AI helps scientists to create world’s largest 3D map of the universe

Dimapur, Oct. 12 (EMN): A team of astronomers from the University of Hawaii at Mānoa’s Institute for Astronomy (IfA) has created the world’s largest 3D imaging catalogue of stars, galaxies, and quasars with the help of Artificial Intelligence (AI).

The team used optical data from their Panoramic survey telescope and rapid response system or Pan-STARRS1 (PS1) on Haleakalā. According to their press release, “The PS1 3π survey is the world’s largest deep multi-colour optical survey, spanning three-quarters of the sky.”

The team trained an AI algorithm to identify objects in the survey by feeding it publicly-available spectroscopic measurements that provide definitive object classifications and distances.

“Utilizing a state-of-the-art optimization algorithm, we 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,” said lead study author Robert Beck in the press release.

The artificial intelligence neural network was able to provide impressive results for classifying celestial bodies achieving success rates of 98.1% for galaxies, 97.8% for stars, and 96.6% for quasars.

Previously, the largest map of the universe was created by the Sloan Digital Sky Survey (SDSS), which covered only one-third of the sky. The new map is double the size and provides more statistics.

A preliminary, smaller version of the catalogue had already helped the team discover the largest void in the universe, a possible cause of the CMB Cold Spot.

“This beautiful map of the universe provides one example of how the power of the Pan-STARRS big data set can be multiplied with artificial intelligence techniques and complementary observations,” explained Pan-STARRS director and co-author of the study, Ken Chambers.

“As Pan-STARRS collect 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.”

The new map, which was made possible through a National Science Foundation award, is now available as a high-level science product through the Mikulski Archive for Space Telescopes.

It is approximately 300 GB in size and can be downloaded as a computer readable table.