Planetary data has become so vast; it is impossible now for humans to sit through everything and find out nothing has been missed. The advancement in space telescope technology has led to unimaginable amounts of data that, without computer intelligence, cannot be analyzed thoroughly.
A team of UK researchers led by David Armstrong at the University of Warwick have developed a machine-learning algorithm that can handle the confirmation of new planets in the bounds of data that has been stored over time. This new tool can help astronomers sift through chunks of data, old and new, finding planets and other discoveries that were previously missed.
The machine-learning algorithm uses data from telescopes like NASA’s TESS (Transiting Exoplanet Survey Satellite) to look for dips in brightness that indicates something is passing by a star. This method is used to find planets that are hidden, rogue, or just aren’t properly illuminated by a star. The dips in brightness indicate that something is passing by a star, indicating a large mass. This dip could indicate a planet, asteroid, dust, or it could even be a glitch.
The team used data from NASA’s now-retired Kepler mission. The data, including new planets and false positives, was then used to train a machine-learning algorithm. That algorithm was then used on group data, including unconfirmed planetary bodies, where the system identified 50 planets.
In a Warwick press release on Tuesday, Armstrong says: “The algorithm we have developed lets us take 50 candidates across the threshold for planet validation, upgrading them to real planets. 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 1% chance of a candidate being a false positive, it is considered a validated planet.”
Artificial intelligence has a lot of scope in identifying missed planetary bodies from existing data. The algorithm can simply be applied to planetary candidates, reducing the pure manual searching that was required before. The TESS mission alone has found 66 new exoplanets and more than 2,100 planetary candidates.
“We still have to spend time training the algorithm, but once that is done, it becomes much easier to apply it to future candidates,” Armstrong said. “You can also incorporate new discoveries to progressively improve it.”
Do you want to publish on Apple News, Google News, and more? Join our writing community, improve your writing skills, and be read by hundreds of thousands around the world!