Alternative neural-network follow-up for all-sky FrequencyHough in continuous gravitational-wave searches
Abstract
Continuous gravitational waves are long-lived signals emitted by spinning neutron stars (NSs) or boson clouds around black holes. While the Milky Way is expected to host O(108−109) NSs, only O(103) are currently identified through electromagnetic observations. This large observational gap motivates searches based on alternative messengers. In particular, all-sky searches for continuous gravitational waves (GWs) offer a unique opportunity to detect NSs that are electromagnetically silent or otherwise undiscovered. By exploring a broad region of parameter space without any a priori source information, these searches can probe the vast hidden NS population of our Galaxy. In this work, we present a novel way to include a Neural Network (NN) classifier into an all-sky search strategy for isolated NSs. Starting from candidates produced by the FrequencyHough pipeline running on data from ground-based detectors such as LIGO and Virgo, the proposed method improves sensitivity without increasing computational cost and can be parallelized across multiple detectors to enhance detection probability and reduce false alarms. We analyze data from the third observing run (O3) --- April 1, 2019 to March 27, 2020 --- and focus on the frequency range [129, 229] Hz and spin-down interval [−2.5·10−9, 1.0·10−9] Hz/s. The model is trained on noise constructed to be statistically consistent with real O3 data and tested on real O3 data. Results show robust performance in distinguishing signal from noise, even at low strain, and successful identification of hardware injections outside the training spin-down range.
Related
- Neural Network Guided Parameter Space Constraints for Gravitational Wave Searches from Binary Black Holes
- LUMA: A CNN for Strong Gravitational Lens Searches in Astronomical Imaging
- A semicoherent resampling method for long-transient gravitational wave searches with applications to subsolar-mass primordial black-hole binaries
- MADGRAV: a multilevel anomaly-detection pipeline for gravitational-wave searches applied to LIGO data
- Optimizing Prompt Radio Counterpart Searches for Gravitational-Wave Events with the Deep Synoptic Array
BibTeX
@misc{cesare2026alternative,
title = {{Alternative neural-network follow-up for all-sky FrequencyHough in continuous gravitational-wave searches}},
author = {Martina Di Cesare and Pia Astone and Rosario De Rosa and David Keitel and Cristiano Palomba and Marco Serra},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.06211},
eprint = {2609.06211},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.06211},
}
RIS
TY - UNPB
TI - Alternative neural-network follow-up for all-sky FrequencyHough in continuous gravitational-wave searches
AU - Martina Di Cesare
AU - Pia Astone
AU - Rosario De Rosa
AU - David Keitel
AU - Cristiano Palomba
AU - Marco Serra
PY - 2026
DA - 2026/09/05
PB - arXiv
DO - 10.48550/arxiv.2609.06211
UR - https://arxiv.org/abs/2609.06211
AB - Continuous gravitational waves are long-lived signals emitted by spinning neutron stars (NSs) or boson clouds around black holes. While the Milky Way is expected to host O(10^8−10^9) NSs, only O(10^3) are currently identified through electromagnetic observations. This large observational gap motivates searches based on alternative messengers. In particular, all-sky searches for continuous gravitational waves (GWs) offer a unique opportunity to detect NSs that are electromagnetically silent or otherwise undiscovered. By exploring a broad region of parameter space without any a priori source information, these searches can probe the vast hidden NS population of our Galaxy. In this work, we present a novel way to include a Neural Network (NN) classifier into an all-sky search strategy for isolated NSs. Starting from candidates produced by the FrequencyHough pipeline running on data from ground-based detectors such as LIGO and Virgo, the proposed method improves sensitivity without increasing computational cost and can be parallelized across multiple detectors to enhance detection probability and reduce false alarms. We analyze data from the third observing run (O3) --- April 1, 2019 to March 27, 2020 --- and focus on the frequency range [129, 229] Hz and spin-down interval [−2.5·10^−9, 1.0·10^−9] Hz/s. The model is trained on noise constructed to be statistically consistent with real O3 data and tested on real O3 data. Results show robust performance in distinguishing signal from noise, even at low strain, and successful identification of hardware injections outside the training spin-down range.
ER -