Repairing a Satellite with Deep Learning AI in Space

By predicting lost data from other existing sources using deep learning.  Note the alternative uses of the approach, say in the case of solar storms.  Considerable complexity with varying goals.

IBM helped NASA fix one of its satellites using cutting-edge deep learning A.I.
How do you fix a satellite that’s floating 22,000 miles above the Earth’s surface?

That’s a question that NASA had to answer when it ran into problems with one of its crucial satellites. The satellite in question was the Solar Dynamics Observatory (SDO), which launched in 2010 with the important goal of studying the Sun and the effects of solar activity on Earth. This is important for all sorts of reasons — not least because solar storms can knock out GPS satellites, shut down electrical grids, and scramble communications.

Unfortunately, one of the SDO’s three instruments, responsible for measuring ultraviolet light, stopped working due to a fault. This data is essential to satellite operators, since it can affect the flight path of orbiting satellites. Not properly compensating for atmospheric changes due to ultraviolet light may cause satellites to fall out of orbit and burn up or crash.

It was deemed too costly to repair the $850 million satellite in space. As a result, NASA called in experts from IBM, SETI, Nimbix, Lockheed Martin, and its own Frontier Development Lab to see if they could solve the problem from Earth using cutting-edge artificial intelligence. The request? Could they figure out how to use data from the SDO’s remaining two instruments — its atmospheric imaging assembly and helioseismic and magnetic imager — to work out the missing ultraviolet radiation measurements. The answer: Apparently, yes.

“One of the biggest challenges was to find the optimal A.I. framework and model for the problem at hand — namely, virtually ‘resurrecting’ the failed SDO instrument so that we could once again get the data that instrument would have produced if it was still working,” Graham Mackintosh, A.I. advisor to SETI and NASA, told Digital Trends. “The team automated the task of modifying, testing, and recording the results of almost 1,000 different versions of the deep learning model before settling on the final approach they determined to be optimal.”  .... "