The objective of this research is introduce a new machine learning ensemble approach that is a hybridization of Bagging ensemble (BE) and Logistic Model Trees (LMTree), named as BE-LMtree, for improving the performance of the landslide susceptibility model. The LMTree is a relatively new machine learning algorithm that was rarely explored for landslide study, whereas BE is an ensemble framework that has proven highly efficient for landslide modeling. Upper Reaches Area of Red River Basin (URRB) in Northwest region of Viet Nam was employed as a case study. For this work, a GIS database for the URRB area has been established, which contains a total of 255 landslide polygons and eight predisposing factors i.e., slope, aspect, elevation, land cover, soil type, lithology, distance to fault, and distance to river. The database was then used to construct and validate the proposed BE-LMTree model. Quality of the final BE-LMTree model was checked using confusion matrix and a set of statistical measures. The result showed that the performance of the proposed BE-LMTree model is high with the classification accuracy is 93.81% on the training dataset and the prediction capability is 83.4% on the on the validation dataset. When compared to the support vector machine model and the LMTree model, the proposed BE-LMTree model performs better; therefore, we concluded that the BE-LMTree could prove to be a new efficient tool that should be used for landslide modeling. This research could provide useful results for landslide modeling in landslide prone areas.

Accurate and high resolution bathymetric data is a necessity for a wide range of coastal oceanographic research topics. Active sensing methods, such as ship-based soundings and Light Detection and Ranging (LiDAR), are expensive and time consuming solutions. Therefore, the significance of Satellite-Derived Bathymetry (SDB) has increased in the last ten years due to the availability of multi-constellation, multi-temporal, and multi-resolution remote sensing data as Open Data. Effective SDB algorithms have been proposed by many authors, but there is no ready-to-use software module available in the Geographical Information System (GIS) environment as yet. Hence, this study implements a Geographically Weighted Regression (GWR) based SDB workflow as a Geographic Resources Analysis Support System (GRASS) GIS module (i.image.bathymetry). Several case studies were carried out to examine the performance of the module in multi-constellation and multi-resolution satellite imageries for different study areas. The results indicate a strong correlation between SDB and reference depth. For instance, case study 1 (Puerto Rico, Northeastern Caribbean Sea) has shown an coefficient of determination (R²⁾ of 0.98 and an Root Mean Square Error (RMSE) of 0.61 m, case study 2 (Iwate, Japan) has shown an R² of 0.94 and an RMSE of 1.50 m, and case study 3 (Miyagi, Japan) has shown an R² of 0.93 and an RMSE of 1.65 m. The reference depths were acquired by using LiDAR for case study 1 and an echo-sounder for case studies 2 and 3. Further, the estimated SDB has been used as one of the inputs for the Australian National University and Geoscience Australia (ANUGA) tsunami simulation model. The tsunami simulation results also show close agreement with post-tsunami survey data. The i.mage.bathymetry module developed as a part of this study is made available as an extension for the Open Source GRASS GIS to facilitate wide use and future improvements.

In this paper, we present the identification of terrace field by using Feed-forward back propagation deep neural network in pixel-based and several cases of object-based approaches. Terrace field of Lao Cai area in Vietnam is identified from 5-meter RapidEye image. The image includes 5 bands: red, green, blue, rededge and nir-infrared. Reference data are set of terrace points and nonterrace points, which are generated by randomly selected from reference map. The reference data is separated into three sets: training set for training processing, validation set for generating optimal parameters of deep neural network model, and test set for assessing the accuracy of classification. Six optimal thresholds (T): 0.06, 0.09, 0.12, 0.14, 0.2 and 0.22 are chosen from Rate of Change graph, and then used to generate six cases of object-based classification. Deep neural network (DNN) model is built with 8 hidden layers, input units are 5 bands of RapidEye, and output is terrace and non-terrace classes. Each hidden layer includes 256 units – a large number, to avoid under-fitting. Activation function is Rectifier. Dropout and two regularization parameters are applied to avoid overfitting. Seven terrace maps are generated. The classification results show that the DNN is able to identify terrace field effectively in both pixel-based and object-based approaches. Pixel-based classification is the most accurate approach, achieves 90% accuracy. The values of object-based approaches are 88.5%, 87.3%, 86.7%, 86.6%, 85% and 85.3% correspond to the segmentation thresholds.