Data-driven detection of multi-messenger transients

Abstract

The primary challenge in the study of explosive astrophysical transients is their detection and characterisation using multiple messengers. For this purpose, we have developed a new data-driven discovery framework, based on deep learning. We demonstrate its use for searches involving neutrinos, optical supernovae, and gamma rays. We show that we can match or substantially improve upon the performance of state-of-the-art techniques, while significantly minimising the dependence on modelling and on instrument characterisation. Particularly, our approach is intended for near- and real-time analyses, which are essential for effective follow-up of detections. Our algorithm is designed to combine a range of instruments and types of input data, representing different messengers, physical regimes, and temporal scales. The methodology is optimised for agnostic searches of unexpected phenomena, and has the potential to substantially enhance their discovery prospects.

16 pages

References in corpus (9)

• Gravitational Waves and Gamma-rays from a Binary Neutron Star Merger: GW170817 and GRB 170817A
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• All-sky search for time-integrated neutrino emission from astrophysical sources with 7 years of IceCube data
• Teraelectronvolt emission from the $\gamma$-ray burst GRB 190114C
• A very-high-energy component deep in the Gamma-ray Burst afterglow
• Low-Luminosity Gamma-Ray Bursts as a Distinct GRB Population:A Firmer Case from Multiple Criteria Constraints
• GammaLib and ctools: A software framework for the analysis of astronomical gamma-ray data
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Constraining high-energy neutrino emission from choked jets in stripped-envelope supernovae