Analysis: How AI is helping astronomers study the universe

AI tools can help astronomers unlock information about the cosmos. Yuga Kurita/Momento via Getty Images

The famous first image of a black hole just got twice as sharp. A research team has used artificial intelligence to dramatically improve its first image from 2019, which now shows the black hole at the center of the M87 galaxy darker and larger than the first image pictured.

I am an astronomer who studies and has written on cosmology, black holes and exoplanets. Astronomers have been using artificial intelligence for decades. In fact, in 1990, astronomers at 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 shape of galaxies.

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

Better telescopes, more data

As long as astronomy has been a science, it has involved trying to make sense of the multitude of objects 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 is filled not only with stars and gas clouds, but also with countless galaxies. As telescopes have continued to improve, the number of celestial objects humans can see and the amount of data astronomers must sort has also grown exponentially.

TO KNOW MORE: How the James Webb Space Telescope captures stunning images of space

For example, the soon-to-be-completed Vera Rubin Observatory in Chile will make the images so large that it would take 1,500 high-definition TV screens to see them all in their entirety. Over 10 years it is expected to generate 0.5 exabytes of data, approximately 50,000 times the amount of information contained in all the books contained in the Library of Congress.

There are 20 telescopes with mirrors larger than 20 feet (6 meters) in diameter. Artificial intelligence algorithms are the only way astronomers could ever hope to process all the data available to them today. There are several ways AI is proving to be useful in processing this data.

One of the earliest uses of artificial intelligence in astronomy was to spot the multitude of faint galaxies hidden in the background of images. Photo by ESA/Webb, NASA and CSA, J. Rigby, CC BY

Locate 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 darkness of space: only 1% have the thin shapes of faint galaxies.

Artificial intelligence algorithms, especially neural networks that use many interconnected nodes and are capable of learning to recognize patterns, are perfectly suited for spotting patterns in galaxies. Astronomers started using neural networks to classify galaxies in the early 2010s. Now the algorithms are so good that they can classify galaxies with 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 look for signals from distant civilizations. In the beginning, radio astronomers scanned the charts by eye to look for anomalies that could not be explained. More recently, researchers have harnessed 150,000 personal computers and 1.8 million citizen scientists to search for artificial radio signals. Now, researchers are using artificial intelligence to sift through reams of data far more quickly and thoroughly than people can. This has allowed SETI efforts to cover more ground, while also greatly reducing the number of false positive signals.

Another example is the search for exoplanets. Astronomers discovered most of the 5,300 known exoplanets by measuring a drop in the amount of light from a star when a planet passes in front of it. AI tools can now pinpoint signs of an exoplanet with 96% accuracy.

AI tools can help astronomers discover new exoplanets like TRAPPIST-1 b. Photos by NASA, ESA, CSA, Joseph Olmsted (STScI), CC BY

Make new discoveries

The AI ​​has proven excellent at identifying known objects, such as galaxies or exoplanets, that astronomers tell it to look for. But it is also quite powerful in finding theorized but not yet discovered objects or phenomena in the real world.

The teams have used this approach to detect new exoplanets, learn about the ancestral stars that led to the formation and growth of the Milky Way, and predict the signatures of new types of gravitational waves.

TO KNOW MORE: Meet the 4 astronauts who will fly around the moon during NASA’s Artemis II mission

To do this, astronomers first use artificial intelligence to convert theoretical models into observational signatures, including realistic levels of noise. Then they use machine learning to sharpen the AI’s ability to detect predicted phenomena.

Finally, radio astronomers have also used artificial intelligence algorithms to sift through signals that do not correspond to known phenomena. Recently a team from South Africa found a unique object that may be a remnant of the explosive merger of two supermassive black holes. If that turns out to be true, the data will enable a new test of general relativity: Albert Einstein’s description of space-time.

The team that first photographed a black hole, left, used AI to generate a sharper version of the image, right, showing the black hole is larger than initially thought. Photo by Medeiros et al 2023, CC BY-ND

Making predictions and plugging holes

As in many areas of life recently, generative AI and large language models 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 generative AI to produce their new image. To do this, it first taught an AI how to recognize black holes by giving it simulations of many types of black holes. Then, the team used the AI ​​model they had built 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 is 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 at the Harvard-Smithsonian Center for Astrophysics has created a language model called astroBERT to read and organize 15 million scientific articles on astronomy. Another team, based at NASA, has even proposed using artificial intelligence to prioritize astronomy projects, a process astronomers undertake every 10 years.

As artificial intelligence has progressed, it has become an essential tool for astronomers. As telescopes get better, data sets get bigger, and AIs keep getting better, it’s likely this technology will play a central role in future discoveries about the universe.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

#Analysis #helping #astronomers #study #universe

Leave a Comment