Exploring ESSνSB Near Water Cherenkov Detector Designs Through Graph Neural Network Flavour Identification

@misc{aguilar2026exploring,
  title = {{Exploring ESS$ν$SB Near Water Cherenkov Detector Designs Through Graph Neural Network Flavour Identification}},
  author = {J Aguilar and M Anastasopoulos and D Barčot and E Baussan and A.K Bhattacharyya and A Bignami and M Blennow and M Bogomilov and B Bolling and E Bouquerel and F Bramati and A Branca and G Brunetti and A Burgman and I Bustinduy and C.J Carlile and J Cederkall and T.W Choi and S Choubey and P Christiansen and I Christodoulou and E. Cristaldo Morales and P Cupiał and D d'Ago and H Danared and J.P.A.M de André and M Dracos and I Efthymiopoulos and T Ekelöf and M Eshraqi and G Fanourakis and A Farricker and E Fasoula and T Fukuda and S Gago and N Gazis and Th Geralis and M Ghosh and A Giarnetti and G Gokbulut and C Hagner and L Halić and S.G Hernández and J Hiegel and M Hooft and K.E Iversen and N Jachowicz and M Jakkapu and M Jensen and I Karakoulias and E Kasimi and A Kayis Topaksu and B Kliček and K Kordas and B Kovač and A Leisos and A Longhin and M López and C Maiano and S Marangoni},
  howpublished = {HAL},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2608.23773},
  eprint = {2608.23773},
  archivePrefix = {arXiv},
  url = {https://hal.science/hal-05737746v1},
  note = {CC BY 4.0},
}

TY  - UNPB
TI  - Exploring ESSνSB Near Water Cherenkov Detector Designs Through Graph Neural Network Flavour Identification
AU  - J Aguilar
AU  - M Anastasopoulos
AU  - D Barčot
AU  - E Baussan
AU  - A.K Bhattacharyya
AU  - A Bignami
AU  - M Blennow
AU  - M Bogomilov
AU  - B Bolling
AU  - E Bouquerel
AU  - F Bramati
AU  - A Branca
AU  - G Brunetti
AU  - A Burgman
AU  - I Bustinduy
AU  - C.J Carlile
AU  - J Cederkall
AU  - T.W Choi
AU  - S Choubey
AU  - P Christiansen
AU  - I Christodoulou
AU  - E. Cristaldo Morales
AU  - P Cupiał
AU  - D d'Ago
AU  - H Danared
AU  - J.P.A.M de André
AU  - M Dracos
AU  - I Efthymiopoulos
AU  - T Ekelöf
AU  - M Eshraqi
AU  - G Fanourakis
AU  - A Farricker
AU  - E Fasoula
AU  - T Fukuda
AU  - S Gago
AU  - N Gazis
AU  - Th Geralis
AU  - M Ghosh
AU  - A Giarnetti
AU  - G Gokbulut
AU  - C Hagner
AU  - L Halić
AU  - S.G Hernández
AU  - J Hiegel
AU  - M Hooft
AU  - K.E Iversen
AU  - N Jachowicz
AU  - M Jakkapu
AU  - M Jensen
AU  - I Karakoulias
AU  - E Kasimi
AU  - A Kayis Topaksu
AU  - B Kliček
AU  - K Kordas
AU  - B Kovač
AU  - A Leisos
AU  - A Longhin
AU  - M López
AU  - C Maiano
AU  - S Marangoni
PY  - 2026
DA  - 2026/09/03
PB  - HAL
DO  - 10.48550/arxiv.2608.23773
UR  - https://hal.science/hal-05737746v1
AB  - The ESSνSB experiment aims to measure CP violation in the leptonic sector with high precision, necessitating robust reconstruction of neutrino events in the water Cherenkov (WC) detectors. In this work, we investigate the flavour identification potential of the proposed near WC detector using graph neural network (GNN)-based classification, with a focus on variations of key detector design parameters. In particular, we study whether a smaller and/or less instrumented detector can achieve the required classification performance. Using detailed Monte Carlo simulations of charged-current (CC) neutrino interactions, we train GNN classifiers to distinguish electron and muon neutrino CC events. We find that GNN-based classification remains accurate even for detector configurations with volumes up to a factor of eight smaller than the nominal design, with only moderate degradation in classification efficiency at fixed background rejection. The resulting loss in efficiency can largely be compensated by increased exposure time. Furthermore, we demonstrate that reduced photomultiplier tube (PMT) coverage in the nominal detector has a limited impact on classification performance, provided that coverage is maintained in regions of highest signal yield, in particular near the forward end-cap.
ER  -