Improved calorimetric particle identification in NA62 using machine learning techniques

A bstract Measurement of the ultra-rare K + → π + ν ν ¯ 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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:JHEP 2023-11, Vol.2023 (11), p.138-15, Article 138
Hauptverfasser: Minucci, E., Petrov, P., Shaikhiev, A., Volpe, R., Fedorko, W., Yu, M., Fu, J., Jerhot, J., Kampf, K., De Martino, B., Perrin-Terrin, M., Aliberti, R., Khoriauli, G., Kunze, J., Lomidze, D., Vormstein, M., Dalpiaz, P., Soldani, M., Wahl, H., Cotta Ramusino, A., Romagnoni, M., Sytov, A., Iacopini, E., Lo Chiatto, P., Panichi, I., Antonelli, A., Lanfranchi, G., Tinti, G., Capussela, T., Corvino, M., Napolitano, M., Anzivino, G., Piandani, R., Cenci, P., Checcucci, B., Costantini, F., Di Lella, L., Lamanna, G., Pedreschi, E., Fantechi, R., Mannelli, I., D’Agostini, G., Raggi, M., Lonardo, A., Turisini, M., Vicini, P., Fucci, A., Salamon, A., Arcidiacono, R., Boretto, M., Migliore, E., Briano Olvera, A., Boboc, P., Bragadireanu, A. M., Ghinescu, S. A., Hutanu, O. E., Blazek, T., Cerny, V., Bernhard, J., Danielsson, H., De Simone, N., Duval, F., Gatignon, L., Guida, R., Holzer, E. B., Jenninger, B., Laycock, P., Lichard, P., Mapelli, A., Noy, M., Palladino, V., Pinzino, J., Schuchmann, S., Brunetti, M. B., Duk, V., Fascianelli, V., Goudzovski, E., Iacobuzio, L., Lazzeroni, C., Lurkin, N., Newson, F., Sergi, A., Tomczak, A., Trilov, S., Carmignani, J., Fulton, L., Hutchcroft, D., Coward, D., Baeva, A., Falaleev, V., Fedotov, S., Kereibay, D., Khotyantsev, A., Kurshetsov, V., Medvedeva, M., Movchan, S., Obraztsov, V., Sadovskiy, A., Semenov, V., Zinchenko, A.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A bstract Measurement of the ultra-rare K + → π + ν ν ¯ 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 .
ISSN:1029-8479
1029-8479
DOI:10.1007/JHEP11(2023)138