UA Scientists Help Create Spacecraft That Think For Themselves
There’s nothing worse than a satellite that can’t make decisions.
Rather than organizing data, it simply spews out everything it collects, swamping scientists with huge amounts of information. It’s like getting a newspaper with no headlines or section pages in which all the stories are strung together end-to-end.
Researchers at the University of Arizona (UA), Arizona State University (ASU) and the Jet Propulsion Laboratory (JPL) are working to solve this problem by developing machine-learning and pattern-recognition software. This smart software can be used on all kinds of spacecraft, including orbiters, landers and rovers.
Scientists currently are developing this kind of software for NASA’s EO-1 satellite. The smart software allows the satellite to organize data so it sends back the most timely news first, while holding back less-timely data for later transmission.
Although the project, called the Autonomous Sciencecraft Experiment (ASE), is still in the test and development stage, software created by UA hydrologists has already detected flooding on Australia’s Diamantina River.
"We had ordered some images from the satellite to test our software in the lab," said Felipe Ip, a Ph.D. student in UA’s Hydrology and Water Resources (HWR) Department. "We didn’t know the Diamantina River was flooding, but when we started running the images through our software, it told us, ’Hey, we’ve got a flood here.’ We were delighted because that’s just what it’s supposed to do."
While Ip, under the direction of HWR researchers James Dohm and Victor Baker, is developing the flood-detection software for EO-1, JPL team members are creating similar software to detect volcanic activity and ASU researchers are working on software to find changes in ice fields.
The flood-detection software compares images from the satellite’s cameras with images stored in its computer memory. If the rivers are not flooding and images come close to matching, the satellite remains silent. But if the satellite’s computer finds significant differences, it takes more photos and notifies scientists.
UA hydrologists developed the software by comparing satellite observations with on-site observations at Tucson Water’s 11 recharge basins. The basins are part of the Central Avra Valley Storage and Recovery Project (CAVSARP) west of Tucson.
The basins are filled with water that flows across the desert from the Colorado River to Tucson via the Central Arizona Project canal. The water percolates into the ground where it is stored in a natural underground aquifer. The large basins are routinely dried out so they don’t become sealed like a typical pond or lake.
The next stage of testing comes in July, when the flood-detection software will fly aboard EO-1 in nearly full autonomous mode.
While the short-term goal is to record transient events, such as volcanic eruptions, floods and changes in ice fields on Earth, ASE software will eventually allow scientists to detect, map out, and study similar events throughout the solar system.
This could include activity on Mars that might indicate water produced by springs. On Jupiter’s moons, the software could be used to detect volcanic eruptions on Io or cracking ice sheets on Europa. Scientists also could use the software to study changes in Saturn’s rings or the formation of jets on comets.
"By using smart spacecraft, we won’t miss short-term events such as floods, dust storms, and volcanic eruptions," Ip said. "Finally, instead of sifting through thousands of images, I can actually get some sleep at night, knowing that a smart robot is on alert twenty-four-seven."
The ASE project is funded by NASA’s New Millennium Program, which focuses on testing exciting new technologies in space.
Ed Stiles | University of Arizona