Google DeepMind wins 2024 MacRobert Award

GraphCast signifies a breakthrough in weather forecasting. Leveraging advanced machine-learning algorithms and extensive datasets, this AI-driven technology delivers highly accurate and timely weather predictions. This advancement could help mitigate the effects of severe weather events and ultimately save lives.

The announcement of GraphCast as the MacRobert Award winner was made at the Royal Academy of Engineering’s annual Awards Dinner, held at The Peninsula Hotel in London. The Google DeepMind team was presented with the MacRobert Award gold medal and a £50,000 prize by Vice Admiral Sir Tim Laurence KCVO CB, on behalf of the Academy’s Royal Fellow, HRH The Princess Royal. Sir Tim also serves as Chair of Trustees at the Science Museum Group.

Celebrating its 55th year, the MacRobert Award honours UK engineering skills and innovation that uphold the nation’s esteemed engineering heritage. To win, teams must demonstrate exceptional engineering ingenuity, proven commercial success, and tangible social benefits.

GraphCast departs from traditional numerical weather prediction methods, using machine learning to provide precise and timely forecasts up to ten days in advance. By utilising graph neural networks, it models complex weather patterns with unparalleled accuracy, significantly enhancing the prediction of extreme weather conditions. Remarkably, the model generates a forecast in just 45 seconds, compared to the over one hour required by traditional methods on a supercomputer. This efficiency represents a five-year leap forward in weather forecasting.

By vastly improving the speed and reliability of weather predictions, GraphCast can aid critical decision-making across various industries, optimise resource allocation, and reduce the impact of severe weather events. This capability enables authorities to issue timely safety and evacuation warnings, thereby potentially saving lives.

The MacRobert Award winning Google DeepMind team are:

• Ferran Alet, Research Scientist
• Peter Battaglia, Research Scientist
• Meire Fortunato, Staff Research Scientist
• Remi Lam, Staff Research Scientist
• Shakir Mohamed, Director of Research
• Alexander Pritzel, Senior Staff Research Scientist
• Alvaro Sanchez-Gonzalez, Staff Research Engineer
• Jacklynn Stott, Research Program Manager
• Matthew Willson, Staff Research Engineer
• Peter Wirnsberger, Staff Research Scientist

 Professor Sir Richard Friend FREng FRS, Chair of the Royal Academy of Engineering MacRobert Award judging panel, said: “The heroes behind the UK’s world-changing engineering innovations deserve to be celebrated, and the GraphCast team has made a revolutionary advance.  

“Modern weather forecasting depends on supercomputers to solve the many coupled equations that project forward in time and the only way to improve that methodology has been to use more computing power. But GraphCast, trained on the huge data set of past weather, speeds up what used to take hours to less than a minute and presents a new roadmap for improving both the timeliness and accuracy of weather forecasting.

“GraphCast is a great example of how engineering innovation can be an important driving force behind economic growth and a sustainable future. In an age of climate change and increasingly volatile weather events, accurate forecasting is an essential tool that can benefit society worldwide.”  

Remi Lam, Staff Research Scientist at Google DeepMind, added: "We are deeply humbled and incredibly proud to receive the MacRobert Award. Our passion for engineering has always been fuelled by the desire to build AI that helps solve some of the hardest scientific and engineering challenges of our time, and, ultimately, improve billions of people’s lives.  

“This recognition reaffirms the crucial role engineering plays in that mission and brings a spotlight to the nascent field of data-driven weather forecasting. We are particularly excited that GraphCast will enable a new generation of researchers to build on this technology, and we look forward to the breakthroughs they will achieve. Thank you to the Royal Academy of Engineering for sharing our vision."