The exoplanet discovery marks the first time scientists have used machine learning to analyse planet candidates in deep space. The machine algorithm, which is a form of artificial intelligence (AI), sifted through potential exoplanets to determine which are real and which are fakes. The results were published in the journal Monthly Notices of the Royal Astronomical Society.
The new planets are as big as Neptune or as small as Earth, with orbits ranging from 200 days to just one.
Dr David Armstrong, from the University of Warwick Department of Physics, said: “The algorithm we have developed lets us take fifty candidates across the threshold for planet validation, upgrading them to real planets.
“We hope to apply this technique to large samples of candidates from current and future missions like TESS and PLATO.
“In terms of planet validation, no-one has used a machine learning technique before.”
The hunt for exoplanets relies on copious amounts of data from telescopes like NASA’s Transiting Exoplanet Survey Satellite or TESS.
The satellites observe swathes of the night sky for transiting planets – planets passing in front of their star – which cause a tiny dip in the star’s brightness.
However, some of these dips can be caused by binary stars, interference from other objects, and even errors in the camera.
Astronomers aim to iron out these kinks during the validation process, with the aid of machine learning.
Dr Amrstrong said: “Machine learning has been used for ranking planetary candidates but never in a probabilistic framework, which is what you need to truly validate a planet.
We hope to apply this technique to large samples of candidates
Dr David Armstrong, University of Warwick
“Rather than saying which candidates are more likely to be planets, we can now say what the precise statistical likelihood is.
“Where there is less than a one percent chance of a candidate being a false positive, it is considered a validated planet.”
Warwick’s Departments of Physics and Computer Science paired with The Alan Turing Institute to develop an algorithm that can sort out real planets from fake one in databases of thousands of worlds.
The algorithm was trained to recognise exoplanets using confirmed samples collected by NASA’s Kepler mission.
Aliens on Mars? ‘Lioness statue’ found on the Red Planet [PICTURES]
UFO sighting near ISS in NASA live stream [VIDEO]
Life on Mars bombshell: Expert insists ‘there’s something’ [INSIGHT]
The algorithm was then used on a dataset of unconfirmed Kepler candidates, weeding out the fakes and confirming 50 new planets.
Past efforts to use machine learning have only been used to rank candidates.
Dr Theo Damoulas from the University of Warwick and Turing Fellow at The Alan Turing Institute said: “Probabilistic approaches to statistical machine learning are especially suited for an exciting problem like this in astrophysics that requires incorporation of prior knowledge – from experts like Dr Armstrong – and quantification of uncertainty in predictions
“A prime example when the additional computational complexity of probabilistic methods pays off significantly.”
The scientists are positive their algorithm is faster than existing techniques.
And even more impressively, the algorithm can be completely automated to trawl through thousands of exoplanet candidates.
Dr Armstrong said: “Almost 30 percent of the known planets to date have been validated using just one method, and that’s not ideal.
“Developing new methods for validation is desirable for that reason alone.
“But machine learning also lets us do it very quickly and prioritise candidates much faster.
“We still have to spend time training the algorithm, but once that is done it becomes much easier to apply it to future candidates.
“You can also incorporate new discoveries to progressively improve it.
“A survey like TESS is predicted to have tens of thousands of planetary candidates and it is ideal to be able to analyse them all consistently.
“Fast, automated systems like this that can take us all the way to validated planets in fewer steps let us do that efficiently.”
Source: Read Full Article