The artificial intelligence helps to break through the audit Find new fast radio bursts

Scientists in search of extraterrestrial life discover new bursts of radio using AI

The new FRB discovered by the AI ​​algorithm will help scientists not only shed light on their nature but also on their source.

Theories range from highly magnetized neutron stars blown by gas flows from a supermassive black hole close to the signatures of technologies developed by an advanced civilization. The source is known "repeater"Fast radio bursts – the only known object to date – called FRB 121102. And the source of the FRB remains a mystery to astronomers.Fast radio waves are light pulses of a few milliseconds.But they are also extremely short, not lasts only a few milliseconds and the majority occurs only once, without warning.

A lot of new signals have been discovered from the famous repeat fast radio source FRB 121102 – and we can thank the artificial intelligence for these results.

"As the FRBs themselves turn out to be signatures of extraterrestrial technologies, Breakthrough Listen helps push the boundaries of a new and rapidly growing field of our understanding of the universe around us," said UC Berkeley Ph. D. student Gerry Zhang.

The astronomical program of 100 million dollars looking for signs of intelligent life in the universe, Breakthrough listenOn Monday night, artificial intelligence helped scientists detect 72 new fast bursts (FRB) from FRB-121102.

To better understand the new fast radio, the Breakthrough listen The SETI research team at the University of California at Berkeley observed FRB 121102 on August 26, 2017. "All were viewed in one hour, suggesting that the source alternates between sessions of rest and relaxation. frenzied process, "said Vishal Gajjar, a postdoctoral researcher at Berkeley. The strategy is similar to that used by IT companies to optimize search results on the Internet, Breakthrough listen representatives said in a statement.

Scientists can not yet identify the process that produces short and sudden radio bursts, which means that it is not possible to decide that they have not not made by extraterrestrials. According to a press release from the University of California at Berkeley, researchers have "formed an algorithm called a convolutional neural network" to replicate traditional methods of detecting gusts.

Knowing that human observations are not always ideal, UC Berkeley Ph.D. Student Gerry Zhang has created a machine learning algorithm to apply to the dataset, hoping to collect the FRB that researchers could have missed.

Breakthrough listen Also applies the successful machine learning algorithm to find new types of signals likely to emerge from an extraterrestrial civilization. After reviewing the raw data, the team was able to determine a total of 21 FRBs, all in one hour, which indicates that the object, whatever it is, varies between an extremely calm and extreme activity. . The AI ​​results give insight into the periodicity of pulses from 121102 and suggest that it is not always the same patterns that determine when the explosions occur.