- Google DeepMind AI can predict storms like Debi faster than normal methods
An AI developed by Google can accurately predict the weather up to ten days in advance, outperforming traditional forecasting methods and even top supercomputers.
The new Google DeepMind model GraphCast was trained on 40 years of meteorological data from weather stations, satellite images and radar recordings and, thanks to its machine learning, can produce forecasts in less than a minute.
The tool was used to predict the path of Hurricane Lee in September three days ahead of traditional methods, as it was recognized that it would make landfall in Nova Scotia nine days before it arrived.
The forecasts produced by GraphCast could mean storms like Debi, which hit the south coast this week, could be detected much earlier.
An AI developed by Google can accurately predict the weather up to ten days in advance, outperforming traditional forecasting methods and even top supercomputers
Pushmeet Kohli, vice president of research at Google DeepMind, said: “Weather forecasting is one of the most challenging problems humanity has been working on in a long time.”
“GraphCast is really very accurate and incredibly fast compared to traditional systems.” It can make predictions in less than a minute. It’s very exciting.’
The developers said the technology “marks a turning point in weather forecasting.”
A paper published Tuesday in the journal Science concluded that Google’s AI is more accurate than the most advanced forecasting system, the European Medium Range Weather Forecasting Model.
It was able to outperform the EMRWFM on 90 percent of the 1,380 metrics tested, including temperature, barometric pressure, wind speed, humidity and atmospheric level.
The forecasts produced by GraphCast could mean storms like Debi, which hit the south coast this week, could be detected much earlier (waves breaking in Folkestone, Kent).
Matthew Chantry, machine learning coordinator at ECMWF, said weather forecasting systems were “progressing much faster and more impressively than we expected just two years ago.”
Remy Lam of Google DeepMind said that AI cannot yet replace the supercomputers currently in use and that the new technology will complement the older system.
“We stand on the shoulders of giants to build these models,” he said, according to the BBC.
“AI models are trained from data and this data is generated using traditional approaches, so we still need the traditional approach to collect data to train the model,” Mr Lam said.
You didn’t expect this! Google DeepMind AI can accurately predict the weather up to 10 days in advance, leaving meteorologists and even top supercomputers out in the cold