Flood susceptibility assessment using hybrid machine learning and remote sensing in Quang Tri province, Vietnam

Abstract

Flooding is the most dangerous of all environmental hazards and leads to significant impacts both on the environment and on human life. Environmental protection and water management can be achieved by modeling flood susceptibility, to inform strategy that will reduce flood damage. The aim of this study is to develop novel hybrid models based on a radial basis functions neural network (RBFNN), arithmetic optimization algorithm (AOA), artificial bee colony (ABC), and ant lion optimizer (ALO), to build flood susceptibility maps in the Quang Tri province of Vietnam. The obtained models were trained and validated using 1511 flood points and 14 conditioning factors. Various statistical indices were used to assess the performance of the models, namely root mean square error, receiver operation characteristics (ROC), area under the receiver operating characteristic curve (AUC), and the coefficient of determination (R2). The comparison analysis highlights that the RBFNN‐ABC model was better than other models with an AUC of 0.98, followed by RBFNN‐AOA, support vector machine, and random forest, all with an AUC value of 0.96, and finally RBFNN‐ALO, with an AUC of 0.95. From the flood susceptibility map, it can be seen that the eastern areas of the study area have high and very high flood susceptibility, that requires local government attention. The approach and results of this study can support national and local authorities, decision‐makers, and other planners in the construction of appropriate strategies to reduce potential damage in the future.

Multi‐hazard assessment using machine learning and remote sensing in the North Central region of Vietnam

“…Such floods are caused by sea level rise; for these events, rainfall is not an important factor. This has been echoed in previous studies (Nguyen, 2022a).…”

“…Considering the statistical relationships between the conditioning factors and inventory points based on RF, we can see that topographical factors such as elevation and slope are the most influential factors on the probability of flood occurrence in the study area. Several studies have shown that topography influences the hydrological regime that leads to flood (Nguyen, 2022a(Nguyen, , 2022b(Nguyen, , 2022cPham, Vu, et al, 2022). Distance to road, soil, and NDVI ranked third to fifth most important of the 13 factors used.…”

“…All models have their own advantages and disadvantages, and their performance depends on the input data used and the model's structure. There is no single model that can be used for all types of natural hazards and all regions (Nguyen, 2022a). Karakas et al (2023) used RF to construct a multi-hazard map (flooding, landslides, and earthquakes) in the Elazig Province of Turkiye; the results showed that RF was successfully constructing the multi-hazard map with precision.…”

“…In addition, several studies have pointed out that knowledge of the areas of potential occurrence of natural hazards is paramount for decision makers involved in economic development and new infrastructure programs (Arabameri et al, 2022; Chang et al, 2022; Nguyen, 2022a; Prasad et al, 2022; Saravanan & Abijith, 2022).…”

“…All models have their own advantages and disadvantages, and their performance depends on the input data used and the model's structure. There is no single model that can be used for all types of natural hazards and all regions (Nguyen, 2022a).…”