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.

In recent years, many landslides have occurred in Vietnam, particularly in the Northern mountainous region during the rainy season from May to October. On the morning of October 12, 2017, the Khanh waterfall landslide in Khanh Village, Hoa Binh Province, Northern Vietnam occurred. The landslide killed eighteen people and destroyed five houses. Topographical and geological surveys were conducted around the area to determine its causes. The rainfall data and flow discharge were also analyzed. The results showed that this collapse was different from some previous ones collapsed due to the erosion at the toe of the slope. Khanh waterfall landslide occurred due to the increasing amount of water in cracks and caves in the limestone layer in the slope. The collapse process was simulated based on Coulomb mixture theory. The numerical simulation results show similarities with the actual collapse process. The results provide indicators for assessing the risk of such limestone waterfall landslides in the future.

Landslide damage has been reported in many limestone areas in Europe, where the population lives close to limestone areas, and in Guilin in southern China and Ha Long in Vietnam, which are known for their unique limestone landscapes. There are few studies on the mechanism and type of landslide motion in and around such limestone areas. The lack of basic data is a problem for risk assessment and countermeasures in limestone areas. In this study, we summarized the causes and mechanisms of landslide occurrence, including geology and groundwater, focusing on six landslides that occurred in limestone areas in northern Vietnam, and classified them into six types of landslide movement. In the case of Japan, the occurrence of landslides in limestone areas is rare despite the wide distribution of limestone, and it is difficult to classify the type of movement. Differences in the landslide mechanisms are caused by the difference between limestones generated in the pelagic environment of Japan and limestones developed along the Tethys Sea coast, which are mixed with pelitic rocks as shallow-water sediments in Europe, China, and Vietnam. It is necessary to elucidate the relationship between landslides and the formation environment and sedimentary characteristics of limestone as an accretionary prism based on comparisons of a wide range of cases in future studies.