Communications of the ACM
AI Could Set Bar for Designing Hurricane-Resistant Buildings
NIST researchers paired 100 years of hurricane data with modern artificial intelligence techniques to simulate realistic storm trajectories and wind speeds.
Credit: B. Hayes/NIST/Shutterstock
U.S. National Institute of Standards and Technology (NIST) researchers have created a new digital hurricane modeling technique that more accurately simulates storm trajectory and wind speeds.
The researchers simulated the storms' inner workings to develop the latest maps; NIST's Adam Pintar said the team trained the model to mimic actual hurricane data with machine learning.
The training data came from the National Hurricane Center's Atlantic Hurricane Database (HURDAT2), which encompasses information about more than 1,500 hurricanes going back more than a century.
The researchers used the model to simulate sets of 100 years' worth of hypothetical storms in just seconds, which exhibited significant overlap with the HURDAT2 storms' behavior.
The team suggests this method can help to improve guidelines for designing hurricane-resistant buildings.
From NIST News
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA
No entries found