http://arxiv.org/abs/2111.14546
The coalescences of massive black hole binaries (MBHBs) are one of the main targets of space-based gravitational wave observatories. Such gravitational wave sources are expected to be accompanied by electromagnetic emission. Low latency time of gravitational wave searches and accurate sky localization are keys in triggering successful follow-up observations on the electromagnetic counterparts. Here we present a deep learning method for the first time to rapidly search for MBHB signals in the strain data. Our model is capable to process 1-year of data in just several seconds, identifying all MBHB coalescences with no false alarms. We test the performance of our model on the simulated data from the LISA data challenge. We demonstrate that the model shows a robust resistance for a wide range of generalization for MBHB signals. This method is supposed to be an effective approach, which combined the advances of artificial intelligence to open a new pathway for space-based gravitational wave observations.
W. Ruan, H. Wang, C. Liu, et. al.
Tue, 30 Nov 21
102/105
Comments: 8 pages, 5 figures