More accurate weather forecasts could save lives. (NOAA photo, Unsplash) |
Over the past five years, "using AI to predict weather has evolved from an academic notion to operational tests at weather agencies in the U.S. and Europe," reports Eric Niiler of The Wall Street Journal. "In time, AI-based programs could calculate forecasts faster and at a lower cost than existing methods, scientists say."
This year, "Microsoft released a forecasting tool called Aurora that produces five-day global air-pollution predictions and 10-day weather forecasts 5,000 times faster than existing models run by the National Oceanic and Atmospheric Administration," Niiler writes. As the weather has become more severe and dangerous, faster and more accurate predictions are more important and could save lives.
To train Aurora, Microsoft researchers used "huge amounts of historical weather data so it could make those predictions," Niiler reports, "about 16 times more data than the amount used to train the latest version of the AI-powered chatbot ChatGPT, according to Paris Perdikaris, the project's principal researcher. . . . Microsoft expects to make Aurora publicly available in coming months to allow more people, including researchers at weather-forecasting agencies, to give it a test drive."
Other weather forecasting businesses and meteorology academics are working to develop their own AI tools. "The Weather Channel app and Weather Underground recently signed a deal with chip maker Nvidia to develop a global AI weather forecast program that can predict extreme weather events such as tornadoes, hurricanes and thunderstorms," Niiler adds. And groups of researchers are focusing on "developing AI forecasts to extend the warning time for tornado and hail warnings to an hour from the current 15 minutes."
No comments:
Post a Comment