Artificial Intelligence is Augmenting Astronomy

The real "eye on sky" of our civilization will be machine learning

China’s “Sky Eye” telescope that has been in the News recently.

Hey Guys,

This is AiSupremacy Premium,

When you think of a person or a field that is being augmented by AI and machine learning, astronomy and science comes is for me top of mind. Artificial Intelligence is changing the entire future of space technology and quantum computing and 3D-printing will help as well as they mature.

In 2020, astronomers and computer scientists from the University of Warwick built a machine learning algorithm to dig through old NASA data containing thousands of potential planet candidates. The result? They found over 50 more new planets.

A.I. is good at:

• Helping to classify stellar objects and structures

• Finding patterns that humans miss in the existing data

• Helping to spot more Earth-like planets and those most likely to be suitable candidates for life

• Improving our knowledge of the Galaxy and universe

The research team trained the algorithm by having it go through data collected by NASA's now-retired Kepler Space Telescope, which spent nine years in deep space on a world-hunting mission. Once the algorithm learned to accurately separate real planets from false positives, it was used to analyze old data sets that had not yet been confirmed — which is where it found the 50 exoplanets.

The question is, what else can A.I. do for astronomers?

In 2022, there’s now a widespread recognition Artificial intelligence (AI) algorithms trained on real astronomical observations now outperform astronomers in sifting through massive amounts of data to find new exploding stars, identify new types of galaxies and detect the mergers of massive stars, accelerating the rate of new discovery in the world's oldest science.

Is A.I. extending “human perception” and augmenting our abilities or is it something else?

Astronomers identify 116,000 new variable stars

A.I. gives us more objective methods of exploring the data we have.

Ohio State University astronomers have identified about 116,000 new variable stars, according to a new paper. 

These heavenly bodies were found by The All-Sky Automated Survey for Supernovae (ASAS-SN), a network of 20 telescopes around the world which can observe the entire sky about 50,000 times deeper than the human eye. Researchers from Ohio State have operated the project for nearly a decade.

Chinese researchers are also more able now to search for alien signals from the known galaxy.

The “Sky Eye” radio telescope in Qiannan Buyei and Miao Autonomous Prefecture, Guizhou Province, China. Qu Honglun/China News Service via Getty Images

I personally have no idea why human beings thought it prudent to send messages to the Universe about us and our location. Most civilizations wouldn’t be so reckless, but humanity is a special breed.

Some scientists believe this could represent a real existential threat from outer space, one that takes advantage of the very curiosity that leads us to look to the stars.

If highly advanced aliens really wanted to conquer Earth, the most effective way likely wouldn’t be through fleets of warships crossing the stellar vastness. It would be through information that could be sent far faster. Call it “cosmic malware.”

• On June 15th, 2022, a story published in China’s state-backed Science and Technology Daily reported that the country’s giant Sky Eye radio telescope had picked up unusual signals from space.

NASA has been good at photoshopping (Adobe) its images for years but is now saying UFO research should (Axios) be legit. It’s pretty amusing.

However what if A.I. could be at the cusp of helping us figure out more about quantum physics, quantum computing as applied to space travel and deeper things about the Universe?

A.I. Will Help us Find More Suitable Planets

Machine learning, can reveal something deeper, University of California, Berkeley, astronomers found: unsuspected connections hidden in the complex mathematics arising from general relativity -- in particular, how that theory is applied to finding new planets around other stars.

In a paper appearing in late May, 2022 in the journal Nature Astronomy, the researchers describe how an AI algorithm developed to more quickly detect exoplanets when such planetary systems pass in front of a background star and briefly brighten it -- a process called gravitational microlensing -- revealed that the decades-old theories now used to explain these observations are woefully incomplete. A.I. can also complement Einstein if you will.

Artificial intelligence Is Outperforming Astronomers to find Earth like Planets

I write a lot, you might keep in touch with my work better on Substack’s App (if you have iOS).

I am also developing new kinds of A.I. content on my other major A.I. Newsletter here:

Artificial intelligence helps in the identification of astronomical objects

In any task that’s visual search related, scientists now turn to machine learning. Think about it, classifying celestial objects is a long-standing problem. With sources at near unimaginable distances, sometimes it's difficult for researchers to distinguish between objects such as stars, galaxies, quasars or supernovae.

Instituto de Astrofísica e Ciências do Espaço's (IA) researchers Pedro Cunha and Andrew Humphrey tried to solve this classical problem by creating SHEEP, a machine-learning algorithm that determines the nature of astronomical sources.

"The problem of classifying celestial objects is very challenging, in terms of the numbers and the complexity of the universe, and artificial intelligence is a very promising tool for this type of task."

• SHEEP is a supervised machine learning pipeline that estimates photometric redshifts and uses this information when subsequently classifying the sources as a galaxy, quasar or star.

• "The photometric information is the easiest to obtain and thus is very important to provide a first analysis about the nature of the observed sources," says Pedro Cunha (who is based in Portugal).

A.I. and Climate Change Will Push Civilization to the Stars

Realistically I think machine learning will help our civilization find a way to travel into the stars. I’m of the belief as an amateur futurist that quantum computing based machine learning will enable a slew of new breakthroughs in science and innovation. Space technology will be a major industry as well as mining in our solar system.

Even in the 21st century, there will be serious economic and survival incentives to explore further out into space. This is a form of environmental-press.

China’s “discovery” of alien signals story was apparently deleted from the internet for unknown reasons, though not before it was picked up by other outlets (Bloomberg). Even the NYT was refuting the story. Whatever the case may be, A.I. is improving in astronomy at a decent pace opening up new possibilities in research and stellar classification.

An eye on the sky

Sky Eye, which is officially known as the Five-hundred-meter Aperture Spherical Telescope (FAST), is the the largest and most sensitive single-dish radio telescope in the world. A engineering marvel, its gargantuan structure is built inside a natural basin in the mountains of Guizhou, China.

The true “eye on the sky” in the end will be machine learning and the AI based probes we eventually will send further and further out from our solar system.

Astronomers live in exciting times but even more so augmented by machine-learning that improves the chances that their work is meaningful and makes breakthroughs.

More than 5,000 exoplanets, or extrasolar planets, have been discovered around stars in the Milky Way, though few have actually been seen through a telescope. A.I. will help us find more and enable us to investigate them in new ways.

A.I. will enhance our surveys of space in multiple ways in the next 20 years. One field that is already benefitting in the search for extrasolar planets, where researchers rely on machine-learning algorithms to distinguish between faint signals and background noise. As this field continues to transition from discovery to characterization, the role of machine intelligence is likely to become even more critical.

In late 2021, newly-detected exoplanets and the ExoMiner algorithm were described in a paper that was recently accepted for publication in the Astrophysical Journal. More and more papers are now appearing that describe how scientists and astronomers are using machine learning to do quality work.

As of June 9th, 2022 Machine-learning methods are used to provide a more unified picture of mathematical degeneracies in light curves of planetary microlensing events. These are just the tip of the ice-berg in how A.I. is augmenting the future of astronomy.

At AiSupremacy I will be following closely the papers and observations of how A.I. is revolutionizing and empowering science. Thanks for supporting me in this journey, I’m lucky to count 77 paying subscribers after 7 months of writing. I won’t be able to continue writing without more community support.

If you know someone interested in A.I. (a colleague, a friend, a family member) or who you think would be open to supporting this cause, please let them know.

Thanks for reading!