susceptibility map. The receiver operating characteristic (ROC) curve and R2 of this region were calculated to evaluate the model's performance. The results indicate that RF obtained the highest predictive performance (area under the curve (AUC) = 0.82) in landslide risk prediction, followed by SVM (AUC = 0.8) and DT (AUC = 0.69). The results of this study serve as a predictive map for landslide susceptibility areas and provide critical support for the security of lives and property for the human and socio-economic development in the Longmen Mountain region. In addition, the experiment results reveal that the machine learning model based on the FR method can improve the accuracy and performance of methods in studies related to landslide susceptibility. The method is equally applicable to research in other fields.

Landslide Susceptibility Assessment Using GIS-Based Weights-of-Evidence Model in the Khimti Khola Watershed, Eastern Nepal

The Khimti Khola watershed of the Eastern Nepal experiences numerous landslides each year, pose a significant natural hazard that can cause property damage and fatalities. In mountainous areas like Nepal, an accurate evaluation of landslide hazards may be an essential tool for disaster risk reduction and the strategic planning of development initiatives. To address this concern, a landslide susceptibility assessment was conducted in the Khimti Khola watershed, which covers an area of 440 km2. The purpose of this assessment is to locate areas that are susceptible to landslides and to provide light on the factors that affect them. A total of 415 landslides were identified, covering 1.715 km2 or 0.39% of the entire study area. The assessment derived the landslide susceptibility map using the Weights-of-Evidence (WoE) model from selected conditioning factor classes that were processed in ArcGIS and categorized into five classes: Very High, High, Moderate, Low, and Very Low. Each of these classes covers 7.12%, 16.63%, 25.23%, 30.24%, and 20.78% of the total study area, respectively. According to the findings, the Khimti Khola watershed has a 33.2% landslide occurrence percentage in the high susceptibility zone, out of the total area. Additionally, the very high, moderate, low, and very low susceptibility zones cover 24.35%, 20.75%, 17.08%, and 4.62% area of the landslide occurrence, respectively. In this assessment, the Area Under Curve (AUC) is used to validate the model and is plotted using ArcSDM. Identified a total of 415 landslides, out of which 311 (75%) were used as training sample for susceptibility mapping, while the remaining 104 (25%) were used to validate. The AUC for the landslide susceptibility map is 83%, indicating a very good degree of accuracy and satisfaction. The resulting susceptibility map provides information for predicting landslide-prone areas. It can be used to minimize the risk of potential landslides, safeguard lives, and prevent property damage. It will be a vital tool for disaster preparedness, future construction planning and development projects in this area.

Quantitative susceptibility mapping of the head-and-neck using SMURF fat-water imaging with chemical shift and relaxation rate corrections.

PurposeTo address the challenges posed by fat-water chemical shift artifacts and relaxation rate discrepancies to quantitative susceptibility mapping (QSM) outside the brain, and to generate accurate susceptibility maps of the head-and-neck at 3 and 7 Tesla.MethodsSimultaneous Multiple Resonance Frequency (SMURF) imaging was extended to 7 Tesla and used to acquire head-and-neck gradient echo images at both 3 and 7 Tesla. Separated fat and water images were corrected for Type 1 (displacement) and Type 2 (phase discrepancy) chemical shift artefacts, and for the bias resulting from differences in T1 and relaxation rates, recombined and used as the basis for QSM. A novel phase signal-based masking approach was used to generate head-and-neck masks.ResultsSMURF generated well-separated fat and water images of the head-and-neck. Corrections for chemical shift artefacts and relaxation rate differences removed overestimation of the susceptibility values, blurring in the susceptibility maps, and the disproportionate influence of fat in mixed voxels. The resulting susceptibility maps showed high correspondence between the paramagnetic areas and the locations of fatty tissues and the susceptibility estimates were similar to literature values. The proposed masking approach was shown to provide a simple means of generating head-and-neck masks.ConclusionCorrections for Type 1 and Type 2 chemical shift artefacts and for fat-water relaxation rate differences, mainly in T1, were shown to be required for accurate susceptibility mapping of fatty-body regions. SMURF made it possible to apply these corrections and generate high-quality susceptibility maps of the entire head-and-neck at both 3 and 7 Tesla.

Incorporating Landslide Spatial Information and Correlated Features among Conditioning Factors for Landslide Susceptibility Mapping

This study proposed a new hybrid model based on the convolutional neural network (CNN) for making effective use of historical datasets and producing a reliable landslide susceptibility map. The proposed model consists of two parts; one is the extraction of landslide spatial information using two-dimensional CNN and pixel windows, and the other is to capture the correlated features among the conditioning factors using one-dimensional convolutional operations. To evaluate the validity of the proposed model, two pure CNN models and the previously used methods of random forest and a support vector machine were selected as the benchmark models. A total of 621 earthquake-triggered landslides in Ludian County, China and 14 conditioning factors derived from the topography, geological, hydrological, geophysical, land use and land cover data were used to generate a geospatial dataset. The conditioning factors were then selected and analyzed by a multicollinearity analysis and the frequency ratio method. Finally, the trained model calculated the landslide probability of each pixel in the study area and produced the resultant susceptibility map. The results indicated that the hybrid model benefitted from the features extraction capability of the CNN and achieved high-performance results in terms of the area under the receiver operating characteristic curve (AUC) and statistical indices. Moreover, the proposed model had 6.2% and 3.7% more improvement than the two pure CNN models in terms of the AUC, respectively. Therefore, the proposed model is capable of accurately mapping landslide susceptibility and providing a promising method for hazard mitigation and land use planning. Additionally, it is recommended to be applied to other areas of the world.

Assessment of gully erosion on the territory of Tomsk using GIS technologies

Relevance and purpose of the work. Currently, the area of development of Tomsk is increasing. New neighborhoods are growing on previously undeveloped land (for example, on the left bank of the river Tom). The central part of the city is being redeveloped and reconstructed. It is impossible to develop a high-quality territory without taking into account the dynamics, mechanisms, factors and patterns of development of dangerous natural and technological processes, the forecast of their development. The purpose of the work is to establish the patterns of gully erosion, assess the intensity of its development, and predict the probability of its occurrence within the new city boundaries. Methods of research. We performed an assessment and forecast of the development of gully erosion in Tomsk using GIS technologies, which are an important tool in the city management process due to their ability to process and analyze multidimensional data about the geological environment. We compared the traditional model of data-driven frequency ratio (FR) and expert-based multi-criteria assessment, i.e. analytical hierarchical process by weighting of gulley conditioning factors. Results of the work. We constructed a map of the distribution of gullies on the territory of the city, including 23 polygons. These polygons were then randomly divided into training (16 polygons or 70%) and validation data (7 polygons or 30%). We used seven gulley-conditioning factors for the two models to produce gulley susceptibility maps: slope angle, slope aspect, curvature, elevation, geological structure of the territory; types of filtration sections; distance to the river, to analyze the spatial patterns that determine the development of gully erosion. The spatial correlation between gulley locations and the conditioning factors were identified using GIS-based statistical models. We constructed gulley susceptibility maps based on the ranking of each factor by two methods using a training data set. Receiver operating characteristics (ROC) were used to validate the resulting susceptibility maps. The area under the curve (AUC) was 0.905 for the AHP model and 0,800 for the FR model, respectively, which indicates excellent and high quality of forecast maps. We proved that both methods are beneficial for assessment the susceptibility of the territory to gully erosion. We recommend using the constructed maps for regional planning and hazard mitigation, as well as in education by teaching the discipline “Engineering geodynamics”.

Comparing methods of landslide data acquisition and susceptibility modelling: Examples from New Zealand

The acquisition of landslide inventory data remains an important challenge for landslide susceptibility modelling. For rainfall-induced landslides, comprehensive mapping may be hindered by the size of storm-affected areas and large number of landslides generated as well as the time and costs involved in preparing multi-temporal inventories. In New Zealand, storm events trigger hundreds to thousands of shallow landslides, causing significant damage to land and infrastructure as well as impacts on freshwater and marine environments. Despite this, there are few quantitative assessments of shallow landslide susceptibility to inform targeting of control measures. Here, we compare the effect of using landslide inventories assembled from a) manual versus semi-automated mapping and b) event versus multi-temporal records on the performance of two widely applied methods for landslide susceptibility modelling, namely logistic regression and random forest classification. Evaluation of object-based image analysis (OBIA) for semi-automated landslide mapping showed mixed results, where producer's and user's accuracies ranged 62–81 and 45–55%, respectively, without manual refinement. However, the relative reduction of 6–11% in susceptibility model predictive performance based on area under receiver operating characteristic curves (AUC) using OBIA (AUC = 0.63–0.75) versus manual (AUC = 0.67–0.81) inventories with different variable combinations was low in comparison, and the spatial patterns in modelled susceptibility were generally similar. The random forest model produced slightly better prediction performance compared with logistic regression based on cross-validation within the same study area. However, this was reversed and logistic regression mostly outperformed random forest when the models were fitted and tested with data from different study areas. Model predictive performance for event versus multi-temporal records was comparable. Our results highlight both the challenges associated with semi-automated landslide detection over large areas as well as the opportunity to use OBIA for efficient data collection without necessarily compromising the resulting susceptibility maps. This potentially overcomes significant time and cost impediments to the preparation of landslide inventories that continue to hinder quantitative landslide susceptibility assessment.

Improved flood susceptibility mapping using a best first decision tree integrated with ensemble learning techniques

Improving the accuracy of flood prediction and mapping is crucial for reducing damage resulting from flood events. In this study, we proposed and validated three ensemble models based on the Best First Decision Tree (BFT) and the Bagging (Bagging-BFT), Decorate (Bagging-BFT), and Random Subspace (RSS-BFT) ensemble learning techniques for an improved prediction of flood susceptibility in a spatially-explicit manner. A total number of 126 historical flood events from the Nghe An Province (Vietnam) were connected to a set of 10 flood influencing factors (slope, elevation, aspect, curvature, river density, distance from rivers, flow direction, geology, soil, and land use) for generating the training and validation datasets. The models were validated via several performance metrics that demonstrated the capability of all three ensemble models in elucidating the underlying pattern of flood occurrences within the research area and predicting the probability of future flood events. Based on the Area Under the receiver operating characteristic Curve (AUC), the ensemble Decorate-BFT model that achieved an AUC value of 0.989 was identified as the superior model over the RSS-BFT (AUC = 0.982) and Bagging-BFT (AUC = 0.967) models. A comparison between the performance of the models and the models previously reported in the literature confirmed that our ensemble models provided a reliable estimate of flood susceptibilities and their resulting susceptibility maps are trustful for flood early warning systems as well as development of mitigation plans.

Effect of using various weighting methods in a process of landslide susceptibility assessment

This study discusses the evaluation of the effect of using different weighting approaches in the process of landslide susceptibility assessment. Weighting process is needed, especially for landslide susceptibility assessment using bivariate statistical analysis, and can radically affect the resulting susceptibility map. The bivariate analysis belongs to a set of quantitative methods. The initial point for the bivariate analysis is selection and processing of input factors in the form of parametric maps, factors that play a dominant role in slope stability. The parametric maps were subsequently evaluated related to landslide inventory map. Another essential part of the bivariate analysis is the determination of the weight of the given input factors. Herein, four methods were applied to determine the weights of each class within reclassified input factors, as well as the total weight of the individual input factors. As a study area, the district of Kysucke Nove Mesto in Slovakia was chosen. Four prognostic maps were the result using entropy index, AHP method (AHP—analytic hierarchy process) (the input factors weighted as a whole), frequency ratio and landslide index (the weights were calculated for each class of input factor). Final landslide susceptibility maps were verified trough ROC curves (ROC—receiver operating characteristics). The accuracy of maps was ascertained by the size area (AUC—area under curve) under ROC curve. The highest accuracy was obtained for maps using weights calculated from the landslide index (88.5%) and the frequency ratio (88.4%).

Landslide susceptibility modelling using integrated evidential belief function based logistic regression method: A study from Southern Western Ghats, India

The present study aims to develop a spatially integrated evidential belief function based logistic regression model (EBF-LR) for landslide susceptibility mapping in a naturally sloping terrain of Southern Western Ghats in Kerala, India. For this, a landslide inventory map of 83 previous landslides was prepared using satellite imageries and verified in field check. Thereafter the landslide inventory was randomly divided into 70%–30% basis for model training and testing. Twelve landslide conditioning factors viz., lithology, land use/land cover, NDVI, slope angle, slope aspect, profile curvature, distance to stream, distance to roads, distance to lineaments, soil texture, topographic wetness index and average annual rainfall were considered for landslide susceptibility modelling. The resultant susceptibility maps were validated using receiver operating characteristics curve (ROC) with area under the curve (AUC) value, sensitivity, specificity, kappa index, mean absolute error (MAE) and root mean square error (RMSE). Analysis shows that the integrated EBF-LR model outweigh other conventional bivariate and multivariate approaches with a ROC-AUC value of 0.935, Kappa score 0.719, sensitivity 0.885, specificity 0.833 and least RMSE of 0.456 in the validation stage. The study also reveals that anthropogenic disturbances have a significant role on landslide initiation in the study area. Considering the ROC- AUC, MAE, RMSE and other validation measures, the accuracy of the proposed landslide susceptibility model is satisfactory and can be used for future land use planning and landslide mitigation in the study area.

A Probabilistic Assessment of Soil Erosion Susceptibility in a Head Catchment of the Jemma Basin, Ethiopian Highlands

Soil erosion represents one of the most important global issues with serious effects on agriculture and water quality, especially in developing countries, such as Ethiopia, where rapid population growth and climatic changes affect widely mountainous areas. The Meskay catchment is a head catchment of the Jemma Basin draining into the Blue Nile (Central Ethiopia) and is characterized by high relief energy. Thus, it is exposed to high degradation dynamics, especially in the lower parts of the catchment. In this study, we aim at the geomorphological assessment of soil erosion susceptibilities. First, a geomorphological map was generated based on remote sensing observations. In particular, we mapped three categories of landforms related to (i) sheet erosion, (ii) gully erosion, and (iii) badlands using a high-resolution digital elevation model (DEM). The map was validated by a detailed field survey. Subsequently, we used the three categories as dependent variables in a probabilistic modelling approach to derive the spatial distribution of the specific process susceptibilities. In this study we applied the maximum entropy model (MaxEnt). The independent variables were derived from a set of spatial attributes describing the lithology, terrain, and land cover based on remote sensing data and DEMs. As a result, we produced three separate susceptibility maps for sheet and gully erosion as well as badlands. The resulting susceptibility maps showed good to excellent prediction performance. Moreover, to explore the mutual overlap of the three susceptibility maps, we generated a combined map as a color composite where each color represents one component of water erosion. The latter map yields useful information for land-use managers and planning purposes.

Performance Evaluation of Machine Learning Methods for Forest Fire Modeling and Prediction

Predicting and mapping fire susceptibility is a top research priority in fire-prone forests worldwide. This study evaluates the abilities of the Bayes Network (BN), Naïve Bayes (NB), Decision Tree (DT), and Multivariate Logistic Regression (MLP) machine learning methods for the prediction and mapping fire susceptibility across the Pu Mat National Park, Nghe An Province, Vietnam. The modeling methodology was formulated based on processing the information from the 57 historical fires and a set of nine spatially explicit explanatory variables, namely elevation, slope degree, aspect, average annual temperate, drought index, river density, land cover, and distance from roads and residential areas. Using the area under the receiver operating characteristic curve (AUC) and seven other performance metrics, the models were validated in terms of their abilities to elucidate the general fire behaviors in the Pu Mat National Park and to predict future fires. Despite a few differences between the AUC values, the BN model with an AUC value of 0.96 was dominant over the other models in predicting future fires. The second best was the DT model (AUC = 0.94), followed by the NB (AUC = 0.939), and MLR (AUC = 0.937) models. Our robust analysis demonstrated that these models are sufficiently robust in response to the training and validation datasets change. Further, the results revealed that moderate to high levels of fire susceptibilities are associated with ~19% of the Pu Mat National Park where human activities are numerous. This study and the resultant susceptibility maps provide a basis for developing more efficient fire-fighting strategies and reorganizing policies in favor of sustainable management of forest resources.

Novel Ensemble Landslide Predictive Models Based on the Hyperpipes Algorithm: A Case Study in the Nam Dam Commune, Vietnam

Development of landslide predictive models with strong prediction power has become a major focus of many researchers. This study describes the first application of the Hyperpipes (HP) algorithm for the development of the five novel ensemble models that combine the HP algorithm and the AdaBoost (AB), Bagging (B), Dagging, Decorate, and Real AdaBoost (RAB) ensemble techniques for mapping the spatial variability of landslide susceptibility in the Nam Dan commune, Ha Giang province, Vietnam. Information on 76 historical landslides and ten geo-environmental factors (slope degree, slope aspect, elevation, topographic wetness index, curvature, weathering crust, geology, river density, fault density, and distance from roads) were used for the construction of the training and validation datasets that are the prerequisites for building and testing the proposed models. Using different performance metrics (i.e., the area under the receiver operating characteristic curve (AUC), negative predictive value, positive predictive value, accuracy, sensitivity, specificity, root mean square error, and Kappa), we verified the proficiency of all five ensemble learning techniques in increasing the fitness and predictive powers of the base HP model. Based on the AUC values derived from the models, the ensemble ABHP model that yielded an AUC value of 0.922 was identified as the most efficient model for mapping the landslide susceptibility in the Nam Dan commune, followed by RABHP (AUC = 0.919), BHP (AUC = 0.909), Dagging-HP (AUC = 0.897), Decorate-HP (AUC = 0.865), and the single HP model (AUC = 0.856), respectively. The novel ensemble models proposed for the Nam Dan commune and the resultant susceptibility maps can aid land-use planners in the development of efficient mitigation strategies in response to destructive landslides.

Assessment of landslide susceptibility at a local spatial scale applying the multi-criteria analysis and GIS: a case study from Slovakia

Landslide susceptibility is an important topic mainly because its geo-spatial analysis provides a useful tool for planning, disaster management and hazard mitigation. In this study, the aim is to identify and analyze landslide susceptibility at a local spatial scale, which is represented by the town of Handlová, using the multi-criteria evaluation (i.e., the analytical hierarchy process technique – AHP) and geographic information systems (GIS). The following landslide conditioning factors were selected representing the local terrain predispositions: slope angle, geology, slope aspect, elevation, distance from rivers, distance from faults and land use. The raster-based analysis was performed using the spatial resolution of 10 × 10 m. The weights for each factor were determined by the AHP technique where slope angle had the highest relative importance. Based on the resulting susceptibility map, 51.98% out of the total study area is characterized by high and very high susceptibility class. The Atlas of Slope Stability of the Slovak Republic, which contains past landslides until 2006, was used for verification of the results. The verification confirmed a moderate accuracy between the landslide susceptibility map and landslide inventory from the atlas since 60.8% of all landslide areas from the atlas corresponded with high and very high susceptibility class.