AI Finds Merging Neutron Stars In Real Time

Max Planck Society

Neural network registers gravitational wave signal from neutron star collisions early on and shows telescopes where to find the subsequent kilonova explosion in the sky

When two neutron stars merge, gravitational waves propagate into space. Shortly after this disturbance of space-time, a glistening explosion follows - a kilonova, in which, as in a cosmic goldsmith's, heavy atoms arise that stars can not form. Kilonovae express themselves in many different facets, which provide astronomers with an excellent opportunity to study gravity and matter under extreme conditions. But they are rare and short-lived. To give gravitational wave detectors and telescopes a chance of finding such signals, speed and precision are required. An interdisciplinary research team is using machine learning to analyze data from gravitational wave detectors at high speed and find a neutron star collision before the subsequent explosion is in full swing.

The satellite orbits the Earth in space, while glowing green gravitational waves can be seen in the background, spreading through the cosmos.

When two neutron stars merge far from Earth, they emit electromagnetic signals and gravitational waves, which astronomers measure with suitable instruments on and around Earth.

© MPI for Intelligent Systems / A. Posada

When two neutron stars merge far from Earth, they emit electromagnetic signals and gravitational waves, which astronomers measure with suitable instruments on and around Earth.
© MPI for Intelligent Systems / A. Posada

Neutron stars are exotic and extremely compact stellar remnants. Only black holes have a higher mass density. While black holes colliding with each other can only be detected by the emitted gravitational waves, neutron star mergers briefly emit a flash of light across the electromagnetic spectrum shortly after the gravitational wave signal. Such kilonovae occur millions of light-years from Earth. The goal is to locate them before telescopes can see them: their gravitational wave signal must be found as quickly as possible in the data stream of corresponding instruments. This is a major challenge for tranditional data analysis methods. These signals correspond to minutes of data from current detectors and potentially hours to days of data from future observatories. Analyzing such massive data sets is computationally expensive and time-consuming.

Two glowing blue spheres create ripples in the cosmos.

Artist's impression of two merging neutron stars and the gravitational waves they produce.

© MPI-IS / A. Posada

Artist's impression of two merging neutron stars and the gravitational waves they produce.
© MPI-IS / A. Posada

An international team of scientists has developed a machine learning algorithm, called DINGO-BNS (Deep INference for Gravitational-wave Observations from Binary Neutron Stars) that saves valuable time in interpreting gravitational waves emitted by binary neutron star mergers. They trained a neural network to fully characterize systems of merging neutron stars in about a second, compared to about an hour for the fastest traditional methods. Their results are published today in Nature in the paper "Real-time inference for binary neutron star mergers using machine learning".

Why is real-time computation important?

Neutron star mergers emit visible light (in the subsequent kilonova explosion) and other electromagnetic radiation in addition to gravitational waves. "Rapid and accurate analysis of the gravitational-wave data is crucial to localize the source and point telescopes in the right direction as quickly as possible to observe all the accompanying signals," says Maximilian Dax, a PhD student in the Empirical Inference department at the Max Planck Institute for Intelligent Systems (MPI-IS) and first author of the paper.

The real-time method could set a new standard for data analysis of neutron star mergers, giving the broader astronomy community more time to point their telescopes toward the merging neutron stars as soon as the large detectors of the LIGO-Virgo-KAGRA (LVK) collaboration identify them.

"Current rapid analysis algorithms used by the LVK make approximations that sacrifice accuracy. Our new study addresses these shortcomings," says Jonathan Gair, a group leader in the Astrophysical and Cosmological Relativity department at the Max Planck Institute for Gravitational Physics in the Potsdam Science Park.

Indeed, the machine learning framework fully characterizes the neutron star merger (e.g., its masses, spins, and location) in just one second without making such approximations. This allows, among other things, to quickly determine the sky position 30% more precisely. Because it works so quickly and accurately, the neural network can provide critical information for joint observations of gravitational-wave detectors and other telescopes. It can help to search for the light and other electromagnetic signals produced by the merger and to make the best possible use of the expensive telescope observing time.

Catching a neutron star merger in the act

"Gravitational wave analysis is particularly challenging for binary neutron stars, so for DINGO-BNS, we had to develop various technical innovations. This includes for example a method for event-adaptive data compression," says Stephen Green, UKRI Future Leaders Fellow at the University of Nottingham. Bernhard Schölkopf, director of the Empirical Inference department at MPI-IS, adds: "Our study showcases the effectiveness of combining modern machine learning methods with physical domain knowledge."

DINGO-BNS could one day help to observe electromagnetic signals before and at the time of the collision of the two neutron stars. "Such early multi-messenger observations could provide new insights into the merger process and the subsequent kilonova, which are still mysterious," says Alessandra Buonanno, director of the Astrophysical and Cosmological Relativity department at the Max Planck Institute for Gravitational Physics.

/Public Release. This material from the originating organization/author(s) might be of the point-in-time nature, and edited for clarity, style and length. Mirage.News does not take institutional positions or sides, and all views, positions, and conclusions expressed herein are solely those of the author(s).View in full here.