The ARCAFF project aims to use deep learning AI to make better predictions of space weather events and calculate how probable these predictions are, to help protect vital technology and infrastructure.
A new project led by the Dublin Institute for Advanced Studies (DIAS) is using AI as a way of getting faster and more accurate warnings about space weather events like solar flares.
These solar flares have the potential to disrupt vital technologies and infrastructure, including radio communications, electrical power grids and navigation systems. They can also present risks to spacecraft and astronauts.
The new project – Active Region Classification and Flare Forecasting (ARCAFF) – aims to use a form of AI called deep learning to make better predictions than the equipment at forecasting centres.
The project also aims to provide information about how certain these predictions are, which DIAS claims is information that is not currently available.
ARCAFF project lead Dr Shane Moloney said space weather covers a “variety of phenomena” that occurs from the sun and that these predictions are becoming more important as technology becomes more advanced.
“Studying these space weather events helps us learn more about the sun and better predict space weather,” Moloney said. “It may seem like these events have little effect on our daily lives, as we are largely protected from the sun’s harmful radiation.
“However, solar flares emission can change the atmosphere and create technological issues, like interfering with radio communication and GPS on Earth. They can also create beautiful displays in our night skies like the Northern Lights or aurora borealis.”
The ARCAFF project is being funded by Horizon Europe and is being supported by partners across Europe, to combine expertise in fields such as solar physics, machine learning and computer science.
DIAS head of astronomy and physics Prof Peter Gallagher said the project has been “an excellent opportunity for cross-disciplinary collaboration” for DIAS and the partner organisations.
“As well as being faster and more accurate at predicting solar flares, ARCAFF will make new datasets and software available for scientists to use and the outputs of the project will be freely available online,” Gallagher said. “We are also excited to educate the wider public about space weather and how it impacts Ireland and Europe, through our public engagement hub at DIAS Dunsink Observatory.”
In 2020, a team led by researchers from Skoltech in Russia developed a new method of studying fast coronal mass ejections – powerful ejections of magnetised matter from the sun’s outer atmosphere.
10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.