WIREDGOV

A trio of students from the University of Glasgow funded by STFC have developed a sophisticated artificial intelligence which could underpin the next phase of gravitational wave astronomy.

In a new paper published yesterday the researchers discuss how they used artificial intelligence tools to train an AI ‘brain’ to search for gravitational wave signals.

Gravitational waves, ripples in space-time caused by massive astronomical events, were first hypothesised by Albert Einstein in 1915. It took another century until September 2015 before the Laser Interferometry Gravitational-Wave Observatory (LIGO) detectors in the United States first picked up the very faint signals from the collision of binary black holes. Since that historic first detection the Advanced LIGO and European VIRGO detectors have picked up numerous signals from other binary black holes and one from the collision of binary neutron stars.

Currently, gravitational wave signals are picked from the background noise of the detectors using a technique known as matched filtering, which measures the outputs from the detectors against a bank of template waveforms. Signals which match the shape of a template waveform are then examined more closely to determine whether they represent genuine gravitational wave detection.

However, the process requires a great deal of computing power.

University of Glasgow Physics and Astronomy postgraduate students Hunter Gabbard and Fergus Hayes and undergraduate Michael Williams decided to investigate whether deep learning, a form of artificial intelligence, could help make the process of detection more computationally efficient.

Under the direction of University of Glasgow astrophysicist Dr Christopher Messenger, they used a process known as supervised deep learning to build an artificial intelligence capable of correctly picking out gravitational wave signals buried in noise from thousands of simulated datasets which they created.

In this research paper the team concentrated specifically on binary black hole detections but looking at potential next steps they think the process could easily be applied to other types of gravitational wave signals and they are keen to continue their research.

The researchers’ paper, titled ‘Matching matched filtering with deep networks for gravitational-wave astronomy’, is published in Physical Review Letters and is available online.

Learn more about the research: University of Glasgow - Machine Learning Could Help Search for Gravitational Waves.

Jake Gilmore
STFC Media Manager
M: 07970 994586

LIGO

It is funded by the NSF, and operated by Caltech and MIT, which conceived and built the project. Financial support for the Advanced LIGO project was led by NSF with Germany (Max Planck Society), the U.K. (Science and Technology Facilities Council) and Australia (Australian Research Council) making significant commitments and contributions to the project. More than 1,200 scientists from around the world participate in the effort through the LIGO Scientific Collaboration, which includes the GEO Collaboration. Additional partners are listed online.

Advanced LIGO
It is a second generation gravitational-wave detector consisting of two identical interferometers located in Hanford, WA and Livingston, LA. It uses precision laser interferometry similar to Advanced Virgo to detect gravitational waves. Beginning operating in September 2015, Advanced LIGO has conducted two observing runs. The second ‘O2’ observing run began on Nov. 30, 2016 and ended on Aug. 25, 2017. LIGO multimedia.

LIGO consists of two L-shaped interferometers, one in Hanford, Washington, and one in Livingston, Louisiana. Each arm of each L is 2½ miles (4 km) long. Lasers look for changes in each arm's length as small as a millionth the diameter of a proton. Passing gravitational waves might distort space-time by that much.

The search for Gravitational Waves

A short film where UK collaborators discuss the search for gravitational waves.