AI Models Misjudge Extreme Weather Events
A study published in the journal Science Advances found that AI models are less accurate when predicting very hot weather, very cold weather, and wind storms. While previous tests showed AI effectiveness for everyday weather, these findings suggest limitations for extreme events. The research has implications for how weather agencies apply AI technology to forecasting. The study was conducted in Switzerland. A new study by climate scientists in Germany and Switzerland found that AI weather models misjudge extremely hot and extremely cold weather events. Researchers compared AI models against traditional forecasting models that utilize physics to determine predictive accuracy.
Topics
Developing
- 862d Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore.
- 862d Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
- 862d Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est.
- 862d Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium.
Sources · 7 independent
KQED FM
“the new study finds that doesn't extend to extreme weather events. The findings have implications for how weather agencies might apply AI technology to forecasting.”
KQED FM
“found that AI was not as accurate when it came to very hot weather, very cold weather, and wind storms. The study was published in the journal Science Advances.”
WBUR Boston
“NPR's Rebecca Hurser reports a new study finds AI misjudges extremely hot and extremely cold weather. Researchers compared AI weather models to other forecasting models that use physics.”
Unlock the full story
Get a Pro subscription or above to see the live story progression and the full list of independent sources confirming each event as they happen.
Log in to upgrade