Particle identification with machine learning in ALICE Run 3

TL;DR

This paper presents advanced machine learning techniques, including domain adaptation neural networks, to improve particle identification in the ALICE experiment, leveraging more detector data for better accuracy in Run 3.

Contribution

It introduces domain adaptation neural networks with feature embedding and attention mechanisms for particle identification, enhancing performance over traditional methods.

Findings

Domain adaptation improves classification accuracy.

ML models outperform standard PID techniques.

Integration with ALICE framework enables real-world application.

Abstract

The main focus of the ALICE experiment, quark--gluon plasma measurements, requires accurate particle identification (PID). The ALICE subdetectors allow identifying particles over a broad momentum interval ranging from about 100 MeV/c up to 20 GeV/c. However, a machine learning (ML) model can explore more detector information. During LHC Run 2, preliminary studies with Random Forests obtained much higher efficiencies and purities for selected particles than standard techniques. For Run 3, we investigate Domain Adaptation Neural Networks that account for the discrepancies between the Monte Carlo simulations and the experimental data. Preliminary studies show that domain adaptation improves particle classification. Moreover, the solution is extended with Feature Set Embedding and attention to give the network more flexibility to train on data with various sets of detector signals. PID ML is already integrated with the ALICE Run 3 Analysis Framework. Preliminary results for the PID of selected particle species, including real-world analyzes, are discussed as well as the possible optimizations.