Discovering planets that no one has ever seen before is even harder than it sounds. NASA room telescopes and other scientific bodies have collected an incredible amount of data that will take astronomers year and year through, and many times there is nothing there.
But people do not have to do everything The work and Anne Dattilo, a senior at the University of Texas in Austin, helped artificial intelligence study data from NASA's Kepler space telescope and did not find one but two new exoplanets in the process.
Scientists led by 22-year-old Dattilo designed a computer algorithm capable of detecting the faint hints of planets orbiting stars spotted by the Kepler telescope.
Using a computer to quickly scan data from planet-hunting instruments like Kepler is not new alone, but the data Dattilo and her fellow researchers were dealing with required a unique approach. The second round planet spotting of the Kepler telescope was slightly different from its first, and the expanded mission known as K2 provided data muddy with instability.
Kepler developed mechanical problems later in his life, and while the data collected during K2 was still usable, conventional planetary detecting algorithms would simply not work due to movement of the sensor. This required an AI that was specifically designed to take this movement into consideration and effectively cancel it so that the computer could see the nozzles in brightness associated with a planet passing in front of a distant star.
Dattilo and her team created an algorithm that did just that, and when applied to some of Kepler's K2 data, managed to sniff a couple of previously undiscovered worlds. The planets, both about 1