Flood Vulnerability Assessment Using the Triangular Fuzzy Number-based Analytic Hierarchy Process and Support Vector Machine Model for the Belt and Road Region

Abstract Floods are one of the most serious natural disasters. Flood disaster losses in the developing countries in the Belt and Road region are more than twice the global average. However, to date, the extent of the vulnerability of the Belt and Road Region remains poorly understood. This study sought to address this knowledge gap. In this study, the flood vulnerability throughout the Belt and Road region was evaluated by adopting the triangular fuzzy number-based analytic hierarchy process (TFN-AHP) and the support vector machine (SVM) model. According to the results, the vulnerability of most areas (47,105,300 km2) is low or extremely low, accounting for 93% of the Belt and Road region. The highly-vulnerable areas (accounting for 3.54%) are primarily concentrated in the southern and eastern parts of China, northern India, most areas of Bangladesh, the Indus Valley in Pakistan, the Nile River Basin in Egypt, and the central region of Indonesia. From a local perspective, in the Belt and Road region, many major cities have higher vulnerability, such as Beijing, Shanghai, and Hong Kong. Compared with the three typical cities, the level of vulnerability in other cities (including Bangkok, Bangalore, Cairo, Riyadh, and Moscow) is lower, due to their higher disaster reduction capability. Thus, these highly vulnerable regions and cities coincide with areas characterized by frequent economic activity and dense populations. Based on these results, this study provides scientific and technological evidence for the prevention and mitigation of flood disasters in the countries along the Belt and Road region.