Deep Learning Classifier for Low-Energy Events in IceCube
Tau appearance from neutrino oscillations of atmospheric muon neutrinos is studied by the DeepCore subarray, the densely-instrumented region of IceCube, an ice-Cherenkov neutrino detector 1.5 kilometers below the surface of the South Pole. These studies probe the unitarity of the PMNS matrix. Distin...
Main Author: | |
---|---|
Format: | Conference Object |
Language: | unknown |
Published: |
2020
|
Subjects: | |
Online Access: | https://zenodo.org/record/4122569 https://doi.org/10.5281/zenodo.4122569 |
id |
ftzenodo:oai:zenodo.org:4122569 |
---|---|
record_format |
openpolar |
spelling |
ftzenodo:oai:zenodo.org:4122569 2023-05-15T18:22:23+02:00 Deep Learning Classifier for Low-Energy Events in IceCube Maria Prado Rodriguez 2020-06-22 https://zenodo.org/record/4122569 https://doi.org/10.5281/zenodo.4122569 unknown doi:10.5281/zenodo.4122568 https://zenodo.org/communities/neutrino2020-posters https://zenodo.org/record/4122569 https://doi.org/10.5281/zenodo.4122569 oai:zenodo.org:4122569 info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode info:eu-repo/semantics/conferencePoster poster 2020 ftzenodo https://doi.org/10.5281/zenodo.412256910.5281/zenodo.4122568 2023-03-10T23:27:09Z Tau appearance from neutrino oscillations of atmospheric muon neutrinos is studied by the DeepCore subarray, the densely-instrumented region of IceCube, an ice-Cherenkov neutrino detector 1.5 kilometers below the surface of the South Pole. These studies probe the unitarity of the PMNS matrix. Distinguishable event signatures in this region include track-like and shower-like events. Because the contribution of tau neutrinos manifests as a statistically significant excess of shower-like events, accurate event classification is crucial. However, at the low energies relevant to the oscillation maximum, separation of tracks and showers is challenging. This poster shows an ongoing study of a deep learning event classifier that currently achieves an accuracy comparable to that of previously used methods, with still large room for improvement. We show that DNNs can learn complex features in DeepCore data at hit level (not relying on reconstructed quantities) that differentiate the signal types. Conference Object South pole Zenodo South Pole |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
unknown |
description |
Tau appearance from neutrino oscillations of atmospheric muon neutrinos is studied by the DeepCore subarray, the densely-instrumented region of IceCube, an ice-Cherenkov neutrino detector 1.5 kilometers below the surface of the South Pole. These studies probe the unitarity of the PMNS matrix. Distinguishable event signatures in this region include track-like and shower-like events. Because the contribution of tau neutrinos manifests as a statistically significant excess of shower-like events, accurate event classification is crucial. However, at the low energies relevant to the oscillation maximum, separation of tracks and showers is challenging. This poster shows an ongoing study of a deep learning event classifier that currently achieves an accuracy comparable to that of previously used methods, with still large room for improvement. We show that DNNs can learn complex features in DeepCore data at hit level (not relying on reconstructed quantities) that differentiate the signal types. |
format |
Conference Object |
author |
Maria Prado Rodriguez |
spellingShingle |
Maria Prado Rodriguez Deep Learning Classifier for Low-Energy Events in IceCube |
author_facet |
Maria Prado Rodriguez |
author_sort |
Maria Prado Rodriguez |
title |
Deep Learning Classifier for Low-Energy Events in IceCube |
title_short |
Deep Learning Classifier for Low-Energy Events in IceCube |
title_full |
Deep Learning Classifier for Low-Energy Events in IceCube |
title_fullStr |
Deep Learning Classifier for Low-Energy Events in IceCube |
title_full_unstemmed |
Deep Learning Classifier for Low-Energy Events in IceCube |
title_sort |
deep learning classifier for low-energy events in icecube |
publishDate |
2020 |
url |
https://zenodo.org/record/4122569 https://doi.org/10.5281/zenodo.4122569 |
geographic |
South Pole |
geographic_facet |
South Pole |
genre |
South pole |
genre_facet |
South pole |
op_relation |
doi:10.5281/zenodo.4122568 https://zenodo.org/communities/neutrino2020-posters https://zenodo.org/record/4122569 https://doi.org/10.5281/zenodo.4122569 oai:zenodo.org:4122569 |
op_rights |
info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/legalcode |
op_doi |
https://doi.org/10.5281/zenodo.412256910.5281/zenodo.4122568 |
_version_ |
1766201792782139392 |