Israeli space weather researchers report they’ve used AI to predict the sun’s radiation outbreaks up to 96 hours before they occurred. A huge solar blast is likely to hit the earth with unpredictable results, but it could include destroying satellites. “The impacts of such a storm can be wide varying—[it can affect] power delivery and grid security, communications, satellite operations, and collision avoidance, spacecraft charging and damage, [lead to] radiation exposure [for] astronauts and commercial airlines passengers and crews, and more,” Piyush Mehta, a professor of Space Systems at West Virginia University told Lifewire in an email interview.
Storm Watchers
Scientists have spent decades trying to predict damaging solar storms more accurately. But, said Mehta, “we have a long way to go before we can accurately forecast solar storms and the likelihood of their impacts with confidence.” Now, remote sensing expert Yuval Reuveni of Ariel University in Israel says his team has invented a new solar storm forecasting method, called the Convolutional Neural Network, according to a recent paper published in The Astrophysical Journal. The technique uses deep learning, a type of AI, to scrutinize X-ray measurements from satellites. A sudden outburst of electromagnetic radiation originating at the solar surface travels at the speed of light and reaches Earth within minutes, Reuveni and his fellow researchers wrote in the paper. “Solar flares have the ability to interfere in radio communication systems, affect global navigation satellite systems, neutralize satellite equipment, cause electric power blackouts on Earth, harm the health of astronauts, and can easily mean a loss exceeding several billion dollars in repairs and months of reconstruction when they reach a very high magnitude,” they added. Just what such a storm could mean on earth is still open to debate. Scientists recently held a workshop to determine how a big solar storm might affect the power grid. The participants used a table-top exercise and simulation to reveal research and development gaps for the Sun-to-power grid system. The group highlighted the human dimension of an outage by modeling the population of Washington DC, including social, economic, and medical details. “Space weather is about societal resilience, multiphysics, and multiscale. This simulation game embodied all three facets,” Mangala Sharma, the program director for Space Weather Research at the National Science Foundation, said in a news release.
Storms on the Horizon
It’s a matter of when rather than if a damaging solar storm will hit the earth. Daniel Baker, a professor of Planetary & Space Physics at the University of Colorado Boulder, told Lifewire in an email interview. The probability that a very severe storm will occur is about 10 percent per decade. “There is not a whole lot that can be done for the most extreme cases, unfortunately,” Baker said. In February, SpaceX lost 40 Starlink satellites when they were launched into a geomagnetic storm. During a particularly intense solar burst, airlines monitor radiation levels, which could cause them to reroute polar routes. A storm is unlikely to directly affect personal electronic devices but can impact them indirectly, like GPS performance on your phone which runs off signals from satellites, Mehta explained. The worst solar storm on record is the Carrington event of 1859, Mehta said. The incident created strong auroral displays that were reported globally and caused sparking and even fires in multiple telegraph stations. “It is likely that stronger storms have occurred, either prior to when we started keeping records or originating at regions of the Sun not visible from Earth,” Mehta said. The next big storm could arrive sooner rather than later. The sun follows an 11-year solar cycle, where its activity peaks every 11 years, and solar storms are much more likely to occur when the sun is more active, Mehta explained. We’re just coming out of a deep solar minimum and moving towards the sun’s most active period of the solar cycle. “So, we should not be complacent and work on our ability to improve forecasting solar storms and their impacts,” Mehta added.
