There are enough problems on this planet already that we don’t need new problems to come from the sun. Unfortunately, we can’t destroy this merciless star yet, so we are at its mercy. But NASA at least soon you will be able to inform us when one of their killer flares goes to disrupt our Earth systems.
Understanding and predicting space weather is a big part of NASA’s job. There’s no air up there, so no one can hear you yell, “Wow, what’s up with this radiation!” Consequently, we rely on a set of satellites to detect and transmit this important data to us.
One such measure is the solar wind, “a relentless stream of material from the sun.” Even NASA can’t find anything good to say about it! Normally this current is absorbed or dissipated by our magnetosphere, but if there is a solar storm it can be intense enough to overwhelm local defences.
When this happens, it can cause electronics to go bad, as these charged particles can shift bits or disrupt volatile memory like RAM and solid-state storage. NASA reports that even the telegraph stations were not secure and blew up during the largest solar storm on record. Carrington event of 1859.
While we can’t stop these stellar events from happening, we could better prepare for them if we knew they were coming. But usually, by the time we know, they’re basically already here. But how can we predict such infrequent and chaotic events?
View of NASA’s SOHO satellite overwhelmed during a 2003 solar storm. Image Credits: POT
A joint project between NASA, the US Geological Survey, and the Department of Energy at the Frontier Development Laboratory has been investigating this problem, and the answer is exactly what you’d expect: machine learning.
The team collected data on solar flares from multiple satellites that monitor the sun, as well as from ground stations that watch for geomagnetic disruptions (called perturbations), such as those that affect technology. The deep learning model they designed identified patterns in how the former leads to the latter, and they named the resulting system DAGGER: D.eep andTOthe rhineggeomagnetic pmyrtuR.feel.
Yes, it is a stretch. But it seems to work.
Using the geomagnetic storms that hit Earth in 2011 and 2015 as test data, the team found that DAGGER could quickly and accurately forecast their effects around the world. This combines the strengths of the previous approaches and avoids their drawbacks. As NASA put it:
Previous prediction models have used AI to produce local geomagnetic forecasts for specific locations on Earth. Other models that did not use AI provided global predictions that were not very timely. DAGGER is the first to combine rapid AI analysis with real measurements from space and across the Earth to generate frequently updated forecasts that are fast and accurate for sites around the world.
It may take a while before you get a sun alert on your phone telling you to stop or your car could stall (this won’t actually happen…probably), but it could make a world of difference when we know there’s a vulnerable infrastructure that could suddenly shut down. A few minutes warning is better than nothing!
You can read the article describing the DAGGER model, which is open source, by the way, in this issue of the magazine. space weather.
