© W. Scheible - MPI for Intelligent Systems
16. December 2021
New publi­ca­tion by Maxim­il­ian Dax

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!