Previously unknown exoplanet discovered using machine learning

By Georgina Torbet Updated April 26, 2023

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.

Topics

Tech News

Georgina Torbet

Space Writer

Georgina is the Digital Trends space writer, covering human space exploration, planetary science, and cosmology. She…

Space

James Webb telescope gets a view of the ‘white whale’ of exoplanet research

This artist’s concept depicts the planet GJ 1214 b, a “mini-Neptune” with what is likely a steamy, hazy atmosphere. A new study based on observations by NASA’s Webb telescope provides insight into this type of planet, the most common in the galaxy.

Studying other planets is difficult not only because they are so far away, but also because they can have properties that make taking readings much harder. Here in our solar system, we only have scant information about the surface of Venus because its thick atmosphere makes it hard to view. Being 50 light-years away, the planet GJ 1214 b has proved similarly tricky, defying 15 years of attempted observations due to its hazy nature.

But now, the James Webb Space Telescope has been able to peer into the planet's atmosphere for the first time, revealing the secrets of this mysterious place. It's known as a mini-Neptune because it has a thick atmosphere and layers of ice like Neptune. Only around three times the diameter of the Earth, the planet likely has lots of water, but it is located in the atmosphere, not on the surface, due to its high surface temperature.

Space

Machine learning used to sharpen the first image of a black hole

A team of researchers, including an astronomer with NSF’s NOIRLab, has developed a new machine-learning technique to enhance the fidelity and sharpness of radio interferometry images. To demonstrate the power of their new approach, which is called PRIMO, the team created a new, high-fidelity version of the iconic Event Horizon Telescope's image of the supermassive black hole at the center of Messier 87, a giant elliptical galaxy located 55 million light-years from Earth. The image of the M87 supermassive black hole originally published by the EHT collaboration in 2019 (left); and a new image generated by the PRIMO algorithm using the same data set (right).

The world watched in delight when scientists revealed the first-ever image of a black hole in 2019, showing the huge black hole at the center of galaxy Messier 87. Now, that image has been refined and sharpened using machine learning techniques. The approach, called PRIMO or principal-component interferometric modeling, was developed by some of the same researchers that worked on the original Event Horizon Telescope project that took the photo of the black hole.

That image combined data from seven radio telescopes around the globe which worked together to form a virtual Earth-sized array. While that approach was amazingly effective at seeing such a distant object located 55 million light-years away, it did mean that there were some gaps in the original data. The new machine learning approach has been used to fill in those gaps, which allows for a more sharp and more precise final image.

Space

James Webb spots exoplanet with gritty clouds of sand floating in its atmosphere

This illustration conceptualises the swirling clouds identified by the James Webb Space Telescope in the atmosphere of the exoplanet VHS 1256 b. The planet is about 40 light-years away and orbits two stars that are locked in their own tight rotation. Its clouds, which are filled with silicate dust, are constantly rising, mixing, and moving during its 22-hour day.

One of the most exciting things about the James Webb Space Telescope is that not only can it detect exoplanets, but it can even peer into their atmospheres to see what they are composed of. Understanding exoplanet atmospheres will help us to find potentially habitable worlds, but it will also turn up some fascinating oddities -- like a recent finding of an exoplanet with an atmosphere full of gritty, sand clouds.

Exoplanet VHS 1256 b, around 40 light-years away, has a complex and dynamic atmosphere that shows considerable changes over a 22-hour day. Not only does the atmosphere show evidence of commonly observed chemicals like water, methane, and carbon monoxide, but it also appears to be dotted with clouds made up of silicate grains.