How to better forecast once-in-a-millennium weather events
Researchers have developed a hybrid forecasting method that combines the speed of AI with the physical accuracy of traditional models to better predict rare, extreme weather events. This approach addresses the current limitation where AI models often fail to account for 'gray swan' events not present in their training data.
Why it matters
Improving the prediction of extreme climate events is essential for disaster preparedness and mitigating the societal impacts of climate change.
edited by Gaby Clark , reviewed by Robert Egan
This article has been reviewed according to Science X's editorial process and policies . Editors have highlighted the following attributes while ensuring the content's credibility:
Add as preferred source Plumes of smoke from fires worsened by the extreme temperatures in Moscow, Russia, in 2010. Some areas recorded pollution levels ten times the normal levels for the capital. Credit: European Space Agency/CC BY-SA 3.0 IGO For all that day-to-day weather forecasts have improved, it remains a challenge to forecast events that might happen once in 1,000 years—like the deadliest heat waves.
Traditional supercomputer-based models can forecast these events, but they require a lot of time and energy. Meanwhile, newer forecasting models, based on artificial intelligence , are good at day-to-day forecasts but often fail to predict outlier events that weren't represented in their training data.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in