A new artificial intelligence algorithm has found more than 300 previously unknown exoplanets in data collected by the defunct exoplanet-hunting telescope.
NS kepler space telescope, NASA’s first dedicated exoplanet hunter, has looked at hundreds of thousands of stars in search of potentially habitable worlds beyond our own. Solar system. The collection of potential planets you’ve amassed continues to make new discoveries even after the telescope dies. Human experts analyze data for signs of exoplanets. But a new algorithm called ExoMiner can now simulate this procedure and clean up the catalog faster and more efficiently.
The telescope, which stopped operating in November 2018, is looking for a temporary decrease in stellar brightness that may be caused by a planet transiting in front of the stellar disk as seen from Kepler’s perspective. But not all this darkness is the reason outer planet, and scientists must follow detailed procedures to distinguish false positives from real things, according to A NASA statement.
Related: These 10 Ultra Extreme Exoplanets are out of this world
ExoMiner, is a so-called neural network, which is a kind of artificial intelligence algorithm that can learn and improve its capabilities when given enough data. And Kepler has produced a wealth of data: In less than 10 years, telescopes have found thousands of planet candidates, nearly 3,000 of which have been confirmed. This is a large part of the total 4,569 exoplanets currently known.
For each exoplanet candidate, scientists looking at the Kepler data will look at the light curve and calculate the fractional size of star It looks like the planet is closed. They will also analyze how long it would take a potential planet to cross the stellar disk. In some cases, the observed change in brightness is unlikely to be explained by an exoplanet orbiting the Solar System. The ExoMiner algorithm follows exactly the same process but is more efficient, allowing the researchers to add a previously unknown group of 301 exoplanets to Kepler’s planetary catalog simultaneously.
“When ExoMiner says something is a planet, you can be sure that it is a planet,” Hamid Valizadegan, ExoMiner Project Leader and Director of Machine Learning with the University Space Research Consortium at NASA Ames Research Center, said in the statement. “ExoMiner is extremely accurate and in some ways more reliable than current machine classifiers and human experts that it should emulate because of the bias that comes with the human label.”
Now that ExoMiner has demonstrated its expertise, scientists want to use it to help examine data from current and future exoplanet-search missions, such as current NASA missions. Satellite transit to survey the outer planets (TESS) or the European Space Agency’s Transiting Planets and Star Oscillation (PLATO) mission, which will launch in 2026.
Unfortunately, there are no newly confirmed exoplanets that are likely to host life, as they are outside the habitable zone of their parent star.
In a statement, NASA said the paper had been accepted for publication in the Astrophysical Journal. A concept paper Available for reading on prepress arXiv.org.
Follow Teresa Poltarova on Twitter at tweet embed. Follow us in twitter tweet embed and continue Facebook social networking site.
–
