Astronomers have a phenomenal assistant in the search for runaway stars – a piece of software designed to mimic the human brain. Researchers are using the artificial neural network to sift through a huge database to find stars that appear to be fleeing the center of the Milky Way.

The software was designed to work on the Gaia data set, which includes the distances and velocities of about 2 million stars. Out of those 2 million, six were kicked out of the galactic core and are now flying through the galaxy at 500 kilometers (310 miles) per second. This discovery is reported in the Monthly Notices of the Royal Astronomical Society.

“These hypervelocity stars are extremely important to study the overall structure of our Milky Way,” co-author Elena Maria Rossi, from Leiden University in the Netherlands, said in a statement. “These are stars that have travelled great distances through the Galaxy but can be traced back to its core – an area so dense and obscured by interstellar gas and dust that it is normally very difficult to observe – so they yield crucial information about the gravitational field of the Milky Way from the center to its outskirts.”

The discovery was presented at the European Week of Astronomy and Space Science in Prague, Czech Republic, and shows just how Gaia's enormous database can impact astronomy. The Gaia mission, which belongs to the European Space Agency, is building the most precise 3D map of the Milky Way. So far, it has cataloged the position of 1 billion stars.

Only 20 runaway stars were spotted before this research. The Gaia database clearly offers a unique opportunity to find more of these objects, but looking for them in Gaia is like looking for a needle in a haystack in the dark.

“In the end, we chose to use an artificial neural network, which is software designed to mimic how our brain works,” lead author Tommaso Marchetti, a PhD student at Leiden University, explained. “After proper ‘training’, it can learn how to recognize certain objects or patterns in a huge data set. In our case, we taught it to spot hypervelocity stars in a stellar catalogue like the one compiled with Gaia.”

It took the software just one hour to reduce the catalog to 20,000 interesting objects. A few refinements allowed it to further reduce it to 80 potential runaway stars. The team collected as much information as possible about these 80 objects from other catalogs.

“Combining all these data, we found that six stars can be traced back to the Galactic Centre, all with velocities above 360 km/s,” added Marchetti.

The team hopes to find more of these incredible objects in Gaia's next data release in April 2018.