This can provide ample time to prepare for these storms and prevent severe impacts to the power grid and other critical infrastructure
Posted Date – 07:40 AM, Sat – 4/1/23
New Delhi: As solar storms increase, an international team of researchers, including from India, has teamed up with NASA to develop a new computer model that combines artificial intelligence (AI) and satellite data to warn of dangerous space weather .
Scientists predict an increase in solar storms as the sun prepares for the peak of activity, which occurs about every 11 years and is expected to arrive sometime in 2025.
The effects of these storms range from mild to extreme, but in a world increasingly reliant on technology, their effects are increasingly damaging.
The new model uses AI to analyze spacecraft measurements of the solar wind, the constant flow of material from the sun, and predicts that impending solar storms will hit anywhere on Earth, with a 30-minute warning.
This can provide enough time to prepare for these storms and prevent severe impacts on the power grid and other critical infrastructure.
“With this type of artificial intelligence, it is now possible to make fast and accurate global predictions and inform decisions in the event of solar storms that minimize—or even prevent—disruptions to modern society,” said the Interuniversity Center’s Vishal Upendran said. Indian Astronomy and Astrophysics (IUCAA).
A team of researchers at the Frontier Development Lab—a public-private partnership that includes NASA, the U.S. Geological Survey, the U.S. Department of Energy, and IUCAA—applied an artificial intelligence method called “deep learning” and developed an artificial intelligence method called DAGGER. Computer models (formally, deep learning of geomagnetic disturbances).
DAGGER, detailed in the journal Space Weather, can quickly and accurately predict geomagnetic disturbances worldwide up to 30 minutes before they occur. It can produce forecasts in less than a second, and forecasts are updated every minute.
With models like DAGGER’s, there could one day be solar storm sirens sounding alarms at power stations and satellite control centers around the world, the researchers say.
The DAGGER team tested the model on two geomagnetic storms in August 2011 and March 2015. In each case, DAGGER was able to quickly and accurately predict the storm’s global impact.
DAGGER is the first to combine AI’s rapid analysis with actual measurements from space and across Earth to generate frequently updated forecasts that are timely and accurate for sites around the globe.
The computer code in the DAGGER model is open source, and according to Upendran, grid operators, satellite controllers, telecommunications companies and others can adopt it with help to apply the predictions to their specific needs.
Such warnings could give them time to take action to protect their assets and infrastructure from impending solar storms, such as temporarily taking sensitive systems offline or moving satellites to different orbits to minimize damage.
