Classification of electron and muon neutrino events for the ESSνSB near water Cherenkov detector using Graph Neural Networks

(ESSnuSB) Aguilar, J.; Anastasopoulos, M.; Barčot, Doris; Baussan, E.; Bhattacharyya, A.K.; Bignami, A.; Blennow, M.; Bogomilov, M.; Bolling, B.; Bouquerel, E.; Bramati, F.; Branca, A.; Brunetti, G.; Burgman, A.; Bustinduy, I.; Carlile, C.J.; Cederkall, J.; Choi, T.W.; Choubey, S.; Christiansen, P.; Collins, M.; Cristaldo Morales, E.; Cupiał, P.; D'Ago, D.; Danared, H.; de André, J.P.A.M.; Dracos, M.; Efthymiopoulos, I.; Ekelöf, T.; Eshraqi, M.; Fanourakis, G.; Farricker, A.; Fasoula, E.; Fukuda, T.; García-Marcos, J.; Gazis, N.; Geralis, Th.; Ghosh, Manojit; Giarnetti, A.; Gokbulut, G.; Hagner, C.; Halić, Leon; Hooft, M.; Iversen, K.E.; Jachowicz, N.; Jenssen, M.; Johansson, R.; Karakoulias, I.; Kasimi, E.; Kayis Topaksu, A.; Kildetoft, B.; Kliček, Budimir; Kordas, K.; Leisos, A.; Lindroos, M.; Longhin, A.; Maiano, C.; Marangoni, S.; Marrelli, C.; Meloni, D.; Mezzetto, M.; Milas, N.; Muñoz, J.L.; Niewczas, K.; Oglakci, M.; Ohlsson, T.; Olvegård, M.; Pari, M.; Park, J.; Patrzalek, D.; Petkov, G.; Petridou, Ch.; Poussot, P.; Psallidas, A.; Pupilli, F.; Saiang, D.; Sampsonidis, D.; Scanu, A.; Schwab, C.; Sordo, F.; Sosa, A.; Stavropoulos, G.; Stipčević, Mario; Tarkeshian, R.; Terranova, F.; Tolba, T.; Trachanas, E.; Tsenov, R.; Tsirigotis, A.; Tzamarias, S.E.; Vanderpoorten, M.; Vankova-Kirilova, G.; Vassilopoulos, N.; Vihonen, S.; Wurtz, J.; Zeter, V.; Zormpa, O. (2025) Classification of electron and muon neutrino events for the ESSνSB near water Cherenkov detector using Graph Neural Networks. Journal of Instrumentation, 20 (08). ISSN 1748-0221

	PDF - Published Version - article Available under License Creative Commons Attribution. Download (13MB)
	PDF - Submitted Version - article Available under License Creative Commons Attribution. Download (4MB)

Abstract

In the effort to obtain a precise measurement of leptonic CP-violation with the ESSνSB experiment, accurate and fast reconstruction of detector events plays a pivotal role. In this work, we examine the possibility of replacing the currently proposed likelihood-based reconstruction method with an approach based on Graph Neural Networks (GNNs). As the likelihood-based reconstruction method is reasonably accurate but computationally expensive, one of the benefits of a Machine Learning (ML) based method is enabling fast event reconstruction in the detector development phase, allowing for easier investigation of the effects of changes to the detector design. Focusing on classification of flavour and interaction type in muon and electron events and muon- and electron neutrino interaction events, we demonstrate that the GNN reconstructs events with greater accuracy than the likelihood method for events with greater complexity, and with increased speed for all types of events. The GNN flavour classification of neutrino interaction events results in a true positive rate of 85.87 % (57.90 %) for muon (electron) neutrinos, compared to 35.55 % (0.21 %) for the likelihood-based method with identical constraints on the false positive rate, while the reconstruction speed is increased by a factor of 10^4 Additionally, we investigate the key factors impacting reconstruction performance, and demonstrate how separation of events by pion production using another GNN classifier can benefit flavour classification.

Item Type:	Article
Uncontrolled Keywords:	Analysis and statistical methods; Cherenkov detectors; Neutrino detectors; Performance of High Energy Physics Detectors
Subjects:	NATURAL SCIENCES > Physics
Divisions:	Center of Excellence for Advanced Materials and Sensing Devices
Projects:	Project title Project leader Project code Project type Study of the use of the ESS facility to accurately measure the neutrino cross-sections for ESSnuSB leptonic CP violation measurements and to perform sterile neutrino searches and astroparticle physics (ESSnuSBplus) Budimir Kliček 101094628 Znanstveno-istraživački projekti
Depositing User:	Ana Zečević
Date Deposited:	12 Nov 2025 10:00
URI:	http://fulir.irb.hr/id/eprint/10200
DOI:	10.1088/1748-0221/20/08/P08030

Actions (login required)

View Item