Paper by Maximilian Dax published in the journal Physical Review Letters
Black holes are one of the greatest mysteries of our Universe. With a mass billions of times that of our sun, two black holes merging into each other create a gravitational wave in a massive explosion that propagates through the universe at the speed of light. Gigantic detectors in the USA (LIGO) and Italy (Virgo) measure this evidence of the phenomenon predicted by Albert Einstein in 1916: the change of space-time.
Since the first detection of gravitational waves scientists in LIGO and Virgo compare the data collected by the observatories against theoretical predictions to estimate the properties of the source. Currently, this procedure takes at least hours, often months.
An interdisciplinary team of researchers from the Max Planck Institute for Intelligent Systems in Tübingen and the Max Planck Institute for Gravitational Physics in Potsdam is using state-of-the-art machine learning methods to speed up this process. They developed an algorithm using a deep neural network, a complex computer code built from a sequence of simpler operations, inspired by the human brain. “Our method can make very accurate statements in a few seconds about how big and massive the two black holes were that generated the gravitational waves when they merged”, explains Maximilian Dax, first author of the study and doctoral researcher within the Hector Fellow Academy. Hector Fellow Bernhard Schölkopf mentors Maximilian Dax.
The neural network can also be used for merging neutron stars. During the merger, radiation in the electromagnetic spectrum is emitted, which is visible to conventional telescopes. The neural network allows telescopes to be pointed at the merging stars in seconds.
Congratulations to Maximilian Dax and Bernhard Schölkopf!