From one to many: A deep learning coincident gravitational-wave search

Gravitational waves from the coalescence of compact-binary sources are now routinely observed by Earth bound detectors. The most sensitive search algorithms convolve many different precalculated gravitational waveforms with detector data and look for coincident matches between Machine learning is being explored as an alternative approach to building a algorithm that has prospect reduce computational costs target more complex signals. In this work we construct two-detector binary black hole mergers using neural networks trained on nonspinning single detector. network applied both observatories independently check events in time two. This enables efficient analysis large quantities background time-shifting independent data. We find while retains 91.5% sensitivity matched filtering can achieve, number drops 83.9% two observatories. To enable signal consistency detectors, then set simple operate directly none these capable improving over applying individually detectors searching coincidences.