AI-powered weather forecasting promises precise predictions at lightning speed
When Hurricane Beryl was reeling through the Caribbean, European weather forecasters warned Mexicans to take heed. But, when GraphCast, an AI-powered tool from Google’s DeepMind predicted Beryl would make landfall in southeastern Texas, it was Houston, Texas that took the hit on July 8, 2024.
“This is a really exciting step,” Matthew Chantry, an A.I. specialist at the European Center for Medium-Range Weather Forecasts, the agency that got upstaged on its Beryl forecast, told the New York Times.
Holy Hurricane, Batman, We Gotta Go
AI-powered weather forecasting can spot dangerous weather systems more quickly giving local authorities more time to prepare for the weather event and save lives in the process. AI-powered weather forecasting will also advance scientific discovery according to Dr. Amy McGovern, a professor of meteorology and computer science at the University of Oklahoma. McGovern runs the National Science Foundation’s AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES). Using AI, meteorologists can rapidly visualize thousands of possible weather variations helping them to forecast what was previously unpredictable, weather events such as tornadoes. “It’s letting us look for fundamental processes. It’s a valuable tool to discover new things,” Dr. McGovern said.
A new twist on predicting twisters
“It’s a turning point,” Maria Molina, a research meteorologist at the University of Maryland who studies AI programs for extreme-event prediction. “You don’t need a supercomputer to generate a forecast. You can do it on your laptop, which makes the science more accessible.”
Instead of predicting weather based on real-time readings and millions of calculations, an AI agent uses the data it’s accumulated about the cause-and-effect relationships that drive Earth’s weather.
The A.I. approach is radically different. Instead of relying on current readings and millions of calculations, an A.I. agent draws on what it has learned about the cause-and-effect relationships, the patterns that govern the planet’s weather.
AI weather forecasting still needs people power
Jamie Rhome, deputy director of the U.S. National Hurricane Center in Miami, called A.I. “evolutionary rather than revolutionary” and predicted that humans and supercomputers would continue to play major roles.
“Having a human at the table to apply situational awareness is one of the reasons we have such good accuracy,” he said.
Mr. Rhome added that the hurricane center had used aspects of artificial intelligence in its forecasts for more than a decade, and that the agency would evaluate and possibly draw on the brainy new programs.
“With A.I. coming on so quickly, many people see the human role as diminishing,” Mr. Rhome added. “But our forecasters are making big contributions. There’s still very much a strong human role.”
#AItoday #AI #machinelearning #weatherforecasting
Keep up with the latest AI news, insight, and analysis.
