AI saves the day in space

NASA could soon use an artificial intelligence-fueled fix for a malfunctioning instrument on its Solar Dynamics Observatory, which observes solar activity in extraordinary detail.

Why it matters: Powerful solar storms — bursts of solar plasma and charged particles — can harm satellites in orbit and even cause major problems for power grids on Earth. And the SDO, which can spot solar storms in real-time, is a key part of that.

What they did: The SDO instrument in question is known as MEGS-A, and it was designed to keep an eye on ultraviolet radiation levels, which correlate with a ballooning of the Earth's outer atmosphere that can harm satellites in near-Earth orbit.

A deep-learning network that researchers at NASA Frontier Development Lab created with help from IBM, SETI, and Nimbix in 2018 may soon replace the failed instrument by inferring what ultraviolet radiation levels that instrument would detect based on what the other instruments on SDO are observing at any given time, NASA AI consultant Graham Mackintosh tells Axios.

"Imagine you've got an orchestra playing, and at some point, for some reason, partway through, one of the musicians playing the violin just stopped and walked off. Could you know enough about the way that music was playing to fill in the gap and re-create what you think that musician would have played if that musician was still sitting in the chair? That's sort of what we did."

While NASA isn't yet using the fix operationally, the results are promising, Mackintosh added.

What to watch: AI models like this could also be used for other future missions, Mackintosh said. Instead of loading 3 instruments on a satellite to measure different aspects of the space environment, you could potentially launch two and use the data collected to infer the information that would have been measured by a third.

Editor's note: This story has been updated to specify all the groups that participated in the AI research related to the SDO satellite.