By: Vivian Tang

In early July, Artificial Intelligence, also called AI, is now predicting global weather in a matter of minutes, when it once took hours.

Artificial intelligence software predicted that a hurricane would make landfall in Texas. Just four days later, Hurricane Beryl struck Texas, flooding the roads and killing at least 36 people.

Christopher S. Bretherton is an emeritus professor of atmospheric sciences at the University of Washington.

“In general, superfast A.I. can shine at spotting dangers to come for treacherous heats, winds and downpours. The usual warnings will be more up-to-date than right now, saving untold lives,” Bretherton said.

Amy McGovern is a professor of meteorology and computer science at the University of Oklahoma who directs an A.I. weather institute.

“Weather sleuths now use A.I. to create thousands of subtle forecast variations that let them find unexpected factors that can drive such extreme events as tornadoes,” McGovern said.

AI models can be run on desktop computers, making the technology much easier to control since they now rule the world’s global forecasting.

Maria Molina is a research meteorologist at the University of Maryland who studies A.I. programs for extreme-event prediction.

“It’s a turning point,” Molina said. “You don’t need a supercomputer to generate a forecast. You can do it on your laptop, which makes the science more accessible.”

People rely on accurate weather forecasting to plan and decide where to travel and what to pack based on natural disasters or other dangers.

Even now, accurate weather forecasts are incredibly hard to achieve, and weather forecasts may fail after a few days or hours.

“You have to blend data from many sources into a guess at what the atmosphere is doing right now,” Bretherton said. “These inputs are crucial and somewhat improvisational.”

Jamie Rhome is the deputy director of the National Hurricane Center in Miami. He agreed on the need for multiple tools. He 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,” Rhome said.“With A.I. coming on so quickly, many people see the human role as diminishing, but our forecasters are making big contributions. There’s still very much a strong human role.”

Many weather experts say that AI systems will likely complement the supercomputer approach because each way has its strengths.

https://www.nytimes.com/interactive/2024/07/29/science/ai-weather-forecast-hurricane.html