Solar wind speeds can be predicted by AI model
Scientists from NYU Abu Dhabi (NUYAD) have created an artificial intelligence (AI) model to forecast solar wind speeds as much as four days early. This is significantly more accurate than current methods. Their research is published in The Astrophysical Journal Supplement Series.
Solar wind is a constant stream of charged particles from the Sun. When they speed up, they can cause “space weather” events which can disrupt the planet’s atmosphere, push satellites out of orbit, damage electrons, and interfere with global power grids. In 2022, one solar wind caused SpaceX to lose 40 Starlink satellites. This highlights a need for better forecasting.
The NYUAD team trained an AI model with high-resolution ultraviolet (UV) images from NASA’s Solar Dynamics Observatory. They combined it with historical records of solar wind. Rather than analysing text like today’s AI models, this model analyses images of the Sun, looking for patterns linked to changes in solar winds.
The result is an improvement in forecast accuracy 45% compared with current operational methods, and a 20% improvement over previous methods.
“This is a major step forward in protecting the satellites, navigation systems, and power infrastructure that modern life depends on,” said Postdoctoral Associate Dattaraj Dhuri, lead author of the study. “By combining advanced AI with solar observations, we can give early warnings that help safeguard critical technology on Earth and in space.”
The breakthrough shows how AI can solve one of the toughest challenges in space. More reliable forecasts allow scientists and engineers to better prepare for space weather events, allowing them to toughen our resilience against disruption to crucial infrastructure.
Stay tuned to EyeOnLondon for the latest news and expert opinions.
Follow us on:
Subscribe to our YouTube channel for the latest videos and updates!
We value your thoughts! Share your feedback and help us make EyeOnLondon even better!
