World’s largest 3D astronomical imaging catalog of stars, galaxies and quasars was produced making use of Artificial Intelligence (AI) by researchers at the University of Hawaiʻi at Mānoa Institute for Astronomy (IfA).
World’s largest deep multi-colored optical survey, produced by the Pan-STARRS observatory at Haleakalā, Maui, was by the team of astronomers for developing the 3D map by using AI
They trained the algorithm spectroscopic measurements to determine accurately definite object classifications and distances between celestial objects.
Robert Beck, lead study author and former cosmology postdoctoral fellow at IfA stated that utilizing a state-of-the-art optimization algorithm, the team leveraged the spectroscopic training set of almost 4 million light sources to teach the neural network to predict source types and galaxy distances, while at the same time correcting for light extinction by dust in the Milky Way.
“This enabled the neural network to achieve a classification accuracy of 98.1% for galaxies, 97.8% for stars, and 96.6% for quasars.” the study said.
The team confirmed their catalog is double the size of the map created by Sloan Digital Sky Survey (SDSS), which was the largest map of the universe, and almost covered 33% of the sky.
IfA astronomer and co-author of the study, István Szapudi, said this photometric redshift catalog will be the starting point for many future discoveries as it is new, more accurate, and larger.
“As Pan-STARRS collects more and more data, we will use machine learning to extract even more information about near-Earth objects, our Solar System, our Galaxy and our Universe,” Ken Chambers, Pan-STARRS Director and IfA Associate Astronomer said.
The 3D catalog is approximately 300 GB in size, which can be downloaded as a computer-readable table.