Sign In

Communications of the ACM

ACM TechNews

How AI Can Make Weather Forecasting Less Cloudy

View as: Print Mobile App Share:
 Damage in Louisiana from Hurricane Zeta, one of 22 weather and climate disasters in the U.S. that did more than $1 billion of damage last year.

Artificial Intelligence is making existing weather prediction methods more efficient and contributing to increases in the speed and accuracy of forecasting, and it shows promise for tracking the paths of severe weather like tornadoes and hail with greater

Credit: Bill Feig/The Advocate/Associated Press

Scientists are applying artificial intelligence (AI) to weather and climate forecasting to boost accuracy and efficiency.

The University of Oklahoma's Amy McGovern used $20 million from the U.S. National Science Foundation to launch an institute for that purpose, in partnership with six other universities and private partners.

Their intent is to use AI to augment and supplement traditional weather forecasting methods.

Machine learning also is being explored to facilitate accurate nowcasting—rapidly-computed short-term predictions that are infeasible for traditional techniques.

Stephan Rasp at startup cautions that much of this research is still in the proof-of-concept stage, with AI successfully applied to simplified datasets, but still lacking many examples of actually enhancing weather and climate forecasts.

From The Wall Street Journal
View Full Article - May Require Paid Subscription


Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA


No entries found

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