Identifying extra high frequency gravitational waves generated from oscillons with cuspy potentials using deep neural networks

View the article online for updates and enhancements. This content was downloaded from IP address 218.70.255.146 on 18/04/2019 at 03:20 New J. Phys. 21 (2019) 043005 https://doi.org/10.1088/1367-2630/ab1310 PAPER Identifying extra high frequency gravitational waves generated from oscillons with cuspy potentials using deep neural networks Li-Li Wang1, Jin Li1,4 , Nan Yang2 and Xin Li3 1 Department of Physics, Chongqing University, Chongqing 401331, Peopleʼs Republic of China 2 Department of Electronical Information Science and Technology, Xingtai University, Xingtai 054001, Peopleʼs Republic of China 3 Department of Physics, Chongqing University, Chongqing 401331, Peopleʼs Republic of China 4 Author to whom any correspondence should be addressed. E-mail: 20152702016@cqu.edu.cn, cqujinli1983@cqu.edu.cn, cqunanyang@hotmail.com and lixin1981@cqu.edu.cn Keywords: extra high frequency gravitational waves, deep neural networks, signal classification, parameters estimation Abstract During oscillations of cosmology inflation around the minimum of a cuspy potential after inflation, the existence of extra high frequency gravitational waves (HFGWs) (∼GHz) has been proven effectively recently. Based on the electromagnetic resonance system for detecting such extra HFGWs, we adopt a new data processing scheme to identify the corresponding GW signal, which is the transverse perturbative photon fluxes (PPF). In order to overcome the problems of low efficiency and high interference in traditional data processing methods, we adopt deep learning to extract PPF and make some source parameters estimation. Deep learning is able to provide an effective method to realize classification and prediction tasks. Meanwhile, we also adopt anti-overfitting technique and make adjustment of some hyperparameters in the course of study, which improve the performance of classifier and predictor to a certain extent. Here the convolutional neural network (CNN) is used to implement deep learning process concretely. In this case, we investigate the classification accuracy varying with the ratio between the number of positive and negative samples. When such ratio exceeds to 0.11, the accuracy could reach up to 100%. Besides, we also investigate the classification accuracy with different amplitude of extra HFGWs. As a predictor, the mean relative error of parameters estimation decreases when the amplitude of extra HFGWs increases. Especially, when amplitude h(t) is in 10−31–10−30 the mean relative error reaches around 0.014. On the contrary, the mean relative error increases with frequency increasing in 108–1011 Hz. At the optimal resonance frequency 5×109 Hz, the mean relative error is 0.12. Then we also study the mean relative error varying with waist radius W0 of Gaussian beam, its optimal value is 0.138 when W0 is in (0.05 m, 0.1 m) approximately. Compared with classifiers and predictors using other machine learning algorithms, deep CNN for our datasets has higher accuracy and lower error.

1. Introduction GWas one ofthepredictions ofgeneral relativity,hasbeen discussedintensivelyinastronomyandtheoretical physics.CurrentlyseveralGWsignalsemitted fromcoalescenceofbinaryblackholes andbinaryneutronstars wereverifiedas reality,which areallcontributedto aLIGO’s frequencyband (101–103 Hz) [1–7]. Except those sources, GWcouldalso arise from manyothersources,including corecollapsesupernovae[8],rotating neutron stars [9], coalescing stellar binaries [10–14],coalescing massive blackholebinaries[15–19] and magnetars[20, 21], which are inotherfrequency regions. ThereforeGWdetectors indifferentfrequencybands aredesignedand will beinoperationsuccessionally.For instance,thereare pulsartiming arrays(10−9–10−7 Hz) [22–26], space-based interferometers such as eLISA (10−4–100 Hz) [27].Inrecentyears,ithas beenindicated that inflatonoscillations around the minimum ofacuspypotentialafter inflation [28] andparametricresonance offfieldwith othermatter fieldsinpreheating orat theend ofinflation[29] couldproduce extraHFGWsat108–1011 Hzandwith dimensionless amplitudeofGWh∼10−36–10−30. Thesource ofextraHFGWs (i.e.inflatonoscillations around OPEN ACCESS RECEIVED 2 November 2018 REVISED 3 March 2019 ACCEPTED FOR PUBLICATION 25 March 2019 PUBLISHED 8 April 2019 Original content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. © 2019 The Author(s). Published by IOP Publishing Ltd on behalf of the Institute of Physics and Deutsche Physikalische Gesellschaft theminimumofacuspypotentialafterinflation) isourstudyobject.AnEM resonancesystem fordetecting extra HFGWsregardedasa supplementofcurrent GWprojects had be

…(Full text truncated)…