Skip to main content

Previously unknown exoplanet discovered using machine learning

When it comes to discovering new astronomical bodies, sometimes humans are irreplaceable thanks to their skills in pattern detection. But in other cases, computers can spot things that aren’t visible to humans — including a recent instance where an exoplanet was discovered using machine learning.

The exoplanet was discovered by University of Georgia researchers within a protoplanetary disk called HD 142666. A protoplanetary disk is a rotating disk of gas that swirls around young stars, and from which planets are formed. Planets are formed within these disks as matter clumps together until it eventually has enough gravity to pull more material in. The researchers looked at a previous set of observations of a whole set of protoplanetary disks, and used a machine learning model to search for exoplanets that might have been missed the first time around. They identified one disk where a planet was likely to be, based on the unusual way that gas moved around within the disk.

Disk Substructures at High Angular Resolution Project (DSHARP)

“We confirmed the planet using traditional techniques, but our models directed us to run those simulations and showed us exactly where the planet might be,” said lead author Jason Terry in a statement. “When we applied our models to a set of older observations, they identified a disk that wasn’t known to have a planet despite having already been analyzed. Like previous discoveries, we ran simulations of the disk and found that a planet could recreate the observation.”

The researchers say that this is a proof of concept showing that machine learning can be used to make new discoveries of exoplanets, even with data that has previously been analyzed. That could mean more exoplanet discoveries in the future, as well as discoveries being made faster.

“This demonstrates that our models — and machine learning in general — have the ability to quickly and accurately identify important information that people can miss. This has the potential to dramatically speed up analysis and subsequent theoretical insights,” Terry said. “It only took about an hour to analyze that entire catalog and find strong evidence for a new planet in a specific spot, so we think there will be an important place for these types of techniques as our data sets get even larger.”

The research is published in The Astrophysical Journal.

Editors' Recommendations

Georgina Torbet
Georgina is the Digital Trends space writer, covering human space exploration, planetary science, and cosmology. She…
Age of ancient galaxy discovered by Webb confirmed using ALMA
The radio telescope array ALMA has pin-pointed the exact cosmic age of a distant JWST-identified galaxy, GHZ2/GLASS-z12, at 367 million years after the Big Bang. ALMA’s deep spectroscopic observations revealed a spectral emission line associated with ionized Oxygen near the galaxy, which has been shifted in its observed frequency due to the expansion of the Universe since the line was emitted. This observation confirms that the JWST is able to look out to record distances, and heralds a leap in our ability to understand the formation of the earliest galaxies in the Universe.

Since the James Webb Space Telescope launched in December 2021, astronomers and the public have been excited to see how powerful this new tool is, and how it has been able to see some of the most distant galaxies ever observed. However, as cutting-edge science, some of these early results have been contentious as astronomers work to figure out how accurate the data is, due to issues like calibration of the instruments.

Another way to verify results is to look for supporting evidence from other tools, such as recent work using the Atacama Large Millimeter/submillimeter Array or ALMA, a ground-based array of telescopes located in Chile, which has confirmed the age of a very distant galaxy using the detection of oxygen.

Read more
NASA is asking for your help to study exoplanets
Members of the public can help astronomers observe and study the night sky through NASA’s Universe of Learning Exoplanet Watch program.

With new tools like the James Webb Space Telescope, we're discovering more exoplanets than ever and even peering into their atmospheres. Now, NASA is asking for the public's help in learning more about some of the exoplanets that have already been detected in a citizen science program called Exoplanet Watch.

“With Exoplanet Watch you can learn how to observe exoplanets and do data analysis using software that actual NASA scientists use,” said Rob Zellem, the creator of Exoplanet Watch and an astrophysicist at NASA’s Jet Propulsion Laboratory, in a statement. “We’re excited to show more people how exoplanet science is really done.”

Read more
How James Webb peers into the atmospheres of far-off exoplanets
Illustration of a planet on a black background. The planet is large and rocky. Roughly two-thirds of the planet is lit, while the rest is in shadow.

We are entering a new period of exoplanet astronomy, with a recent announcement that the James Webb Space Telescope has detected its first exoplanet. The promise of Webb is that it will be able to not only spot exoplanets but also study their atmospheres, which would mark a major step forward in exoplanet science.

Studying exoplanets is extremely challenging because they are generally far too far away and too small to be observed directly. Very occasionally, a telescope is able to directly image an exoplanet, but most of the time researchers have to infer that a planet is present by looking at the star around which it orbits. There are several methods for detecting planets based on their effects on a star, but one of the most commonly used is the transit method, in which a telescope observes a star and looks for a very small dip in brightness which happens when a planet passes between the star and us. This is the method Webb used to detect its first exoplanet, named LHS 475 b.

Read more