Machine Learning in KM3NeT
The KM3NeT Collaboration is building a network of underwater Cherenkov telescopes at two sites in the Mediterranean Sea, with the main goals of investigating astrophysical sources of high-energy neutrinos (ARCA) and of determining the neutrino mass hierarchy (ORCA). Various Machine Learning techniqu...
Published in: | EPJ Web of Conferences |
---|---|
Main Author: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
EDP Sciences
2019
|
Subjects: | |
Online Access: | https://doi.org/10.1051/epjconf/201920705004 https://doaj.org/article/09818b2cf1ba4836af9cbee48b2db813 |
id |
ftdoajarticles:oai:doaj.org/article:09818b2cf1ba4836af9cbee48b2db813 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:09818b2cf1ba4836af9cbee48b2db813 2023-05-15T17:53:41+02:00 Machine Learning in KM3NeT De Sio Chiara 2019-01-01T00:00:00Z https://doi.org/10.1051/epjconf/201920705004 https://doaj.org/article/09818b2cf1ba4836af9cbee48b2db813 EN eng EDP Sciences https://www.epj-conferences.org/articles/epjconf/pdf/2019/12/epjconf_vlvnt2018_05004.pdf https://doaj.org/toc/2100-014X 2100-014X doi:10.1051/epjconf/201920705004 https://doaj.org/article/09818b2cf1ba4836af9cbee48b2db813 EPJ Web of Conferences, Vol 207, p 05004 (2019) Physics QC1-999 article 2019 ftdoajarticles https://doi.org/10.1051/epjconf/201920705004 2022-12-31T06:31:03Z The KM3NeT Collaboration is building a network of underwater Cherenkov telescopes at two sites in the Mediterranean Sea, with the main goals of investigating astrophysical sources of high-energy neutrinos (ARCA) and of determining the neutrino mass hierarchy (ORCA). Various Machine Learning techniques, such as Random Forests, BDTs, Shallow and Deep Networks are being used for diverse tasks, such as event-type and particle identification, energy/direction estimation, source identification, signal/background discrimination and data analysis, with sound results as well as promising research paths. The main focus of this work is the application of Convolutional Neural Network models to the tasks of neutrino interaction classification, as well as the estimation of energy and direction of the propagating particles. The performances are also compared to those of the standard reconstruction algorithms used in the Collaboration. Article in Journal/Newspaper Orca Directory of Open Access Journals: DOAJ Articles EPJ Web of Conferences 207 05004 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Physics QC1-999 |
spellingShingle |
Physics QC1-999 De Sio Chiara Machine Learning in KM3NeT |
topic_facet |
Physics QC1-999 |
description |
The KM3NeT Collaboration is building a network of underwater Cherenkov telescopes at two sites in the Mediterranean Sea, with the main goals of investigating astrophysical sources of high-energy neutrinos (ARCA) and of determining the neutrino mass hierarchy (ORCA). Various Machine Learning techniques, such as Random Forests, BDTs, Shallow and Deep Networks are being used for diverse tasks, such as event-type and particle identification, energy/direction estimation, source identification, signal/background discrimination and data analysis, with sound results as well as promising research paths. The main focus of this work is the application of Convolutional Neural Network models to the tasks of neutrino interaction classification, as well as the estimation of energy and direction of the propagating particles. The performances are also compared to those of the standard reconstruction algorithms used in the Collaboration. |
format |
Article in Journal/Newspaper |
author |
De Sio Chiara |
author_facet |
De Sio Chiara |
author_sort |
De Sio Chiara |
title |
Machine Learning in KM3NeT |
title_short |
Machine Learning in KM3NeT |
title_full |
Machine Learning in KM3NeT |
title_fullStr |
Machine Learning in KM3NeT |
title_full_unstemmed |
Machine Learning in KM3NeT |
title_sort |
machine learning in km3net |
publisher |
EDP Sciences |
publishDate |
2019 |
url |
https://doi.org/10.1051/epjconf/201920705004 https://doaj.org/article/09818b2cf1ba4836af9cbee48b2db813 |
genre |
Orca |
genre_facet |
Orca |
op_source |
EPJ Web of Conferences, Vol 207, p 05004 (2019) |
op_relation |
https://www.epj-conferences.org/articles/epjconf/pdf/2019/12/epjconf_vlvnt2018_05004.pdf https://doaj.org/toc/2100-014X 2100-014X doi:10.1051/epjconf/201920705004 https://doaj.org/article/09818b2cf1ba4836af9cbee48b2db813 |
op_doi |
https://doi.org/10.1051/epjconf/201920705004 |
container_title |
EPJ Web of Conferences |
container_volume |
207 |
container_start_page |
05004 |
_version_ |
1766161390435827712 |