Deep learning for estimating parameters of gravitational waves

Abstract

In recent years, improvements in Deep Learning (DL) techniques towards Gravitational Wave (GW) astronomy have led to a significant rise in the development of various classification algorithms that have been successfully employed to extract GWs of binary blackhole merger events from noisy time-series data. However, the success of these models is constrained by the length of time-sample and the class of GW source: binary blackhole and neutron star binaries to some extent. In this work, we intended to advance the boundaries of DL techniques using Convolutional Neural Networks, to go beyond binary classification and predict the physical parameters of the events. We aim to propose an alternative method that can be employed for realtime detection and parameter prediction. The DL model we present has been trained on 12s of data to predict the GW source parameters if detected. During training, the maximum accuracy attained was 90.93%, with a validation accuracy of 89.97%.

Data quality up to the third observing run of advanced LIGO: Gravity Spy glitch classifications

“…Compiling a catalogue of classified glitches is useful for both identifying the physical causes of glitches (such that commissioning work could be done to remove them), and evaluating the impact of glitches on data analysis (creating new analyses to mitigate their effect where necessary). For example, Gravity Spy classifications have been used for: selecting example glitches to evaluate their impact on data analysis [48][49][50][51]; studying glitch morphology [52][53][54][55]; cross-referencing glitches with environmental-noise or auxiliary-channel measurements [20,[56][57][58], and as a component of training for gravitational-wave detection algorithms [59][60][61][62][63][64][65] or glitch-classification algorithms [32,[66][67][68][69]. Additionally, identification of new classes can indicate new sources of noise and suggest areas for further commissioning [42].…”

Multimodal Analysis of Gravitational Wave Signals and Gamma-Ray Bursts from Binary Neutron Star Mergers

“…The synergy between the information that only GWs can provide and the concomitant observations through other detectors of the EM and neutrino counterparts can strongly accelerate our knowledge of the Universe. It is clear that multi-messenger astronomy discloses the need for new paradigms for data analysis and introduces new challenges for real-time analysis, and there are many efforts ongoing to face them that involve the use of machine learning techniques (see, e.g., [3][4][5][6][7][8][9][10][11][12]). Multimodal machine learning MMML analysis is efficiently applied in many fields of data analysis for the more inclusive interpretation of events where several modalities are concurrent, such as in a video with audio; images with captions; or images, text, and sound [13].…”

Multimodal analysis of Gravitational Wave signals and Gamma-Ray Bursts from binary neutron star mergers

“…The synergy between the information that only GWs can provide and the concomitant observations through other detectors of the EM and neutrino counterparts can strongly accelerate our knowledge of the Universe. It is clear that multi-messenger astronomy discloses the need of new paradigms for data analysis and introduces new challenges for real-time analysis, and there are many efforts ongoing to face with them, which involve the use of machine learning techniques (see, e.g., [3][4][5][6][7][8][9][10][11][12]). Multimodal machine learning (MMML) analysis is efficiently applied in many fields of data analysis for the more inclusive interpretation of events where several modalities are concurrent, such as in a video with audio, or images with caption, or images, text and sound [13].…”