Vision Transformer for Transient Noise Classification

• Autorzy: Srivastava D. , Niedzielski A.

Identyfikatory

DOI

10.32023/0001-5237/74.3.3

• Języki publikacji: EN

Abstrakty

EN

Transient noise (glitches) in LIGO data hinders the detection of gravitational waves (GW). The Gravity Spy project has categorized these noise events into various classes. With the O3 run, there is the inclusion of two additional noise classes and, thus, a need to train new models for effective classification. We aim to classify glitches in LIGO data into 22 existing classes from the first run plus 2 additional noise classes from O3a using the Vision Transformer (ViT) model. We train a pre-trained Vision Transformer (ViT-B/32) model on a combined dataset consisting of the Gravity Spy dataset with the additional two classes from the LIGO O3a run. We achieve a classification efficiency of 92.26%, demonstrating the potential of Vision Transformer to improve the accuracy of gravitational wave detection by effectively distinguishing transient noise.

Słowa kluczowe

EN

gravitational waves; methods: numerical

• Wydawca: Copernicus Foundation for Polish Astronomy
• Czasopismo: Acta Astronomica
• Rocznik: 2024
• Tom: Vol. 74, No. 3
• Strony: 231--238
• Opis fizyczny: Bibliogr. 11 poz., rys., wykr., zdj.

Twórcy

autor

Srivastava D.

• Institute of Astronomy, Nicolaus Copernicus University in Toruń ul. Gagarina 11, 87-100 Toruń, Poland

autor

Niedzielski A.

• Institute of Astronomy, Nicolaus Copernicus University in Toruń ul. Gagarina 11, 87-100 Toruń, Poland

Bibliografia

• Carruba, V., Aljbaae, S., Smirnov, E., and Caritá, G. 2025, Icarus, 425, 116346.
• Coughlin, S. 2018, Zenodo: Updated Gravity Spy Data Set (v1.1.0) [Data set].
• Dosovitskiy, A. Beyer, L. Kolesnikov, A. et al. 2021, arXiv:2010.11929.
• George, D., Shen, H., and Huerta, E.A. 2017, arXiv:1711.07468
• Glanzer, J., Banagiri, S., Coughlin S.B. et al. 2023, Classical and Quantum Gravity, 40, 065004.
• Li, C., and Zhang, C. 2023, arXiv:2309.05375.
• Macleod, D.M., Areeda, J.S., Coughlin, S.B. Massinger, T.J. and Urban, A.L. 2021, SoftwareX, 13, 100657.
• Paszke, A., Gross, S., Massa, F., et al. 2019, in: “Advances in Neural Information Processing Systems 32”, Curran Associates, Inc. p. 8024.
• Robinet, F., Arnaud, N., Leroy, N., et al. 2020, SoftwareX, 12, 100620.
• Yang, Yi, and Li, Xin 2024, Universe, 10, 2.14.
• Tanoglidis, D., Jain, B., and Qu, H. 2023, arXiv:2310.12069.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).