A High School Student Uses Artificial Intelligence to identify Gravitational Waves

A High School Student Uses Artificial Intelligence to identify Gravitational Waves

Before he could legally drive, high school student Adam Rebei already employed on Blue Waters Supercomputer at the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign (NCSA) to run the complex regulations of black hole. 

Rebei told the NCSA that "For the first time, using Blue Waters, we did a first tour and got to see a computer, which is a wonderful thing because it is a very powerful machine. 

To reach there, Rebei first took an astronomy class, that led him to his work with NCSA. There he worked closely with research scientist Eliu Huerta, who leads the gravitational group.

Heurta said "Adam started his first talk in the group at our weekly meeting about the history of general relativity and gravitational waves. Soon, though, I realized that he had the skills and determination to do research at the level of a graduate student. Since then, he has participated in many publications which allows him to learn about how to combine high performance computing, deep learning, and numerical relativity to upgrade our knowledge in gravitational wave astrophysics."

Story of Rebei is being highlighted on the NCSA blog, explaining his journey as a student to published author.

NVIDIA GPU accelerated the Blue Waters Supercomputer at the National Center for Supercomputing Applications. Rebei uses it to provide more effectiveness to his project i.e. morphology of gravitational waves, that could be produced by two black holes that collide following eccentric or elliptical orbits.

Current methods used to detect gravitational waves can identify that a dark matter incident has happened but what kind of event is not there. They also do not recognize complex events where dark matter objects do not come in simple shape.

Rebei saw an opportunity to build the first generation algorithms developed by Huerta’s lab so that high accuracy can be obtained. Adam’s models were trained within thirty minutes using 64 NVIDIA GPUs on Blue Waters using the Horowode deep learning framework.

Rebei and his co-authors wrote in one of their papers, "Building upon our deep learning work, we show for the first time that machine learning can accurately coexist high-order waveform multipole signals from the eccentric binary black mergers embedded in actual LIGO data."

Blue Waters Supercomputer is furnished with NVIDIA Tesla GPUs and it has a peak performance of 13.34 petaflops.

Rebei is currently completing his senior year of high school in Illinois. Already with three publications in his portfolio, including the one above in which he is a lead author, Rebei plans to study astrophysics or physics at Princeton in the fall.

For more updates on Artificial Intelligence stay tuned with us at LunaticAI. 

Source: NCSA

Don't Miss

1. A High School Student uses AI to Detect Plant Diseases

2. Top 100+ Artificial Intelligence, Machine Learning, and Data Science Courses

3. PoemPortrait: Google's New AI Project

4. Why Google's Best AI Failed in a High School Math Test?

5. Here's How Scientist Used AI to Convert Brain Signals into Voice

Post a Comment