AI discovers two planets from space telescope data

Scientists used artificial intelligence to uncover two more hidden planets in the data collected by the Kepler Space Telescope. The technique shows the promise to identify many additional planets as traditional methods couldn’t catch. Researchers from The University of Texas at Austin in the United States created an algorithm that sifts throughout the data taken by Kepler to ferret out signals which have been missed by traditional planet hunting methods. The process, described in The Astronomical Journal, should help astronomers find many other missing planets hidden in Kepler’s data. K2 data is more challenging to work with because the spacecraft is moving around all the time, said Andrew Vanderburg, from UT Austin.

This change came into being following a mechanical failure. While the mission planners found a workaround, the spacecraft was left with a wobble, which the AI had to take into account. The Kepler and K2 missions have already discovered thousands of planets around other stars, with an equal number of candidates awaiting confirmation. The two planets are very typical of the planets found in K2, the researchers said. They are really close in to their host star, they’ve short orbital periods, and they are hot. They are little more than Earth, said Anne Dattilo, who led the study. Of the two planets, one is called K2-293b and orbits a star 1, 300 light years away in the constellation Aquarius.

The other, K2-294b, orbits a star 1, 230 light years away, also located in Aquarius. After the team used their algorithm to find these planets, they followed up by studying the host stars using ground based telescopes to confirm that the planets are real. These observations were made with the 1.5 meter telescope at the Whipple Observatory of the Smithsonian Institution in Arizona and Gillett Telescope at the Gemini Observatory in Hawaii. The future of the AI concept for finding planets hidden in data sets looks bright. The current algorithm may be utilized to probe the whole K2 data set, Dattilo said, approximately 300, 000 stars. The method couls also be applied to Kepler’s heir planet hunting mission, TESS, which launched in Apr 2018. Kepler’s mission ended later that year.

Share this post