2023 Articles

Improved calorimetric particle identification in NA62 using machine learning techniques

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.; Fascianelli, Valeria

Measurement of the ultra-rare 𝐾⁺→ 𝜋⁺𝜈𝜈̄ 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.