Student Astronomer Uses AI to Spot Two New Planets

Student Astronomer Uses AI to Spot Two New Planets

We are searching data for your request:

Forums and discussions:
Manuals and reference books:
Data from registers:
Wait the end of the search in all databases.
Upon completion, a link will appear to access the found materials.

Spotting planets is hard work. Astronomers have to sift through countless amounts of complex data in hopes that new planets will be discovered.

Two exoplanets spotted

That's why when a University of Texas at Austin student found not one but two exoplanets there was much to be impressed by.


Working in partnership with Google, a team led by undergraduate Anne Dattilo used artificial intelligence (AI) to uncover two hidden planets in the Kepler space telescope archive. The planets were from Kepler’s extended mission, called K2.

“K2 data is more challenging to work with because the spacecraft is moving around all the time,” team member NASA Sagan fellow at UT Austin Andrew Vanderburg explained.

This is because data taken during Kepler’s extended mission K2 was corrupted by a mechanical failure this spacecraft suffered. To counter this obstacle, Dattilo and her team created a new algorithm that ferreted out signals that were missed by traditional planet-hunting methods.

Searching the data uniformly

“AI will help us search the data set uniformly,” Vanderburg 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 explained.

The two planets Dattilo’s team found “are both very typical of planets found in K2,” she said.

“They’re really close in to their host star, they have short orbital periods, and they’re hot. They are slightly larger than Earth.”

To confirm the planets are real, the students followed up by studying the host stars using two ground-based telescopes: the 1.5-meter telescope at the Smithsonian Institution’s Whipple Observatory in Arizona and the Gillett Telescope at Gemini Observatory in Hawaii.

Now, the new AI algorithm should continue to help astronomers find many more missed planets hiding in Kepler and other data sets. Dattilo believes the method is also applicable to Kepler’s successor planet-hunting mission, TESS.

The two new planets discovered are called K2-293b and K2-294b. The first orbits a star 1,300 light-years away in the constellation Aquarius while the latter orbits a star 1,230 light-years away, also in Aquarius.

The discoveries will be published in an upcoming issue of The Astronomical Journal.

Watch the video: Machine Learning to Find Planets u0026 Astronomical Objects w. Dr. Pankratius @MIT EP 49 #DataTalk (July 2022).


  1. Klaus

    Thank you very much for your help in this matter. I did not know it.

  2. Akigami

    I confirm. I join told all above. We can communicate on this theme. Here or in PM.

  3. Davis

    You have hit the spot. A good idea, I agree with you.

  4. Badru

    the exact answer

  5. Sigwald

    I find that you are not right.Write in PM, we will talk.

  6. Carmel

    This message, is incomparable))), it is interesting to me :)

Write a message