Google's DeepMind AI can predict weather conditions with greater speed and better accuracy

Reading time icon 1 min. read


Readers help support MSPoweruser. When you make a purchase using links on our site, we may earn an affiliate commission. Tooltip Icon

Read the affiliate disclosure page to find out how can you help MSPoweruser effortlessly and without spending any money. Read more

Google DeepMind has developed a new AI model called GraphCast that can predict weather conditions up to 10 days in advance with greater accuracy than the current gold standard. This discovery has the potential to improve weather forecasting and disaster preparedness greatly.

GraphCast uses machine learning to do these calculations in under a minute. At the same time, traditional weather forecasting models are very energy-intensive and time-consuming. Meteorologists could make more timely and accurate predictions with the help of this speed and efficiency.

The European Centre for Medium-Range Weather Forecasts (ECMWF) is already using GraphCast, and other weather agencies are also developing their models based on the graph neural network architecture proposed by Google DeepMind.

GraphCast has much potential and still needs to catch up to conventional weather forecasting models in some areas, such as precipitation. However, it is a significant improvement over current methods. It could help to save lives by providing more accurate warnings of extreme weather events.

Google DeepMind is making GraphCast open source, allowing scientists to improve the model and develop new applications. This is a good development as it will help to accelerate progress in weather forecasting and other areas.