학술논문

Improved calorimetric particle identification in NA62 using machine learning techniques
Document Type
Original Paper
Author
Cortina Gil, E.Kleimenova, A.Minucci, E.Padolski, S.Petrov, P.Shaikhiev, A.Volpe, R.Fedorko, W.Numao, T.Petrov, Y.Velghe, B.Wong, V. W. S.Yu, M.Bryman, D.Fu, J.Hives, Z.Husek, T.Jerhot, J.Kampf, K.Zamkovsky, M.De Martino, B.Perrin-Terrin, M.Akmete, A. T.Aliberti, R.Khoriauli, G.Kunze, J.Lomidze, D.Peruzzo, L.Vormstein, M.Wanke, R.Dalpiaz, P.Fiorini, M.Mazzolari, A.Neri, I.Norton, A.Petrucci, F.Soldani, M.Wahl, H.Bandiera, L.Cotta Ramusino, A.Gianoli, A.Romagnoni, M.Sytov, A.Iacopini, E.Latino, G.Lenti, M.Lo Chiatto, P.Panichi, I.Parenti, A.Bizzeti, A.Bucci, F.Antonelli, A.Georgiev, G.Kozhuharov, V.Lanfranchi, G.Martellotti, S.Moulson, M.Spadaro, T.Tinti, G.Ambrosino, F.Capussela, T.Corvino, M.D’Errico, M.Di Filippo, D.Fiorenza, R.Giordano, R.Massarotti, P.Mirra, M.Napolitano, M.Rosa, I.Saracino, G.Anzivino, G.Brizioli, F.Imbergamo, E.Lollini, R.Piandani, R.Santoni, C.Barbanera, M.Cenci, P.Checcucci, B.Lubrano, P.Lupi, M.Pepe, M.Piccini, M.Costantini, F.Di Lella, L.Doble, N.Giorgi, M.Giudici, S.Lamanna, G.Lari, E.Pedreschi, E.Sozzi, M.Cerri, C.Fantechi, R.Pontisso, L.Spinella, F.Mannelli, I.D’Agostini, G.Raggi, M.Biagioni, A.Cretaro, P.Frezza, O.Leonardi, E.Lonardo, A.Turisini, M.Valente, P.Vicini, P.Ammendola, R.Bonaiuto, V.Fucci, A.Salamon, A.Sargeni, F.Arcidiacono, R.Bloch-Devaux, B.Boretto, M.Menichetti, E.Migliore, E.Soldi, D.Biino, C.Filippi, A.Marchetto, F.Briano Olvera, A.Engelfried, J.Estrada-Tristan, N.Reyes Santos, M. A.Boboc, P.Bragadireanu, A. M.Ghinescu, S. A.Hutanu, O. E.Bician, L.Blazek, T.Cerny, V.Kucerova, Z.Bernhard, J.Ceccucci, A.Ceoletta, M.Danielsson, H.De Simone, N.Duval, F.Döbrich, B.Federici, L.Gamberini, E.Gatignon, L.Guida, R.Hahn, F.Holzer, E. B.Jenninger, B.Koval, M.Laycock, P.Lehmann Miotto, G.Lichard, P.Mapelli, A.Marchevski, R.Massri, K.Noy, M.Palladino, V.Pinzino, J.Ryjov, V.Schuchmann, S.Venditti, S.Bache, T.Brunetti, M. B.Duk, V.Fascianelli, V.Fry, J. R.Gonnella, F.Goudzovski, E.Henshaw, J.Iacobuzio, L.Kenworthy, C.Lazzeroni, C.Lurkin, N.Newson, F.Parkinson, C.Romano, A.Sanders, J.Sergi, A.Sturgess, A.Swallow, J.Tomczak, A.Heath, H.Page, R.Trilov, S.Angelucci, B.Britton, D.Graham, C.Protopopescu, D.Carmignani, J.Dainton, J. B.Jones, R. W. L.Ruggiero, G.Fulton, L.Hutchcroft, D.Maurice, E.Wrona, B.Conovaloff, A.Cooper, P.Coward, D.Rubin, P.Baeva, A.Baigarashev, D.Emelyanov, D.Enik, T.Falaleev, V.Fedotov, S.Gorshanov, K.Gushchin, E.Kekelidze, V.Kereibay, D.Kholodenko, S.Khotyantsev, A.Korotkova, A.Kudenko, Y.Kurochka, V.Kurshetsov, V.Litov, L.Madigozhin, D.Medvedeva, M.Mefodev, A.Misheva, M.Molokanova, N.Movchan, S.Obraztsov, V.Okhotnikov, A.Ostankov, A.Polenkevich, I.Potrebenikov, Yu.Sadovskiy, A.Semenov, V.Shkarovskiy, S.Sugonyaev, V.Yushchenko, O.Zinchenko, A.
Source
Journal of High Energy Physics. 2023(11)
Subject
Fixed Target Experiments
Branching fraction
Rare Decay
Flavour Physics
Language
English
ISSN
1029-8479
Abstract
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.