A group of research institutions launched a program during the International Asteroid Day in 2019, which could deeply affect our knowledge of the diminutive bodies. By the use of citizen science to train a machine learning algorithm, the Hubble Asteroid Hunter project discovers more than 1,000 new asteroids. These discoveries could help scientists understand the ring of heavenly bodies that roams between Mars and Jupiter.
Asteroid Hunter is a combined effort between various groups, including the European Science and Technology Centre, the European Space Astronomy Centre’s Science Data Centre, the Zooniverse citizen science platform, and Google.
In 2019, the researchers sent out an alarm for citizen scientists to associate with the crowd-sourced effort. With the help of the Zooniverse platform, nearly 11,400 members of the public from around the world discovered asteroid trails in 37,000 composite pictures taken by the Hubble Space Telescope between 2002 and 2021. The citizen scientists studied the images for a year and found more than 1,000 trails.
Hubble is an outstanding mission, and it developed a very rich database of astronomical observations over the years that we should take advantage of Sandor Kruk, a postdoc at the Max Planck Institute for Extraterrestrial Physics, told Ars. “We should pay more attention to this long time span of data [that is] starting to be available.” Kruk is, however, involved with Asteroid Hunter.
According to him, there is a lot of variety within the asteroid trails found by Hubble. Generally, when taking long-exposure imagery of an asteroid from the ground, the remaining trail in the picture is a line. However, the combined movement of the asteroids with Hubble’s movement produces curved trails. These are, however, harder to classify by the use of machine learning because they come up in a wide variety of shapes.