Deep learning merger masses estimation from gravitational waves signals in the frequency domain

Marulanda, Juan Pablo; Santa, Camilo; Romano, Antonio Enea

doi:10.1016/j.physletb.2020.135790

Cited by 10 publications

(5 citation statements)

References 9 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

“…For example, the problem of noisy speech recognition has been addressed by various machine-learning strategies (see Zhang et al 2018 for a comprehensive review). Among a few examples in astrophysics, neural network applications have been useful in optical astronomy to correct atmospheric-turbulence-distorted images (Gómez et al 2019) and in variable stars classification (Jamal & Bloom 2020) and have even succeeded in recovering gravitational waves from structured-noisy temporal series (George & Huerta 2018;Marulanda et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Time-domain Deep-learning Filtering of Structured Atmospheric Noise for Ground-based Millimeter Astronomy

Alejandra¹,

Rodríguez‐Montoya²,

Sánchez-Argüelles³

et al. 2022

ApJS

View full text Add to dashboard Cite

The complex physics involved in atmospheric turbulence makes it very difficult for ground-based astronomy to build accurate scintillation models and develop efficient methodologies to remove this highly structured noise from valuable astronomical observations. We argue that a deep-learning approach can bring a significant advance to treat this problem because of deep neural networks’ inherent ability to abstract nonlinear patterns over a broad scale range. We propose an architecture composed of long short-term memory cells and an incremental training strategy inspired by transfer and curriculum learning. We develop a scintillation model and employ an empirical method to generate a vast catalog of atmospheric-noise realizations and train the network with representative data. We face two complexity axes: the signal-to-noise ratio (S/N) and the degree of structure in the noise. Hence, we train our recurrent network to recognize simulated astrophysical pointlike sources embedded in three structured-noise levels, with a raw-data S/N ranging from 3 to 0.1. We find that a slow and repetitive increase in complexity is crucial during training to obtain a robust and stable learning rate that can transfer information through different data contexts. We probe our recurrent model with synthetic observational data, designing alongside a calibration methodology for flux measurements. Furthermore, we implement traditional matched filtering (MF) to compare its performance with our neural network, finding that our final trained network can successfully clean structured noise and significantly enhance the S/N compared to raw data and in a more robust way than traditional MF.

show abstract

“…For example, the problem of noisy speech recognition has been addressed by various machine learning strategies (see Zhang et al (2018) for a comprehensive review). Among a few examples in astrophysics, neural network applications have been useful in optical astronomy to correct atmosphericturbulence distorted images (Gómez et al 2019), variable stars classification (Jamal & Bloom 2020), and have even succeeded in recovering gravitational waves from structured noisy temporal series (George & Huerta 2018;Marulanda et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Time-domain deep learning filtering of structured atmospheric noise for ground-based millimeter astronomy

Rocha-Solache,

Rodríguez-Montoya,

Sánchez-Argüelles

et al. 2022

Preprint

View full text Add to dashboard Cite

The complex physics involved in atmospheric turbulence makes it very difficult for ground-based astronomy to build accurate scintillation models and develop efficient methodologies to remove this highly structured noise from valuable astronomical observations. We argue that a Deep Learning approach can bring a significant advance to treat this problem because of deep neural networks' inherent ability to abstract non-linear patterns over a broad scale range. We propose an architecture composed of long-short term memory cells and an incremental training strategy inspired by transfer and curriculum learning. We develop a scintillation model and employ an empirical method to generate a vast catalog of atmospheric noise realizations and train the network with representative data. We face two complexity axes: the signal-to-noise ratio (SNR) and the degree of structure in the noise. Hence, we train our recurrent network to recognize simulated astrophysical point-like sources embedded in three structured noise levels, with a raw-data SNR ranging from 3 to 0.1. We find that a slow and repetitive increase in complexity is crucial during training to obtain a robust and stable learning rate that can transfer information through different data contexts. We probe our recurrent model with synthetic observational data, designing alongside a calibration methodology for flux measurements. Furthermore, we implement a traditional matched filtering (MF) to compare its performance with our neural network, finding that our final trained network can successfully clean structured noise and significantly enhance the SNR compared to raw data and in a more robust way than traditional MF.

show abstract

Deep learning merger masses estimation from gravitational waves signals in the frequency domain

Cited by 10 publications

References 9 publications

Gravitational-wave surrogate models powered by artificial neural networks

Gravitational-wave surrogate models powered by artificial neural networks

Time-domain Deep-learning Filtering of Structured Atmospheric Noise for Ground-based Millimeter Astronomy

Time-domain deep learning filtering of structured atmospheric noise for ground-based millimeter astronomy

Contact Info

Product

Resources

About