As machine learning approaches get more and more sophisticated, they are increasingly used in astronomy for difficult tasks like spotting dim and distant galaxy clusters. It can be tremendously helpful to have computers search through astronomical data to look for particular objects as they can process a huge amount of data — however, there are some judgments that still require the human touch.
This week’s image from the Hubble Space Telescope shows an object that was spotted by a human even after it had been missed by a computer algorithm. The dwarf galaxy Donatiello II is very faint and hard to pick out from the background behind it, but an amateur astronomer was able to point it out.
“Even the best algorithms have their limitations when it comes to distinguishing very faint galaxies from individual stars and background noise,” Hubble scientists write. “In such challenging situations, identification must be done the old-fashioned way – by a dedicated human trawling through the data themselves.”
The dwarf galaxy is located in the center of this image and was identified by Giuseppe Donatiello from data collected during the Dark Energy Survey. Along with two other similar dwarf galaxies named Donatiello III and IV, it orbits the Sculptor Galaxy. Once Donatiello spotted the trio in the Dark Energy Survey data, researchers used Hubble to confirm the discovery and take this image.
The Dark Energy Survey was a project that surveyed the sky from 2013 to 2019, looking at objects like galaxy clusters to understand more about dark energy. Though the survey is now complete, the data collected from the first three years of observations was released to the public in 2021 and is still leading to discoveries like this trio of dwarf galaxies.