Low energy event classification in IceCube using boosted decision trees
Abstract The DeepCore sub-array within the IceCube Neutrino Observatory is a densely instrumented region of Antarctic ice designed to observe atmospheric neutrino interactions above 5 GeV via Cherenkov radiation. An essential aspect of any neutrino oscillation analysis is the ability to accurately i...
Published in: | Journal of Instrumentation |
---|---|
Main Author: | |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
IOP Publishing
2021
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1088/1748-0221/16/12/c12007 https://iopscience.iop.org/article/10.1088/1748-0221/16/12/C12007 https://iopscience.iop.org/article/10.1088/1748-0221/16/12/C12007/pdf |
id |
crioppubl:10.1088/1748-0221/16/12/c12007 |
---|---|
record_format |
openpolar |
spelling |
crioppubl:10.1088/1748-0221/16/12/c12007 2024-06-02T07:57:59+00:00 Low energy event classification in IceCube using boosted decision trees Leonard DeHolton, K. 2021 http://dx.doi.org/10.1088/1748-0221/16/12/c12007 https://iopscience.iop.org/article/10.1088/1748-0221/16/12/C12007 https://iopscience.iop.org/article/10.1088/1748-0221/16/12/C12007/pdf unknown IOP Publishing https://iopscience.iop.org/page/copyright https://iopscience.iop.org/info/page/text-and-data-mining Journal of Instrumentation volume 16, issue 12, page C12007 ISSN 1748-0221 journal-article 2021 crioppubl https://doi.org/10.1088/1748-0221/16/12/c12007 2024-05-07T13:58:59Z Abstract The DeepCore sub-array within the IceCube Neutrino Observatory is a densely instrumented region of Antarctic ice designed to observe atmospheric neutrino interactions above 5 GeV via Cherenkov radiation. An essential aspect of any neutrino oscillation analysis is the ability to accurately identify the flavor of neutrino events in the detector. This task is particularly difficult at low energies when very little light is deposited in the detector. Here we discuss the use of machine learning to perform event classification at low energies in IceCube using a boosted decision tree (BDT). A BDT is trained using reconstructed quantities to identify track-like events, which result from muon neutrino charged current interactions. This new method improves the accuracy of particle identification compared to traditional classification methods which rely on univariate straight cuts. Article in Journal/Newspaper Antarc* Antarctic IOP Publishing Antarctic Journal of Instrumentation 16 12 C12007 |
institution |
Open Polar |
collection |
IOP Publishing |
op_collection_id |
crioppubl |
language |
unknown |
description |
Abstract The DeepCore sub-array within the IceCube Neutrino Observatory is a densely instrumented region of Antarctic ice designed to observe atmospheric neutrino interactions above 5 GeV via Cherenkov radiation. An essential aspect of any neutrino oscillation analysis is the ability to accurately identify the flavor of neutrino events in the detector. This task is particularly difficult at low energies when very little light is deposited in the detector. Here we discuss the use of machine learning to perform event classification at low energies in IceCube using a boosted decision tree (BDT). A BDT is trained using reconstructed quantities to identify track-like events, which result from muon neutrino charged current interactions. This new method improves the accuracy of particle identification compared to traditional classification methods which rely on univariate straight cuts. |
format |
Article in Journal/Newspaper |
author |
Leonard DeHolton, K. |
spellingShingle |
Leonard DeHolton, K. Low energy event classification in IceCube using boosted decision trees |
author_facet |
Leonard DeHolton, K. |
author_sort |
Leonard DeHolton, K. |
title |
Low energy event classification in IceCube using boosted decision trees |
title_short |
Low energy event classification in IceCube using boosted decision trees |
title_full |
Low energy event classification in IceCube using boosted decision trees |
title_fullStr |
Low energy event classification in IceCube using boosted decision trees |
title_full_unstemmed |
Low energy event classification in IceCube using boosted decision trees |
title_sort |
low energy event classification in icecube using boosted decision trees |
publisher |
IOP Publishing |
publishDate |
2021 |
url |
http://dx.doi.org/10.1088/1748-0221/16/12/c12007 https://iopscience.iop.org/article/10.1088/1748-0221/16/12/C12007 https://iopscience.iop.org/article/10.1088/1748-0221/16/12/C12007/pdf |
geographic |
Antarctic |
geographic_facet |
Antarctic |
genre |
Antarc* Antarctic |
genre_facet |
Antarc* Antarctic |
op_source |
Journal of Instrumentation volume 16, issue 12, page C12007 ISSN 1748-0221 |
op_rights |
https://iopscience.iop.org/page/copyright https://iopscience.iop.org/info/page/text-and-data-mining |
op_doi |
https://doi.org/10.1088/1748-0221/16/12/c12007 |
container_title |
Journal of Instrumentation |
container_volume |
16 |
container_issue |
12 |
container_start_page |
C12007 |
_version_ |
1800741216715800576 |