Artificial Intelligence (AI) programs can now forecast extreme weather faster and more accurately than traditional forecasting methods.
That sort of thing could come in handy when, for instance, you're predicting where a hurricane will make landfall, and that's exactly what happened.
GraphCast, an experimental program created by DeepMind, which is owned by Google, correctly predicted that Hurricane Beryl would make landfall in Texas, according to The New York Times, while other European and American forecasts had Beryl making landfall in Mexico.
The software made the prediction based on what it had learned about the Earth's atmosphere and made a more accurate prediction than the European Centre for Medium-Range Weather Forecasts, one of the most respected forecasters on the planet.
AI-assisted forecasts are expected to predict extreme heat, high winds, downpours, and tornadoes in a matter of seconds, as opposed to the hours it takes now to feed loads of atmospheric information into a supercomputer and wait for a forecast.
A new weather prediction system also developed by Google, NeuralGCM, combines AI with traditional techniques and expects to be able to predict local weather events and changing weather patterns due to the overheating of the planet caused by carbon pollution.
The predictive capabilities could prove to be life-saving as extreme weather events become more and more common.
The use of predictive AI isn't new to the realm of forecasting extreme weather. Researchers at the National Institute of Standards and Technology have developed AI software that can accurately predict the trajectory and wind speed of future hurricanes.
AI is also being used to reduce the risk of catastrophic wildfires by evaluating risk mitigation tactics, as well as anticipating environmental factors like dryness and wind speed to understand how a wildfire might spread.
Maria Molina, a research meteorologist at the University of Maryland who studies AI programs for extreme-event prediction, told the New York Times, "It's a turning point. You don't need a supercomputer to generate a forecast. You can do it on your laptop, which makes the science more accessible."
"If you know where a cyclone is going, that's quite important," said Dr. Rémi Lam, GraphCast's lead scientist. "It's important for saving lives."
Join our free newsletter for weekly updates on the latest innovations improving our lives and shaping our future, and don't miss this cool list of easy ways to help yourself while helping the planet.
Cool Picks
