Tag
Microsoft Research researchers developed an end-to-end machine learning pipeline that forecasts geomagnetically induced current risk for 66,935 U.S. substations 30–60 minutes before space-weather events, combining solar-wind forecasts (AE/Dst indices), physics-informed constraints, and local geological conductivity. The system detected nearly 80% of major events during evaluation.
Scientists have corrected the year of a historical space weather event affecting technology in the 1840s, establishing the earliest documented case of space weather disrupting telegraph systems.
Scientists have found that a November 2025 solar superstorm caused widespread, unprecedented GPS disruptions across the US, with errors up to 33 feet, potentially impacting precision agriculture and autonomous vehicles.
A new AI model called EarlyDetect can detect hidden signs of solar eruptions nearly nine hours in advance by analyzing acoustic and magnetic data, potentially aiding in the prediction and mitigation of solar storms.
New research indicates that extreme solar storms may be far more devastating than previously thought, as a statistical bias in satellite measurements may have created a false impression that Earth's magnetic field saturates during intense events.
NOAA's GOES-19 weather satellite has entered a safe hold mode, as reported by the Space Weather Prediction Center.