Machine learning forecasts space weather risks to power grids

Extreme space-weather events can disrupt critical infrastructure on Earth, including power systems, GPS accuracy and satellite operations. These storms can create conditions that damage electrical grids and affect technologies that rely on reliable positioning and orbital communications.

A new machine learning system can predict where damage is likely to occur 30-60 minutes before a storm arrives. The advance is designed to give operators earlier insight into location-specific risks, improving preparedness for severe space-weather impacts on power grids.