A novel hybrid approach to flood susceptibility assessment based on machine learning and land use change. Case study: a river watershed in Vietnam.

This study aims to develop a comprehensive approach including an analysis of the relationships between flood susceptibility and land-use change, based on the relevance vector machine (RVM) and coyote optimization algorithm (COA) models, applied to Gianh River watershed, Quang Binh province, Central Vietnam. Standard statistical indices, e.g. area under the curve (AUC), were used to assess the model performance. Comparative analyses emphasize that the COA successfully improves the performance of the RVM model (AUC = 0.99) and is also better than the reference models such as support vector machine (AUC = 0.98), gradient boosting machine (AUC = 0.97), random forest (AUC = 0.99), extra trees regressor (AUC = 0.98), and AdaBoost (AUC = 0.96). The improved model, when used in conjunction with land use maps, is able to show that urbanization has increased in flood-susceptible areas. The results highlight that urbanization has increased in the low and very low flood susceptibility areas by 110% between 2005 and 2020, while in the high and very high areas it has increased by 30 to 40%, despite urban and demographic growth. [ABSTRACT FROM AUTHOR]