Although coastal classification has been attended in recent years, it is still a complicated problem in quantitative geomorphological and hydrological sciences. Nowadays, the integration of deep learning in remote sensing and GIS analysis can quickly classify and detect different characteristics on both land and sea. Therefore, the authors proposed the use of a convolutional neural network (ConvNet) for coastal classification based on these technologies and geomorphic profile graphs. The primary input data is digital elevation/depth models obtained from ALOS and NOAA satellite. Eight hundred coastal samples representing eight types of coasts taken along the coastline in Vietnam were used for training and testing various ConvNets. As a result, three ConvNet models using three different optimizer functions were developed with the accuracies of about 98% and low values of the loss function. These models were used to classify 1029 in 1150 coasts (equal to 89%) in Vietnam. Nearly 11% of Vietnamese coasts could not be defined by three ConvNet models due to their complex geomorphic profile graphs, and require assessments of other natural components. The trained ConvNet models can potentially update new coastal types in different tropical countries towards coastal classification on national and global scales.

Landslides affect properties and the lives of a large number of people in many hilly parts of Vietnam and in the world. Damages caused by landslides can be reduced by understanding distribution, nature, mechanisms and causes of landslides with the help of model studies for better planning and risk management of the area. Development of landslide susceptibility maps is one of the main steps in landslide management. In this study, the main objective is to develop GIS based hybrid computational intelligence models to generate landslide susceptibility maps of the Da Lat province, which is one of the landslide prone regions of Vietnam. Novel hybrid models of alternating decision trees (ADT) with various ensemble methods, namely bagging, dagging, MultiBoostAB, and RealAdaBoost, were developed namely B-ADT, D-ADT, MBAB-ADT, RAB-ADT, respectively. Data of 72 past landslide events was used in conjunction with 11 landslide conditioning factors (curvature, distance from geological boundaries, elevation, land use, Normalized Difference Vegetation Index (NDVI), relief amplitude, stream density, slope, lithology, weathering crust and soil) in the development and validation of the models. Area under the receiver operating characteristic (ROC) curve (AUC), and several statistical measures were applied to validate these models. Results indicated that performance of all the models was good (AUC value greater than 0.8) but B-ADT model performed the best (AUC= 0.856). Landslide susceptibility maps generated using the proposed models would be helpful to decision makers in the risk management for land use planning and infrastructure development.