“New Discoveries in Astronomy Made Possible by AI and Faster Learning of the Universe”

The first famous image of a black hole It became twice as sharp. My research team used artificial intelligence to improve it greatly her first photo from 2019, which now shows the black hole at the center of the M87 galaxy as being darker and larger than the first image imaged.

I astronomer who studies and writes about it CosmologyAnd black holes And outer planets. Astronomers have been using artificial intelligence for decades. Indeed, in 1990, astronomers from the University of Arizona, where I am a professor, were among The first to use a type of artificial intelligence called a neural network To study the shapes of galaxies.

Since then, artificial intelligence has permeated every field of astronomy. As technology has become more powerful, AI algorithms have begun to help astronomers tame huge data sets and discover new knowledge about the universe.

Better telescopes, more data

For as long as astronomy has been a science, it has involved trying to understand many things in the night sky. It was relatively simple when the only tools were the naked eye or a simple telescope, and all that could be seen were a few thousand stars and a handful of planets.

A hundred years ago, Edwin Hubble used newly built telescopes to show that the universe was filled not only with stars and gas clouds, But countless galaxies. As telescopes continue to improve, so does the huge number of celestial bodies that humans can see and amount of data Astronomers need to sort out, and both have grown exponentially, too.

For example, soon to be completed Vera Rubin Observatory In Chile, it will make the pictures so big that it would take 1,500 HDTV screens to display each one in its entirety. Over 10 years, it is expected to generate 0.5 exabytes of data—about 50,000 times the amount of information contained in all the books in the Library of Congress.

There are 20 telescopes with mirrors over 20 feet (6 m) in diameter. Artificial intelligence algorithms are the only way astronomers can hope to work through all the data available to them today. There are a number of ways in which AI is proving useful in processing this data.

Picking patterns

Astronomy often involves looking for needles in a haystack. About 99% of the pixels in an astronomical image contain background radiation, light from other sources or the darkening of space – only 1% have subtle shapes of faint galaxies.

Artificial intelligence algorithms – in particular, neural networks that use many interconnected nodes and are able to learn to recognize patterns – are well suited to picking out patterns in galaxies. Astronomers started Using neural networks to classify galaxies In the early 2000s. Now the algorithms very effective They can classify galaxies with up to 98% accuracy.

This story has been repeated in other areas of astronomy. Astronomers working on SETI, the search for extraterrestrial intelligence, use radio telescopes to search for signals from distant civilizations. Early on, radio astronomers scanned the charts with the naked eye Look for anomalies It can not be explained. Recently, researchers used 150,000 personal computers and 1.8 million citizen scientists to search for artificial devices radio signals. Now, researchers are using artificial intelligence to sift through mounds of data faster and more thoroughly than people can do. This has allowed SETI’s efforts to cover more ground while reducing the range The number of false positive signals.

Another example is the search for exoplanets. Most astronomers have discovered 5,300 known exoplanets By measuring the decrease in the amount of light coming from a star When a planet passes in front of it. AI tools can now pick up signs of an exoplanet using 96% accuracy.

Make new discoveries

Artificial intelligence has proven to be excellent at identifying known objects — such as galaxies or exoplanets — that astronomers are asking to search for. But it is also very powerful at finding things or phenomena that have been put into theory but not yet discovered in the real world.

Teams used this approach to detection New exoplanetsget to know me ancestral stars that led to the formation and growth of the Milky Way, predicting the signatures of new species of gravitational waves.

To do this, astronomers first use artificial intelligence to convert theoretical models into observational signatures — including realistic levels of noise. They then use machine learning to hone the AI’s ability to detect predictable phenomena.

Finally, radio astronomers have also used artificial intelligence algorithms to examine signals that do not align with known phenomena. A South African team recently found a Unique object It may be leftover from the explosive merger of two supermassive black holes. If this proves to be true, the data will allow for a new test of general relativity – Albert Einstein’s description of spacetime.

Make predictions and fill in the gaps

As in many areas of life lately, generative artificial intelligence and big language paradigms like ChatGPT are also making waves in the world of astronomy.

The team that created the first image of a black hole in 2019 used the Generative AI to produce its new image. To do this, it first taught the AI ​​how to identify black holes by simulating several types of black holes for it. Next, the team used the AI ​​model it created to fill in the gaps in the massive amount of data collected by radio telescopes on the M87 black hole.

Using this simulated data, the team was able to create a new image that is twice as sharp as the original and fully consistent with the predictions of general relativity.

Astronomers are also turning to artificial intelligence to help tame the complexity of modern research. A team from the Harvard-Smithsonian Center for Astrophysics created a Linguistic model called Astrobert To read and organize 15 million scientific papers in astronomy. Another team, based at NASA, proposed using artificial intelligence Prioritize astronomy projectsa process that astronomers participate in every 10 years.

With the advancement of artificial intelligence, it has become an essential tool for astronomers. As telescopes improve, as data sets get larger and as artificial intelligence continues to improve, this technology is likely to play a major role in future discoveries about the universe.

This article has been republished from Conversation Under Creative Commons Licence. Read the The original article.