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: | Still Image |
Language: | unknown |
Published: |
Zenodo
2020
|
Subjects: | |
Online Access: | https://dx.doi.org/10.5281/zenodo.4122569 https://zenodo.org/record/4122569 |
id |
ftdatacite:10.5281/zenodo.4122569 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.5281/zenodo.4122569 2023-05-15T18:22:24+02:00 Deep Learning Classifier for Low-Energy Events in IceCube Rodriguez, Maria Prado 2020 https://dx.doi.org/10.5281/zenodo.4122569 https://zenodo.org/record/4122569 unknown Zenodo https://zenodo.org/communities/neutrino2020-posters https://dx.doi.org/10.5281/zenodo.4122568 https://zenodo.org/communities/neutrino2020-posters Open Access Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 info:eu-repo/semantics/openAccess CC-BY Text Poster article-journal ScholarlyArticle 2020 ftdatacite https://doi.org/10.5281/zenodo.4122569 https://doi.org/10.5281/zenodo.4122568 2021-11-05T12:55:41Z 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. Still Image South pole DataCite Metadata Store (German National Library of Science and Technology) South Pole |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
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 |
Still Image |
author |
Rodriguez, Maria Prado |
spellingShingle |
Rodriguez, Maria Prado Deep Learning Classifier for Low-Energy Events in IceCube |
author_facet |
Rodriguez, Maria Prado |
author_sort |
Rodriguez, Maria Prado |
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 |
publisher |
Zenodo |
publishDate |
2020 |
url |
https://dx.doi.org/10.5281/zenodo.4122569 https://zenodo.org/record/4122569 |
geographic |
South Pole |
geographic_facet |
South Pole |
genre |
South pole |
genre_facet |
South pole |
op_relation |
https://zenodo.org/communities/neutrino2020-posters https://dx.doi.org/10.5281/zenodo.4122568 https://zenodo.org/communities/neutrino2020-posters |
op_rights |
Open Access Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 info:eu-repo/semantics/openAccess |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.5281/zenodo.4122569 https://doi.org/10.5281/zenodo.4122568 |
_version_ |
1766201800777531392 |