Artificial intelligence to forecast solar storms

The Sun is constantly spewing solar material into space, both in a steady stream known as the “solar wind” and in shorter, more profuse, and energetic bursts from solar flares. When this solar material collides with Earth’s magnetic environment (its magnetosphere), it sometimes creates so-called geomagnetic storms. The effects of these magnetic storms can range from mild to extreme, but in a world increasingly reliant on technology, such effects are increasingly damaging.

For example, a particularly intense solar storm in 1989 caused power blackouts across Quebec for 12 hours, leaving millions of Canadians in the dark and forcing businesses, schools and others to close. The most intense solar storm on record, the Carrington event of 1859, caused fires at telegraph stations and prevented the sending of messages. If the Carrington event occurred today, it would have even more serious consequences, such as very long power and communication outages. This technological chaos could cripple economies and jeopardize the safety of many people.

A new computer model that combines artificial intelligence and data from NASA satellites could soon issue impending solar storm alerts to help protect critical infrastructure.

The model uses artificial intelligence to analyze measurements of the solar wind made by spacecraft and predict where an impending solar storm will hit, anywhere on Earth, 30 minutes in advance. This could provide enough time to prepare for these storms and prevent the most serious damage to power grids and other critical infrastructure.

The model, called DAGGER, is the work of an international team of researchers from the FDL (Frontier Development Lab), a public-private partnership that includes NASA, the US Geological Survey and the US Department of Energy.

Solar flare photographed by NASA’s Solar Dynamics Observatory (SDO) space telescope on October 2, 2014. Solar flare is the bright flash of light at the top. Just to your right you can see a burst of solar material shooting out into space. (Photo: NASA/SDO)

The DAGGER model software is open source and could be adopted, with some help, by power grid operators, satellite controllers, telecommunications companies, and others to apply the predictions to their specific needs. These alerts could give them time to take steps to protect their infrastructure from an impending solar storm, such as temporarily shutting down sensitive systems or moving satellites to different orbits to minimize damage.

With models like DAGGER, there could one day be solar storm sirens sounding the alarm at power plants and satellite control centers around the world, just as towns and cities across the United States sound sirens announcing the imminent arrival of a tornado.

Solar flares occur relatively frequently. Without going any further, on March 28 (or 29, depending on the time zone), one was triggered. (Fountain: NCYT by Amazings)