Droids beat astronomers in predicting survivability of exoplanets

Artist's impression of Kepler-16b, discovered by NASA's Kepler mission and the first confirmed circumbinary planet. It is a gas giant that orbits close to the edge of its binary system's habitable zone. Credit: T. Pyle / NASA / JPL-Caltech

---

Artificial intelligence is giving scientists new hope for studying the habitability of planets, in a study from astronomers Chris Lam and David Kipping. Their work looks at so-called ‘Tatooines’, and uses machine learning techniques to calculate how likely such planets are to survive into stable orbits. The study is published in the journal Monthly Notices of the Royal Astronomical Society. 

Circumbinary planets are those planets that orbit two stars instead of just one, much like the fictional planet Tatooine in the Star Wars franchise. Tens of these planets have so far been discovered, but working out whether they may be habitable or not can be difficult.

Moving around two stars instead of just one can lead to large changes in a planet’s orbit, which mean that it is often either ejected from the system entirely, or it crashes violently into one of its twin stars. Traditional approaches to calculating which of these occurs for a given planet get significantly more complicated as soon as the extra star is thrown into the mix.

“When we simulated millions of possible planets with different orbits using traditional methods, we found that planets were being predicted as stable that were clearly not, and vice versa,” explains Lam, lead author of the study and a recent graduate of Columbia University.

Planets need to survive for billions of years in order for life to evolve, so finding out whether orbits are stable or not is an important question for habitability. The new work shows how machine learning can make accurate predictions even if the standard approach - based on Newton’s laws of gravity and motion - breaks down.

“Classification with numerous complex, inter-connected parameters is the perfect problem for machine learning,” says Professor Kipping, supervisor of the work.

After creating ten million hypothetical Tatooines with different orbits, and simulating each one to test for stability, this huge training set was fed into the deep learning network. Within just a few hours, the network was able to out-perform the accuracy of the standard approach.

More circumbinary planets look set to be discovered by NASA’s Transiting Exoplanet Survey Satellite (TESS) mission, and Lam expects their work to help: “Our model helps astronomers to know which regions are best to search for planets around binary stars. This will hopefully help us discover new exoplanets and better understand their properties.”

Source:  Royal Astronomical Society (RAS)

---

Media contacts 

Dr Morgan Hollis
Royal Astronomical Society
Mob: +44 (0)7802 877 700
mhollis@ras.ac.uk

Dr Robert Massey
Royal Astronomical Society
Mob: +44 (0)7802 877 699
rmassey@ras.ac.uk

---

Science contacts

Mr Chris Lam
Columbia University
Tel: +1 954 540 1339
cl3425@columbia.edu

Prof. David Kipping
Columbia University
dkipping@astro.columbia.edu

---

Video:

Prof. David Kipping explains why three-body systems are so tricky and how a neural network can save the day. Neural networks can capture borderline cases that are missed by even the most sophisticated mathematical solutions. He also highlights how neural networks might play an increasingly larger role in answering similarly complex science questions. Credit: D. Kipping / Cool Worlds Lab

---

Further information

The new work appears in: "A machine learns to predict the stability of circumbinary planets", C. Lam & D. Kipping, Monthly Notices of the Royal Astronomical Society (2018) 476 (4): 5692-5697 (DOI: 10.1093/mnras/sty022).

A copy of the paper is available at: https://doi.org/10.1093/mnras/sty022

---

Notes for editors 

The Royal Astronomical Society (RAS), founded in 1820, encourages and promotes the study of astronomy, solar-system science, geophysics and closely related branches of science. The RAS organizes scientific meetings, publishes international research and review journals, recognizes outstanding achievements by the award of medals and prizes, maintains an extensive library, supports education through grants and outreach activities and represents UK astronomy nationally and internationally. Its more than 4,000 members (Fellows), a third based overseas, include scientific researchers in universities, observatories and laboratories as well as historians of astronomy and others. The RAS accepts papers for its journals based on the principle of peer review, in which fellow experts on the editorial boards accept the paper as worth considering. The Society issues press releases based on a similar principle, but the organisations and scientists concerned have overall responsibility for their content. Follow the RAS on Twitter, Facebook and Instagram

---

New Planet Is Largest Discovered That Orbits Two Suns

Artist's impression of the simultaneous stellar eclipse and planetary transit events on Kepler-1647. 

Credits: Lynette Cook

Comparison of the relative sizes of several Kepler circumbinary planets. Kepler-1647 b is substantially larger than any of the previously known circumbinary planets. 

Credits: Lynette Cook

A bird's eye view comparison of the orbits of the Kepler circumbinary planets. Kepler-1647 b's orbit, shown in red, is much larger than the other planets (shown in gray). For comparison, the Earth's orbit is shown in blue. Credits: B. Quarles

If you cast your eyes toward the constellation Cygnus, you’ll be looking in the direction of the largest planet yet discovered around a double-star system. It’s too faint to see with the naked eye, but a team led by astronomers from NASA’s Goddard Space Flight Center in Greenbelt, Maryland, and San Diego State University (SDSU) in California, used NASA's Kepler Space Telescope to identify the new planet, Kepler-1647b.

The discovery was announced today in San Diego at a meeting of the American Astronomical Society. The research has been accepted for publication in the Astrophysical Journal with Veselin Kostov, a NASA Goddard postdoctoral fellow, as lead author.

Kepler-1647 is 3,700 light-years away and approximately 4.4 billion years old, roughly the same age as Earth. The stars are similar to the sun, with one slightly larger than our home star and the other slightly smaller. The planet has a mass and radius nearly identical to that of Jupiter, making it the largest transiting circumbinary planet ever found.

Planets that orbit two stars are known as circumbinary planets, or sometimes “Tatooine” planets, after Luke Skywalker’s home world in “Star Wars.” Using Kepler data, astronomers search for slight dips in brightness that hint a planet might be passing or transiting in front of a star, blocking a tiny amount of the star’s light.

“But finding circumbinary planets is much harder than finding planets around single stars,” said SDSU astronomer William Welsh, one of the paper’s coauthors. “The transits are not regularly spaced in time and they can vary in duration and even depth.”

“It’s a bit curious that this biggest planet took so long to confirm, since it is easier to find big planets than small ones,” said SDSU astronomer Jerome Orosz, a coauthor on the study. “But it is because its orbital period is so long.”

The planet takes 1,107 days – just over three years – to orbit its host stars, the longest period of any confirmed transiting exoplanet found so far. The planet is also much further away from its stars than any other circumbinary planet, breaking with the tendency for circumbinary planets to have close-in orbits. Interestingly, its orbit puts the planet with in the so-called habitable zone–the range of distances from a star where liquid water might pool on the surface of an orbiting planet.

Like Jupiter, however, Kepler-1647b is a gas giant, making the planet unlikely to host life. Yet if the planet has large moons, they could potentially be suitable for life.

“Habitability aside, Kepler-1647b is important because it is the tip of the iceberg of a theoretically predicted population of large, long-period circumbinary planets,” said Welsh.

Once a candidate planet is found, researchers employ advanced computer programs to determine if it really is a planet. It can be a grueling process.

Laurance Doyle, a coauthor on the paper and astronomer at the SETI Institute, noticed a transit back in 2011. But more data and several years of analysis were needed to confirm the transit was indeed caused by a circumbinary planet. A network of amateur astronomers in the Kilodegree Extremely Little Telescope "Follow-Up Network” provided additional observations that helped the researchers estimate the planet’s mass.

For more information about the Kepler mission, please see: www.nasa.gov/kepler

A preprint of the paper can be found at: http://arxiv.org/pdf/1512.00189v2

High-resolution artwork can be obtained at: http://go.sdsu.edu/kepler/

Editor: Ashley Morrow

Source: NASA/Kepler anda K2