Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning

Soni, S.; Berry, C. P. L.; Coughlin, S. B.; Harandi, Mahboobeh; Jackson, Corey; Crowston, Kevin; Østerlund, Carsten; Patane, Oli; Katsaggelos, Aggelos K.; Trouille, Laura; Baranowski, V-G; Domainko, W.; Kamiński, K.; Rodríguez, Mauricio; Marciniak, U; Nauta, P; Niklasch, G; Rote, Roshni; Téglás, B; Unsworth, Charles P.; Zhang, C

doi:10.1088/1361-6382/ac1ccb

Cited by 64 publications

(87 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These classes are classified into different classes on unsupervised learning, whereas their characteristics are similar to Figure 3. A previous study 12 on supervised learning with the Gravity Spy labels indicated the existence of a subclass that might be in the "Scattered_Light" class. The unsupervised classification yielded the same results as in the previous study, indicating the existence of a subclass of the "Scattered_Light" class.…”

Section: Evaluation Of Our Architecturementioning

confidence: 99%

“…Classifying transient noise could provide us with one of the clues to explore its origins and to improve the performance of the detector. Among others, the Gravity Spy project 10,11,12,13 is one of such efforts to classify transient noise. The Gravity Spy project used the Omicron software 14 to identify the signal of transient noise observed in the time-series data.…”

mentioning

confidence: 99%

“…Unsupervised clustering applying transfer learning 17 showed a new class of transient noise in addition to the 22 classes of the Gravity Spy project. Moreover, the supervised classification using the latest observation O3 dataset presented a new class of transient noise 12 .…”

mentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Learning Architecture for Classifying the Transient Noise of Interferometric Gravitational-Wave Detectors

Sakai

Itoh

Jung

et al. 2021

Preprint

View full text Add to dashboard Cite

In the data of laser interferometric gravitational wave detectors, transient noise with non-stationary and non-Gaussian features occurs at a high rate. It often causes problems such as instability of the detector, hiding and/or imitating gravitational-wave signals. This transient noise has various characteristics in the time-frequency representation, which is considered to be associated with environmental and instrumental origins. Classification of transient noise can offer one of the clues for exploring its origin and improving the performance of the detector. One approach for the classification of these noises is supervised learning. However, generally, supervised learning requires annotation of the training data, and there are issues with ensuring objectivity in the classification and its corresponding new classes. On the contrary, unsupervised learning can reduce the annotation work for the training data and ensuring objectivity in the classification and its corresponding new classes. In this study, we propose an architecture for the classification of transient noise by using unsupervised learning, which combines a variational autoencoder and invariant information clustering. To evaluate the effectiveness of the proposed architecture, we used the dataset (time-frequency two-dimensional spectrogram images and labels) of the LIGO first observation run prepared by the Gravity Spy project. We obtain the consistency between the label annotated by Gravity spy project and the class provided by our proposed unsupervised learning architecture and provide the potential for the existence of the unrevealed classes.

show abstract

Section: Evaluation Of Our Architecturementioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Learning Architecture for Classifying the Transient Noise of Interferometric Gravitational-Wave Detectors

Sakai

Itoh

Jung

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This would be especially beneficial for searches that require low latency, such as the early warning of binary neutron star mergers (Baltus et al, 2021 ; Yu et al, 2021 ). Other successful usage of ML techniques in GW astronomy include the identification of various GW events (Bayley et al, 2020 ; Chan et al, 2020 ; Dreissigacker and Prix, 2020 ; Huerta et al, 2020 ; Krastev, 2020 ; Schäfer et al, 2020 ; Wong et al, 2020 ; Beheshtipour and Papa, 2021 ; Chang et al, 2021 ; Chatterjee et al, 2021 ; López et al, 2021 ; Marianer et al, 2021 ; Mishra et al, 2021 ; Saiz-Pérez et al, 2021 ; Wei and Huerta, 2021 ; Yan et al, 2021 ), source parameter estimations (Gabbard et al, 2019 ; Chatterjee et al, 2020 ; Chua and Vallisneri, 2020 ; Green et al, 2020 ; Talbot and Thrane, 2020 ; Álvares et al, 2021 ; D'Emilio et al, 2021 ; Krastev et al, 2021 ; Williams et al, 2021 ; Xia et al, 2021 ), and detector characterization (Biswas et al, 2020 ; Colgan et al, 2020 ; Cuoco et al, 2020 ; Essick et al, 2020 ; Torres-Forné et al, 2020 ; Mogushi, 2021 ; Sankarapandian and Kulis, 2021 ; Soni et al, 2021 ; Zhan et al, 2021 ). Besides GW astronomy, the usage of CNNs has led to breakthroughs in a variety of topics related to time-series forecasting and classification (e.g., Refs.…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Noise Cleaning in Gravitational-Wave Detectors With Convolutional Neural Networks

Adhikari

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Currently, the sub-60 Hz sensitivity of gravitational-wave (GW) detectors like Advanced LIGO (aLIGO) is limited by the control noises from auxiliary degrees of freedom which nonlinearly couple to the main GW readout. One promising way to tackle this challenge is to perform nonlinear noise mitigation using convolutional neural networks (CNNs), which we examine in detail in this study. In many cases, the noise coupling is bilinear and can be viewed as a few fast channels' outputs modulated by some slow channels. We show that we can utilize this knowledge of the physical system and adopt an explicit “slow×fast” structure in the design of the CNN to enhance its performance of noise subtraction. We then examine the requirements in the signal-to-noise ratio (SNR) in both the target channel (i.e., the main GW readout) and in the auxiliary sensors in order to reduce the noise by at least a factor of a few. In the case of limited SNR in the target channel, we further demonstrate that the CNN can still reach a good performance if we use curriculum learning techniques, which in reality can be achieved by combining data from quiet times and those from periods with active noise injections.

show abstract

“…However, such sensitivity can be overwhelmed by intrinsic noises or local environment noises coupling into the instrument [6,7,8]. One common noise affecting the sensitivity of gravitational-wave detectors is scattered-light noise [9]. It originates when a fraction of laser light is undesirably scattered, reflected from moving surfaces, and recombined in any of the detectors' optical cavities [10].…”

Section: Introductionmentioning

confidence: 99%

Gwadaptive_scattering: an automated pipeline for scattered light noise characterization

Bianchi,

Longo,

Valdes

et al. 2021

Preprint

View full text Add to dashboard Cite

Scattered light noise affects the sensitivity of gravitational waves detectors. The characterization of such noise is needed to mitigate it. The time-varying filter empirical mode decomposition algorithm is suitable for identifying signals with time-dependent frequency such as scattered light noise (or scattering). We present a fully automated pipeline based on the pytvfemd library, a python implementation of the tvf-EMD algorithm, to identify objects inducing scattering in the gravitational-wave channel with their motion. The pipeline application to LIGO Livingston O3 data shows that most scattering noise is due to the penultimate mass at the end of the X-arm of the detector (EXPUM) and with a motion in the micro-seismic frequency range.

show abstract

Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning

Cited by 64 publications

References 72 publications

Unsupervised Learning Architecture for Classifying the Transient Noise of Interferometric Gravitational-Wave Detectors

Unsupervised Learning Architecture for Classifying the Transient Noise of Interferometric Gravitational-Wave Detectors

Nonlinear Noise Cleaning in Gravitational-Wave Detectors With Convolutional Neural Networks

Gwadaptive_scattering: an automated pipeline for scattered light noise characterization

Contact Info

Product

Resources

About