Extraction of gravitational wave signals with optimized convolutional neural network

Gabbard et al. have demonstrated that convolutional neural networks can achieve the sensitivity of matched filtering in the recognization of the gravitational-wave signals with high efficiency [Phys. Rev. Lett. 120, 141103 (2018)]. In this work we show that their model can be optimized for better accuracy. The convolutional neural networks typically have alternating convolutional layers and max pooling layers, followed by a small number of fully connected layers. We increase the stride in the max pooling layer by 1, followed by a dropout layer to alleviate overfitting in the original model. We find that these optimizations can effectively increase the area under the receiver operating characteristic curve for various tests on the same dataset.

[1]  Alexei A. Efros,et al.  Colorful Image Colorization , 2016, ECCV.

[2]  E. Huerta,et al.  Classification and unsupervised clustering of LIGO data with Deep Transfer Learning , 2018 .

[3]  B. A. Boom,et al.  GW170814: A Three-Detector Observation of Gravitational Waves from a Binary Black Hole Coalescence. , 2017, Physical review letters.

[4]  Xin Li,et al.  Applying deep neural networks to the detection and space parameter estimation of compact binary coalescence with a network of gravitational wave detectors , 2018, Science China Physics, Mechanics & Astronomy.

[5]  A. Katsaggelos,et al.  Classifying the unknown: Discovering novel gravitational-wave detector glitches using similarity learning , 2019, Physical Review D.

[6]  Daniel George,et al.  Glitch Classification and Clustering for LIGO with Deep Transfer Learning , 2017, ArXiv.

[7]  B. A. Boom,et al.  Prospects for observing and localizing gravitational-wave transients with Advanced LIGO, Advanced Virgo and KAGRA , 2013, Living Reviews in Relativity.

[8]  Bing Zhang.  The delay time of gravitational wave — gamma-ray burst associations , 2019, Frontiers of Physics.

[9]  Daniel George,et al.  Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-encoders , 2017, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[11]  John J. Oh,et al.  Application of machine learning algorithms to the study of noise artifacts in gravitational-wave data , 2013, 1303.6984.

[12]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[13]  Daniela M. Witten,et al.  An Introduction to Statistical Learning: with Applications in R , 2013 .

[14]  Hunter Gabbard,et al.  Matching Matched Filtering with Deep Networks for Gravitational-Wave Astronomy. , 2017, Physical review letters.

[15]  Michael Purrer,et al.  Frequency-domain gravitational waves from nonprecessing black-hole binaries. I. New numerical waveforms and anatomy of the signal , 2015, 1508.07250.

[16]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[17]  Von Welch,et al.  Reproducing GW150914: The First Observation of Gravitational Waves From a Binary Black Hole Merger , 2016, Computing in Science & Engineering.

[18]  B. Schölkopf,et al.  Convolutional neural networks: a magic bullet for gravitational-wave detection? , 2019, Physical Review D.

[19]  Timothy Dozat,et al.  Incorporating Nesterov Momentum into Adam , 2016 .

[20]  Henggui Zhang,et al.  Computational Cardiac Modeling Reveals Mechanisms of Ventricular Arrhythmogenesis in Long QT Syndrome Type 8: CACNA1C R858H Mutation Linked to Ventricular Fibrillation , 2017, Front. Physiol..

[21]  Igor Kononenko,et al.  Machine learning for medical diagnosis: history, state of the art and perspective , 2001, Artif. Intell. Medicine.

[22]  B. P. Abbott,et al.  Erratum: Binary Black Hole Mergers in the First Advanced LIGO Observing Run [Phys. Rev. X 6 , 041015 (2016)] , 2018, Physical Review X.

[23]  B. A. Boom,et al.  GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral. , 2017, Physical review letters.

[24]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[25]  Michael Purrer,et al.  Frequency-domain gravitational waves from nonprecessing black-hole binaries. II. A phenomenological model for the advanced detector era , 2015, 1508.07253.

[26]  Kai Staats,et al.  Finding the Origin of Noise Transients in LIGO Data with Machine Learning , 2018, Communications in Computational Physics.

[27]  Antonio Marquina,et al.  Classification of gravitational-wave glitches via dictionary learning , 2018, Classical and Quantum Gravity.

[28]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[29]  B. A. Boom,et al.  GW170104: Observation of a 50-Solar-Mass Binary Black Hole Coalescence at Redshift 0.2. , 2017, Physical review letters.

[30]  N. M. Brown,et al.  Prospects for Observing and Localizing Gravitational-Wave Transients with Advanced LIGO and Advanced Virgo , 2013, Living Reviews in Relativity.

[31]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[32]  Daniel George,et al.  Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation with Advanced LIGO Data , 2017, ArXiv.

[33]  B. A. Boom,et al.  GW170608: Observation of a 19 Solar-mass Binary Black Hole Coalescence , 2017, 1711.05578.

[34]  B. A. Boom,et al.  Binary Black Hole Mergers in the First Advanced LIGO Observing Run , 2016, 1606.04856.

[35]  G. González,et al.  Gravitational wave astronomy , 2013, Frontiers of Physics.

[36]  Daniel George,et al.  Deep Neural Networks to Enable Real-time Multimessenger Astrophysics , 2016, ArXiv.

[37]  D Huet,et al.  GW151226: Observation of Gravitational Waves from a 22-Solar-Mass Binary Black Hole Coalescence , 2016 .

[38]  Armand Joulin,et al.  Deep Fragment Embeddings for Bidirectional Image Sentence Mapping , 2014, NIPS.