Data Science Investment Counter —Funding raised by UK data science companies in 2018.
£ 5.640 Million

Artificial Intelligence program discovers two new planets

Artist’s conception of the Kepler space telescope observing planets transiting a distant star.

Astronomers at The University of Texas at Austin have used artificial intelligence (AI) to discover two hidden planets more than 1,000 light-years away in the constellation Aquarius. 

The new algorithm, developed in partnership with Google, shows potential for identifying many additional planets that traditional methods could not locate. The program sifts through the data taken by the Kepler space telescope to find signals missed by more conventional planet-hunting methods.

The discovered planets were dubbed by the team led by Anne Dattilo, an undergraduate student at UT Austin, K2-293b and K2-294b. Other team members include NASA Sagan fellow at UT Austin Andrew Vanderburg and Google engineer Christopher Shallue.

Commenting on the news, Vanderburg explained: “K2 data is more challenging to work with because the spacecraft is moving around all the time”. And while missions using K2 and Kepler data has already contributed to extended planets’ discoveries, Vanderburg is confident AI will impact this research area even further.

AI will help us search the data set uniformly,” he said. “Even if every star had an Earth-sized planet around it, when we look with Kepler, we won’t find all of them. That’s just because some of the data’s too noisy, or sometimes the planets are just not aligned right. So, we have to correct for the ones we missed. We know there are a lot of planets out there that we don’t see for those reasons.

“If we want to know how many planets there are in total, we have to know how many planets we’ve found, but we also have to know how many planets we missed. That’s where this comes in,” he added.

The current algorithm can probe the entire K2 data set, Dattilo said—approximately 300,000 stars. She also thinks the method can apply to Kepler’s successor planet-hunting mission, TESS, which launched in April 2018.

The discoveries have been accepted for publication in The Astronomical Journal, UT said.

“I’m really proud of what we accomplished. Finding two planets is [a] pretty big deal, especially for an undergraduate such as myself,” Dattilo said. “But I still think there’s more to do, and I’m still doing the research and continuing to make it better.”

Image via NASA Ames/ W Stenzel.


Co-working space and blog dedicated to all things data science.

Subscribe to our newsletter