Machine-learning aided detector optimization of the Pacific Ocean Neutrino Experiment

Haack C, Schumacher L, Agostini M, Bailly N, Baron AJ, Bedard J, Bellenghi C, Böhmer M, Bosma C, Brussow D, Clark K, Crudele B, Danninger M, De Leo F, Deis N, DeYoung T, Dinkel M, Garriz J, Gärtner A, Gernhäuser R, Ghuman D, Gousy-Leblanc V, Grant D, Halliday R, Hatch P, Henningsen F, Holzapfel K, Jenkyns R, Kerscher T, Kerschtien S, Kopański K, Kopper C, Krauss CB, Kulin I, Kurahashi N, Lai PC, Lavallee T, Leismüller K, Leys S, Li R, Malecki P, McElroy T, Maunder A, Michel J, Trejo SM, Miller C, Molberg N, Moore R, Niederhausen H, Noga W, Papp L, Park N, Paulson M, Pirenne B, Qiu T, Resconi E, Retza N, Agreda SR, Robertson S, Ruskey A, Sclafani S, Spannfellner C, Stacho J, Taboada I, Terliuk A, Tradewell M, Traxler M, Tung CF, Twagirayezu JP, Veenstra B, Wagner S, Weaver C, Whitehorn N, Wu K, Yañez JP, Yu S, Zheng Y (2024)

Publication Type: Conference contribution

Publication year: 2024

Journal

PoS - Proceedings of Science SISSA

Publisher: Sissa Medialab Srl

Book Volume: 444

Conference Proceedings Title: Proceedings of Science

Event location: Nagoya JP

Abstract

The Pacific Ocean Neutrino Experiment (P-ONE) is a planned cubic-kilometer-scale neutrino detector in the Pacific Ocean. P-ONE will measure high-energy astrophysical neutrinos to characterize the nature of astrophysical accelerators. Using existing deep-sea infrastructure provided by Ocean Networks Canada (ONC), P-ONE will instrument the ocean with optical modules - which host PMTs and readout electronics - deployed on several vertical cables of about 1 km in length. While the hardware design of the first prototype cable is currently being finalized, the detector geometry of the final instrument (up to 70 cables) is not yet fixed. Conventional design optimization typically requires extensive Monte-Carlo simulations, which limits the testable search space to a few configurations. In this contribution, we present the progress of optimizing the detector design using machine-learning-based surrogate models, which replace the computationally expensive MC simulations. By providing gradients, these models also allow for the efficient computation of detector resolutions via the Fisher Information Matrix, without having to rely on specific event-reconstruction algorithms.

Authors with CRIS profile

Christian Haack Lehrstuhl für Experimentelle Astroteilchenphysik Lisa Schumacher Lehrstuhl für Experimentelle Astroteilchenphysik Claudio Kopper Lehrstuhl für Experimentelle Astroteilchenphysik

Additional Organisation(s)

Erlangen Centre for Astroparticle Physics (ECAP)

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) University College London (UCL) GB United Kingdom (GB) University of Victoria (UVic) CA Canada (CA) Queen's University CA Canada (CA) Simon Fraser University CA Canada (CA) Michigan State University US United States (USA) (US) University of Alberta CA Canada (CA) Institute of Nuclear Physics Polish Academy of Sciences / Instytut Fizyki Jądrowej im. Henryka Niewodniczańskiego Polskiej Akademii Nauk PL Poland (PL) Drexel University US United States (USA) (US) Georgia Institute of Technology US United States (USA) (US) GSI Helmholtzzentrum für Schwerionenforschung GmbH DE Germany (DE)

How to cite

APA:

Haack, C., Schumacher, L., Agostini, M., Bailly, N., Baron, A.J., Bedard, J.,... Zheng, Y. (2024). Machine-learning aided detector optimization of the Pacific Ocean Neutrino Experiment. In Proceedings of Science. Nagoya, JP: Sissa Medialab Srl.

MLA:

Haack, Christian, et al. "Machine-learning aided detector optimization of the Pacific Ocean Neutrino Experiment." Proceedings of the 38th International Cosmic Ray Conference, ICRC 2023, Nagoya Sissa Medialab Srl, 2024.

BibTeX: Download