This is the Largest 3D Map of The Universe and It Was Created With the Help of AI

The new catalog doubles the area surveyed compared to the previous largest map of the universe.

There’s nothing like taking time off to go somewhere where light pollution is minimal, allowing you to observe, among other things, the Milky Way Galaxy. However, the unaided eye can only see so much.

I’ve been learning the “secrets” of astrophotography for the last few months. In this process, I have learned a lot about our planet, the stars, galaxies, and the unfathomable number of stars that we cannot see with the unaided eye. My camera produces some stunning views of the cosmos, and when paired with my telescope, the results are awestriking.

But this is just with simple tools most of us can acquire.

However, experts use much better “telescopes” and cameras when looking at the stars. Their quest to understand the cosmos is of great importance. Humans have made fantastic progress in cataloging the solar system, our immediate cosmic neighborhood, the Milky Way Galaxy, and the universe in general.

Now, a team of scientists from the University of Hawaii at the Manoa Institute for Astronomy (IfA) has produced the largest catalog of 3D astronomical images of stars, galaxies, and quasars, in a massive leap forward towards understanding the cosmos.

With the help of data from the panoramic telescope and the UH or Pan-STARRS1 (PS1) rapid response system, researchers could obtain the largest deep multi-color optical survey, covering three-quarters of the sky. In other words, it is massive.

How massive, you ask? Well, according to the astronomers, the new tools have allowed them to go through a humongous cosmic catalog and identified which of the 3 billion objects are stars, galaxies, and quasars. Computational algorithms have also allowed scientists to obtain the distances to distant galaxies in the universe. In other words, what scientists obtained is a total of approximately 300 gigabytes of data.

This can be accessed by scientists and users worldwide, allowing them to consult the catalog through the MAST CasJobs SQL interface or download the entire collection as a machine-readable table.

Astronomers took publicly available spectroscopic measurements that provide definitive object classifications and distances and sent them to an artificial intelligence algorithm that helped get the job done; it has been revealed.

Astronomers stress that the AI process was key in helping the team figure out how to accurately determine the same properties from various measurements of object colors and sizes.

This artificial intelligence learning approach with a “feedback neural network” achieved an overall ranking accuracy of 98.1% for galaxies, 97.8% for stars, and 96.6% for quasars.

Estimates of the galaxy’s distance are nearly 3% accurate. This means that the AI has allowed scientists to understand better what the sky is like and what the objects in it represent.

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,” explained Rover Beck, the lead author of the study.

The largest map of the universe is a true wonder, and it proves that new tools, such as AI, can help scientists better explore the cosmos.

Previously, the largest cosmic chart was created by the Sloan Digital Sky Survey (SDSS), and it covered one-third of the sky.

The new catalog is so large that it doubles the area surveyed. Furthermore, the new cosmic chart has much more accurate statistics with specific areas in the sky that the SDSS missed.


Join the discussion and participate in awesome giveaways in our mobile Telegram group. Join Curiosmos on Telegram Today. t.me/Curiosmos

All sources and references are linked to the article.

Back to top button

Adblock detected :(

Hi, we understand that enjoy and Ad-free experience while surfing the internet, however, many sites, including ours, depend on ads to continue operating and producing the content you are reading now. Please consider turning off Ad-Block. We are committed to reducing the number of ads shown on the site.