Time series analysis of gravitational wave signals using neural networks

Carrillo, M.; González, José Antonio García-Cruces; Gracia-Linares, Miguel; Guzmán, F. S.

doi:10.1088/1742-6596/654/1/012001

Cited by 7 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANNs are a versatile tool [50] and have recently been applied to solve reduced-order modeling problems across multiple disciplines using a nonintrusive framework [51][52][53][54][55]. The use of ANNs in GW astronomy is increasing [48,[56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72][73]. In particular, the authors of [74] used ANNs to model the greedy reduced basis coefficients for a frequency domain inspiral post-Newtonian waveforms in the context of massive binary black holes (BBHs) that the space-based GW observatory LISA [75] will be sensitive to.…”

Section: Introductionmentioning

confidence: 99%

Gravitational-wave surrogate models powered by artificial neural networks

Khan

Green

2021

Phys. Rev. D

View full text Add to dashboard Cite

Inferring the properties of black holes and neutron stars is a key science goal of gravitational-wave (GW) astronomy. To extract as much information as possible from GW observations, we must develop methods to reduce the cost of Bayesian inference. In this paper, we use artificial neural networks (ANNs) and the parallelization power of graphics processing units (GPUs) to improve the surrogate modeling method, which can produce accelerated versions of existing models. As a first application of our method, the artificial neural networks surrogate model (ANN-Sur), we build a time-domain surrogate model of the spinaligned binary black hole (BBH) waveform model SEOBNRv4. We achieve median mismatches of approximately 2e − 5 and mismatches no worse than approximately 2e − 3. For a typical BBH waveform generated from 12 Hz with a total mass of 60 M ⊙ , the original SEOBNRv4 model takes 1794 ms. Existing custom-made code optimizations (SEOBNRv4opt) reduced this to 83.7 ms, and the interpolation-based, frequency-domain surrogate SEOBNRv4ROM can generate this waveform in 3.5 ms. Our ANN-Sur model when run on a CPU takes 1.2 ms and when run on a graphics processing unit (GPU) takes just 0.5 ms. ANN-Sur can also generate large batches of waveforms simultaneously. We find that batches of up to 10 3 waveforms can be evaluated on a GPU in just 1.57 ms, corresponding to a time per waveform of 0.0016 ms. This method is a promising way to utilize the parallelization power of GPUs to drastically increase the computational efficiency of Bayesian parameter estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

Gravitational-wave surrogate models powered by artificial neural networks

Khan

Green

2021

Phys. Rev. D

View full text Add to dashboard Cite

show abstract

“…In this work we train artificial neural networks (ANNs), developed with the TensorFlow [49] library, to accurately and efficiently estimate the projection coefficients of a reduced basis. The use of ANNs in GW astronomy has increased recently [48,[50][51][52][53][54][55][56][57][58][59][60][61][62][63][64][65][66]68] and in particular [67] where the authors used ANNs to model the greedy reduced basis coefficients for a frequency domain inspiral post-Newtonian waveforms in the context of massive binary black holes (BBHs) that the space based GW observatory LISA [69] will be sensitive to. Here we look at the projection coefficients of an empirical interpolation basis for time domain waveforms.…”

Section: Introductionmentioning

confidence: 99%

Gravitational-wave surrogate models powered by artificial neural networks: The ANN-Sur for waveform generation

Khan,

Green

2020

Preprint

View full text Add to dashboard Cite

Inferring the properties of black holes and neutron stars is a key science goal of gravitational-wave (GW) astronomy. To extract as much information as possible from GW observations we must develop methods to reduce the cost of Bayesian inference. In this paper, we use artificial neural networks (ANNs) and the parallelisation power of graphics processing units (GPUs) to improve the surrogate modelling method, which can produce accelerated versions of existing models. As a first application of our method, ANN-Sur, we build a time-domain surrogate model of the spin-aligned binary black hole (BBH) waveform model SEOBNRv4. We achieve median mismatches of ∼ 2e−5 and mismatches no worse than ∼ 2e−3. For a typical BBH waveform generated from 12 Hz with a total mass of 60M the original SEOBNRv4 model takes 1812 ms. Existing bespoke code optimisations (SEOBNRv4opt) reduced this to 91.6 ms and the interpolation based, frequency-domain surrogate SEOBNRv4ROM can generate this waveform in 6.9 ms. Our ANN-Sur model, when run on a CPU takes 2.7 ms and just 0.4 ms when run on a GPU. ANN-Sur can also generate large batches of waveforms simultaneously. We find that batches of up to 10 4 waveforms can be evaluated on a GPU in just 163 ms, corresponding to a time per waveform of 0.016 ms. This method is a promising way to utilise the parallelisation power of GPUs to drastically increase the computational efficiency of Bayesian parameter estimation. 1 We were limited to batches O(10 4 ) due to GPU memory limitations.

show abstract

“…However, as more and more advanced detectors appear, it is important to reduce even further the computation time for these determinations (to achieve low latency and to produce alerts), especially in the current context of complementary observations, which uses several observation facilities located on the ground or in space. Thus, in recent years, new methods have been investigated to quickly characterize gravitational wave sources, which use the analysis of signal properties (assuming it has been filtered) and strategies to treat the problem in reverse, so starting from simulating the physical phenomena and then the signal to identify different types of signals observed [15]. The latter approach proved to be solved very efficiently by the use of machine learning techniques, more precisely by involving a neural network with simulated gravitational wave signals to recognize and characterize the observed gravitational waves.…”

Section: Introductionmentioning

confidence: 99%

“…Machine learning techniques such as artificial neural networks already have applications in various disciplines including gravitational wave astronomy for detecting and characterizing multiple signals of gravitational waves from black hole systems [16,15,17,18,19,20].…”

Section: Introductionmentioning

confidence: 99%

Characterization of Gravitational Waves Signals Using Neural Networks

Caramete,

Constantinescu,

Caramete

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

Time series analysis of gravitational wave signals using neural networks

Cited by 7 publications

References 8 publications

Gravitational-wave surrogate models powered by artificial neural networks

Gravitational-wave surrogate models powered by artificial neural networks

Gravitational-wave surrogate models powered by artificial neural networks: The ANN-Sur for waveform generation

Characterization of Gravitational Waves Signals Using Neural Networks

Contact Info

Product

Resources

About