Communications of the ACM
DeepMind Accurately Forecasts Weather on a Desktop Computer
Conventional weather forecasts are the result of intensive processing of data from weather stations around the world.
Credit: Carlos Munoz Yague/Look At Science/Science Photo Library
Google DeepMind developed a machine-learning weather-forecasting model that outperformed the best conventional forecasting tools, as well as other artificial intelligence (AI)-based approaches.
The GraphCast model can run on a desktop computer and makes its predictions in minutes.
Researchers trained the model using estimates of past global weather made from 1979 to 2017 by physical models, allowing GraphCast to learn links between different weather variables.
The trained model uses the current state of global weather, and weather estimates from six hours earlier, to predict the weather six hours ahead.
The researchers found GraphCast could use global weather estimates from 2018 to make forecasts up to 10 days ahead in less than a minute, with the resulting predictions more accurate than those made by the European Centre for Medium-Range Weather Forecasts’ High RESolution forecasting system, which takes hours to forecast.
From Nature
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA
No entries found