Met Office contributes to landmark artificial intelligence conference

On March 22 and 23, the Alan Turing Institute will host Artificial Intelligence UK (AIUK). Broadcast live from London, this virtual event showcases the latest UK research in artificial intelligence (AI) and data science to explore how the pioneering work and collaboration taking place in these fields can be applied to solve real-world challenges.

AI UK is hosted by the Alan Turning Institute

The Met Office is partnering with the event, which will feature panels, demos and talks from a range of thought leaders in the data science sector. Met Office Chief Scientist Professor Stephen Belcher took part in this morning’s panel session”AI and climate: a reason for hope? in which speakers reflected on COP26 and the role of AI on the path to net zero and adaptation to climate change over the next decade.

AIUK comes at a time of pivotal growth for artificial intelligence and an expansion of what is made possible by an explosion of data, greater availability across a broad spectrum of computing, and growing expertise in data science approaches (including learning). automatic and AI). An acceleration in the development and adoption of new data science presents a tremendous opportunity, offering significant gains in efficiency and performance for most sectors, including but not limited to science and weather and climate services.

Dr Kirstine Dale, Senior Research Fellow for Data Sciences at the Met Office and Co-Director of the Joint Center for Excellence in Ambient Intelligence, said: “We are in the midst of a revolution in AI, where the world’s fastest growing deep technology it has the potential to rewrite the rules of entire industries, fundamentally changing the way we work and live.

“At the Met Office we are committed to harnessing the power of data science to push the frontiers of weather and climate science and services.”

The Met Office works in partnership with a range of institutions to deliver on ambitions within data science. For example, the Joint Center for Excellence in Ambient Intelligence was launched in 2020 with the University of Exeter, while the Met Office works in collaboration with the Alan Turning Institute, as well as leading universities, to further explore applications of data science within weather, climate and AI.

Kirstine continued: “Working at the forefront of this transformative technology requires collaboration, which is why we are collaborating with world-leading partners in the application of machine learning, data science and AI.

“By working together with other organizations in this area, we are able to fully explore and take advantage of different opportunities and challenges within data science.”

One such challenge is space weather: By implementing data-driven and machine learning techniques, the Met Office hopes to improve the way Earth system models model the thermosphere, the part of our atmosphere where many satellites fly. These techniques would allow model improvements in areas where the science has not fully figured out or where the process is too computationally intensive to fully model and therefore needs to be approximated.

Theo McCaie, Head of the Informatics Laboratory and Data Science Technical Lead, said: “The Earth system is extremely complicated and events occurring lower in the atmosphere can affect the thermosphere and vice versa. However, modeling a 600 km thick atmosphere around the Earth is scientifically challenging and computationally very expensive.

“We are investigating the use of machine learning techniques to emulate some of the atmospheric processes, such as gravity waves. These emulations could be computationally much, much cheaper and possibly more accurate. In addition to this, we are using data-driven techniques to improve the existing model components and make them more accurate. Used together, these techniques could make modeling and forecasting in the thermosphere more timely and accurate, leading to a safer and more reliable environment for the space components of many of the services we rely on every day.

“Space weather is just one example of the application of Data Science. We don’t know what the next advances or opportunities in AI will be, but we’re making sure we’re ready to take advantage of them, making sure we deliver on our purpose of helping people make better decisions to stay safe and secure. to flourish.”

Leave a Comment