Researchers from Princeton and Rutgers University have used reinforcement learning, a method frequently deployed to train artificial intelligence, to show how flexible responses can substantially increase the cost-effectiveness of steps to defend cities like New York against climate change.

The research is part of an attempt to grapple with the effort to make expensive, long-term investments to mitigate the impacts of climate change. The substantial uncertainty related to long-term climate change makes it difficult for political leaders to make investments now that are designed to protect citizens for decades or longer. The difficulty is enhanced by the vast number of variables that go into any such decision and by the fact that the variables are likely to shift in unforeseen ways.

“There is a lot of uncertainty regarding how much melting ice sheets will cause sea levels to rise, and a lot of controversy about how planners should consider the possibility of rapid ice-sheet loss. We show that if you can’t adapt flexibly and instead have to pick a single protection level now, there can be large tradeoffs between cost and safety,” said Robert Kopp, one of the study’s authors and a distinguished professor of Earth and planetary sciences at Rutgers. “Planning for high-end sea-level rise costs a lot, and there’s a good chance it won’t be necessary, but failing to plan for it can be devastating. Flexible approaches, like those we model with reinforcement learning, allow planners to protect against high-end rise without incurring excessive costs.”

In a March 18 article in the Proceedings of the National Academy of Sciences, the researchers looked at flooding, which has caused increasing damage along the coastal United States and around the world. Governments are building coastal defenses against flooding, but they cannot rely on past conditions to guide defenses that will be needed in the future.