Home > Research > Publications & Outputs > Improved calorimetric particle identification i...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Improved calorimetric particle identification in NA62 using machine learning techniques

Research output: Contribution to Journal/Magazine › Journal article › peer-review

E-pub ahead of print

Standard

Improved calorimetric particle identification in NA62 using machine learning techniques. / The NA62 Collaboration.
In: Journal of High Energy Physics, Vol. 2023, No. 11, 21.11.2023.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

The NA62 Collaboration 2023, 'Improved calorimetric particle identification in NA62 using machine learning techniques', Journal of High Energy Physics, vol. 2023, no. 11. https://doi.org/10.1007/jhep11(2023)138

APA

The NA62 Collaboration (2023). Improved calorimetric particle identification in NA62 using machine learning techniques. Journal of High Energy Physics, 2023(11). Advance online publication. https://doi.org/10.1007/jhep11(2023)138

Vancouver

The NA62 Collaboration. Improved calorimetric particle identification in NA62 using machine learning techniques. Journal of High Energy Physics. 2023 Nov 21;2023(11). Epub 2023 Nov 21. doi: 10.1007/jhep11(2023)138

Author

The NA62 Collaboration. / Improved calorimetric particle identification in NA62 using machine learning techniques. In: Journal of High Energy Physics. 2023 ; Vol. 2023, No. 11.

Bibtex

@article{57d1c15851144b94a1d41e24d522f1d0,
title = "Improved calorimetric particle identification in NA62 using machine learning techniques",
abstract = "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.",
keywords = "Fixed Target Experiments, Rare Decay, Branching fraction, Flavour Physics",
author = "{The NA62 Collaboration} and {Cortina Gil}, E. and A. Kleimenova and E. Minucci and S. Padolski and P. Petrov and A. Shaikhiev and R. Volpe and W. Fedorko and T. Numao and Y. Petrov and B. Velghe and Wong, {V. W. S.} and M. Yu and D. Bryman and J. Fu and Z. Hives and T. Husek and J. Jerhot and K. Kampf and M. Zamkovsky and {De Martino}, B. and M. Perrin-Terrin and Akmete, {A. T.} and R. Aliberti and G. Khoriauli and J. Kunze and D. Lomidze and L. Peruzzo and M. Vormstein and R. Wanke and P. Dalpiaz and M. Fiorini and A. Mazzolari and I. Neri and A. Norton and F. Petrucci and M. Soldani and H. Wahl and L. Bandiera and {Cotta Ramusino}, A. and A. Gianoli and M. Romagnoni and A. Sytov and E. Iacopini and G. Latino and M. Lenti and L. Gatignon and K. Massri and Dainton, {J. B.} and Jones, {R. W. L.}",
year = "2023",
month = nov,
day = "21",
doi = "10.1007/jhep11(2023)138",
language = "English",
volume = "2023",
journal = "Journal of High Energy Physics",
issn = "1029-8479",
publisher = "Springer Science and Business Media Deutschland GmbH",
number = "11",

}

RIS

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 -