Artificial Intelligence Uncovers 72 New Fast Radio Bursts in GBT’s Breakthrough Listen Data

Single image of a Fast Radio burst (FRB) captured by Breakthrough Listen using the Green Bank Telescope.
Single image of a Fast Radio burst (FRB) captured by Breakthrough Listen using the Green Bank Telescope. (GBO/Breakthrough Listen)

For Immediate Release

Machine learning algorithms applied to data from the National Science Foundation’s Green Bank Telescope find new pulses from the mysterious repeating source FRB 121102. These algorithms are also helping Breakthrough Listen search for new kinds of candidate signals from extraterrestrial intelligence.

Breakthrough Listen – the astronomical program searching for signs of intelligent life in the Universe – has applied machine learning techniques to detect 72 new fast radio bursts (FRBs) emanating from the “repeater” FRB 121102.

Fast radio bursts, or FRBs, are bright pulses of radio emission, just milliseconds in duration, thought to originate from distant galaxies. Most FRBs have been witnessed during just a single outburst.

In contrast, FRB 121102 is the only one to date known to emit repeated bursts, including 21 detected during Breakthrough Listen observations made in 2017 with the National Science Foundation’s (NSF) Green Bank Telescope (GBT) in West Virginia.

The source and mechanism of FRBs are still mysterious. Previous studies with the NSF’s Very Large Array and other observatories have shown that the bursts from 121102 are emanating from a galaxy 3 billion light-years from Earth, but the nature of the object emitting them is still unknown. Theories range from highly magnetized neutron stars, blasted by gas streams near to a supermassive black hole, to suggestions that the burst properties are consistent with signatures of technology developed by an advanced civilization.

“Not all discoveries come from new observations,” remarked Pete Worden, Executive director of the Breakthrough Initiatives, which include Listen, “In this case, it was smart, original thinking applied to an existing dataset. It has advanced our knowledge of one of the most tantalizing mysteries in astronomy.”

animation showing 93 detected signals from FRB121102
This animation shows 93 detected signals from FRB121102. Among them 21 have previously been reported (denoted by red numbers), and 72 are new (white numbers). Each signal is shown as a spectrogram – the colors indicate the intensity of the signal as a function of frequency from 4.5 to 8.0 GHz (vertical axis) and time (horizontal axis, showing 100 milliseconds around the time of detection of each burst). The pulses exhibit a wide range of modulations and brightness. (GBO/Breakthrough Listen)

In search of a deeper understanding of this intriguing object, the Listen science team at the University of California, Berkeley SETI Research Center observed FRB 121102 for five hours on August 26, 2017, using the Breakthrough Listen digital instrumentation at the GBT. Combing through 400 TB of data, they reported (in a paper led by Berkeley SETI postdoctoral researcher Vishal Gajjar, recently accepted for publication in the Astrophysical Journal) a total of 21 bursts. All were seen within one hour, suggesting that the source alternates between periods of quiescence and frenzied activity.

Now, UC Berkeley PhD student Gerry Zhang and collaborators have developed a new, powerful machine-learning algorithm, and reanalyzed the 2017 GBT dataset, finding an additional 72 bursts that were not detected originally. Zhang’s team used some of the same techniques that Internet technology companies use to optimize search results and classify images. They trained an algorithm known as a convolutional neural network to recognize bursts found with the classical search method used by Gajjar and collaborators, and then set it loose on the 400 TB dataset to find bursts that the classical approach missed.

The results have helped put new constraints on the periodicity of the pulses from FRB 121102, suggesting that the pulses are not received with a regular pattern (at least if the period of that pattern is longer than about 10 milliseconds). Just as the patterns of pulses from pulsars have helped astronomers constrain computer models of the extreme physical conditions in such objects, the new measurements of FRBs will help figure out what powers these enigmatic sources.

“This work is only the beginning of using these powerful methods to find radio transients,” said Gerry Zhang. “We hope our success may inspire other serious endeavors in applying machine learning to radio astronomy.”

“Gerry’s work is exciting not just because it helps us understand the dynamic behavior of FRBs in more detail,” remarked Berkeley SETI Research Center Director and Breakthrough Listen Principal Investigator Dr. Andrew Siemion, “but also because of the promise it shows for using machine learning to detect signals missed by classical algorithms.”

Whether or not FRBs themselves eventually turn out to be signatures of extraterrestrial technology, Breakthrough Listen is helping to push the frontiers of a new and rapidly growing area of our understanding of the Universe around us.

The new results are described in an article (Zhang et al. 2018) accepted for publication in the Astrophysical Journal. A preprint of the paper, the data and code used in the analysis, and further details of the observations are available at on the Berkley SETI website.

Breakthrough Listen is a scientific program in search for evidence of technological life in the Universe. It aims to survey one million nearby stars, the entire galactic plane and 100 nearby galaxies at a wide range of radio and optical bands.

Green Bank Observatory is a facility of the National Science Foundation and is operated by Associated Universities, Inc.