Final published version
Licence: CC BY: Creative Commons Attribution 4.0 International License
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Improved calorimetric particle identification in NA62 using machine learning techniques
AU - The NA62 Collaboration
AU - Cortina Gil, E.
AU - Kleimenova, A.
AU - Minucci, E.
AU - Padolski, S.
AU - Petrov, P.
AU - Shaikhiev, A.
AU - Volpe, R.
AU - Fedorko, W.
AU - Numao, T.
AU - Petrov, Y.
AU - Velghe, B.
AU - Wong, V. W. S.
AU - Yu, M.
AU - Bryman, D.
AU - Fu, J.
AU - Hives, Z.
AU - Husek, T.
AU - Jerhot, J.
AU - Kampf, K.
AU - Zamkovsky, M.
AU - De Martino, B.
AU - Perrin-Terrin, M.
AU - Akmete, A. T.
AU - Aliberti, R.
AU - Khoriauli, G.
AU - Kunze, J.
AU - Lomidze, D.
AU - Peruzzo, L.
AU - Vormstein, M.
AU - Wanke, R.
AU - Dalpiaz, P.
AU - Fiorini, M.
AU - Mazzolari, A.
AU - Neri, I.
AU - Norton, A.
AU - Petrucci, F.
AU - Soldani, M.
AU - Wahl, H.
AU - Bandiera, L.
AU - Cotta Ramusino, A.
AU - Gianoli, A.
AU - Romagnoni, M.
AU - Sytov, A.
AU - Iacopini, E.
AU - Latino, G.
AU - Lenti, M.
AU - Gatignon, L.
AU - Massri, K.
AU - Dainton, J. B.
AU - Jones, R. W. L.
PY - 2023/11/21
Y1 - 2023/11/21
N2 - Measurement of the ultra-rare K+→π+νν¯ decay at the NA62 experiment at CERN requires high-performance particle identification to distinguish muons from pions. Calorimetric identification currently in use, based on a boosted decision tree algorithm, achieves a muon misidentification probability of 1.2 × 10−5 for a pion identification efficiency of 75% in the momentum range of 15–40 GeV/c. In this work, calorimetric identification performance is improved by developing an algorithm based on a convolutional neural network classifier augmented by a filter. Muon misidentification probability is reduced by a factor of six with respect to the current value for a fixed pion-identification efficiency of 75%. Alternatively, pion identification efficiency is improved from 72% to 91% for a fixed muon misidentification probability of 10−5.
AB - Measurement of the ultra-rare K+→π+νν¯ decay at the NA62 experiment at CERN requires high-performance particle identification to distinguish muons from pions. Calorimetric identification currently in use, based on a boosted decision tree algorithm, achieves a muon misidentification probability of 1.2 × 10−5 for a pion identification efficiency of 75% in the momentum range of 15–40 GeV/c. In this work, calorimetric identification performance is improved by developing an algorithm based on a convolutional neural network classifier augmented by a filter. Muon misidentification probability is reduced by a factor of six with respect to the current value for a fixed pion-identification efficiency of 75%. Alternatively, pion identification efficiency is improved from 72% to 91% for a fixed muon misidentification probability of 10−5.
KW - Fixed Target Experiments
KW - Rare Decay
KW - Branching fraction
KW - Flavour Physics
U2 - 10.1007/jhep11(2023)138
DO - 10.1007/jhep11(2023)138
M3 - Journal article
VL - 2023
JO - Journal of High Energy Physics
JF - Journal of High Energy Physics
SN - 1029-8479
IS - 11
ER -