As artificial intelligence and machine learning continues to be integrated into all sorts of sectors, the question we keep asking ourselves is, “will they replace humans?” And that debate is still ongoing because the possibilities for these two technologies are endless, we truly don’t know its full power yet.
What we do know is that a machine learning algorithm just confirmed the existence of 50 new exoplanets. This discovery came from NASA’s Kepler mission, which has already discovered over 4,000 exoplanets. Algorithms have been used plenty of times before, but have never used one based on machine learning.
With 4,201 exoplanets confirmed, scientists believe there are billions in the Milky Way. The algorithm was created to separate real planets from fake ones at the University of Warwick with no help from humans.
According to an article from Forbes, “machine learning is a form of artificial intelligence. It’s about automating repetitive tasks, essentially training a computer to recognize patterns and categorize data without any input from humans.”
The algorithm used is able to recognize real planets using two large samples of confirmed planets and “false positives.” Scientists hope to apply this technique to future missions and discover more of what is out there. Machine learning has never been used in this capacity before, in the past, it was only used for ranking planetary candidates.
So then we ask ourselves the question: does modern astronomy need humans?
Scientists say we still need humans but need to change the image in our heads that we have for astronomers. Instead of thinking of people using a big telescope, its data scientists creating cutting-edge algorithms and machine learning techniques to make discoveries.
With faster and automated results, machine learning has been a game-changer for scientists. The more the algorithm learns what is a real exoplanet, the more accurate it becomes.
So far, the planets that have been discovered range from being smaller than Earth to Neptune-sized gas planets. Orbits have been a day to 200 days long. Machine learning has helped scientists validate new and existing planets and can accomplish the task at a much quicker speed.
This is only the beginning for machine learning, it might hit your sector next!