Search

We used AdaBoost (AB), alternating decision tree (ADTree), and their combination as an ensemble model (AB-ADTree) to spatially predict landslides in the Cameron Highlands, Malaysia. The models were trained with a database of 152 landslides compiled using Synthetic Aperture Radar Interferometry, Google Earth images, and field surveys, and 17 conditioning factors (slope, aspect, elevation, distance to road, distance to river, proximity to fault, road density, river density, normalized difference vegetation index, rainfall, land cover, lithology, soil types, curvature, profile curvature, stream power index, and topographic wetness index). We carried out the validation process using the area under the receiver operating characteristic curve (AUC) and several parametric and non-parametric performance metrics, including positive predictive value, negative predictive value, sensitivity, specificity, accuracy, root mean square error, and the Friedman and Wilcoxon sign rank tests. The AB model (AUC = 0.96) performed better than the ensemble AB-ADTree model (AUC = 0.94) and successfully outperformed the ADTree model (AUC = 0.59) in predicting landslide susceptibility. Our findings provide insights into the development of more efficient and accurate landslide predictive models that can be used by decision makers and land-use managers to mitigate landslide hazards.

In this research, eight individual machine learning and statistical models are implemented and compared, and based on their results, seven ensemble models for flood susceptibility assessment are introduced. The individual models included artificial neural networks, classification and regression trees, flexible discriminant analysis, generalized linear model, generalized additive model, boosted regression trees, multivariate adaptive regression splines, and maximum entropy, and the ensemble models were Ensemble Model committee averaging (EMca), Ensemble Model confidence interval Inferior (EMciInf), Ensemble Model confidence interval Superior (EMciSup), Ensemble Model to estimate the coefficient of variation (EMcv), Ensemble Model to estimate the mean (EMmean), Ensemble Model to estimate the median (EMmedian), and Ensemble Model based on weighted mean (EMwmean). The data set covered 201 flood events in the Haraz watershed (Mazandaran province in Iran) and 10,000 randomly selected non-occurrence points. Among the individual models, the Area Under the Receiver Operating Characteristic (AUROC), which showed the highest value, belonged to boosted regression trees (0.975) and the lowest value was recorded for generalized linear model (0.642). On the other hand, the proposed EMmedian resulted in the highest accuracy (0.976) among all models. In spite of the outstanding performance of some models, nevertheless, variability among the prediction of individual models was considerable. Therefore, to reduce uncertainty, creating more generalizable, more stable, and less sensitive models, ensemble forecasting approaches and in particular the EMmedian is recommended for flood susceptibility assessment., (Copyright © 2018 Elsevier Ltd. All rights reserved.)

Soil erosion is a major cause of damage to agricultural lands in many parts of the world and is of particular concern in semiarid parts of Iran. We use five machine learning techniques—Random Forest (RF), M5P, Reduced Error Pruning Tree (REPTree), Gaussian Processes (GP), and Pace Regression (PR)—under two scenarios to predict soil erodibility in the Dehgolan region, Kurdistan Province, Iran. Our models are based on a variety of soil properties, including soil texture, structure, permeability, bulk density, aggregates, organic matter, and chemical constituents. We checked the validity of the models with statistical metrics, including the coefficient of determination (R2 ), mean absolute error (MAE), root mean squared error (RMSE), T-tests, Taylor diagrams, and box plots. All five algorithms show a positive correlation between the soil erodibility factor (K) and silt, sand, fine sand, bulk density, and infiltration. The GP model has the highest prediction accuracy (R² ¼ 0.843, MAE ¼ 0.0044, RMSE ¼ 0.0050). It outperformed the RF (R² ¼ 0.812, MAE ¼ 0.0050, RMSE ¼ 0.0061), PR, (R² ¼ 0.794, MAE ¼ 0.0037, RMSE ¼ 0.0052), M5P (R² ¼ 0.781, MAE ¼ 0.0043, RMSE ¼ 0.0053), and REPTree (R² ¼ 0.752, MAE ¼ 0.0045, RMSE ¼ 0.0056) algorithms and thus is a useful complement to studies aimed at predicting soil erodibility in areas with similar climate and soil characteristics. [ABSTRACT FROM AUTHOR]

In the present study, Rotation Forest ensemble was integrated with different base classifiers to develop different hybrid models namely Rotation Forest based Support Vector Machines (RFSVM), Rotation Forest based Artificial Neural Networks (RFANN), Rotation Forest based Decision Trees (RFDT), and Rotation Forest based Naïve Bayes (RFNB) for landslide susceptibility modelling. The validity of these models was evaluated using statistical methods such as Root Mean Square Error (RMSE), Kappa index, accuracy, and the area under the success rate and predictive rate curves (AUC). Part of the landslide prone area of Pithoragarh district, Uttarakhand, Himalaya, India was selected as the study area. Results indicate that the RFDT is the best model showing the highest predictive capability (AUC = 0.741) in comparison to RFANN (AUC = 0.710), RFSVM (AUC = 0.701), and RFNB (AUC = 0.640) models. The present study would be helpful in the selection of best model for landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

Gully erosion destroys agricultural and domestic grazing land in many countries, especially those with arid and semi-arid climates and easily eroded rocks and soils. It also generates large amounts of sediment that can adversely impact downstream river channels. The main objective of this research is to accurately detect and predict areas prone to gully erosion. In this paper, we couple hybrid models of a commonly used base classifier (reduced pruning error tree, REPTree) with AdaBoost (AB), bagging (Bag), and random subspace (RS) algorithms to create gully erosion susceptibility maps for a sub-basin of the Shoor River watershed in northwestern Iran. We compare the performance of these models in terms of their ability to predict gully erosion and discuss their potential use in other arid and semi-arid areas. Our database comprises 242 gully erosion locations, which we randomly divided into training and testing sets with a ratio of 70/30. Based on expert knowledge and analysis of aerial photographs and satellite images, we selected 12 conditioning factors for gully erosion. We used multi-collinearity statistical techniques in the modeling process, and checked model performance using statistical indexes including precision, recall, F-measure, Matthew correlation coefficient (MCC), receiver operatic characteristic curve (ROC), precision–recall graph (PRC), Kappa, root mean square error (RMSE), relative absolute error (PRSE), mean absolute error (MAE), and relative absolute error (RAE). Results show that rainfall, elevation, and river density are the most important factors for gully erosion susceptibility mapping in the study area. All three hybrid models that we tested significantly enhanced and improved the predictive power of REPTree (AUC=0.800), but the RS-REPTree (AUC= 0.860) ensemble model outperformed the Bag-REPTree (AUC= 0.841) and the AB-REPTree (AUC= 0.805) models. We suggest that decision makers, planners, and environmental engineers employ the RS-REPTree hybrid model to better manage gully erosion-prone areas in Iran. [ABSTRACT FROM AUTHOR]

A novel artificial intelligence approach of Bayesian Logistic Regression (BLR) and its ensembles [Random Subspace (RS), Adaboost (AB), Multiboost (MB) and Bagging] was introduced for landslide susceptibility mapping in a part of Kamyaran city in Kurdistan Province, Iran. A spatial database was generated which includes a total of 60 landslide locations and a set of conditioning factors tested by the Information Gain Ratio technique. Performance of these models was evaluated using the area under the ROC curve (AUROC) and statistical index-based methods. Results showed that the hybrid ensemble models could significantly improve the performance of the base classifier of BLR (AUROC = 0.930). However, RS model (AUROC = 0.975) had the highest performance in comparison to other landslide ensemble models, followed by Bagging (AUROC = 0.972), MB (AUROC = 0.970) and AB (AUROC = 0.957) models, respectively. [ABSTRACT FROM AUTHOR]

The most dangerous landslide disasters always cause serious economic losses and human deaths. The contribution of this work is to present an integrated landslide modelling framework, in which an adaptive neuro-fuzzy inference system (ANFIS) is combined with the two optimization algorithms of whale optimization algorithm (WOA) and grey wolf optimizer (GWO) at Anyuan County, China. It means that WOA and GWO are used as two meta-heuristic algorithms to improve the prediction performance of the ANFIS-based methods. In addition, the step-wise weight assessment ratio analysis (SWARA) method is used to obtain the initial weight of each class of landslide influencing factors. To validate the effectiveness of the proposed framework, 315 landslide events in history were selected for our experiments and were randomly divided into the training and verification sets. To perform landslide susceptibility mapping, fifteen geological, hydrological, geomorphological, land cover, and other factors are considered for the modelling construction. The landslide susceptibility maps by SWARA, SWARA-ANFIS, SWARA-ANFIS-PSO, SWARA-ANFIS-WOA, and SWARA-ANFIS-GWO models are assessed using the measures of the receiver operating characteristic (ROC) curve and root-mean-square error (RMSE). The experiments demonstrated that the obtained results of modelling process from the SWARA to the SAWRA-ANFIS-GWO model were more accurate and that the proposed methods have satisfactory prediction ability. Specifically, prediction accuracy by area under the curve (AUC) of SWARA, SWARA-ANFIS, SWARA-ANFIS-PSO, SWARA-ANFIS-GWO, and SWARA-ANFIS-WOA models were 0.831, 0.831, 0.850, 0.856, and 0.869, respectively. Due to adaptability and usability, the proposed prediction methods can be applied to other areas for landslide management and mitigation as well as prevention throughout the world. [ABSTRACT FROM AUTHOR]

Since it is not possible to determine the exact time of a natural disaster's occurrence and the amount of physical and financial damage on humans or the environment resulting from their event, decision-makers need to identify areas with potential vulnerability in order to reduce future losses. In this paper, a GIS-based open source software entitled Seismic-Related Vulnerability Calculation Software (SEVUCAS), based on the Step-wise Weight Assessment Ratio Analysis (SWARA) method and geographic information system, has been developed to assess seismic vulnerability by considering four groups of criteria (i.e., geotechnical, structural, socio-economic, and physical distance to needed facilities and away from dangerous facilities). The software was developed in C# language using ArcGIS Engine functions, which provide enhanced visualization as well as user-friendly and automatic software for the seismic vulnerability assessment of buildings. Weighting of the criteria (indicators) and alternatives (sub-indicators) was done using SWARA. Also, two interpolation methods based on a radial basis function (RBF) and teaching–learning-based optimization (TLBO) were used to optimize the weights of the criteria and the classes of each alternative as well. After weighing the criteria and alternatives, the weighted overlay analysis was used to determine the final vulnerability map in the form of contours and statistical data. The difference between this software and similar ones is that people with a low level of knowledge in the area of earthquake crisis management can use it to determine and estimate the seismic vulnerabilities of their houses. This visualized operational forecasting software provides an applicable tool for both government and people to make quick and correct decisions to determine higher priority structures for seismic retrofitting implementation. [ABSTRACT FROM AUTHOR]

Globally, and in China, landslides constitute one of the most important and frequently encountered natural hazard events. In the present study, landslide susceptibility evaluation was undertaken using novel ensembles of bivariate statistical-methods-based (evidential belief function (EBF), statistical index (SI), and weights of evidence (WoE)) kernel logistic regression machine learning classifiers. A landslide inventory comprising 222 landslides and 15 conditioning factors (slope angle, slope aspect, altitude, plan curvature, profile curvature, stream power index, sediment transport index, topographic wetness index, distance to rivers, distance to roads, distance to faults, NDVI, land use, lithology, and rainfall) was prepared as the spatial database. Correlation analysis and selection of conditioning factors were conducted using multicollinearity analysis and classifier attribute evaluation methods, respectively. The receiver operating characteristic curve method was used to validate the models. The areas under the success rate (AUC_T) and prediction rate (AUC_P) curves and landslide density analysis were also used to assess the prediction capability of the landslide susceptibility maps. Results showed that the EBF-KLR hybrid model had the highest predictive capability in landslide susceptibility assessment (AUC values of 0.814 and 0.753 for the training and validation datasets, respectively; AUC_T value of 0.8511 and AUC_P value of 0.7615), followed in descending order by the SI-KLR and WoE-KLR hybrid models. These findings indicate that hybrid models could improve the predictive capability of bivariate models, and that the EBF-KLR is a promising hybrid model for the spatial prediction of landslides in susceptible areas. [ABSTRACT FROM AUTHOR]

We proposed an innovative hybrid intelligent approach, namely, the multiboost based naïve bayes trees (MBNBT) method for the spatial prediction of landslides in the Mu Cang Chai District of Yen Bai Province, Vietnam. The MBNBT, which is an ensemble of the multiboost (MB) and naïve bayes trees (NBT) base classifier, has rarely been applied for landslide susceptibility mapping around the world. For the modeling, we selected 248 landslide locations in the hilly terrain of the study area. Fifteen landslide conditioning factors were selected for the construction of the database based on the one-R attribute evaluation (ORAE) technique. Model validation was done using statistical metrics, namely, sensitivity, specificity, accuracy, mean absolute error (MAE), root mean square error (RMSE), and the area under the receiver operating characteristics curve (AUC). Performance of the hybrid model was evaluated and compared with popular soft computing benchmark models, namely, multiple perceptron neural network (MLPN), Support Vector Machines (SVM), and single NBT. Results indicated that the proposed MBNBT (AUC = 0.824) model outperformed the popular models, namely, the MLPN (AUC = 0.804), SVM (AUC = 0.804), and NBT (AUC = 0.800) models. Analysis of the model results also suggested that the MB meta classifier ensemble model could enhance the prediction power of the NBT model. Therefore, the MBNBT is a suitable method for the assessment of landslide susceptibility in landslide prone areas. [ABSTRACT FROM AUTHOR]

This study attempts to compare popular statistical methods (linear, logarithmic, quadratic, power and exponential functions) with machine learning methods (multi-layer perceptron (MLP), radial base function (RBF), adaptive neural-based fuzzy inference system (ANFIS) and support vector machine (SVM)) for simulating the volume of landslides based on their surface area (VL ~ AL) in the Kurdistan province, Iran. Performances of the models were validated using some commonly error functions including the Adjusted R 2 , F-test and AIC (Akaike Information Criteria). The results showed that the power model demonstrates the best performance compared to other statistical methods whereas the ANFIS model outperforms other machine learning approaches. Furthermore, the comparative results showed that machine learning methods indicate better performances than simple statistical methods for simulating the volume of landslides in the study area. In practice, the outputs of this research can help managers and investigators decrease the cost of field surveys and measurements of volumes of landslides in landslide hazard management projects. [ABSTRACT FROM AUTHOR]

This study evaluates state-of-the-art machine learning models in predicting the most sustainable arsenic mitigation preference. A Gaussian distribution-based Naïve Bayes (NB) classifier scored the highest Area Under the Curve (AUC) of the Receiver Operating Characteristic curve (0.82), followed by Nu Support Vector Classification (0.80), and K-Neighbors (0.79). Ensemble classifiers scored higher than 70% AUC, with Random Forest being the top performer (0.77), and Decision Tree model ranked fourth with an AUC of 0.77. The multilayer perceptron model also achieved high performance (AUC=0.75). Most linear classifiers underperformed, with the Ridge classifier at the top (AUC=0.73) and perceptron at the bottom (AUC=0.57). A Bernoulli distribution-based Naïve Bayes classifier was the poorest model (AUC=0.50). The Gaussian NB was also the most robust ML model with the slightest variation of Kappa score on training (0.58) and test data (0.64). The results suggest that nonlinear or ensemble classifiers could more accurately understand the complex relationships of socio-environmental data and help develop accurate and robust prediction models of sustainable arsenic mitigation. Furthermore, Gaussian NB is the best option when data is scarce. [Display omitted] • GaussianNB produce robust sustainable arsenic mitigation prediction models. • Non-linear models best fit to model socio-economic and environmental data. • GaussianNB achieved 0.825 AUC score. • SGD, perceptron, and BernoulliNB could not produce robust sustainable arsenic mitigation prediction models. [ABSTRACT FROM AUTHOR]

We mapped landslide susceptibility in Kamyaran city of Kurdistan Province, Iran, using a robust deep-learning (DP) model based on a combination of extreme learning machine (ELM), deep belief network (DBN), back propagation (BP), and genetic algorithm (GA). A total of 118 landslide locations were recorded and divided in the training and testing datasets. We selected 25 conditioning factors, and of these, we specified the most important ones by an information gain ratio (IGR) technique. We assessed the performance of the DP model using statistical measures including sensitivity, specificity, accuracy, F1-measure, and area under-the-receiver operating characteristic curve (AUC). Three benchmark algorithms, i.e., support vector machine (SVM), REPTree, and NBTree, were used to check the applicability of the proposed model. The results by IGR concluded that of the 25 conditioning factors, only 16 factors were important for our modeling procedure, and of these, distance to road, road density, lithology and land use were the four most significant factors. Results based on the testing dataset revealed that the DP model had the highest accuracy (0.926) of the compared algorithms, followed by NBTree (0.917), REPTree (0.903), and SVM (0.894). The landslide susceptibility maps prepared from the DP model with AUC = 0.870 performed the best. We consider the DP model a suitable tool for landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

The robustness of landslide prediction models has become a major focus of researchers worldwide. We developed two novel hybrid predictive models that combine the self-organizing, deep-learning group method of data handling (GMDH) with two swarm intelligence optimization algorithms, i.e., cuckoo search algorithm (CSA) and whale optimization algorithm (WOA) for spatially explicit prediction of landslide susceptibility. Eleven landslide-causing factors and 334 historic landslides in a 31,340 km2 landslide-prone area in Iran were used to produce geospatial training and validation datasets. The GMDH model was employed to develop a basic predictive model that was then restructured and its parameters were optimized using the CSA and WOA algorithms, yielding the novel hybrid GMDH-CSA and GMDH-WOA models. The hybrid models were validated and compared to the standalone GMDH model by calculating the area under the receiver operating characteristic (AUC) curve and root mean square error (RMSE). The results demonstrated that the hybrid models overcame the computational shortcomings of the basic GMDH model and significantly improved landslide susceptibility prediction (GMDH-CSA, AUC = 0.909 and RMSE = 0.089; GMDH-WOA, AUC = 0.902 and RMSE = 0.129; standalone GMDH, AUC = 0.791 and RMSE = 0.226). Further, the hybrid models were more robust than the standalone GMDH model, showing consistently excellent performance when the training and validation datasets were changed. Overall, the swarm intelligence-optimized models, but not the standalone model, identified the best trade-offs among objectives, accuracy, and robustness. [Display omitted] • Optimizing GMDH parameters using two swarm intelligence optimization algorithms. • Comparing predictive capabilities of the hybrid GMDH-CSA and GMDH-WOA models. • Overcoming the computational shortcomings of the standalone GMDH model. • Proving model robustness with AUC > 0.90 for modeling landslide susceptibilities. [ABSTRACT FROM AUTHOR]

Flood probability maps are essential for a range of applications, including land use planning and developing mitigation strategies and early warning systems. This study describes the potential application of two architectures of deep learning neural networks, namely convolutional neural networks (CNN) and recurrent neural networks (RNN), for spatially explicit prediction and mapping of flash flood probability. To develop and validate the predictive models, a geospatial database that contained records for the historical flood events and geo-environmental characteristics of the Golestan Province in northern Iran was constructed. The step-wise weight assessment ratio analysis (SWARA) was employed to investigate the spatial interplay between floods and different influencing factors. The CNN and RNN models were trained using the SWARA weights and validated using the receiver operating characteristics technique. The results showed that the CNN model (AUC = 0.832, RMSE = 0.144) performed slightly better than the RNN model (AUC = 0.814, RMSE = 0.181) in predicting future floods. Further, these models demonstrated an improved prediction of floods compared to previous studies that used different models in the same study area. This study showed that the spatially explicit deep learning neural network models are successful in capturing the heterogeneity of spatial patterns of flood probability in the Golestan Province, and the resulting probability maps can be used for the development of mitigation plans in response to the future floods. The general policy implication of our study suggests that design, implementation, and verification of flood early warning systems should be directed to approximately 40% of the land area characterized by high and very susceptibility to flooding. [Display omitted] • CNN and RNN deep learnings were adopted for flood probability mapping. • CNN (AUC = 0.832) performed slightly better than RNN (AUC = 0.814). • Very low to very high probabilities of flood occurrences were delineated. • Flood prevention activities primarily needed on 40% of the land area. [ABSTRACT FROM AUTHOR]

With the development of remote sensing algorithms and increased access to satellite data, generating up-to-date, accurate land use/land cover (LULC) maps has become increasingly feasible for evaluating and managing changes in land cover as created by changes to ecosystem and land use. The main objective of our study is to evaluate the performance of Support Vector Machine (SVM), Artificial Neural Network (ANN), Maximum Likelihood Classification (MLC), Minimum Distance (MD), and Mahalanobis (MH) algorithms and compare them in order to generate a LULC map using data from Sentinel 2 and Landsat 8 satellites. Further, we also investigate the effect of a penalty parameter on SVM results. Our study uses different kernel functions and hidden layers for SVM and ANN algorithms, respectively. We generated the training and validation datasets from Google Earth images and GPS data prior to pre-processing satellite data. In the next phase, we classified the images using training data and algorithms. Ultimately, to evaluate outcomes, we used the validation data to generate a confusion matrix of the classified images. Our results showed that with optimal tuning parameters, the SVM classifier yielded the highest overall accuracy (OA) of 94%, performing better for both satellite data compared to other methods. In addition, for our scenes, Sentinel 2 date was slightly more accurate compared to Landsat 8. The parametric algorithms MD and MLC provided the lowest accuracy of 80.85% and 74.68% for the data from Sentinel 2 and Landsat 8. In contrast, our evaluation using the SVM tuning parameters showed that the linear kernel with the penalty parameter 150 for Sentinel 2 and the penalty parameter 200 for Landsat 8 yielded the highest accuracies. Further, ANN classification showed that increasing the hidden layers drastically reduces classification accuracy for both datasets, reducing zero for three hidden layers. [ABSTRACT FROM AUTHOR]

Reliable flash flood susceptibility maps are a vital tool for land planners and emergency management officials for early flood warning and mitigation. We have developed a new ensemble learning model that predicts flash flood susceptibility at Haraz, Iran. The new model couples a Bayesian Belief Network (BBN) model with an extreme learning machine (ELM) and backpropagation (BP) structure optimized by a genetic algorithm (GA) named GA-BN-NN model. We applied the support vector machine (SVM) technique to a database of 194 flood locations with ten conditioning factors. An artificial neural network (ANN) algorithm with a multi-layer perceptron function, MLP-BP, optimized by a genetic algorithm, GA-MLP, and a shuffled frog-leaping algorithm, SFLA-MLP, were used as benchmark models for assessing the power prediction of the proposed model. Statistical measures, including sensitivity, specificity, accuracy, F1-measure and Jaccard coefficient, and root mean square error, were used to evaluate the goodness-of-fit and prediction accuracy, respectively, of the training and testing datasets. We found that all ten factors are positively correlated with flood occurrence, but slope angle has the highest average merit (AM = 9.7) and thus contributes most to the occurrence of flooding. Results indicate that the GA-BN-NN model has the highest goodness-of-fit and prediction accuracy (AUC = 0.966) and hence outperforms other ensemble learning models that we tested — the SFLA-MLP, MLP-BP, and GA-MLP models. We thus conclude that the proposed model is a promising technique for managing risk in flood-prone areas around the world. • A new deep learning model, E(T)-ELM-DBN-BP, was explored for flash flood susceptibility mapping. • The LSSVM technique was applied to determine the most important flash flood conditioning factors. • The MLP was optimized by BP, GA and SFLA algorithms as benchmark models to validity of the new model. • The E(T)-ELM-DBN-BP model outperformed the E(T)-MLP-BP, E(W)-MLP-GA and E(W)-MLP-SFLA models. • The new proposed model was offered as a promising and trustworthy tool for flash flood mitigation. [ABSTRACT FROM AUTHOR]

In the present study, gully erosion susceptibility was evaluated for the area of the Robat Turk Watershed in Iran. The assessment of gully erosion susceptibility was performed using four state-of-the-art data mining techniques: random forest (RF), credal decision trees (CDTree), kernel logistic regression (KLR), and best-first decision tree (BFTree). To the best of our knowledge, the KLR and CDTree algorithms have been rarely applied to gully erosion modeling. In the first step, from the 242 gully erosion locations that were identified, 70% (170 gullies) were selected as the training dataset, and the other 30% (72 gullies) were considered for the result validation process. In the next step, twelve gully erosion conditioning factors, including topographic, geomorphological, environmental, and hydrologic factors, were selected to estimate gully erosion susceptibility. The area under the ROC curve (AUC) was used to estimate the performance of the models. The results revealed that the RF model had the best performance (AUC = 0.893), followed by the KLR (AUC = 0.825), the CDTree (AUC = 0.808), and the BFTree (AUC = 0.789) models. Overall, the RF model performed significantly better than the others, which may support the application of this method to a transferable susceptibility model in other areas. Therefore, we suggest using the RF, KLR, and CDT models for gully erosion susceptibility mapping in other prone areas to assess their reproducibility. [ABSTRACT FROM AUTHOR]

We generated high-quality shallow landslide susceptibility maps for Bijar County, Kurdistan Province, Iran, using Random Forest (RAF), an ensemble computational intelligence method and three meta classifiers—Bagging (BA, BA-RAF), Random Subspace (RS, RS-RAF), and Rotation Forest (RF, RF-RAF). Modeling and validation were done on 111 shallow landslide locations using 20 conditioning factors tested by the Information Gain Ratio (IGR) technique. We assessed model performance with statistically based indexes, including sensitivity, specificity, accuracy, kappa, root mean square error (RMSE), and area under the receiver operatic characteristic curve (AUC). All four machine learning models that we tested yielded excellent goodness-of-fit and prediction accuracy, but the RF-RAF ensemble model (AUC = 0.936) outperformed the BA-RAF, RS-RAF (AUC = 0.907), and RAF (AUC = 0.812) models. The results also show that the Random Forest model significantly improved the predictive capability of the RAF-based classifier and, therefore, can be considered as a useful and an effective tool in regional shallow landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

We prepared a landslide susceptibility map for the Sarkhoon watershed, Chaharmahal-w-bakhtiari, Iran, using novel ensemble artificial intelligence approaches. A classifier of support vector machine (SVM) was employed as a base classifier, and four Meta/ensemble classifiers, including Adaboost (AB), bagging (BA), rotation forest (RF), and random subspace (RS), were used to construct new ensemble models. SVM has been used previously to spatially predict landslides, but not together with its ensembles. We selected 20 conditioning factors and randomly portioned 98 landslide locations into training (70%) and validating (30%) groups. Several statistical metrics, including sensitivity, specificity, accuracy, kappa, root mean square error (RMSE), and area under the receiver operatic characteristic curve (AUC), were used for model comparison and validation. Using the One-R Attribute Evaluation (ORAE) technique, we found that all 20 conditioning factors were significant in identifying landslide locations, but "distance to road" was found to be the most important. The RS (AUC = 0.837) and RF (AUC = 0.834) significantly improved the goodness-of-fit and prediction accuracy of the SVM (AUC = 0.810), whereas the BA (AUC = 0.807) and AB (AUC = 0.779) did not. The random subspace based support vector machine (RSSVM) model is a promising technique for helping to better manage land in landslide-prone areas. [ABSTRACT FROM AUTHOR]

In this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as a Meta/ensemble classifier based on alternating decision tree (ADTree) as a base classifier called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed of Kurdistan province, Iran. A total of 915 gully erosion locations along with 22 gully conditioning factors were used to construct a database. Some soft computing benchmark models (SCBM) including the ADTree, the Support Vector Machine by two kernel functions such as Polynomial and Radial Base Function (SVM-Polynomial and SVM-RBF), the Logistic Regression (LR), and the Naïve Bayes Multinomial Updatable (NBMU) models were used for comparison of the designed model. Results indicated that 19 conditioning factors were effective among which distance to river, geomorphology, land use, hydrological group, lithology and slope angle were the most remarkable factors for gully modeling process. Additionally, results of modeling concluded the RF-ADTree ensemble model could significantly improve (area under the curve (AUC) = 0.906) the prediction accuracy of the ADTree model (AUC = 0.882). The new proposed model had also the highest performance (AUC = 0.913) in comparison to the SVM-Polynomial model (AUC = 0.879), the SVM-RBF model (AUC = 0.867), the LR model (AUC = 0.75), the ADTree model (AUC = 0.861) and the NBMU model (AUC = 0.811). [ABSTRACT FROM AUTHOR]

We used a novel hybrid functional machine learning algorithm to predict the spatial distribution of landslides in the Sarkhoon watershed, Iran. We developed a new ensemble model which is a combination of a functional algorithm, stochastic gradient descent (SGD) and an AdaBoost (AB) Meta classifier namely ABSGD model to predict the landslides. The model incorporates 20 landslide conditioning factors, which we ranked using the least-square support vector machine (LSSVM) technique. For the modeling, we considered 98 landslide locations, of which 70% (79) were used for training and 30% (19) for validation processes. Model validation was performed using sensitivity, specificity, accuracy, the root mean square error (RMSE) and the area under the receiver operatic characteristic (AUC) curve. We also used soft computing benchmark models, including SGD, logistic regression (LR), logistic model tree (LMT) and functional tree (FT) algorithms for model validation and comparison. The selected conditioning factors were significant in landslide occurrence but distance to road was found to be the most important factor. The ABSGD model (AUC= 0.860) outperformed the LR (0.797), SGD (0.776), LMT (0.740) and FT (0.734) models. Our results confirm that the combined use of a functional algorithm and a Meta classifier prevents over-fitting, reduces noise and enhances the power prediction of the individual SGD algorithm for the spatial prediction of landslides. [ABSTRACT FROM AUTHOR]

This paper presents novel hybrid machine learning models, namely Adaptive Neuro Fuzzy Inference System optimized by Particle Swarm Optimization (PSOANFIS), Artificial Neural Networks optimized by Particle Swarm Optimization (PSOANN), and Best First Decision Trees based Rotation Forest (RFBFDT), for landslide spatial prediction. Landslide modeling of the study area of Van Chan district, Yen Bai province (Vietnam) was carried out with the help of a spatial database of the area, considering past landslides and 12 landslide conditioning factors. The proposed models were validated using different methods such as Area under the Receiver Operating Characteristics (ROC) curve (AUC), Mean Square Error (MSE), Root Mean Square Error (RMSE). Results indicate that the RFBFDT (AUC = 0.826, MSE = 0.189, and RMSE = 0.434) is the best method in comparison to other hybrid models, namely PSOANFIS (AUC = 0.76, MSE = 0.225, and RMSE = 0.474) and PSOANN (AUC = 0.72, MSE = 0.312, and RMSE = 0.558). Thus, it is reasonably concluded that the RFBFDT is a promising hybrid machine learning approach for landslide susceptibility modeling. [ABSTRACT FROM AUTHOR]

The main objective of this research was to introduce a novel machine learning algorithm of alternating decision tree (ADTree) based on the multiboost (MB), bagging (BA), rotation forest (RF) and random subspace (RS) ensemble algorithms under two scenarios of different sample sizes and raster resolutions for spatial prediction of shallow landslides around Bijar City, Kurdistan Province, Iran. The evaluation of modeling process was checked by some statistical measures and area under the receiver operating characteristic curve (AUROC). Results show that, for combination of sample sizes of 60%/40% and 70%/30% with a raster resolution of 10 m, the RS model, while, for 80%/20% and 90%/10% with a raster resolution of 20 m, the MB model obtained a high goodness-of-fit and prediction accuracy. The RS-ADTree and MB-ADTree ensemble models outperformed the ADTree model in two scenarios. Overall, MB-ADTree in sample size of 80%/20% with a resolution of 20 m (area under the curve (AUC) = 0.942) and sample size of 60%/40% with a resolution of 10 m (AUC = 0.845) had the highest and lowest prediction accuracy, respectively. The findings confirm that the newly proposed models are very promising alternative tools to assist planners and decision makers in the task of managing landslide prone areas. [ABSTRACT FROM AUTHOR]

In this study, land subsidence susceptibility was assessed for a study area in South Korea by using four machine learning models including Bayesian Logistic Regression (BLR), Support Vector Machine (SVM), Logistic Model Tree (LMT) and Alternate Decision Tree (ADTree). Eight conditioning factors were distinguished as the most important affecting factors on land subsidence of Jeong-am area, including slope angle, distance to drift, drift density, geology, distance to lineament, lineament density, land use and rock-mass rating (RMR) were applied to modelling. About 24 previously occurred land subsidence were surveyed and used as training dataset (70% of data) and validation dataset (30% of data) in the modelling process. Each studied model generated a land subsidence susceptibility map (LSSM). The maps were verified using several appropriate tools including statistical indices, the area under the receiver operating characteristic (AUROC) and success rate (SR) and prediction rate (PR) curves. The results of this study indicated that the BLR model produced LSSM with higher acceptable accuracy and reliability compared to the other applied models, even though the other models also had reasonable results. [ABSTRACT FROM AUTHOR]

Documenting habitats of rangeland plant species is required to properly manage rangelands and to understand ecosystem processes. A reliable rangeland species potential map can help managers and policy makers design a sustainable grazing system on rangelands. The aim of this study is to map the plant species in the Qurveh City rangelands, Kurdistan Province, Iran, using state-of-the-art machine learning algorithms, including Support Vector Machine (SVM), Artificial Neural Network (ANN), Naïve Bayes (NB), Bayes Net (BN) and Classification and Regression Tree (CART). A total of 185 rangeland species were used in the study, together with 20 conditioning factors, to build and validate models. The One-R feature section technique and multicollinearity test were used, respectively, to determine the most important factors and correlations between them. Model validation was performed using sensitivity, specificity, accuracy, F1-measure, Matthews correlation coefficient (MCC), Kappa, root mean square error (RMSE), and area under the receiver operating characteristic curve (AUC). Results showed that topographic wetness index (TWI), slope angle, elevation, soil phosphorus and soil potassium were the five most important factors to increase the rangeland plants habitat suitability. The Naïve Bayes algorithm (AUC = 0.782) had the highest performance and prediction accuracy and best consistency across the species in the investigated rangeland, followed by the SVM (AUC = 0.763), ANN (AUC = 0.762), CART (AUC = 0.627), and BN (AUC = 0.617) models. [Display omitted] • The habitats of important ecological rangeland plants were modeled and mapped. • Machine learning algorithms are robust tools in rangeland rehabilitation and management. • Topographic, phosphorus and potassium were the main factors to increase habitat suitability. • NB and CART had the highest and lowest prediction for studied species of investigated rangeland. • High potential rangeland habitats can help decision makers in better rangeland management. [ABSTRACT FROM AUTHOR]

• MCDM and machine learning models were compared for flood modelling. • Results show that machine learning is more potential for flood modelling. • Out of machine learning methods, NB outperforms NBT. • Out of MCDM methods, SAW and VIKOR outperform TOPSIS. Floods around the world are having devastating effects on human life and property. In this paper, three Multi-Criteria Decision-Making (MCDM) analysis techniques (VIKOR, TOPSIS and SAW), along with two machine learning methods (NBT and NB), were tested for their ability to model flood susceptibility in one of China's most flood-prone areas, the Ningdu Catchment. Twelve flood conditioning factors were used as input parameters: Normalized Difference Vegetation Index (NDVI), lithology, land use, distance from river, curvature, altitude, Stream Transport Index (STI), Topographic Wetness Index (TWI), Stream Power Index (SPI), soil type, slope and rainfall. The predictive capacity of the models was evaluated and validated using the Area Under the Receiver Operating Characteristic curve (AUC). While all models showed a strong flood prediction capability (AUC > 0.95), the NBT model performed best (AUC = 0.98), suggesting that, among the models studied, the NBT model is a promising tool for the assessment of flood-prone areas and can allow for proper planning and management of flood hazards. [ABSTRACT FROM AUTHOR]

Abstract Nowadays, a number of machine learning prediction methods are being applied in the field of landslide susceptibility modeling of the large area especially in the difficult hilly terrain. In the present study, hybrid machine learning approaches of Reduced Error Pruning Trees (REPT) and different ensemble techniques were used for the construction of four novel hybrid models namely Bagging based Reduced Error Pruning Trees (BREPT), MultiBoost based Reduced Error Pruning Trees (MBREPT), Rotation Forest-based Reduced Error Pruning Trees (RFREPT), Random Subspace-based Reduced Error Pruning Trees (RSREPT) for landslide susceptibility assessment and prediction. In total, ten topographical and geo-environmental landslide conditioning factors were considered for analyzing their spatial relationship with landslide occurrences. Receiver Operating Characteristic curve, Statistical Indexes, and Root Mean Square Error methods were used to validate performance of these models. Analysis of model results indicate that the BREPT is the best model for landslide susceptibility assessment in comparison to other models. Highlights • New hybrid models of REPT and its ensembles developed for landslide susceptibility modeling. • RMSE, accuracy, Chi square test, and ROC curve used for validation of the models. • Results indicate that BREPT is the best method for modeling of landslide susceptibility. [ABSTRACT FROM AUTHOR]

Floods are one of the most damaging natural hazards causing huge loss of property, infrastructure and lives. Prediction of occurrence of flash flood locations is very difficult due to sudden change in climatic condition and manmade factors. However, prior identification of flood susceptible areas can be done with the help of machine learning techniques for proper timely management of flood hazards. In this study, we tested four decision trees based machine learning models namely Logistic Model Trees (LMT), Reduced Error Pruning Trees (REPT), Naïve Bayes Trees (NBT), and Alternating Decision Trees (ADT) for flash flood susceptibility mapping at the Haraz Watershed in the northern part of Iran. For this, a spatial database was constructed with 201 present and past flood locations and eleven flood-influencing factors namely ground slope, altitude, curvature, Stream Power Index (SPI), Topographic Wetness Index (TWI), land use, rainfall, river density, distance from river, lithology, and Normalized Difference Vegetation Index (NDVI) . Statistical evaluation measures, the Receiver Operating Characteristic (ROC) curve, and Freidman and Wilcoxon signed-rank tests were used to validate and compare the prediction capability of the models. Results show that the ADT model has the highest prediction capability for flash flood susceptibility assessment, followed by the NBT, the LMT, and the REPT, respectively. These techniques have proven successful in quickly determining flood susceptible areas. [ABSTRACT FROM AUTHOR]

• A new robustness deep learning model, DEBP, was developed for flood susceptibility mapping. • The IGR feature selection was applied to determine the most important flood conditioning factors. • The proposed model was optimized by PSO to enhance the goodness-of-fit and prediction accuracy. • The DEBP model outperformed the ANNRBF, LR, LMTree, FTree, and ADTree machine learning algorithms. • The new proposed model was offered as a promising and trustworthy tool for flood mitigation. This paper introduces a new deep-learning algorithm of deep belief network (DBN) based on an extreme learning machine (ELM) that is structured by back propagation (BN) and optimized by particle swarm optimization (PSO) algorithm, named DEBP, for flood susceptibility mapping in the Vu Gia-Thu Bon watershed, central Vietnam. We use 847 locations of floods that occurred in 2007, 2009, and 2013 and 16 flood conditioning factors evaluated by an information gain ratio (IGR) technique to construct and validate the proposed model. Statistical metrics, including sensitivity, specificity, accuracy, F1-measure, Jaccard coefficient, Matthews correlation coefficient (MCC), root mean square error (RMSE), and area under the receiver operating characteristic curve (AUC), are used to assess the goodness-of-fit/performance and prediction accuracy of the new deep learning model. We further compare the proposed model with several well-known machine learning algorithms, including artificial neural network-based radial base function (ANNRBF), logistic regression (LR), logistic model tree (LMTree), functional tree (FTree), and alternating decision tree (ADTree). The new proposed model, DEBP, has the highest goodness-of-fit (AUC = 0.970) and prediction accuracy (AUC = 0.967) of all of the tested models and thus shows promise as a tool for flood susceptibility modeling. We conclude that novel deep learning algorithms such as the one used in this study can improve the accuracy of flood susceptibility maps that are required by planners, decision makers, and government agencies to manage of areas vulnerable to flood-induced damage. [ABSTRACT FROM AUTHOR]