Landslides are one of the most dangerous hazards in Vietnam. Most landslides occur at excavated slopes, and natural slope failures are rare in the country. However, the volume of natural slope failures can be very significant and can badly affect large areas. After a long period of heavy rainfall in the fourth quarter of 2005 in Van Canh district, a series of landslides with volumes of 20,000–195,000 m³ occurred on 15 December 2005. The travel distances for the landslides reached over 300–400 m, and the landslides caused some remarkable loud booming noises. The failures took place on natural slopes with unfavorable geological settings and slope angles of 28–31°. The rainfall in the fourth quarter of 2005 is estimated to have a return period of 100 years and was the main triggering factor. Because of the large affected area and low population density, resettling people from the dangerous landslide-prone residential areas to safer sites was the most appropriate solution. In order to do so, a map of landslide susceptibility was produced that took into account slope angle, distance to faults, and slope aspect. The map includes four levels from low to very high susceptibility to landslides.

Development of landslide predictive models with strong prediction power has become a major focus of many researchers. This study describes the first application of the Hyperpipes (HP) algorithm for the development of the five novel ensemble models that combine the HP algorithm and the AdaBoost (AB), Bagging (B), Dagging, Decorate, and Real AdaBoost (RAB) ensemble techniques for mapping the spatial variability of landslide susceptibility in the Nam Dan commune, Ha Giang province, Vietnam. Information on 76 historical landslides and ten geo-environmental factors (slope degree, slope aspect, elevation, topographic wetness index, curvature, weathering crust, geology, river density, fault density, and distance from roads) were used for the construction of the training and validation datasets that are the prerequisites for building and testing the proposed models. Using different performance metrics (i.e., the area under the receiver operating characteristic curve (AUC), negative predictive value, positive predictive value, accuracy, sensitivity, specificity, root mean square error, and Kappa), we verified the proficiency of all five ensemble learning techniques in increasing the fitness and predictive powers of the base HP model. Based on the AUC values derived from the models, the ensemble ABHP model that yielded an AUC value of 0.922 was identified as the most efficient model for mapping the landslide susceptibility in the Nam Dan commune, followed by RABHP (AUC = 0.919), BHP (AUC = 0.909), Dagging-HP (AUC = 0.897), Decorate-HP (AUC = 0.865), and the single HP model (AUC = 0.856), respectively. The novel ensemble models proposed for the Nam Dan commune and the resultant susceptibility maps can aid land-use planners in the development of efficient mitigation strategies in response to destructive landslides.