Artificial intelligence is now inquiring one of the hot mysteries of astronomy. To examine cosmic data and recognize fast radio eruptions, weird and powerful pulses which are considered to originate from far away galaxies, researchers have created a machine learning algorithm. This team of researchers is from University of California, Berkeley, and they are working on Search for Extraterrestrial Intelligence (SETI) project. The cause of these radio eruptions is not exactly known but there are theories that maybe this is a sign of presence of aliens or maybe black holes are colliding or simply the neutron stars are being magnetized.
In a recent research work, a personalized A.I. system was used by SETI researchers to find out dozens of fast radio eruptions which have not been recognized before, these eruptions originated from a 3 billion light-years away source. This identification of radio eruptions has been done using the already present data set, which had also been previously examined by space scientists.
“Artificial Intelligence has seen very rapid development in recent years and its application in medicine, security, finance, and everyday object recognition have already reached certain level of maturity,” Gerry Zhang, Ph.D. student of University of California, Berkeley, who also helped in developing the machine learning algorithm, said. “Astronomy represents a relatively unexplored area for A.I. The very large volume of data that astronomers collect present a challenging playground for state-of-the-art A.I. Radio astronomical data themselves presents challenges of large scale and high noise. Learning to apply A.I. to such new data is challenging and fruitful.”
A machine learning algorithm named “convolutional neural network” was used by Zhang and his team to make this discovery. This algorithm mimics the functioning of a human brain, and is already been used to identify earthquakes and discover craters on the moon.
In their recent work, simulated signals were used by the researchers to train their algorithm, to make it identify the marks of any radio eruptions, and then “let the trained network loose on the data containing the real signals,” Zhang said. Their work discovered 72 signals which had previously been neglected by the astronomers.
These latest results will help in clearing out the current cosmic theories and the related myth stories regarding the origin of fast radio eruptions. Whether they are caused by aliens? Perhaps not. But still there is a chance. So, using these results and some new results, it can be find out what exactly is happening in space. Hence, right now astronomers need resources to obtain more data and develop better algorithms for data examination.
“Fast radio bursts are one of the most recently discovered unknown signals in astronomy,” Zhang claimed. “With new instruments being designed for them coming online, [they are] well-poised to be one of the unknowns that will be solved within the next five to 10 years.”
A paper on this research has been recently accepted for publication in “The Astrophysical” journal.