New AI-powered model predicts impending solar storms 30 minutes before they occur

In a world that increasingly relies on technology, space weather events like solar flares or geomagnetic storms can have devastating effects on Earthlings. From persistent electrical blackouts to interrupting global communication systems, space weather can pose a significant threat to our critical technological infrastructure.

Having said that, it is crucial to monitor and forecast space weather to mitigate its impacts and minimize the potential damage that can be caused by it.

A new computer model that combines artificial intelligence (AI) and NASA satellite data could predict where an impending solar storm will strike, anywhere on Earth, with 30 minutes of advance warning.

Developed by an international team of researchers at the Frontier Development Lab, the model called DAGGER (formally, Deep Learning Geomagnetic Perturbation) can quickly and accurately predict geomagnetic disturbances worldwide. The team claims that the model can produce predictions in less than a second, and the predictions update every minute.

DAGGER was successfully tested against two geomagnetic storms that happened in August 2011 and March 2015. It is the first model to combine the swift analysis of AI with real measurements from space and across Earth to generate frequently updated predictions that are both prompt and precise for sites worldwide, according to NASA.

"With this AI, it is now possible to make rapid and accurate global predictions and inform decisions in the event of a solar storm, thereby minimizing – or even preventing – devastation to modern society," said Vishal Upendran of the Inter-University Center for Astronomy and Astrophysics in India, who is the lead author of a paper about the DAGGER model published in the journal Space Weather.

How can we better protect satellites and power grids from solar storms?A new computer model combining NASA satellite observations and AI can warn where an impending solar storm will strike, anywhere on Earth, 30 minutes in advance.Find out more: https://t.co/wtZQ25Rfcm pic.twitter.com/EF9Fccd2OS

— NASA Sun & Space (@NASASun) March 30, 2023