Discovering strategies for coastal resilience with AI-based prediction and optimization
🤖 AI Summary
Tropical storm–induced coastal flooding imposes substantial economic losses and safety risks.
Method: We propose an AI-driven decision framework for the joint optimization of flood mitigation interventions—namely, intervention type, location, and scale—integrating generative storm surge simulation, a surrogate model for intervention efficacy, and a continuous-armed bandit optimization algorithm. The objective is to minimize expected regional flood loss while jointly accounting for capital and maintenance costs and risk reduction benefits.
Contribution/Results: Unlike conventional heuristic or greedy approaches, our framework enables globally near-optimal, data-informed decisions. A case study at Tyndall Air Force Base in Florida demonstrates that the framework significantly reduces expected flood losses compared to standard practices, with potential savings exceeding several billion USD. It establishes a scalable, data-driven, intelligent optimization paradigm for enhancing coastal resilience.
Application Category
📝 Abstract
Tropical storms cause extensive property damage and loss of life, making them one of the most destructive types of natural hazards. The development of predictive models that identify interventions effective at mitigating storm impacts has considerable potential to reduce these adverse outcomes. In this study, we use an artificial intelligence (AI)-driven approach for optimizing intervention schemes that improve resilience to coastal flooding. We combine three different AI models to optimize the selection of intervention types, sites, and scales in order to minimize the expected cost of flooding damage in a given region, including the cost of installing and maintaining interventions. Our approach combines data-driven generation of storm surge fields, surrogate modeling of intervention impacts, and the solving of a continuous-armed bandit problem. We applied this methodology to optimize the selection of sea wall and oyster reef interventions near Tyndall Air Force Base (AFB) in Florida, an area that was catastrophically impacted by Hurricane Michael. Our analysis predicts that intervention optimization could be used to potentially save billions of dollars in storm damage, far outpacing greedy or non-optimal solutions.
Problem
Research questions and friction points this paper is trying to address.
Optimizing coastal intervention strategies to reduce storm damage costs
Developing AI models to select effective flood mitigation interventions
Minimizing expected flooding damage through optimal intervention planning
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI-driven storm surge prediction modeling
Surrogate modeling for intervention impact assessment
Continuous-armed bandit problem optimization solving
🔎 Similar Papers
No similar papers found.
