Speaker
Description
The gravitational-wave detections reported by the LVK collaboration have so far been consistent with quasi-circular compact binary coalescences. Nevertheless, a small fraction of binaries may retain measurable orbital eccentricity in the LVK frequency band. Confident measurement of eccentricity would provide strong evidence for dynamically driven mergers; however, eccentric gravitational-waveform models are computationally expensive, and performing production-level inference on all detected signals is not an efficient use of resources. An intermediate step between detection and analysis, in which the signal is assessed for the potential presence of eccentricity, could provide quick recommendations for which signals should undergo full eccentric inference. We apply the wavelet scattering transform (WST) to a large set of synthetic waveforms in realistic noise and assess its discriminatory power using a shallow neural-network classifier. We find that the WST representation enables effective discrimination between eccentric and quasi-circular binaries and provides a compact multi-scale representation of GW signals. We also examine the ability of our classifier to distinguish eccentricity from spin-induced precession and find robust performance across a range of spin-precession magnitudes.