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 Appl. Sci. 2019, 9, 2824 2 of 24 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.

The main objective of this study is to produce a landslide susceptibility map for the Lao Cai area (Vietnam) using a new hybrid intelligent method based on least squares support vector machines (LSSVM) and artificial bee colony (ABC) optimization, namely LSSVM-BC. LSSVM and ABC are state-of-the-art soft computing techniques that have been rarely utilized in landslide susceptibility assessment. LSSVM is adopted to develop landslide prediction model whereas ABC was used to optimize the prediction model by identifying an appropriate set of the LSSVM hyper-parameters. To establish the hybrid intelligent method, a GIS database with ten landslide-influencing factors and 340 landslide locations that occurred mainly during the last 20-years was constructed. These historical landslide locations were collected from the existing inventories that sourced from (i) five landslide projects carried out in this study areas before and (ii) interpretations of SPOT satellite images with resolution of 2.5 m. The study area was geographically split into two different parts, with landslides located in the first part was used for building models whereas the other landslides in the second part was used for the model validation. Performance of the LSSVM-BC model was assessed using the receiver operating characteristic (ROC) curve and area under the curve (AUC). Result shows that the prediction power of the model is good with the area under the curve (AUC) = 0.900. Experiments have pointed out the prediction power of the LSSVM-BC is better than that obtained from the popular support vector machines. Therefore, the proposed model is a promising tool for spatial prediction of landslides at the study area. The landslide susceptibility map is useful for landuse planning for the Lao Cai area.

A R T I C L E I N F O Keywords: Susceptibility modeling Discriminant analysis Multi-layer perceptron neural network GIS A B S T R A C T With the increasing threat of recurring landslides, susceptibility maps are expected to play a bigger role in promoting our understanding of future landslides and their magnitude. This study describes the development and validation of a spatially explicit deep learning (DL) neural network model for the prediction of landslide susceptibility. A geospatial database was generated based on 217 landslide events from the Muong Lay district (Vietnam), for which a suite of nine landslide conditioning factors was derived. The Relief-F feature selection method was employed to quantify the utility of the conditioning factors for developing the landslide predictive model. Several performance metrics demonstrated that the DL model performed well both in terms of the goodness-of-fit with the training dataset (AUC = 0.90; accuracy = 82%; RMSE = 0.36) and the ability to predict future landslides (AUC = 0.89; accuracy = 82%; RMSE = 0.38). The efficiency of the model was compared to the quadratic discriminant analysis, Fisher's linear discriminant analysis, and multi-layer percep-tron neural network. A comparative analysis using the Wilcoxon signed-rank tests revealed a significant improvement of landslide prediction using the spatially explicit DL model over these other models. The insights provided from this study will be valuable for further development of landslide predictive models and spatially explicit assessment of landslide-prone regions around the world.

Risk of flash floods is currently an important problem in many parts of Vietnam. In this study, we used four machine-learning methods, namely Kernel Logistic Regression (KLR), Radial Basis Function Classifier (RBFC), Multinomial Naïve Bayes (NBM), and Logistic Model Tree (LMT) to generate flash flood susceptibility maps at the minor part of Nghe An province of the Center region (Vietnam) where recurrent flood problems are being experienced. Performance of these four methods was evaluated to select the best method for flash flood susceptibility mapping. In the model studies, ten flash flood conditioning factors, namely soil, slope, curvature, river density, flow direction, distance from rivers, elevation, aspect, land use, and geology, were chosen based on topography and geo-environmental conditions of the site. For the validation of models, the area under Receiver Operating Characteristic (ROC), Area Under Curve (AUC), and various statistical indices were used. The results indicated that performance of all the models is good for generating flash flood susceptibility maps (AUC = 0.983-0.988). However, performance of LMT model is the best among the four methods (LMT: AUC = 0.988; KLR: AUC = 0.985; RBFC: AUC = 0.984; and NBM: AUC = 0.983). The present study would be useful for the construction of accurate flash flood susceptibility maps with the objectives of identifying flood-susceptible areas/zones for proper flash flood risk management.

Indra Prakash (2020): Ensemble modeling of landslide susceptibility using random subspace learner and different decision tree classifiers, Geocarto International, ABSTRACT In this study, we have developed five spatially explicit ensemble predictive machine learning models for the landslide susceptibility mapping of the Van Chan district of the Yen Bai Province, Vietnam. In the model studies, Random Subspace (RSS) was used as the ensemble learner with Best First Decision Tree (BFT), Functional Tree (FT), J48 Decision Tree (J48DT), Naïve Bayes Tree (NBT) and Reduced Error Pruning Trees (REPT) as the base classi-fiers. Data of 167 past and present landslides and various landslide conditioning factors were used for generation of the datasets. The results showed that the RSSFT model achieved the highest performance in terms of Fgiurepredicting future landslides , followed by RSSREPT, RSSBFT, RSSJ48, and RSSNBT, respectively. Therefore, the RSSFT model was found to be more robust model than the other studied models, which can be used in other areas of landslide susceptibility mapping for proper landuse planning and management. ARTICLE HISTORY

Landslide is a natural hazard which causes huge loss of properties and human life in many places of the world. Mapping of landslide susceptibility is an important task for preventing and combating the landslides problems. Main objective of this study is to use different artificial intelligence methods namely support vector machines (SVM), artificial neural networks (ANN), logistic regression (LR), and reduced error-pruning tree (REPT) in the development of models for landslide susceptibility mapping of Muong Lay district of Vietnam. In total data of 217 landslide locations of the study area was used for the development and evaluation of the models. Nine landslide-conditioning factors were used for generating the datasets for training and validating the models. Results show that the SVM outperformed all other methods namely ANN, LR and REPT. Thus, it can be suggested that the SVM method is more useful in developing accurate and robust landslide prediction model. ARTICLE HISTORY

Land subsidence (LS) is a significant problem that can cause loss of life, damage property, and disrupt local economies. The Semnan Plain is an important part of Iran, where LS is a major problem for sustainable development and management. The plain represents the changes occurring in 40% of the country. We introduce a novel-ensemble intelligence approach (called ANN-bagging) that uses bagging as a meta-or ensemble-classifier of an artificial neural network (ANN) to predict LS spatially on the Semnan Plain in Semnan Province, Iran. The ensemble model's goodness-of-fit (to training data) and prediction accuracy (of the validation data) are compared to benchmarks set by ANN-bagging. A total of 96 locations of LS and 12 LS conditioning factors (LSCFs) were collected. Each feature in the LS inventory map (LSIM) was randomly assigned to one of four groups or folds, each comprising 25% of cases. The novel ensemble model was trained using 75% (3 folds) and validated with the remaining 25% (1 fold) in a four-fold cross-validation (CV) system, which is used to control for the effects of the Science of the Total Environment 726 (2020) 138595 Ensemble method K-fold cross-validation (CV) Land-subsidence susceptibility Semnan Plain random selection of the training and validation datasets. LSCFs for LS prediction were selected using the information-gain ratio and multi-collinearity test methods. Factor significance was evaluated using a random forest (RF) model. Groundwater drawdown, land use and land cover, elevation, and lithology were the most important LSCFs. Using the k-fold CV approaches, twelve LS susceptibility maps (LSSMs) were prepared as each fold employed all three models (ANN-bagging, ANN, and bagging). The LS susceptibility mapping showed that between 5.7% and 12.6% of the plain had very high LS susceptibility. All three models produced LS susceptibility maps with acceptable prediction accuracies and goodness-of-fits, but the best maps were produced by the ANN-bagging ensemble method. Overall, LS risk was highest in agricultural areas with high groundwater draw-down in the flat lowlands on quaternary sediments (Qcf). Groundwater extraction rates should be monitored and potentially limited in regions of severe or high LS susceptibility. This investigation details a novel methodology that can help environmental planners and policy makers to mitigate LS to help achieve sustainability.

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 ¼ 0.741) in comparison to RFANN (AUC ¼ 0.710), RFSVM (AUC ¼ 0.701), and RFNB (AUC ¼ 0.640) models. The present study would be helpful in the selection of best model for landslide susceptibility mapping. ARTICLE HISTORY