The physics potential of massive liquid argon TPCs in the low-energy regime is still to be fully reaped because few-hits events encode information that can hardly be exploited by conventional classification algorithms. Machine learning (ML) techniques give their best in these types of classification problems. In this paper, we evaluate their performance against conventional (deterministic) algorithms. We demonstrate that both Convolutional Neural Networks (CNN) and Transformer-Encoder methods outperform deterministic algorithms in one of the most challenging classification problems of low-energy physics (single- versus double-beta events). We discuss the advantages and pitfalls of Transformer-Encoder methods versus CNN and employ these methods to optimize the detector parameters, with an emphasis on the DUNE Phase II detectors (“Module of Opportunity”).

Moretti, R., Rossi, M., Biassoni, M., Giachero, A., Grossi, M., Guffanti, D., et al. (2024). Assessment of few-hits machine learning classification algorithms for low-energy physics in liquid argon detectors. THE EUROPEAN PHYSICAL JOURNAL PLUS, 139(8) [10.1140/epjp/s13360-024-05287-9].

Assessment of few-hits machine learning classification algorithms for low-energy physics in liquid argon detectors

Moretti, R
;
Biassoni, M;Giachero, A;Grossi, M;Guffanti, D;Labranca, D;Terranova, F;
2024

Abstract

The physics potential of massive liquid argon TPCs in the low-energy regime is still to be fully reaped because few-hits events encode information that can hardly be exploited by conventional classification algorithms. Machine learning (ML) techniques give their best in these types of classification problems. In this paper, we evaluate their performance against conventional (deterministic) algorithms. We demonstrate that both Convolutional Neural Networks (CNN) and Transformer-Encoder methods outperform deterministic algorithms in one of the most challenging classification problems of low-energy physics (single- versus double-beta events). We discuss the advantages and pitfalls of Transformer-Encoder methods versus CNN and employ these methods to optimize the detector parameters, with an emphasis on the DUNE Phase II detectors (“Module of Opportunity”).
Articolo in rivista - Articolo scientifico
liquid argon, double beta decay, machine learning, transformer
English
13-ago-2024
2024
139
8
723
none
Moretti, R., Rossi, M., Biassoni, M., Giachero, A., Grossi, M., Guffanti, D., et al. (2024). Assessment of few-hits machine learning classification algorithms for low-energy physics in liquid argon detectors. THE EUROPEAN PHYSICAL JOURNAL PLUS, 139(8) [10.1140/epjp/s13360-024-05287-9].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/434838
Citazioni
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
Social impact