Search

The quantitative spatial analysis is a strong tool for the study of natural hazards and their interactions. Over the last decades, a range of techniques have been exceedingly used in spatial analysis, especially applying GIS and R software. In the present paper, the multi-hazard susceptibility maps compared in 2020 and 2021 using an array of data mining techniques, GIS tools, and Unmanned aerial vehicles. The produced maps imply the most effective morphometric parameters on collapsed pipes, gully heads, and landslides using the linear regression model. The multi-hazard maps prepared using seven classifiers of Boosted regression tree (BRT), Flexible discriminant analysis (FDA), Multivariate adaptive regression spline (MARS), Mixture discriminant analysis (MDA), Random forest (RF), Generalized linear model (GLM), and Support vector machine (SVM). The results of each model revealed that the greatest percentage of the study region was low susceptible to collapsed pipes, landslides, and gully heads, respectively. The results of the multi-hazard models represented that 52.22% and 48.18% of the study region were not susceptible to any hazards in 2020 and 2021, while 6.19% (2020) and 7.39% (2021) of the region were at the risk of all compound events. The validation results indicate the area under the receiver operating characteristic curve of all applied models was more than 0.70 for the landform susceptibility maps in 2020 and 2021. It was found where multiple events co-exist, what their potential interrelated effects are or how they interact jointly. It is the direction to take in the future to determine the combined effect of multi-hazards so that policymakers can have a better attitude toward sustainable management of environmental landscapes and support socio-economic development., (© 2022. The Author(s).)

Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. 2Maps of factors used for hazards mapping in this study The original article has been corrected. [Extracted from the article]

Protection against natural hazards (i.e., floods, landslides, forest fires, and earthquakes) is vital in land-use planning, especially in high-risk areas. Multi-hazard susceptibility maps can be used by land-use manager to guide urban development, to minimize the risk of natural disasters. The objective of the present study was to use four machine learning models to produce multi-hazard susceptibility maps in Khuzestan Province, Iran. In this work, four different natural hazards (flood, landslides, forest fire, and earthquake) using support vector machine (SVM), boosted regression tree (BRT), random forest (RF), and maximum entropy (MaxEnt) techniques were created. Effective factors used in the study include elevation, slope degree, slope aspect, rainfall, temperature, lithology, land use, normalized difference vegetation index (NDVI), wind exposition index (WEI), topographic wetness index (TWI), plan curvature, drainage density, distance from roads, distance from rivers, and distance from villages. The spatial earthquake hazard in the study area was derived from a peak ground acceleration (PGA) susceptibility map. The second step in the study was to combine the model-generated maps of the four hazards in a reliable multi-hazard map. The mean decrease Gini (MDG) method was used to determine the level of importance of each effective factor on the occurrence of landslides, floods, and forest fires. Finally, "area under the curve" (AUC) values were calculated to validate the forest fire, flood, and landslide susceptibility maps and to compare the predictive capability of the machine learning models. The RF model yielded the highest AUC values for the forest fire, flood, and landslide susceptibility maps, specifically, 0.81, 0.85, and 0.94, respectively. [ABSTRACT FROM AUTHOR]

Floods are among the most devastating environmental hazards that directly and indirectly affect people's lives and activities. In many countries, sustainable environmental management requires the assessment of floods and the likely flood-prone areas to avoid potential hazards. In this study, the performance and capabilities of seven machine learning algorithms (MLAs) for flood susceptibility mapping were tested, evaluated, and compared. These MLAs, including support vector machine (SVM), random forest (RF), multivariate adaptive regression spline (MARS), boosted regression tree (BRT), functional data analysis (FDA), general linear model (GLM), and multivariate discriminant analysis (MDA), were tested for the area between Safaga and Ras Gharib cities, Red Sea, Egypt. A geospatial database was developed with eleven flood-related factors, namely altitude, slope aspect, lithology, land use/land cover (LULC), slope length (LS), topographic wetness index (TWI), slope angle, profile curvature, plan curvature, stream power index (SPI), and hydrolithology units. In addition, 420 actual flooded areas were recorded from the study area to create a flood inventory map. The inventory data were randomly divided into training group with 70% and validation group with 30%. The flood-related factors were tested with a multicollinearity test, the variance inflation factor (VIF) was less than 2.135, the tolerance (TOL) was more than 0.468, and their importance was evaluated with a partial least squares (PLS) method. The results show that RF performed the best with the highest AUC (area under curve) value of 0.813, followed by GLM with 0.802, MARS with 0.801, BRT with 0.777, MDA with 0.768%, FDA with 0.763, and SVM with 0.733. The results of this study and the flood susceptibility maps could be useful for environmental mitigation, future development activities in the area, and flood control areas. [ABSTRACT FROM AUTHOR]

Landslides is one of the most important natural disasters that cause excessive human and financial losses in mountain areas worldwide. There are appropriate methodologies for assessing risk and determining the effective risk factors associated with them. In this study, the maximum entropy by three replications was applied in Maxent software to investigate landslide susceptibility in the southern areas of Iran, Fars Province. To prepare the landslide susceptibility map, 13 factors were used: lithological units (Lu), land use/land cover (LULC), slope percentage (SP), slope aspect (SA), altitude, plan curvature (Plan-C), topographic wetness index (TWI), distance to river (DTR), distance to roads (DTRS), distance to fault (DTF), drainage density (DD), normalized difference vegetation index (NDVI), and annual mean rainfall (AMR). After proving the lack of multicollinearity among the effective factors using tolerance (TOL) and variance inflation factor (VIF) indicators. On the other hand, the weighting of these 13 factors was determined using the AHP model. The results of the AHP method show that "Litho logical units, Land use-cover and Slope percentage" are the most important influencing factor the occurrence of landslides in the study area. In real, three affecting factors ranked first to third in order of importance in the study area. Some of the landslide points were used for evaluate the built model according to the ROC/AUC indicator, in the other word, since 30% of the landslide points not used in modeling were randomly selected and used for evaluation. In addition, the final map of the landslide susceptibility by three replications had a good accuracy, whereas the third iteration with an AUC value of 0.778 (ROC=77.8%) had the highest accuracy in preparing the landslide susceptibility map. After that, the evaluation of landslide susceptibility maps with the second and third iterations with AUC values of 0.77 (ROC=77%) and 0.640 (ROC= 64%), respectively, had good and moderate accuracy with the highest efficiency in predicting landslide sensitivity. Finally, the highest percentage of landslide susceptibility area according to the first, second and third repetitions respectively in the moderate sensitivity class (0.03-0.1) with the value of 26.14%, the moderate sensitivity class (0.04-0.4). With a value of 25.91% and also in the moderate sensitivity class (0.04-0.1), there was the highest percentage of landslide area with a value of 25.71%. In general, landslides, due to their dangerous nature in the highlands, suddenly disrupt the morphology and cause major damage to residential areas, roads, agricultural lands, etc. Therefore, landslides are a complex process that has a devastating effect on the environment and human life and requires investigation and preventive measures. [ABSTRACT FROM AUTHOR]

Considering the large number of natural disasters on the planet, many areas in the world are at risk of these hazards; therefore, providing an integrated map as a guide map for multiple natural hazards can be applied to save human lives and reduce financial losses. This study designed a multi-hazard map for three important hazards (earthquakes, floods, and landslides) to identify endangered areas in Kermanshah province located in western Iran using ensemble SWARA-ANFIS-PSO and SWARA-ANFIS-GWO models. In the first step, flood and landslide inventory maps were generated to identify at-risk areas. Then, the occurrence places for each hazard were divided into two groups for training susceptibility models (70%) and testing the models applied (30%). Factors affecting these hazards, including altitude, slope aspect, slope degree, plan curvature, distance to rivers, distance to roads, distance to the faults, rainfall, lithology, and land use, were used to generate susceptibility maps. The SWARA method was used to weigh the subclasses of the influencing factors in floods and landslides. In addition, a peak ground acceleration (PGA) map was generated to investigate earthquakes in the study area. In the next step, the ANFIS machine learning algorithm was used in combination with PSO and GWO meta-heuristic algorithms to train the data, and SWARA-ANFIS-PSO and SWARA-ANFIS-GWO susceptibility maps were separately generated for flood and landslide hazards. The predictive ability of the implemented models was validated using the receiver operating characteristics (ROC), root mean square error (RMSE), and mean square error (MSE) methods. The results showed that the SWARA-ANFIS-PSO ensemble model had the best performance in generating flood susceptibility maps with ROC = 0.936, RMS = 0.346, and MSE = 0.120. Furthermore, this model showed excellent results (ROC = 0.894, RMS = 0.410, and MSE = 0.168) for generating a landslide map. Finally, the best maps and PGA map were combined, and a multi-hazard map (MHM) was obtained for Kermanshah Province. This map can be used by managers and planners as a practical guide for sustainable development. [ABSTRACT FROM AUTHOR]

Considering the slope units as our reference mapping units, three statistical models [frequency ratio (FR), index of entropy (IOE), and evidential belief function (EBF)] are used in combination by two methods [normalized spatial-correlated scale index (NSCI) and weighted calibrated landslide potential model (WCLPM)]. For this aim, ten conditioning factors correlated with landslide namely, altitude, slope angle, slope aspect, relief amplitude, cutting depth, gully density, surface roughness, distance to roads, rainfall, and lithology are considered. The performance of the models is tested using the area under the receiver operating characteristic (ROC) curve (AUC) and several statistical evaluation measures. The weighted calibrated landslide potential index (WCLPI)-based FR model has the highest predictive capability, followed by the calibrated landslide potential index (CLPI)-based FR, the WCLPI-EBF, the CLPI-EBF, the WCLPI-IOE, the CLPI-IOE, the FR, the EBF, and the IOE models, respectively. Results indicated that hybrid models have improved significantly the performance of single models. This highlights that NSCI and WCLPM hybrid techniques are promising methods for landslide susceptibility assessment. [ABSTRACT FROM AUTHOR]

Landslide is one of the most widely distributed surface morphological landscapes, and it can cause a series of major economic and human losses. Field monitoring and limit equilibrium methods were applied to investigate Baota Mountain landslide stability, and soil volumetric water content, different scales of rainfall data, and landslide displacements were monitored using various equipment. The theoretical factor of safety was also calculated for the landslide. Finally, the theoretical results were validated by monitoring data in the field. The results demonstrate that soil volumetric water content experienced the greatest change with time at a depth of 0.2 m and then 1 m; however, the change in soil volumetric water content was relatively small with time at a soil depth ranging from 2.0 m to 4.0 m. Soil volumetric water content also did not change with time at a soil depth of 5.0 m and below. In addition, the retardation effect was found in different depths of volumetric water content for continuous rainfall. The safety factors were 2.713 and 1.133 for landslide No. 1 and landslide No. 2, respectively. These results indicate that landslide No. 1 is relatively stable, but there is a probability of the occurrence of movement in landslide No. 2. The monitoring displacement data indicate that landslide No.1 was in a relatively stable state between 2008 and 2013, and this result was in accordance with the value of theoretical calculation. This study provided relevant parameters for numerical simulation of landslides in loess areas. [ABSTRACT FROM AUTHOR]

This study sought to produce an accurate multi-hazard risk map for a mountainous region of Iran. The study area is in southwestern Iran. The region has experienced numerous extreme natural events in recent decades. This study models the probabilities of snow avalanches, landslides, wildfires, land subsidence, and floods using machine learning models that include support vector machine (SVM), boosted regression tree (BRT), and generalized linear model (GLM). Climatic, topographic, geological, social, and morphological factors were the main input variables used. The data were obtained from several sources. The accuracies of GLM, SVM, and functional discriminant analysis (FDA) models indicate that SVM is the most accurate for predicting landslides, land subsidence, and flood hazards in the study area. GLM is the best algorithm for wildfire mapping, and FDA is the most accurate model for predicting snow avalanche risk. The values of AUC (area under curve) for all five hazards using the best models are greater than 0.8, demonstrating that the model's predictive abilities are acceptable. A machine learning approach can prove to be very useful tool for hazard management and disaster mitigation, particularly for multi-hazard modeling. The predictive maps produce valuable baselines for risk management in the study area, providing evidence to manage future human interaction with hazards. [ABSTRACT FROM AUTHOR]

The main objective of this study to produce landslide susceptibility zones using maximum entropy (MaxEnt) and support vector machine (SVM) data-driven models along the Tipari to Ghuttu highway corridors in the Garhwal Himalaya. A landslide inventory has been prepared through field surveys and LISS-IV and Landsat 8 satellite images. The datasets of 85 landslides were categorised into training and test sets. In this study 11 landslide conditioning variables were used that are; altitude, slope angle, aspect, plan curvature, topographic wetness index, normalised difference vegetation index (NDVI), land use, soil texture, distance to rivers, distance to faults, and distance to the road. The result produced using MaxEnt and SVM model were subsequently validated using receiver operating characteristics curve (ROC) with test sets of landslide dataset. Both the models have good prediction capabilities. MaxEnt has ROC value of 0.78 while SVM has the highest prediction rate of 0.85. [ABSTRACT FROM AUTHOR]

The main aim of this study was to apply and compare two GIS-based data mining models, namely support vector machine (SVM) by four kernel functions (linear-SVM, polynomial-SVM, radial basic function-SVM, and sigmoidal-SVM) and entropy models in landslide susceptibility mapping, in Shangzhou District, China. Initially, 145 landslide locations were mapped using early reports, aerial photographs, and supported by field surveys. Subsequently, landslides in the study area were divided randomly into training and validation datasets (70/30) using ArcGIS 10.0 software. In the current study, 14 landslide conditioning factors, namely, slope aspect, slope angle, profile curvature, plan curvature, altitude, topographic wetness index (TWI), stream power index (SPI), sediment transport index (STI), normalized difference vegetation index (NDVI), distance from roads, distance from rivers, distance from faults, rainfall, and lithology, were exploited to detect the most susceptible areas. In the next step, landslide susceptibility maps generated by four types of SVM or entropy models were produced. Finally, validation of the landslide susceptibility maps produced by different models was evaluated using receiver operating characteristics (ROC) curves. The results showed that the entropy model exhibited the highest success rate (0.7610), followed by polynomial-SVM (0.7526), the sigmoidal-SVM (0.7518), radial basic function-SVM (0.7446), and linear-SVM (0.7390) models. Similarly, the ROC plots also showed that the prediction rates gave almost similar results. The entropy model had the highest prediction rate (0.7599), followed by polynomial-SVM (0.7259), sigmoidal-SVM (0.7203), radial basic function-SVM (0.7149), and linear-SVM (0.7009) models. Hence, it can be concluded that the five models used in this study gave close results, with the entropy model exhibiting best performance in landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

The main objective of the current study is to apply a random forest (RF) data-driven model and prioritization of landslide conditioning factors according to this method and its comparison to a multivariate adaptive regression spline (MARS) model for landslide susceptibility mapping in China. For this purpose, at first, landslide locations were identified by earlier reports, aerial photographs, and field surveys and a total of 348 landslides were mapped from various sources in GIS. Then, the landslide inventory was randomly split into a training dataset (70% = 244 landslides) and the remaining (30% = 104 landslides) were used for validation. In this study, 12 landslide conditioning factors were applied to detect the most susceptible areas. These factors were slope aspect, altitude, distance to faults, lithology, normalized difference vegetation index, plan curvature, profile curvature, distance to rivers, distance to roads, slope angle, stream power index, and topographic wetness index. The relationship between each conditioning factor and landslide was finalized using a frequency ration (FR) model. Subsequently, landslide-susceptible areas were mapped using the MARS and RF models. The results revealed that the most important conditioning factors according to the accuracy measure (mean decrease) of the RF model are lithology (23.47%), distance to faults (22.21%), and altitude (19.58%). We also notice that altitude (19.04%), distance to faults (18.83%), and distance to roads (15.29%) have the highest importance according to the Gini measure. Finally, the accuracy of the landslide susceptibility maps produced from the two models was verified using a receiver operating characteristics curve. The results showed that the landslide susceptibility map produced using the MARS model has a higher prediction rate than RF by area under the curve values of 87.51 and 77.32%, respectively. According to the validation results, the map produced by the MARS model exhibits the better accuracy and could be proposed for land-use planning in the study area. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Landslides are an important natural hazard that causes a great amount of damage around the world every year, especially during the rainy season. The Lianhua area is located in the middle of China's southern mountainous area, west of Jiangxi Province, and is known to be an area prone to landslides. The aim of this study was to evaluate and compare landslide susceptibility maps produced using the random forest (RF) data mining technique with those produced by bivariate (evidential belief function and frequency ratio) and multivariate (logistic regression) statistical models for Lianhua County, China. First, a landslide inventory map was prepared using aerial photograph interpretation, satellite images, and extensive field surveys. In total, 163 landslide events were recognized in the study area, with 114 landslides (70%) used for training and 49 landslides (30%) used for validation. Next, the landslide conditioning factors-including the slope angle, altitude, slope aspect, topographic wetness index (TWI), slope-length (LS), plan curvature, profile curvature, distance to rivers, distance to faults, distance to roads, annual precipitation, land use, normalized difference vegetation index (NDVI), and lithology-were derived from the spatial database. Finally, the landslide susceptibility maps of Lianhua County were generated in ArcGIS 10.1 based on the random forest (RF), evidential belief function (EBF), frequency ratio (FR), and logistic regression (LR) approaches and were validated using a receiver operating characteristic (ROC) curve. The ROC plot assessment results showed that for landslide susceptibility maps produced using the EBF, FR, LR, and RF models, the area under the curve (AUC) values were 0.8122, 0.8134, 0.7751, and 0.7172, respectively. Therefore, we can conclude that all four models have an AUC of more than 0.70 and can be used in landslide susceptibility mapping in the study area; meanwhile, the EBF and FR models had the best performance for Lianhua County, China. Thus, the resultant susceptibility maps will be useful for land use planning and hazard mitigation aims. [ABSTRACT FROM AUTHOR]

Abstract: The purpose of the present study is to investigate the landslide susceptibility mapping using three statistical models such as frequency ratio, Dempster–Shafer, and weights-of-evidence at southern part of Golestan province. At first, landslide locations were identified from the interpretation of aerial photographs, and field surveys. A total of 392 landslides were mapped in GIS out of which 275 (70%) locations were chosen for the modeling purpose and the remaining 118 (30%) cases were used for the model validation. Then layers of the landslide conditioning factors were prepared. The relationship between the conditioning factors and the landslides were calculated using three models. For verification, the results were compared with landslides which were not used during the training of the models. Subsequently, the ROC (Receiver operating characteristic) curves and area under the curves (AUC) for three landslide susceptibility maps were constructed and the areas under curves were assessed for validation purpose. The validation results showed that the area under the curve for frequency ratio, Dempster–Shafer, and weights-of-evidence models are 0.8013 (80.13%), 0.7832 (78.32%), and 0.7460 (74.60%) with prediction accuracy 0.7516 (75%), 0.7396 (73%), and 0.6998 (69%) respectively. The results revealed that frequency ratio model has higher AUC than the other models. In general, all the three models produced reasonable accuracy. The resultant maps would be useful for general land use planning. [Copyright &y& Elsevier]

Abstract: Landslide susceptibility mapping is essential for land use planning and decision-making especially in the mountainous areas. The main objective of this study is to produce landslide susceptibility maps at Safarood basin, Iran using two statistical models such as an index of entropy and conditional probability and to compare the obtained results. At the first stage, landslide locations were identified in the study area by interpretation of aerial photographs and from field investigations. Of the 153 landslides identified, 105 (≈70%) locations were used for the landslide susceptibility maps, while the remaining 48 (≈30%) cases were used for the model validation. The landslide conditioning factors such as slope degree, slope aspect, altitude, lithology, distance to faults, distance to rivers, distance to roads, topographic wetness index (TWI), stream power index (SPI), slope–length (LS), land use, and plan curvature were extracted from the spatial database. Using these factors, landslide susceptibility and weights of each factor were analyzed by index of entropy and conditional probability models. Finally, the ROC (receiver operating characteristic) curves for landslide susceptibility maps were drawn and the areas under the curve (AUC) were calculated. The verification results showed that the index of entropy model (AUC=86.08%) performed slightly better than conditional probability (AUC=82.75%) model. The produced susceptibility maps can be useful for general land use planning in the Safarood basin, Iran. [Copyright &y& Elsevier]

Although numerous models have been employed to address the issue of landslide susceptibility at regional scale, few have incorporated landslide typology into a model application. Thus, the aim of the present study is to perform landslide susceptibility zonation taking landslide classification into account using a data-driven model. The specific objective is to answer the question: how to select reasonable influencing factors for different types of landslides so that the accuracy of susceptibility assessment can be improved? The Qilihe District in Lanzhou City of northwestern China was undertaken as the test area, and a total of 12 influencing factors were set as the predictive variables. An inventory map containing 227 landslides was created first, which was divided into shallow landslides and debris flows based on the geological features, distribution, and formation mechanisms. A weighted frequency ratio model was proposed to calculate the landslide susceptibility. The weights of influencing factors were calculated by the integrated model of logistic regression and fuzzy analytical hierarchy process, whereas the rating among the classes within each factor was obtained by a frequency ratio algorithm. The landslide susceptibility index of each cell was subsequently calculated in GIS environment to create landslide susceptibility maps of different types of landslide. The analysis and assessment process were separately performed for each type of landslide, and the final landslide susceptibility map for the entire region was produced by combining them. The results showed that 73.3% of landslide pixels were classified into "very high" or "high" susceptibility zones, while "very low" or "low" susceptibility zones covered only 3.6% of landslide pixels. The accuracy of the model represented by receiver operating characteristic curve was satisfactory, with a success rate of 70.4%. When the landslide typology was not considered, the accuracy of resulted maps decreased by 1.5~5.4%. [ABSTRACT FROM AUTHOR]

The China–Pakistan Economic Corridor (CPEC) project passes through the Karakoram Highway in northern Pakistan, which is one of the most hazardous regions of the world. The most common hazards in this region are landslides and debris flows, which result in loss of life and severe infrastructure damage every year. This study assessed geohazards (landslides and debris flows) and developed susceptibility maps by considering four standalone machine-learning and statistical approaches, namely, Logistic Regression (LR), Shannon Entropy (SE), Weights-of-Evidence (WoE), and Frequency Ratio (FR) models. To this end, geohazard inventories were prepared using remote sensing techniques with field observations and historical hazard datasets. The spatial relationship of thirteen conditioning factors, namely, slope (degree), distance to faults, geology, elevation, distance to rivers, slope aspect, distance to road, annual mean rainfall, normalized difference vegetation index, profile curvature, stream power index, topographic wetness index, and land cover, with hazard distribution was analyzed. The results showed that faults, slope angles, elevation, lithology, land cover, and mean annual rainfall play a key role in controlling the spatial distribution of geohazards in the study area. The final susceptibility maps were validated against ground truth points and by plotting Area Under the Receiver Operating Characteristic (AUROC) curves. According to the AUROC curves, the success rates of the LR, WoE, FR, and SE models were 85.30%, 76.00, 74.60%, and 71.40%, and their prediction rates were 83.10%, 75.00%, 73.50%, and 70.10%, respectively; these values show higher performance of LR over the other three models. Furthermore, 11.19%, 9.24%, 10.18%, 39.14%, and 30.25% of the areas corresponded to classes of very-high, high, moderate, low, and very-low susceptibility, respectively. The developed geohazard susceptibility map can be used by relevant government officials for the smooth implementation of the CPEC project at the regional scale. [ABSTRACT FROM AUTHOR]

• Different landslide recording methods including pixel-based, centroid, crown, and toe. • Landslide spatial modeling using Mahalanobis distance and random sampling methods. • Negative balance scenariosproposed for landslide susceptibility assessment. The Ziarat Watershed, located in the south of the Golestan Province, Iran, has witnessed several destructive landslide episodes, prompting a number of researchers to aspire to improve landslide susceptibility modeling (LSM) techniques. We constructed three scenarios focusing on landslide positioning techniques (pixel-based, centroid, crown, and toe), training/test sampling strategies (Mahalanobis distance (MD), and random sampling (RS)), with alternative landslide/non-landslide data balances (1:1, 1:2, and 1:3). The data mining boosted regression trees (BRT) model was used for the landslide susceptibility modeling, using landslide data and 13 landslide controlling factors for the Ziarat Watershed. The performance of the scenarios was assessed using the areas under the success and prediction rate curves (AUSRC and AUPRC). A combination of pixel-based–MD–1:2 showed the highest learning capability and goodness-of-fit with an AUSRC value of 0.87, and the highest predictive power and generalization capacity with an AUPRC value of 0.79. Conversely, centroid-based–1:3–RS, crown-based–1:3–RS, and toe-based–1:3–RS performed less well. Comparatively, the pixel-based, MD, and 1:2 data balance scenarios surpassed their counterparts and outperformed the other models. The results indicated a high spatial differentiation with a significant chi-square value of 4549.46 at 95% confidence level. Moreover, 15.21% of the study area, containing almost 50% of the landslides, was found to have a high susceptibility to landslides. According to the premier scenario (pixel-based–MD–1:2), lithological formation, distance from roads, and NDVI, with respective contributions of 31.4%, 12.9%, and 12%, are the main spatial controlling factors leading to landslide occurrences in the study area. [ABSTRACT FROM AUTHOR]

The aim of this study was to apply data mining algorithms to produce a landslide susceptibility map of the national-scale catchment called Bandar Torkaman in northern Iran. As it was impossible to directly use the advanced data mining methods due to the volume of data at this scale, an intermediate approach, called normalized frequency-ratio unique condition units (NFUC), was devised to reduce the data volume. With the aid of this technique, different data mining algorithms such as fuzzy gamma (FG), binary logistic regression (BLR), backpropagation artificial neural network (BPANN), support vector machine (SVM), and C5 decision tree (C5DT) were employed. The success and prediction rates of the models, which were calculated by receiver operating characteristic curve, were 0.859 and 0.842 for FG, 0.887 and 0.855 for BLR, 0.893 and 0.856 for C5DT, 0.891 and 0.875 for SVM, and 0.896 and 0.872 for BPANN that showed the highest validation rates as compared with the other methods. The proposed approach of NFUC proved highly efficient in data volume reduction, and therefore the application of computationally demanding algorithms for large areas with voluminous data was feasible. [ABSTRACT FROM AUTHOR]

This research was conducted to determine which areas in the Robat Turk watershed in Iran are sensitive to gully erosion, and to define the relationship between gully erosion and geo-environmental factors by two data mining techniques, namely, Random Forest (RF) and k-Nearest Neighbors (KNN). First, 242 gully locations we determined in field surveys and mapped in ArcGIS software. Then, twelve gully-related conditioning factors were selected. Our results showed that, for both the RF and KNN models, altitude, distance to roads, and distance from the river had the highest influence upon gully erosion sensitivity. We assessed the gully erosion susceptibility maps using the Receiver Operating Characteristic (ROC) curve. Validation results showed that the RF and KNN models had Area Under the Curve (AUC) 87.4 and 80.9%, respectively. As a result, the RF method has better performance compared with the KNN method for mapping gully erosion susceptibility. Rainfall, altitude, and distance from a river were identified as the most important factors affecting gully erosion in this area. The methodology used in this research is transferable to other regions to determine which areas are prone to gully erosion and to explicitly delineate high-risk zones within these areas. [ABSTRACT FROM AUTHOR]

Landslides every year impose extensive damages to human beings in various parts of the world; therefore, identifying prone areas to landslides for preventive measures is essential. The main purpose of this research is applying different scenarios for landslide susceptibility mapping by means of combination of bivariate statistical (frequency ratio) and computational intelligence methods (random forest and support vector machine) in landslide polygon and point formats. For this purpose, in the first step, a total of 294 landslide locations were determined from various sources such as aerial photographs, satellite images, and field surveys. Landslide inventory was randomly split into a testing dataset 70% (206 landslide locations) for training the different scenarios, and the remaining 30% (88 landslides locations) was used for validation purposes. To providing landslide susceptibility maps, 13 conditioning factors including altitude, slope angle, plan curvature, slope aspect, topographic wetness index, lithology, land use/land cover, distance from rivers, drainage density, distance from fault, distance from roads, convergence index, and annual rainfall are used. Tolerance and the variance inflation factor indices were used for considering multi-collinearity of conditioning factors. Results indicated that the smallest tolerance and highest variance inflation factor were 0.31 and 3.20, respectively. Subsequently, spatial relationship between classes of each landslide conditioning factor and landslides was obtained by frequency ratio (FR) model. Also, importance of the mentioned factors was obtained by random forest (RF) as a machine learning technique. The results showed that according to mean decrease accuracy, factors of altitude, aspect, drainage density, and distance from rivers had the greatest effect on the occurrence of landslide in the study area. Finally, the landslide susceptibility maps were produced by ten scenarios according to different ensembles. The receiver operating characteristics, including the area under the curve (AUC), were used to assess the accuracy of the models. Results of validation of scenarios showed that AUC was varying from 0.668 to 0.749. Also, FR and seed cell area index indicators show a high correlation between the susceptibility classes with the landslide pixels and field observations in all scenarios except scenarios 10RF and 10SVM. The results of this study can be used for landslides management and mitigation and development activities such as construction of settlements and infrastructure in the future. [ABSTRACT FROM AUTHOR]

This paper presents GIS-based new ensemble data mining techniques that involve an adaptive neuro-fuzzy inference system (ANGIS) with genetic algorithm, differential evolution, and particle swarm optimization for landslide spatial modelling. This research was tested in Hanyuan County, which is a landslide-prone area in Sichuan Province, China. Different continuous and categorical landslide conditioning factors according to a literature review and data availability were selected, and their maps were digitized in a GIS environment. These layers are the slope angle, slope aspect, altitude, plan curvature, profile curvature, topographic wetness index, distance to faults, distance to rivers, distance to roads, lithology, normalized difference vegetation index and land use. According to historical information of individual landslide events, interpretation of the aerial photographs, and field surveys supported by the Sichuan Land Resources Bureau of China, 225 landslides were identified in the study area. The landslide locations were divided into two subsets, namely, training and validating (70/30), based on a random selection scheme. In this research, a probability certainty factor (PCF) model was used for the evaluation of the relationship between the landslides and conditioning factors. In the next step, three data mining techniques combined with the ANFIS model, including ANFIS-genetic algorithm (ANFIS-GA), ANFIS-differential evolution (ANFIS-DE), and ANFIS-particle swarm optimization (ANFIS-PSO), were used for the landslide spatial modelling and its zonation. Finally, the landslide susceptibility maps produced by the mentioned models were evaluated by the ROC curve. The results showed that the area under the curve (AUC) of all of the models was > 0.75. At the same time, the highest AUC value was for the ANFIS-DE model (0.844), followed by ANGIS-GA (0.821), and ANFIS-PSO (0.780). In general, the proposed ensemble data mining techniques can be applied for land use planning and management of landslide susceptibility and hazard in the study area and in other areas. [ABSTRACT FROM AUTHOR]

The aim of this study is to investigate the causes of landslides in the Himalayan region and analysis of their sedimentary characteristics. The Himalayan region is unique to topographic as well as geological formations; each range has different litho-tectonic setting such as the Siwalik, the Lesser andthe Great Himalayan ranges. Particularly, the Lesser Himalayan ranges are highly susceptible to landslide during the monsoon season. In this study, a highway corridor is selected passing through the Siwalik and the Lesser Himalayan range. The study comprises of two parts; a) investigates landslide sedimentary characteristics such as particle size, plasticity limit, slope geometry, and land cover; b) comparative analysis of four machine learning methods to find out a best suitable model for landslide susceptibility analysis. In order to achieve the objectives detailed landslide inventory of the area is prepared based on repeated field visits and multi-dated satellite imageries. The field investigation reveals that debris fall and debris flow mostly confined; (a) along the road in proximity to the streams, particularly in scrubs and wasteland; and (b) along the streams due to river undercutting process. Sedimentological characteristics are examined to understand the grain size, plasticity limit, rock mass strength, and its relationship to slope failure mechanism. Landslide susceptibility is analyzed using boosted regression tree (BRT), generalized linear model (GLM), random forest (RF) and support vector machine (SVM) for the study area. These model results are validated using landslide test dataset with the area under curve (AUC) method. The AUC values of BRT (0.85), GLM (0.786), RF (0.904), and SVM (0.865) reveals the high prediction rate for spatial modelling of landslide in the area. The validation results show satisfactory agreement between the computed landslide susceptibility maps and the existing landslides occurred along the highway corridor. • The site-specific sedimentological analysis shows a significant relationship of slope materials with the type of landslide. • Accurate landslide dataset influences the prediction accuracy of the model. • Compared predictive capability of four different models (BRT, GLM, RF, and SVM) • Results indicate that Random Forest model is the best model for landslide susceptibility analysis in the Himalayan region. [ABSTRACT FROM AUTHOR]

Landslide is a common natural hazard and responsible for extensive damage and losses in mountainous areas. In this study, Longju in the Three Gorges Reservoir area in China was taken as a case study for landslide susceptibility assessment in order to develop effective risk prevention and mitigation strategies. To begin, 202 landslides were identified, including 95 colluvial landslides and 107 rockfalls. Twelve landslide causal factor maps were prepared initially, and the relationship between these factors and each landslide type was analyzed using the information value model. Later, the unimportant factors were selected and eliminated using the information gain ratio technique. The landslide locations were randomly divided into two groups: 70% for training and 30% for verifying. Two machine learning models: the support vector machine (SVM) and artificial neural network (ANN), and a multivariate statistical model: the logistic regression (LR), were applied for landslide susceptibility modeling (LSM) for each type. The LSM index maps, obtained from combining the assessment results of the two landslide types, were classified into five levels. The performance of the LSMs was evaluated using the receiver operating characteristics curve and Friedman test. Results show that the elimination of noise-generating factors and the separated modeling of each landslide type have significantly increased the prediction accuracy. The machine learning models outperformed the multivariate statistical model and SVM model was found ideal for the case study area. [ABSTRACT FROM AUTHOR]

The current study aimed at producing a multi-hazard susceptibility map for the Hasher-Fayfa Basin. The basin is part of the Jazan region in southwestern Saudi Arabia and is characterized by mountainous terrain. Recently, this area has experienced many extreme natural processes, which become natural hazard events when they intersect with human activities (urban areas and infrastructures). In this work, the probabilities of the three main hazards; landslides, floods, and gully erosion are mapped using machine learning algorithms such as boosted regression tree (BRT), generalized linear model (GLM), Flexible discriminant analysis (FDA), random forest (RF), and multivariate discriminant analysis (MDA). Several factors from various sources, including, topographic, geologic, meteorological, hydrologic, and human activities, were incorporated to produce the final multi-hazard susceptibility model. The area under the curve (AUC) was used to determine the best predictive model for each type of natural hazard. AUC values between 80 and 90% indicated that the model was very good, and values above 90% indicated that the model had excellent predictive capability. Based on the accuracy evaluation, the FDA model was found to be the most accurate landslides prediction with an AUC value of (92.7%, excellent performance). The RF model was found to be the most accurate in predicting floods and erosion with AUC values of (97.2% - excellent and 83.3% - very good performance, respectively). Finally, a map of multi-hazard susceptibility was created by coupling of the mentioned three hazards. The results showed that 33.5% of the total area is safe (no-hazard), while 66.5% is characterized by at least a single hazard and a combination of two or three hazards. Machine learning approaches are useful tools as a basis for management and mitigation processes, based on multi-hazard modeling. [Display omitted] • Multi-hazards mapping in Southwestern Saudi Arabia. • Testing various machine learning models to select the best model for three hazards. • Variable's importance determining in three hazards such as, flood, gully erosion, and landslides. • The RF model was found to be the most accurate in predicting floods and gully erosion. • The FDA model was found to be the most accurate landslides prediction. [ABSTRACT FROM AUTHOR]