Breakthrough Listen Uses AI To Detect New Fast Radio Bursts

Breakthrough Listen Uses AI To Detect New Fast Radio Bursts

Breakthrough Listen Uses AI To Detect New Fast Radio Bursts

In August of 2017, the Listen science team at the University of California, Berkeley SETI Research Center observed FRB 121102 for five hours, using digital instrumentation at the GBT.

FRBs are bright pulses of radio waves which last only a couple of milliseconds and originate from faraway galaxies. Some theories, however, justify that their properties are consistent with signatures of technology developed by an advanced civilization. One such project, Breakthrough Listen, has implemented Artificial Intelligence (AI) in its methodology to find patterns in collected data - resulting in the discovery of 72 new Fast Radio Bursts (FRB's), supposedly originating from an unknown source 3 billion light years away.

Andrew Siemion, the director of the Berkeley SETI Research Center, said in a UC Berkeley news item that the successful application of machine learning could lead to more breakthroughs. Most fast radio burst signals are one-time events, so the fact that FRB121102 sends them out repeatedly indicates that there is something different about this source that we don't understand yet.

"This work is exciting not just because it helps us understand the dynamic behavior of fast radio bursts in more detail, he said".

The researchers used an algorithm known as a "convolutional neural network" to comb through a massive set of data, 400 terabytes, and identify bursts missed during last year's research. The 21 fast radio bursts were all seen within one hour, which suggests that whatever the source of FRB 121102 is, it demonstrated a period of excessive activity.

The researchers developed the new, powerful machine-learning algorithm and reanalysed the 2017 data, finding an additional 72 bursts not detected originally. The new additions bring the total number of signals detected from FRB 121102 up to 300.

Zhang's team used some of the same techniques that internet technology companies use to optimise search results and classify images.

Читайте также: Russian Federation starts biggest war games since USSR

"This work is simply the starting of the use of these noteworthy how to get radio transients", acknowledged Zhang.

According to the press release, though, the researchers did not find anything to suggest an artificial origin - they detected no pattern to the bursts, "at least if the period of that pattern is longer than about 10 milliseconds".

Researchers have since detected many more FRBs, but their origins remain a mystery to this day. "We hope our success may inspire other serious endeavors in applying machine learning to radio astronomy".

"Whether or not or not FRBs themselves sooner or later turn out to be signatures of extraterrestrial technology, Step forward Listen is helping to push the frontiers of a unique and swiftly increasing place of residing of our understanding of the Universe spherical us", he added.

A paper on the research was recently accepted for publication in The Astrophysical Journal.

In their recent study, the researchers trained their algorithm on simulated signals, teaching it to recognize signs of fast radio bursts, and then "let the trained network loose on the data containing the real signals", Zhang said.

For a decade, astronomers relish puzzled over ephemeral however extremely noteworthy radio bursts from home.

При любом использовании материалов сайта и дочерних проектов, гиперссылка на обязательна.
«» 2007 - 2018 Copyright.
Автоматизированное извлечение информации сайта запрещено.

Код для вставки в блог

Related news