There are so many things in the vast universe that we have yet to discover—fortunately for us, we now have artificial intelligence to help us out.
Scientists recently developed a new machine learning algorithm, trained to identify potential planets, that was able to confirm the existence of 50 new planets. Buzz Lightyear must be especially excited.
NASA launched their Transiting Exoplanet Survey Satellite (TESS) back in 2018 as part of their mission to find new planets. The technology detects movements that a planet is passing between the telescope and a star, which is reflected by a telltale dip in light in the telescope’s data.
Launching today, our planet-hunting @NASA_TESS spacecraft will fly in a unique orbit that’ll allow it to study nearly the entire sky over 2 years. This special orbit is key in potentially finding thousands of new planets outside our solar system. Watch: pic.twitter.com/aEB6zeeYSf
— NASA (@NASA) April 16, 2018
However, the dip isn’t always caused by a planet, which results in a false positive. This means that scientists have to manually sift through the data to figure out which findings are actually accurate. Consequently, this can be a tedious job, but scientists have found a way for Artificial intelligence (AI) to help them out.
Researchers from the University of Warwick’s Departments of Physics and Computer Science, as well as The Alan Turing Institute, developed a new machine learning algorithm that is trained to distinguish which of the findings are correct based on a small sample of potential planets.
Fifty potential planets have had their existence confirmed by a new machine learning algorithm developed by @WarwickAstro and @warwickstats scientists.
Read more: https://t.co/wKBn1ckK4M
— Warwick Newsroom (@warwicknewsroom) August 25, 2020
The AI was trained to identify real planets using two samples of confirmed planets and false positives from the now-retired Kepler mission.
Using its algorithm, the AI was able to confirm the existence of 50 new planets, the first to be validated by machine learning.
It’s no surprise that there is still more to be discovered in our vast universe, but it’s just as fascinating to think about what else could possibly be out there. While most of us can’t explore outer space ourselves, we can look forward to future discoveries brought about by this new technology.
To infinity, and beyond!
POP! Creator Community / Lyshiel Aranal