Artificial Intelligence, a very efficient "meteorologist"

Artificial intelligence is also proving very efficient in the field of meteorology. Google has developed an Artificial Intelligence system capable of forecasting the weather for a period of 15 days and with unprecedented accuracy, thus saving many lives that would be lost due to increasingly frequent climate disasters, the company announced last week. The GenCast model invented by DeepMind, the AI research laboratory owned by Google and headquartered in London, "showed better forecasting capabilities" than the current reference model, according to Google. The European Center for Medium-Range Weather Forecasts currently makes forecasts for 35 countries and is considered a world reference in terms of meteorological accuracy. But now, Google says, GenCast outperforms the European center's forecasts in more than 97 percent of the 1,320 climate disasters recorded in 2019 on which the two models were tested. Google's model, developed over four decades from 1979 to 2018 based on multiple data sets - temperature, wind speed and atmospheric pressure - can produce a 15-day forecast in just eight minutes, compared to a delay of several hours today. "GenCast provides better forecasts of daily weather and extreme events ... and that up to 15 days in advance," a Google statement said. According to warnings from scientists, extreme weather conditions are becoming more frequent and severe due to human-induced climate change. In August 2024, several forest fires in Hawaii killed 100 people. US authorities were criticized at the time for not warning the population in time about the imminent nature of the fires. In the summer, a sudden heat wave that hit Morocco killed at least 21 people in 24 hours. And in September, Hurricane Helene killed 237 people in Florida and other states in the southeastern United States. According to Google, GenCast "systematically outperformed" the current reference model in terms of predicting extreme heat, extreme cold and violent wind speeds. "More accurate forecasts of the risks of extreme weather conditions can help authorities protect more lives, avoid significant property damage and save money," Google group representatives emphasized.