Public officials tasked with designing coastal defenses can achieve cost savings by implementing adaptable solutions that evolve with rising sea levels, according to a study conducted by scientists at Rutgers and Princeton universities. The research suggests that flexible approaches are more effective than static, one-time fixes in addressing the challenges posed by climate change.
The study utilized reinforcement learning, an artificial intelligence technique, to model decision-making processes for preserving coastal infrastructure over time. This method aims to assist planners and engineers working in areas like New York City and coastal New Jersey as they combat flooding.
Robert Kopp, a Distinguished Professor at Rutgers University and one of the study’s authors, highlighted the importance of weighing potential high-end sea-level rise outcomes when planning responses. “If you don’t give sufficient emphasis to it, you run the risk that you are under-adapted and will have very large damages,” he stated. Conversely, overemphasizing such outcomes could lead to excessive spending.
The researchers examined data on flooding impacts across U.S. coastlines and globally. Ning Lin, a professor at Princeton University involved in the study, noted that while climate projections remain uncertain over long periods, advances in data science can offer effective solutions through adaptable planning.
The study simulated Manhattan’s defense strategies against sea-level rise until 2100, comparing dynamic approaches that adjust seawall heights based on new data against static methods relying on historic flood projections. Findings indicated that dynamic strategies were more cost-effective and reduced risks better than other methods.
Reinforcement learning allows software programs to make decisions reinforced by positive results without explicit programmer instructions. This system was used to simulate various scenarios for future sea-level rises and corresponding decisions made every decade up to 2100.
Michael Oppenheimer from Princeton University emphasized the broader applicability of this method beyond New York City: “The method can be applied widely, although its benefit compared to other systems of analysis would vary from place to place.”
This research is part of efforts by the Megalopolitan Coastal Transformation Hub—a consortium funded by the National Science Foundation—to advance understanding of how coastal hazards interact with human decisions affecting climate adaptation in regions including New York City, New Jersey, and Philadelphia.
