Published 13:10 IST, August 26th 2020
Machine learning algorithm discovers 50 new planets from NASA's Kepler mission
A research team led by David Armstrong at the University of Warwick in the UK created a machine learning algorithm and trained it to validate exoplanets.
Advertisement
An AI algorithm has detected 50 potential planets that has stunned scientists about mysteries of undiscovered distant celestial entities. A research team led by David Armstrong at University of Warwick in UK created a machine learning algorithm and trained it using data on confirmed planets and false-positives from NASA's retired Kepler mission. findings from AI systems were published in Oxford's Monthly tices of Royal Astromical Society journal.
" algorithm we have developed lets us take 50 candidates across threshold for planet validation, upgrading m to real planets," Armstrong said in a press release.
While Telescopes like NASA's Transiting Exoplanet Survey Satellite (TESS) records glitch, asteroids, dust, binary star system basis brightness, scientists sat down to sift through Kepler data to analyze actual planetary candidates. “Sky surveys find thousands of planet candidates, and astromers have to separate true planets from fake ones,” Warwick’s press release said. “For first time, Artificial Intelligence was used to analyze a sample of potential planets and determine which ones are real and which are ‘fakes’, or false positives, calculating probability of each candidate to be a true planet,” it added.
Advertisement
" algorithm we have developed lets us take 50 candidates across threshold for planet validation, upgrading m 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, -one has used a machine learning technique before,” —Professor David Armstrong of University of Warwick's department of physics said in study.
Advertisement
[This graphic shows that a small area around Kepler-90 system, on left, has been searched by Kepler telescope. Compared to our solar system, where we kw of planets farr out, it is possible that Kepler-90 has even more planets. Credit: NASA]
[Kepler-90 is a Sun-like star, but all of its eight planets are scrunched into equivalent distance of Earth to Sun. inner planets have extremely tight orbits with a “year” on Kepler-90i lasting only 14.4 days. Credit: NASA]
Advertisement
[Researchers using data from W. M. Keck Observatory and NASA's Kepler mission have discovered a gap in distribution of planet sizes, indicating that most planets discovered by Kepler so far fall into two distinct size classes. Credit: NASA]
Used a process 'Transitioning'
According to release, Previous machine learning techniques have detected and ranked celestial candidates in past, but it never determined wher those candidates were confirmed planets or just star or something else, a crucial step for planet validation. refore, scientists carried out first large-scale compare-and-contrast of vel planet validation techniques, which will statistically confirm future exoplanets. Scientists used a process, kwn as transitioning, to observe huge quantities of data gared via telescopes between Earth and ir host star. However, to separate light dipping objects captured on telescopes with true exoplanets, scientists at Alan Turing Institute and Warwick's departments of physics and computer science built machine learning-method to identify planets from two large samples of confirmed planets and false positives from w-defunct Kepler mission, as per study. Ranging between size of Neptune to potential of Earth-like scales, scientists were able to detect planets that orbit up to 200 days and as low as one day.
Advertisement
"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,” Armstrong said. “ Less than a 1% chance of a candidate being a false positive, it is considered a validated planet."
Advertisement
13:11 IST, August 26th 2020