A Google research lab says it has developed an AI-based application that can produce two-week weather forecasts with unprecedented accuracy and speed. GenCast shows “better prediction capabilities” than the current, world-leading model, the internet company announced on Wednesday.
The benchmark for meteorological accuracy is data from the European Center for Medium-Range Weather Forecasts (ECMWF), which produces forecasts for 35 countries. According to London-based AI research lab DeepMind, GenCast’s predictions exceeded the center’s predictions 97 percent of the time, using 1,320 real-world scenarios from 2019 as a testing basis. The results were also published in the scientific journal “Nature”.
ECMWF chief Florence Rabier said the project was a first step towards integrating AI into weather forecasting and was “indeed a leap forward”. The AI weather forecast was trained using temperature, wind speed and barometric pressure data from 1978 to 2018. It can now produce a two-week forecast in eight minutes, which currently takes several hours.
“Protect lives, prevent damage, save money”
GenCast offers better daily forecasts, as well as better forecasts for extreme weather events, according to a statement from DeepMind. Given the increasing frequency of extreme weather events due to climate change, developers point out the associated opportunities to save human lives. More accurate predictions of the risks of extreme weather events could help authorities “protect more lives, prevent damage and save money.”
Source: Krone
I am an experienced and passionate journalist with a strong track record in news website reporting. I specialize in technology coverage, breaking stories on the latest developments and trends from around the world. Working for Today Times Live has given me the opportunity to write thought-provoking pieces that have caught the attention of many readers.
