Seminars and Journal Clubs

GWSkyNet: a machine learning tool for multi-messenger astronomy

by Miriam Cabero (University of British Columbia)


The rapid release of accurate sky localization for gravitational-wave candidates is crucial for multi-messenger observations. Advanced LIGO and Advanced Virgo release 3D sky localization maps in GraceDB within minutes of detection. Occasionally, gravitational-wave candidates may originate from instrumental artefacts, and astronomers must decide which candidates to follow up based on publicly available information. As a result, valuable and competitive telescope resources are often spent on non-astrophysical sources. GWSkyNet, a machine learning real/noise classifier for astronomers, will help prioritize promising gravitational-wave candidates to ensure successful multi-messenger followup campaigns.