Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-Encoders

Abstract

Denoising of time domain data is a crucial task for many applications such as communication, translation, virtual assistants etc. For this task, a combination of a recurrent neural net (RNNs) with a Denoising Auto-Encoder (DAEs) has shown promising results. However, this combined model is challenged when operating with low signal-to-noise ratio (SNR) data embedded in non-Gaussian and non-stationary noise. To address this issue, we design a novel model, referred to as 'Enhanced Deep Recurrent Denoising Auto-Encoder' (EDRDAE), that incorporates a signal amplifier layer, and applies curriculum learning by first denoising high SNR signals, before gradually decreasing the SNR until the signals become noise dominated. We showcase the performance of EDRDAE using time-series data that describes gravitational waves embedded in very noisy backgrounds. In addition, we show that EDRDAE can accurately denoise signals whose topology is significantly more complex than those used for training, demonstrating that our model generalizes to new classes of gravitational waves that are beyond the scope of established denoising algorithms.

arXiv comment5 pages, 11 figures and 3 tables, accepted to ICASSP 2019

References in corpus (7)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• GW151226: Observation of Gravitational Waves from a 22-Solar-Mass Binary Black Hole Coalescence
• The PyCBC search for gravitational waves from compact binary coalescence
• An improved effective-one-body model of spinning, nonprecessing binary black holes for the era of gravitational-wave astrophysics with advanced detectors
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• Implementing a search for aligned-spin neutron star -- black hole systems with advanced ground based gravitational wave detectors
• Complete waveform model for compact binaries on eccentric orbits

Cited by in corpus (15)

• The Science of the Einstein Telescope
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
• Detecting Gravitational-waves from Extreme Mass Ratio Inspirals using Convolutional Neural Networks
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• A review of unsupervised learning in astronomy
• Space-based gravitational wave signal detection and extraction with deep neural network
• Inference-optimized AI and high performance computing for gravitational wave detection at scale
• Deep Learning for Cardiologist-level Myocardial Infarction Detection in Electrocardiograms
• Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
• SLICK: Strong Lensing Identification of Candidates Kindred in gravitational wave data
• De-noising of galaxy optical spectra with autoencoders
• Mass and tidal parameter extraction from gravitational waves of binary neutron stars mergers using deep learning
• Data-driven detector signal characterization with constrained bottleneck autoencoders