Neural Network Identifies Gravitational Wave Events in Lower Mass Gap

This paper introduces GWSkyNet-MassGap, a neural network model designed to rapidly identify candidate gravitational-wave events with components in the lower mass gap. The model simultaneously predicts the probability that a candidate merger has a component in the lower mass gap ($P_{\mathrm{MassGap}}$) and the probability that it involves a neutron star ($P_{\mathrm{NS}}$). The ability to quickly distinguish these events is crucial for triggering follow-up electromagnetic observations, which can provide valuable insights into the nature of compact objects and the physics governing the boundary between neutron stars and black holes.

The model's performance on data from the first part of LVK's fourth observing run (O4a) is promising, with a mean prediction error of 9% for $P_{\mathrm{MassGap}}$ and 6% for $P_{\mathrm{NS}}$. However, the model's accuracy decreases for lower-mass systems, highlighting the need for further refinement. Future development could focus on improving the model's ability to predict the source chirp mass, which would enhance its overall performance and utility.

Overall, GWSkyNet-MassGap represents a significant step towards using AI to accelerate the analysis of gravitational wave data and improve our understanding of the universe.

_Context: This intelligence report was compiled by the DailyOrbitalWire Strategy Engine. Verified for Art. 50 Compliance._