The increasing severity and frequency of extreme weather events driven by rising temperatures have necessitated innovative solutions to protect the Earth and its future generations. One example comes in the form of a predictive model that combines the power of artificial intelligence with a century’s worth of data.
Researchers from the National Institute of Standards and Technology have developed a groundbreaking digital tool that can predict the trajectory and wind speed of future hurricanes using machine learning and the records of over 1,500 storms from the National Hurricane Center’s Atlantic Hurricane Database.
“Imagine you had a second Earth, or a thousand Earths, where you could observe hurricanes for 100 years and see where they hit on the coast, how intense they are. Those simulated storms, if they behave like real hurricanes, can be used to create the data in the maps almost directly,” NIST mathematical statistician and study co-author Adam Pintar said.
The study, published in Artificial Intelligence for the Earth Systems, had the model use algorithms to imitate data from previous hurricanes. It stands in contrast to previous methods that mathematically created hypothetical storms from scratch, using data like ocean surface temperatures and the Earth’s surface roughness — which isn’t always available.
The AI-based tool accurately replicated the path and wind speed of historical storms it had not previously encountered. It also effectively generated a collection of hypothetical weather events with properties like landfall that largely overlapped with storms from the Atlantic Hurricane Database.
“It performs very well. Depending on where you’re looking at along the coast, it would be quite difficult to identify a simulated hurricane from a real one,” Pintar said.
However, the system isn’t without flaws. The data it is fed does not account for the potential effects of rising temperatures, and the simulated storms produced for areas with less data were not as plausible.
“Hurricanes are not as frequent in, say, Boston as in Miami, for example. The less data you have, the larger the uncertainty of your predictions,” NIST Fellow Emil Simiu said.
Nonetheless, the information gleaned from its simulations benefits the most hurricane-prone regions in the U.S. along the Eastern Seaboard and the Gulf Coast, potentially helping develop guidelines for the construction of buildings that can better withstand gale-force winds.
Join our free newsletter for weekly updates on the coolest innovations improving our lives and saving our planet.