American astronomers have made the most complete catalog of 3D astronomical images of stars, galaxies and quasars PS1-STRM. This is stated on the portal of the University of Hawaii.
Researchers at the University of Hawaii Institute of Astronomy applied data from the Pan-STARRS panoramic view and rapid response telescope system. It is located at the top of the Mauna Kea volcano on the island of Hawaii.
This system has access to three quarters of the entire sky, or 30 thousand square degrees.
So, astronomers have deciphered which of the three billion objects that were recorded by Pan-STARR are stars, and which are galaxies or quasars. According to the authors of the work, the program also calculated the distances to them for galaxies.
Scientists have obtained the world’s largest multicolor optical three-dimensional catalog with a size of about 300 gigabytes. The information was fed into an artificial intelligence algorithm – machine learning with a “feed forward neural network.”
“Using an optimization algorithm, we used a spectroscopic training set of nearly four million light sources to train the neural network to predict source types and distances to galaxies while correcting the attenuation factor of the Milky Way dust,” said lead author Robert Beck.
His colleague, Istvan Sapudi, hopes that the 3D galaxy catalog will help with further research.