Autoencoder helps estimate black hole ringdown signals from noisy data
Parameter Estimation of Ringdown Quasinormal Modes with Autoencoder
Machine Learning
Summary
After two black holes merge, they produce a fading signal called ringdown that carries information about the new black hole. Extracting details from these signals is hard because multiple overlapping parts blend together and noise gets in the way. The authors developed a method using an autoencoder, a type of artificial intelligence, to separate and clean these parts, then estimate their properties reliably. Tests with simulated signals showed the method works well within familiar ranges and can recover many parameters, showing promise for future use with real data.
What this means in practice
- •For gravitational wave data analysts: Improve extraction of multiple overlapping ringdown wave components from noisy merger signals to better characterize remnant black holes.
- •For machine learning engineers in signal processing: Use physics-informed autoencoder designs to denoise and recover parameters in multi-component astrophysical waveforms.
Authors
Momoka Iida, Hayato Motohashi, Hirotaka Takahashi
Abstract
Ringdown gravitational waves from binary black hole mergers can be modeled as superpositions of quasinormal modes (QNMs), whose frequencies and excitation factors encode properties of the remnant Kerr black hole. Reliable extraction of multiple QNM components is challenging because of mode overlap and noise. We develop an autoencoder-based framework for multi-component QNM analysis, in which the latent space is trained to represent the physical parameters of individual modes, enabling waveform denoising and parameter estimation within a common framework. Using controlled model waveforms constructed as finite sums of Kerr QNMs with recently established high-precision frequencies and excitation factors, including their nontrivial spin dependence near resonant excitation, we assess the method across partitioned spin intervals. The model achieves good in-domain waveform reconstruction and parameter recovery for the two longest-lived components of eight-component input waveforms, while its performance degrades when the validation spins lie far outside the training range. In a selected spin interval, the framework also recovers the 32 parameters of an eight-component waveform with good overall agreement. These results demonstrate the feasibility of physics-informed autoencoder-based inference for a prescribed multi-component ringdown waveform family and motivate further tests with progressively more realistic signals.