Year: 2026
Type: article
Abstract: Coastal flooding is increasing, with accelerating impacts ahead. Its impact, however, can be mitigated through proactive risk management, requiring comprehensive risk assessment. Using the US Gulf and Atlantic Coasts (USGAC) as a test bed, this study develops a framework to identify high-risk coastal cities and reveal underlying factors under dual-risk scenarios-general flood damage (GFD) and extreme flood damage (EFD). Using historical flood damage data and 16 factors representing hazard, exposure, and vulnerability, this study adopts three machine learning models-support vector machine, random forest, and multilayer perceptron-to assess flood risk. This study identifies eight coastal cities at high flood risk where New York City has the largest population at risk (GFD: 4.75 million; EFD: 4.40 million) and New Orleans City has the highest relative exposure (~99% under both). Coastal flood risk is greatest in low-lying, densely developed urban areas with high drainage density. Overall, this scalable framework offers actionable insights for policy-makers to manage floods in other flood-prone regions.
Source: Science Advances
Authors: Hemal Dey, Wanyun Shao
Institution: University of Alabama
Language: English
Subfield: Global and Planetary Change
Field: Environmental Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $4,500
Award: G136433309
OpenAlex ID: W7155177102