A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory
Continued improvements on existing reconstruction methods are vital to the success of high-energy physics experiments, such as the IceCube Neutrino Observatory. In IceCube, further challenges arise as the detector is situated at the geographic South Pole where computational resources are limited. Ho...
Published in: | Journal of Instrumentation |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://curis.ku.dk/portal/da/publications/a-convolutional-neural-network-based-cascade-reconstruction-for-the-icecube-neutrino-observatory(6268572d-4f2d-4f3b-b435-298a109667ab).html https://doi.org/10.1088/1748-0221/16/07/P07041 https://arxiv.org/abs/2101.11589 |
id |
ftcopenhagenunip:oai:pure.atira.dk:publications/6268572d-4f2d-4f3b-b435-298a109667ab |
---|---|
record_format |
openpolar |
spelling |
ftcopenhagenunip:oai:pure.atira.dk:publications/6268572d-4f2d-4f3b-b435-298a109667ab 2024-06-09T07:49:37+00:00 A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory 2021-07 https://curis.ku.dk/portal/da/publications/a-convolutional-neural-network-based-cascade-reconstruction-for-the-icecube-neutrino-observatory(6268572d-4f2d-4f3b-b435-298a109667ab).html https://doi.org/10.1088/1748-0221/16/07/P07041 https://arxiv.org/abs/2101.11589 eng eng info:eu-repo/semantics/closedAccess The IceCube collaboration 2021 , ' A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory ' , Journal of Instrumentation , vol. 16 , no. 7 , P07041 . https://doi.org/10.1088/1748-0221/16/07/P07041 Calibration Cluster finding Data analysis Fitting methods Neutrino detectors Pattern recognition article 2021 ftcopenhagenunip https://doi.org/10.1088/1748-0221/16/07/P07041 2024-05-16T11:29:24Z Continued improvements on existing reconstruction methods are vital to the success of high-energy physics experiments, such as the IceCube Neutrino Observatory. In IceCube, further challenges arise as the detector is situated at the geographic South Pole where computational resources are limited. However, to perform real-time analyses and to issue alerts to telescopes around the world, powerful and fast reconstruction methods are desired. Deep neural networks can be extremely powerful, and their usage is computationally inexpensive once the networks are trained. These characteristics make a deep learning-based approach an excellent candidate for the application in IceCube. A reconstruction method based on convolutional architectures and hexagonally shaped kernels is presented. The presented method is robust towards systematic uncertainties in the simulation and has been tested on experimental data. In comparison to standard reconstruction methods in IceCube, it can improve upon the reconstruction accuracy, while reducing the time necessary to run the reconstruction by two to three orders of magnitude. Article in Journal/Newspaper South pole University of Copenhagen: Research South Pole Journal of Instrumentation 16 07 P07041 |
institution |
Open Polar |
collection |
University of Copenhagen: Research |
op_collection_id |
ftcopenhagenunip |
language |
English |
topic |
Calibration Cluster finding Data analysis Fitting methods Neutrino detectors Pattern recognition |
spellingShingle |
Calibration Cluster finding Data analysis Fitting methods Neutrino detectors Pattern recognition A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory |
topic_facet |
Calibration Cluster finding Data analysis Fitting methods Neutrino detectors Pattern recognition |
description |
Continued improvements on existing reconstruction methods are vital to the success of high-energy physics experiments, such as the IceCube Neutrino Observatory. In IceCube, further challenges arise as the detector is situated at the geographic South Pole where computational resources are limited. However, to perform real-time analyses and to issue alerts to telescopes around the world, powerful and fast reconstruction methods are desired. Deep neural networks can be extremely powerful, and their usage is computationally inexpensive once the networks are trained. These characteristics make a deep learning-based approach an excellent candidate for the application in IceCube. A reconstruction method based on convolutional architectures and hexagonally shaped kernels is presented. The presented method is robust towards systematic uncertainties in the simulation and has been tested on experimental data. In comparison to standard reconstruction methods in IceCube, it can improve upon the reconstruction accuracy, while reducing the time necessary to run the reconstruction by two to three orders of magnitude. |
format |
Article in Journal/Newspaper |
title |
A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory |
title_short |
A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory |
title_full |
A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory |
title_fullStr |
A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory |
title_full_unstemmed |
A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory |
title_sort |
convolutional neural network based cascade reconstruction for the icecube neutrino observatory |
publishDate |
2021 |
url |
https://curis.ku.dk/portal/da/publications/a-convolutional-neural-network-based-cascade-reconstruction-for-the-icecube-neutrino-observatory(6268572d-4f2d-4f3b-b435-298a109667ab).html https://doi.org/10.1088/1748-0221/16/07/P07041 https://arxiv.org/abs/2101.11589 |
geographic |
South Pole |
geographic_facet |
South Pole |
genre |
South pole |
genre_facet |
South pole |
op_source |
The IceCube collaboration 2021 , ' A convolutional neural network based cascade reconstruction for the IceCube Neutrino Observatory ' , Journal of Instrumentation , vol. 16 , no. 7 , P07041 . https://doi.org/10.1088/1748-0221/16/07/P07041 |
op_rights |
info:eu-repo/semantics/closedAccess |
op_doi |
https://doi.org/10.1088/1748-0221/16/07/P07041 |
container_title |
Journal of Instrumentation |
container_volume |
16 |
container_issue |
07 |
container_start_page |
P07041 |
_version_ |
1801382329553256448 |