1. Machine Learning Techniques for Pile-Up Rejection in Cryogenic Calorimeters
- Author
-
Fantini, G, Armatol, A, Armengaud, E, Armstrong, W, Augier, C, Avignone, FT, Azzolini, O, Barabash, A, Bari, G, Barresi, A, Baudin, D, Bellini, F, Benato, G, Beretta, M, Bergé, L, Biassoni, M, Billard, J, Boldrini, V, Branca, A, Brofferio, C, Bucci, C, Camilleri, J, Capelli, S, Cappelli, L, Cardani, L, Carniti, P, Casali, N, Cazes, A, Celi, E, Chang, C, Chapellier, M, Charrier, A, Chiesa, D, Clemenza, M, Colantoni, I, Collamati, F, Copello, S, Cova, F, Cremonesi, O, Creswick, RJ, Cruciani, A, D’Addabbo, A, D’Imperio, G, Dafinei, I, Danevich, FA, de Combarieu, M, De Jesus, M, de Marcillac, P, Dell’Oro, S, Domizio, S Di, Dompè, V, Drobizhev, A, Dumoulin, L, Fasoli, M, Faverzani, M, Ferri, E, Ferri, F, Ferroni, F, Figueroa-Feliciano, E, Formaggio, J, Franceschi, A, Fu, C, Fu, S, Fujikawa, BK, Gascon, J, Giachero, A, Gironi, L, Giuliani, A, Gorla, P, Gotti, C, Gras, P, Gros, M, Gutierrez, TD, Han, K, Hansen, EV, Heeger, KM, Helis, DL, Huang, HZ, Huang, RG, Imbert, L, Johnston, J, Juillard, A, Karapetrov, G, Keppel, G, Khalife, H, Kobychev, VV, Kolomensky, Yu G, Konovalov, S, Liu, Y, Loaiza, P, Ma, L, Madhukuttan, M, Mancarella, F, Mariam, R, Marini, L, Marnieros, S, Martinez, M, Maruyama, RH, Mauri, B, and Mayer, D
- Subjects
Convolutional neural networks ,Machine learning ,Cryogenic calorimeters ,CUPID ,Neutrinoless double beta decay ,Majorana ,Pile-up ,Mathematical Physics ,Classical Physics ,Condensed Matter Physics ,General Physics - Abstract
CUORE Upgrade with Particle IDentification (CUPID) is a foreseen ton-scale array of Li2MoO4 (LMO) cryogenic calorimeters with double readout of heat and light signals. Its scientific goal is to fully explore the inverted hierarchy of neutrino masses in the search for neutrinoless double beta decay of 100Mo. Pile-up of standard double beta decay of the candidate isotope is a relevant background. We generate pile-up heat events via injection of Joule heater pulses with a programmable waveform generator in a small array of LMO crystals operated underground in the Laboratori Nazionali del Gran Sasso, Italy. This allows to label pile-up pulses and control both time difference and underlying amplitudes of individual heat pulses in the data. We present the performance of supervised learning classifiers on data and the attained pile-up rejection efficiency.
- Published
- 2022