27 January 2023 in Physical Review D
We present the results of the first Machine Learning Gravitational-Wave Search Mock Data Challenge. For this challenge, participating groups had to identify gravitational-wave signals from binary black hole mergers of increasing complexity and duration embedded in progressively more realistic noise. The final of the 4 provided datasets contained real noise from the O3a observing run and signals up to a duration of 20 s with the inclusion of precession effects and higher order modes. We present the average sensitivity distance and run-time for the 6 entered algorithms derived from 1 month of test data unknown to the participants prior to submission. Of these, 4 are machine learning algorithms. We find that the best machine learning based algorithms are able to achieve up to 95% of the sensitive distance of matched-filtering based production analyses for simulated Gaussian noise at a false-alarm rate (FAR) of one per month. In contrast, for real noise, the leading machine learning search achieved 70%. For higher FARs the differences in sensitive distance shrink to the point where select machine learning submissions outperform traditional search algorithms at FARs per month on some datasets. Our results show that current machine learning search algorithms may already be sensitive enough in limited parameter regions to be useful for some production settings. To improve the state-of-the-art, machine learning algorithms need to reduce the false-alarm rates at which they are capable of detecting signals and extend their validity to regions of parameter space where modeled searches are computationally expensive to run. Based on our findings we compile a list of research areas that we believe are the most important to elevate machine learning searches to an invaluable tool in gravitational-wave signal detection.
17 January 2020 in Physical Review D
Inspirals of stellar-mass compact objects into supermassive black holes are known as extreme mass ratio inspirals. In the simplest approximation, the motion of the compact object is modeled as a geodesic in the space-time of the massive black hole with the orbit decaying due to radiated energy and angular momentum, thus yielding a highly regular inspiral. However, once the spin of the secondary compact body is taken into account, integrability is broken and prolonged resonances along with chaotic motion appear. We numerically integrate the motion of a spinning test body in the field of a nonspinning black hole and analyze it using various methods. We show for the first time that resonances and chaos can be found even for astrophysically relevant values of the spin of the test body. On the other hand, we devise a method to analyze the growth of the resonances, and we conclude that the prolonged resonances we observe are only caused by terms quadratic in spin and will generally stay very small in the small-mass-ratio limit. Last but not least, we compute gravitational waveforms by numerically solving the Teukolsky equations in the time-domain and establish that they carry information on the motion’s dynamics. In particular, we show that the time series of the gravitational wave strain can be used to discern regular from chaotic motion of the source.
8 February 2022 in Physical Review D
Compact binary systems emit gravitational radiation which is potentially detectable by current Earth bound detectors. Extracting these signals from the instruments’ background noise is a complex problem and the computational cost of most current searches depends on the complexity of the source model. Deep learning may be capable of finding signals where current algorithms hit computational limits. Here we restrict our analysis to signals from nonspinning binary black holes and systematically test different strategies by which training data is presented to the networks. To assess the impact of the training strategies, we reanalyze the first published networks and directly compare them to an equivalent matched-filter search. We find that the deep learning algorithms can generalize low signal-to-noise ratio (SNR) signals to high SNR ones but not vice versa. As such, it is not beneficial to provide high SNR signals during training, and fastest convergence is achieved when low SNR samples are provided early on. During testing we found that the networks are sometimes unable to recover any signals when a false alarm probability is required. We resolve this restriction by applying a modification we call unbounded Softmax replacement (USR) after training. With this alteration we find that the machine learning search retains of the sensitivity of the matched-filter search down to a false-alarm rate of 1 per month.
10 July 2024 in Physical Review D
Searching the data of gravitational-wave detectors for signals from compact binary mergers is a computationally demanding task. Recently, machine-learning algorithms have been proposed to address current and future challenges. However, the results of these publications often differ greatly due to differing choices in the evaluation procedure. The Machine Learning Gravitational-Wave Search Challenge was organized to resolve these issues and produce a unified framework for machine-learning search evaluation. Six teams submitted contributions, four of which are based on machine-learning methods, and two are state-of-the-art production analyses. This paper describes the submission from the team TPI FSU Jena and its updated variant. We also apply our algorithm to real O3b data and recover the relevant events of the GWTC-3 catalog. Published by the American Physical Society 2024
3 April 2025 in Physical Review D
20 February 2026 in Physical Review D