VAE-based latent-space classification of RNO-G data

Glüsenkamp T, Aguilar JA, Allison P, Besson D, Bishop A, Botner O, Bouma S, Buitink S, Castiglioni W, Cataldo M, Clark BA, Coleman A, Couberly K, Dasgupta P, de Kockere S, de Vries KD, Deaconu C, DuVernois MA, Eimer A, Glaser C, Hallgren A, Hallmann S, Hanson JC, Hendricks B, Henrichs J, Heyer N, Hornhuber C, Hughes K, Karg T, Karle A, Kelley JL, Korntheuer M, Kowalski M, Kravchenko I, Krebs R, Lahmann R, Lehmann P, Latif U, Laub P, Liu CH, Mammo J, Marsee MJ, Meyers Z, Mikhailova M, Michaels K, Mulrey K, Muzio M, Nelles A, Novikov A, Nozdrina A, Oberla E, Oeyen B, Plaisier I, Punsuebsay N, Pyras LM, Ryckbosch D, Schlüter F, Scholten O, Seckel D, Seikh MF, Smith D, Stoffels J, Southall D, Terveer K, Toscano S, Tosi D, Van Den Broeck DJ, van Eijndhoven N, Vieregg AG, Vischer J, Welling C, Williams DR, Wissel S, Young R, Zink A (2024)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2024

Journal

Publisher: Sissa Medialab Srl

Series: Proceedings of Science

Book Volume: 444

Pages Range: 1056

Conference Proceedings Title: Proceedings of 38th International Cosmic Ray Conference — PoS(ICRC2023)

Event location: Nagoya

DOI: 10.22323/1.444.1056

Abstract

The Radio Neutrino Observatory in Greenland (RNO-G) is a radio-based ultra-high energy neutrino detector located at Summit Station, Greenland. It is still being constructed, with 7 stations currently operational. Neutrino detection works by measuring Askaryan radiation produced by neutrino-nucleon interactions. A neutrino candidate must be found amidst other backgrounds which are recorded at much higher rates—including cosmic-rays and anthropogenic noise—the origins of which are sometimes unknown. Here we describe a method to classify different noise classes using the latent space of a variational autoencoder. The latent space forms a compact representation that makes classification tractable. We analyze data from a noisy and a silent station. The method automatically detects and allows us to qualitatively separate multiple event classes, including physical wind-induced signals, for both the noisy and the quiet station.

Authors with CRIS profile

Involved external institutions

Uppsala University Sweden (SE) University of Delaware (UDEL) United States (USA) (US) University of Nebraska-Lincoln United States (USA) (US) Deutsches Elektronen-Synchrotron DESY Germany (DE) University of Chicago United States (USA) (US) Pennsylvania State University (Penn State) United States (USA) (US) Vrije Universiteit Brussel (VUB) Belgium (BE) University of Kansas (KU) United States (USA) (US) The University of Alabama United States (USA) (US) Ohio State University United States (USA) (US) University of Wisconsin - Madison United States (USA) (US) Université libre de Bruxelles (ULB) / Free University of Brussels Belgium (BE) Universiteit Gent (UGent) / Ghent University Belgium (BE) Radboud University Nijmegen Netherlands (NL) Whittier College United States (USA) (US) University of Maryland, College Park (UMD) United States (USA) (US)

How to cite

APA:

Glüsenkamp, T., Aguilar, J.A., Allison, P., Besson, D., Bishop, A., Botner, O.,... Zink, A. (2024). VAE-based latent-space classification of RNO-G data. In Proceedings of 38th International Cosmic Ray Conference — PoS(ICRC2023) (pp. 1056). Nagoya, JP: Sissa Medialab Srl.

MLA:

Glüsenkamp, Thorsten, et al. "VAE-based latent-space classification of RNO-G data." Proceedings of the 38th International Cosmic Ray Conference, ICRC 2023, Nagoya Sissa Medialab Srl, 2024. 1056.

BibTeX: Download