Artificial Intelligence To Join Humans On Their Quest To Search For Aliens
Artificial Intelligence (AI) is partnering with humans to search for alien life across the universe.
Express UK reported that a machine learning software with algorithms used by Google and Netflix has joined alien hunters on their quest.
This man-made intelligence, which researchers call as "XGBoost machine-learning algorithm," has the ability to observe planets and stars that could eventually lead to identifying if these astronomical bodies are habitable or not. This computer software has been installed with data that could learn by its own without the need for humans to regularly update it.
Created by researchers at the University of Toronto in Scarborough, Canada, this AI machine is reportedly 1,000 times faster at finding out if a planet is habitable and can work 24/7 unlike humans.
"We find that training an XGBoost machine-learning algorithm on physically motivated features yields an accurate classifier of stability in packed systems," the researchers wrote in an article. To train these algorithms, the researchers generated a date set of 5,000 N-body integrations of three planetary systems at over 107 orbits.
The study's lead author, Dan Tamayo, from the Centre for Planetary Science believes that this machine learning provides a "powerful way" to focus on questions about astrophysics and predict if these planetary systems are indeed stable for habitation.
The researchers will also use the same AI software for NASA's Transiting Exoplanet Survey Satellite (TESS) to be launched next year. This two-year mission will study the brightest stars in the universe and eventually find out if these astronomical bodies do belong to the solar system.
"It could be a useful tool because predicting stability would allow us to learn more about the system, from the upper limits of mass to the eccentricities of these planets," Tamayo said. "It could be a very useful tool in better understanding those systems."
This study was published in the journal Astrophysical Journal Letters.