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

• Published in: European physical journal plus Vol. 139; no. 8; p. 723
• Main Authors: Moretti, Roberto, Rossi, Marco, Biassoni, Matteo, Giachero, Andrea, Grossi, Michele, Guffanti, Daniele, Labranca, Danilo, Terranova, Francesco, Vallecorsa, Sofia
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 13-08-2024; Springer Nature B.V
• Subjects: Algorithms; Applied and Technical Physics; Argon; Artificial neural networks; Atomic; Charged particles; Classification; Coders; Complex Systems; Condensed Matter Physics; Dark matter; Detectors; Electric fields; Energy; Machine learning; Mathematical and Computational Physics; Molecular; Neutrinos; Optical and Plasma Physics; Physics; Physics and Astronomy; Regular Article; Sensors; Supernovae; Theoretical; Transformers; Wire
• ISSN: 2190-5444; 2190-5444
• DOI: 10.1140/epjp/s13360-024-05287-9

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”).