Sign In

Communications of the ACM

ACM TechNews

Stanford Researchers Use AI to Unlock Extreme Weather Mysteries

View as: Print Mobile App Share:
Extreme weather moves across the Midwest U.S., with supercell and lightning

Among other things, researchers determined that higher precipitation intensity was linked to higher atmospheric moisture flows from the Gulf of Mexico.

A machine-learning (ML) tool developed by Stanford University researchers aims to more accurately predict extreme weather events.

Researchers trained a ML algorithm to detect large-scale atmospheric circulation patterns tied to extreme precipitation, defined as above the 95th percentile, with a focus on the upper Mississippi and eastern Missouri watersheds. The algorithm found multiple factors responsible for increased extreme precipitation in the region and accurately identified more than 90% of extreme precipitation days.

"While we focused on the Midwest initially, our approach can be applied to other regions and used to understand changes in extreme events more broadly," said Stanford's Frances Davenport. "This will help society better prepare for the impacts of climate change."

From Stanford University
View Full Article


Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account