Artificial Intelligence Beats Astronomers At Finding Fast Radio Bursts From the Universe

Astronomers used artificial intelligence to spot fast radio bursts and discovered an intriguing repeating event not classified yet by scientists. The mysterious signals from an unknown object were picked up by AI.

Fast Radio Bursts – FRB 121102

These signals are tough to spot or study. There have been 30 confirmed events in the last decade and lasted for a few milliseconds.

There is a special signal called FRB 121102 which is 3 billion light years away from our planet, and the most intriguing FRB ever found. Why is this particular signal so baffling?

Breakthrough Listen is a project set by the SETI Institute, a non-profit research organization which focuses on finding alien intelligence, which started studying FRB 121102.

Analysis of the data from the Green Bank Telescope observatory in Virginia was made with a convolutional neural network (CNN), a system that would show the duration and frequency of a signal. The CNN first received some simulated data of what an FRB would look like, adding data of almost 400,000 images. Out of all that data, half of them contained simulated FRBs and the other half didn’t.

The CNN learned the patterns and characteristics of the FRBs, and then the Breakthrough Listen project fed it real data from the Green Bank Telescope observatory.

The AI discovered 72 signals from FRB 121102

The paper was published in the Astrophysical Journal, stating the following:

“Together with the 21 previously reported pulses, this observation marks the highest number of FRB 121102 pulses from a single observation, totaling 93 pulses in five hours, including 45 pulses within the first 30 minutes.”

The co-author of the study, the lead investigator for Breakthrough Listen and the director of the Berkeley SETI Research Center, Andrew Siemion stated:

“This work is exciting not just because it helps us understand the dynamic behavior of fast radio bursts in more detail, but also because of the promise it shows for using machine learning to detect signals missed by classical algorithms.”

As for what the object that sends these signals could be, scientists theorize it could come from a new kind of supernova, neutron stars or even alien life.

Gerry Zhang, a Ph.D. student at the University of California, Berkeley, and co-author of the study concludes that the project is essential in understanding the Universe, even if these FRBs turn out not to be “signatures of extraterrestrial technology.”

Doris’s passion for writing started to take shape in college where she was editor-in-chief of the college newspaper. Even though she ended up working in IT for more than 7 years, she’s now back to what he always enjoyed doing. With a true passion for technology, Doris mostly covers tech-related topics.