Data reconstruction and classification with graph neural networks in KM3NeT/ARCA6-8
- NázevTitle
- Data reconstruction and classification with graph neural networks in KM3NeT/ARCA6-8Data reconstruction and classification with graph neural networks in KM3NeT/ARCA6-8
- Druh výsledkuResult type
- Příspěvek ve sborníkuProceedings paper
- AutořiAuthors
- F. Filippini, E. Androutsou, A. Domi, B. Spisso, Z. Bardačová, E. Eckerová, F. Mamedov, Y. Shitov, I. Štekl
- Klíčová slovaKeywords
- KM3NeT, neutrino telescope, Data reconstruction
- KonferenceConference
- 38th International Cosmic Ray Conference (Nagoya, Japan, 2023-07-26)
- ExperimentCollaboration
- KM3NeT
- DOIDOI
- 10.22323/1.444.1194
- Časopis / citaceJournal / citation
- In: Proceedings of 38th International Cosmic Ray Conference — PoS(ICRC2023), Sissa Medialab, 2024, pp. 1194 · ISSN 1824-8039
- RokYear
- 2024
- JazykLanguage
- eng
- ZáznamyRecords
- ProjektProject
- LSM-CZ III - Podzemní laboratoř LSM - účast České republiky - LM2023063 (2023–2026)LSM-CZ III - Podzemní laboratoř LSM - účast České republiky - LM2023063 (2023–2026); Laboratoire Souterrain de Modane - účast ČRLaboratoire Souterrain de Modane – participation of the Czech Republic
- CitovánoCited by
- 1 (INSPIRE-HEP)
- Plný text (open access)Full text (open access)
- https://pos.sissa.it/444/1194/pdf
- Citace ke staženíDownload citation
- TXT · BibTeX
AbstraktAbstract
KM3NeT is a research infrastructure hosting two large-volume Cherenkov neutrino detectors which are currently under construction in the Mediterranean Sea. The KM3NeT/ARCA detector is optimised for the detection of high-energy neutrinos from astrophysical sources in the TeV-PeV energy range. Once completed, the detector will consist of 230 detection units. Here, we present a Deep Learning method using graph neural networks that is trained and applied to events gathered with 6 and 8 active detection units of KM3NeT/ARCA. Graph neural networks have been trained for classification and regression tasks, showing very promising performances in a range of different tasks like neutrino-background identification, neutrino event topology classification, energy and direction reconstruction, and also in the study of properties of muon bundles.
KM3NeT is a research infrastructure hosting two large-volume Cherenkov neutrino detectors which are currently under construction in the Mediterranean Sea. The KM3NeT/ARCA detector is optimised for the detection of high-energy neutrinos from astrophysical sources in the TeV-PeV energy range. Once completed, the detector will consist of 230 detection units. Here, we present a Deep Learning method using graph neural networks that is trained and applied to events gathered with 6 and 8 active detection units of KM3NeT/ARCA. Graph neural networks have been trained for classification and regression tasks, showing very promising performances in a range of different tasks like neutrino-background identification, neutrino event topology classification, energy and direction reconstruction, and also in the study of properties of muon bundles.