aiqbench analysis
This study benchmarks five neural network architectures for denoising gravitational-wave signals, demonstrating that aligning network structure with the spectral anatomy of coalescence events yields superior fidelity and efficiency. The proposed Multi-Scale Frequency-Aware architecture successfully generalizes from simulated training to real LIGO-Virgo-KAGRA data without retraining, establishing a reproducible benchmark for future astrophysical analysis.
Survey of Novel Deep Learning Architectures for Denoising Gravitational-wave Signals
arXiv:2609.13272v1 Announce Type: cross Abstract: Gravitational-wave denoising must handle the full diversity of spinning, precessing binaries, since the recovered waveform underpins parameter estimation, tests of general relativity, and population studies. Matched filtering achieves this at a cost that becomes prohibitive as next-generation detectors push event rates higher; deep learning offers real-time reconstruction, but current methods are developed on narrow parameter spaces, precluding principled comparison and reliable deployment. We present the first controlled comparison of five neural-network architectures for gravitational-wave denoising, trained identically across the full astrophysically-motivated spinning binary-black-hole parameter space. A unifying principle emerges: matching network structure to the spectral anatomy of a coalescence -- inspiral, merger, ringdown -- outperforms brute-force model scaling. Our Multi-Scale Frequency-Aware architecture embodies this via dedicated parallel branches per frequency regime, achieving the best fidelity while using fewer parameters than larger models. It generalizes from simulated training to real LIGO-Virgo-KAGRA data without retraining, recovering merger morphology across confirmed events spanning three observing runs and both detectors, despite training on a single detector's simulated noise. We construct population-level uncertainty bands from denoising residuals, validate their calibration, and stress-test the framework on extended mass ratios and a spin population resembling hierarchical-merger remnants. Applied to real noise with no known signal, the network suppresses its output almost everywhere, with rare exceptions traced to noise transients rather than a general weakness -- indicating the statistic discriminates signal from noise and motivating a future detection study. Released weights give a deployable, reproducible benchmark for future extensions.
Abstract:Gravitational-wave denoising must handle the full diversity of spinning, precessing binaries, since the recovered waveform underpins parameter estimation, tests of general relativity, and population studies. Matched filtering achieves this at a cost that becomes prohibitive as next-generation detectors push event rates higher; deep learning offers real-time reconstruction, but current methods are developed on narrow parameter spaces, precluding principled comparison and reliable deployment. We present the first controlled comparison of five neural-network architectures for gravitational-wave denoising, trained identically across the full astrophysically-motivated spinning binary-black-hole parameter space. A unifying principle emerges: matching network structure to the spectral anatomy of a coalescence -- inspiral, merger, ringdown -- outperforms brute-force model scaling. Our Multi-Scale Frequency-Aware architecture embodies this via dedicated parallel branches per frequency regime, achieving the best fidelity while using fewer parameters than larger models. It generalizes from simulated training to real LIGO-Virgo-KAGRA data without retraining, recovering merger morphology across confirmed events spanning three observing runs and both detectors, despite training on a single detector's simulated noise. We construct population-level uncertainty bands from denoising residuals, validate their calibration, and stress-test the framework on extended mass ratios and a spin population resembling hierarchical-merger remnants. Applied to real noise with no known signal, the network suppresses its output almost everywhere, with rare exceptions traced to noise transients rather than a general weakness -- indicating the statistic discriminates signal from noise and motivating a future detection study. Released weights give a deployable, reproducible benchmark for future extensions.
General Relativity and Quantum Cosmology (gr-qc); High Energy Astrophysical Phenomena (astro-ph.HE); Instrumentation and Methods for Astrophysics (astro-ph.IM); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
arXiv:2609.13272 [gr-qc]
(or arXiv:2609.13272v1 [gr-qc] for this version)
https://doi.org/10.48550/arXiv.2609.13272 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 281 words
Related coverage
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
News
Quantum Computing Report · Jun 7, 2026
Binary Black Hole Parameter Estimation with Hybrid CNN-Transformer Neural Networks
arXiv · Jun 15, 2026
DREMnet: An Interpretable Denoising Framework for Semi-Airborne Transient Electromagnetic Signal
arXiv · Jul 23, 2026