Nvidia Joins Search for Extraterrestrial Life
SETI Institute taps Nvidia’s accelerated computing platforms in first AI search for fast radio bursts
Radio astronomers at the Search for Extraterrestrial Intelligence (SETI) Institute are using AI to conduct the world’s first real-time search for fast radio bursts (FRBs), high-energy signals from space that may be a sign of life.
Nvidia announced at its AI Summit on Tuesday that SETI radio astronomers are using Nvidia Holoscan, a sensor-processing platform, and Nvidia IGX, an edge-computing solution, to better understand these rare astronomical phenomena.
SETI Institute operates the Allen Telescope Array in Northern California to search for evidence of extraterrestrial intelligence and to study transient astronomical events such as fast radio bursts.
Historically, analyzing radio signals from space has been a slow, offline process. Researchers would collect data and then process it later with custom-built programs.
Nvidia’s platforms have enabled SETI researchers to create a real-time system for detecting FRBs and other faint signals from space, speeding up data analysis from the Allen Telescope Array.
The project was initiated after Andrew Siemion, chair for SETI at the SETI Institute, saw the potential of early machine learning to analyze radio signals over a decade ago.
The SETI Institute was already using Nvidia GPUs to accelerate algorithms to separate signals from background noise. Siemion approached Nvidia's senior technical product manager for edge HPC Adam Thompson to help build a system capable of real-time detection.
“We wanted to create something that would really push our capabilities forward,” Siemion said. “We envisioned a streaming solution that in a more general way takes real-time data from telescopes and brings it directly into the GPUs to do AI inference.”
The project saw the SETI Institute collaborate with Breakthrough Listen, another SETI research program headquartered at the University of Oxford, that processes data from radio telescopes using GPUs.
The SETI Institute developed the real-time data reception and inference pipeline using Holoscan SDK and a Breakthrough Listen researcher built and trained an AI model to detect fast radio bursts.
The latest trial involved pointing 28 antennas at the Crab Nebula, collecting over 90 billion data packets in just 15 hours and processing them at a rate of nearly 100 Gbps—twice the SETI Institute’s previous capability.
According to Siemion, the AI system can capture and analyze all incoming data without needing to discard any for efficiency, a significant improvement over previous methods.
“We’re on the cusp of a fundamentally different way of analyzing streaming astronomical data and the kinds of things we’ll be able to discover with it will be quite amazing,” said Siemion.
This technological breakthrough is not limited to astronomy. The SETI Institute’s new real-time data analysis pipeline, powered by Nvidia, can be applied to other industries requiring accelerated computing and AI.
About the Author
You May Also Like