Last Update: April 27, 2023, 3:59 pm IST
Researchers used machine learning tools, a type of artificial intelligence (AI), and have now confirmed evidence of a previously unknown exoplanet. Researchers from the University of Georgia (UGA) in the US said their study showed machine learning to correctly determine the presence of exoplanets by looking into protoplanetary disks, the gas around newly forming stars. They said their findings, published in The Astrophysical Journal, represent a first step toward using machine learning to identify previously unseen exoplanets.
“We confirmed the planet using conventional techniques, but our model guided us to run those simulations and showed us where the planet could be,” said Professor M. said doctoral student Jason Terry. Lead author on the study.
“When we applied our models to a set of older observations, they identified a disk that was not a planet, despite what had already been analysed. As in previous discoveries, we simulated the disk and found that can recreate a planet observation,” Terry said.
According to Terry, the model suggested the presence of a planet, which was indicated by several images that strongly highlighted a particular region of the disk that turned out to be a distinctive sign of a planet – the velocities of gas near the planet. An unusual deviation in
“This is an incredibly exciting proof of concept. We knew from our previous work that we could use machine learning to create known exoplanets,” said Dr., assistant professor of computational astrophysics and director of the Exoplanet and Planet Formation Research Group at UGA. said principal investigator Cassandra Hall.
“Now, we know for sure that we can use this to make brand new discoveries,” Hall said.
The models were able to detect a signal in data that people had already analyzed; He found something that had not been possible before.
The researchers said their study is an example of how engaging AI can enhance scientists’ work by expanding researchers’ accuracy and efficiently reducing their time.
“This shows that our model – and machine learning in general – has the potential to quickly and accurately identify important information that people may miss. This has the potential to dramatically speed up analysis and subsequent theoretical insights.” It is,” Terry said.
read all Latest Buzz News Here
(This story has not been edited by News18 staff and is published from a syndicated news agency feed)
