Convolutional neural network search for long-duration transient gravitational waves from glitching pulsars

Understand

Machine learning can be a powerful tool to discover new signal types in astronomical data.

• We here apply it to search for long-duration transient gravitational waves triggered by pulsar glitches, which could yield physical insight into the mostly unknown depths of the pulsar.
• Current methods to search for such signals rely on matched filtering and a brute-force grid search over possible signal durations, which is sensitive but can become very computationally expensive.
• We develop a method to search for post-glitch signals on combining matched filtering with convolutional neural networks, which reaches similar sensitivities to the standard method at false-alarm probabilities relevant for practical searches, while being significantly faster.