Modeling hadronization using machine learning

TL;DR

This paper introduces a machine learning-based hadronization model that replicates Pythia's pion emission distributions and generates full hadronization chains, offering a new approach to modeling particle physics processes.

Contribution

It develops and validates a conditional sliced-Wasserstein autoencoder for hadronization, marking a novel application of machine learning in this domain.

Findings

Model accurately replicates Pythia's pion emission distributions.

Generated hadronization chains match Pythia's multiplicities and kinematic distributions.

Demonstrates potential for machine learning in particle physics modeling.

Abstract

We present the first steps in the development of a new class of hadronization models utilizing machine learning techniques. We successfully implement, validate, and train a conditional sliced-Wasserstein autoencoder to replicate the Pythia generated kinematic distributions of first-hadron emissions, when the Lund string model of hadronization implemented in Pythia is restricted to the emissions of pions only. The trained models are then used to generate the full hadronization chains, with an IR cutoff energy imposed externally. The hadron multiplicities and cumulative kinematic distributions are shown to match the Pythia generated ones. We also discuss possible future generalizations of our results.