Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector
Cost effective in-ice radio detection of neutrinos above a few 10(16) eV has been explored successfully in pilot-arrays. Alarge radio detector is currently being constructed in Greenland with the potential to measure the first cosmogenic neutrino, and an order-of-magnitude more sensitive detector is...
Published in: | Proceedings of 37th International Cosmic Ray Conference — PoS(ICRC2021) |
---|---|
Main Authors: | , , , |
Format: | Conference Object |
Language: | English |
Published: |
Uppsala universitet, Högenergifysik
2022
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-518306 https://doi.org/10.22323/1.395.1051 |
id |
ftuppsalauniv:oai:DiVA.org:uu-518306 |
---|---|
record_format |
openpolar |
spelling |
ftuppsalauniv:oai:DiVA.org:uu-518306 2024-01-14T10:07:21+01:00 Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector Glaser, Christian McAleer, Stephen Baldi, Pierre Barwick, Steven 2022 application/pdf http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-518306 https://doi.org/10.22323/1.395.1051 eng eng Uppsala universitet, Högenergifysik Univ Calif Irvine, Dept Comp Sci, Irvine, CA 92697 USA. Univ Calif Irvine, Dept Phys & Astron, Irvine, CA 92697 USA. Proceedings of Science 37th International Cosmic Ray Conference, ICRC2021 orcid:0000-0001-5998-2553 http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-518306 doi:10.22323/1.395.1051 ISI:001081844903009 info:eu-repo/semantics/openAccess Subatomic Physics Subatomär fysik Accelerator Physics and Instrumentation Acceleratorfysik och instrumentering Conference paper info:eu-repo/semantics/conferenceObject text 2022 ftuppsalauniv https://doi.org/10.22323/1.395.1051 2023-12-20T23:31:57Z Cost effective in-ice radio detection of neutrinos above a few 10(16) eV has been explored successfully in pilot-arrays. Alarge radio detector is currently being constructed in Greenland with the potential to measure the first cosmogenic neutrino, and an order-of-magnitude more sensitive detector is being planned with IceCube-Gen2. We present the first end-to-end reconstruction of the neutrino energy from radio detector data. NuRadioMC was used to create a large data set of 40 million events of expected radio signals that are generated via the Askaryan effect following a neutrino interaction in the ice for a broad range of neutrino energies between 100 PeV and 10 EeV. We simulated the voltage traces that would be measured by the five antennas of a shallow detector station in the presence of noise. We designed and trained a deep neural network to determine the shower energy directly from the simulated experimental data and achieve a resolution better than a factor of two (STD < 0.3 in log10(E)) which is below the irreducible uncertainty from inelasticity fluctuations. We present the model architecture and study the dependence of the resolution on event parameters. This method will enable Askaryan detectors to measure the neutrino energy. Conference Object Greenland Uppsala University: Publications (DiVA) Greenland Proceedings of 37th International Cosmic Ray Conference — PoS(ICRC2021) 1051 |
institution |
Open Polar |
collection |
Uppsala University: Publications (DiVA) |
op_collection_id |
ftuppsalauniv |
language |
English |
topic |
Subatomic Physics Subatomär fysik Accelerator Physics and Instrumentation Acceleratorfysik och instrumentering |
spellingShingle |
Subatomic Physics Subatomär fysik Accelerator Physics and Instrumentation Acceleratorfysik och instrumentering Glaser, Christian McAleer, Stephen Baldi, Pierre Barwick, Steven Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector |
topic_facet |
Subatomic Physics Subatomär fysik Accelerator Physics and Instrumentation Acceleratorfysik och instrumentering |
description |
Cost effective in-ice radio detection of neutrinos above a few 10(16) eV has been explored successfully in pilot-arrays. Alarge radio detector is currently being constructed in Greenland with the potential to measure the first cosmogenic neutrino, and an order-of-magnitude more sensitive detector is being planned with IceCube-Gen2. We present the first end-to-end reconstruction of the neutrino energy from radio detector data. NuRadioMC was used to create a large data set of 40 million events of expected radio signals that are generated via the Askaryan effect following a neutrino interaction in the ice for a broad range of neutrino energies between 100 PeV and 10 EeV. We simulated the voltage traces that would be measured by the five antennas of a shallow detector station in the presence of noise. We designed and trained a deep neural network to determine the shower energy directly from the simulated experimental data and achieve a resolution better than a factor of two (STD < 0.3 in log10(E)) which is below the irreducible uncertainty from inelasticity fluctuations. We present the model architecture and study the dependence of the resolution on event parameters. This method will enable Askaryan detectors to measure the neutrino energy. |
format |
Conference Object |
author |
Glaser, Christian McAleer, Stephen Baldi, Pierre Barwick, Steven |
author_facet |
Glaser, Christian McAleer, Stephen Baldi, Pierre Barwick, Steven |
author_sort |
Glaser, Christian |
title |
Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector |
title_short |
Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector |
title_full |
Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector |
title_fullStr |
Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector |
title_full_unstemmed |
Deep learning reconstruction of the neutrino energy with a shallow Askaryan detector |
title_sort |
deep learning reconstruction of the neutrino energy with a shallow askaryan detector |
publisher |
Uppsala universitet, Högenergifysik |
publishDate |
2022 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-518306 https://doi.org/10.22323/1.395.1051 |
geographic |
Greenland |
geographic_facet |
Greenland |
genre |
Greenland |
genre_facet |
Greenland |
op_relation |
37th International Cosmic Ray Conference, ICRC2021 orcid:0000-0001-5998-2553 http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-518306 doi:10.22323/1.395.1051 ISI:001081844903009 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.22323/1.395.1051 |
container_title |
Proceedings of 37th International Cosmic Ray Conference — PoS(ICRC2021) |
container_start_page |
1051 |
_version_ |
1788061766267174912 |