Self-supervised reconstruction of transients in data from space-borne gravitational-wave detectors
Abstract
Space-based gravitational-wave (GW) data may contain transient signals whose waveform morphologies are not known in advance. Extracting these signals is important for characterizing new sources and mitigating instrumental anomalies. However, existing deep neural network (DNN)-based extraction approaches rely on clean training targets and waveform-class-specific examples, which may limit their applicability when the transient morphology is not specified in advance. This work develops a Noise2Noise (N2N)-inspired self-supervised framework that learns from noisy observations without clean training targets and requires no transient-specific waveform templates at inference. A single model trained on noisy massive black-hole binary (MBHB) observations provides high-overlap MBHB recovery and recovers the dominant morphologies of instrumental glitches and other GW transient signals such as cosmic string bursts in source-confused test data. Beyond waveform recovery, when independent information identifies a candidate transient as instrumental, its extracted waveform can be subtracted from the data without an anomaly-specific template. In a simulated continuous data stream, this procedure substantially suppresses the injected-anomaly power within the glitch-dominated frequency band. These results support the use of self-supervised extraction for initial waveform estimation of candidate transients with unknown morphologies, enabling subsequent characterization and, where appropriate, conditional subtraction of instrumental anomalies.
Related
- Clock-noise propagation and calibration for phase-locking configurations in space-based gravitational-wave detectors
- Mock Catalogs of Strongly Lensed Gravitational Waves via a Halo Model Approach with Space-borne Detectors
- GWTC-5.0: Methods for Identifying and Characterizing Gravitational-wave Transients
- Short Gravitational-Wave Transients as Probes of Cosmic Domain Walls
- The Wavelet Detection Filter: a real time unmodeled pipeline for gravitational wave transients, ranking coincidences with a graph neural network
BibTeX
@misc{xu2026selfsupervised,
title = {{Self-supervised reconstruction of transients in data from space-borne gravitational-wave detectors}},
author = {Yuxiang Xu and Minghui Du and Bo Liang and Zihao Xiao and Tianyu Zhao and Peng Xu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.05890},
eprint = {2609.05890},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.05890},
}
RIS
TY - UNPB
TI - Self-supervised reconstruction of transients in data from space-borne gravitational-wave detectors
AU - Yuxiang Xu
AU - Minghui Du
AU - Bo Liang
AU - Zihao Xiao
AU - Tianyu Zhao
AU - Peng Xu
PY - 2026
DA - 2026/09/05
PB - arXiv
DO - 10.48550/arxiv.2609.05890
UR - https://arxiv.org/abs/2609.05890
AB - Space-based gravitational-wave (GW) data may contain transient signals whose waveform morphologies are not known in advance. Extracting these signals is important for characterizing new sources and mitigating instrumental anomalies. However, existing deep neural network (DNN)-based extraction approaches rely on clean training targets and waveform-class-specific examples, which may limit their applicability when the transient morphology is not specified in advance. This work develops a Noise2Noise (N2N)-inspired self-supervised framework that learns from noisy observations without clean training targets and requires no transient-specific waveform templates at inference. A single model trained on noisy massive black-hole binary (MBHB) observations provides high-overlap MBHB recovery and recovers the dominant morphologies of instrumental glitches and other GW transient signals such as cosmic string bursts in source-confused test data. Beyond waveform recovery, when independent information identifies a candidate transient as instrumental, its extracted waveform can be subtracted from the data without an anomaly-specific template. In a simulated continuous data stream, this procedure substantially suppresses the injected-anomaly power within the glitch-dominated frequency band. These results support the use of self-supervised extraction for initial waveform estimation of candidate transients with unknown morphologies, enabling subsequent characterization and, where appropriate, conditional subtraction of instrumental anomalies.
ER -