WVU students develop AI to detect fast radio bursts


MORGANTOWN. W.Va. – Devansh Agarwal and Kshitij Aggarwal, two West Virginia University students studying physics and astronomy, have created artificial intelligent machine-learning software to detect fast radio bursts.

Fast radio bursts are intense, unexplained pulses of energy, light-years away, that pop up for mere milliseconds. They were discovered in 2007, according to a WVU press release. However, since then, only about 100 have been discovered because finding them is a task done manually by reading data plots, recorded with radio telescopes, for hours on end.

Aggarwal, one of the software developers, said normally scientists have to sift through hundreds and thousands of data points, but now the AI can do that work and present them with the 10 or so “candidate events,” in which a data point could possibly turn out to be a fast radio burst. Or, it could just be interference or noise, the release stated.

Kshitij Aggarwal

I would just say it was a really nice learning experience. Even though we faced a lot of troubles and there are parts of the project that didn’t go as well as we planned, we had to redo some of the stuff. Obviously, with any project, there is a learning curve and some ups and downs, so it’s basically just about powering through.

Kshitij Aggarwal – WVU graduate student

According to the press release, the students dubbed the software FETCH, which stands for “fast extragalactic transient candidate hunter.” And they’ve made it open-source, meaning anyone anywhere is free to use it. Devansh Agarwal, the other half of the FETCH team had this to say in the release:

Devansh Agarwal 

Our aim off the bat was to use AI to model a task that humans can do with the same precision or better. People have been using AI for a myriad of techniques in biological systems, x-rays, cat scans and MRIs to identify diseases. We wanted to make our system generic enough that anyone can use it anywhere in the world.

Devansh Agarwal – WVU graduate student

According to the release, the software will also come in handy for research through the Green Bank Observatory, a partner of WVU, and a key site for the university’s astronomy research. The Green Bank Telescope, located in Pocahontas County, is the world’s largest fully-steerable radio telescope.

In 2007, Duncan Lorimer, the associate dean for research in the WVU Eberly College, was credited for helping discover fast radio bursts. In the release, Lorimer said Green Bank has allowed WVU to operate in an environment where it would normally have thousands of pulses to look through per day down to one or two.

Duncan Lorimer

“We’re really pleased when students take an initiative,” Lorimer said. “I see my role nowadays as a few steps away from the research, but I try to give the students the knowledge that they can run with. It’s like learning a new language. You teach them a few phrases, and then they’ll string together full sentences. Or, learning music. You teach them a couple of notes, and they take it and come up with new tunes.”

Aggarwal said he is happy to know a technology he helped to develop is now going to be used all around the world.

“The thing we made is now being used by tons of people around the world,” Aggarwal said. “It’s being used in Puerto Rico, it’s been used in New Mexico, Australia and Europe. So, people around are actually using this, and they’re building on it, as well. They are making similar systems. That is a really nice feeling, you know, being a graduate student and making a contribution to which other people are recognizing and using.”

Copyright 2020 Nexstar Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.

Link to 12 things you need to know page

WBOY 12 News Facebook Page

Trending Stories