Modeling hadronization using machine learning

Ilten, Philip; Menzo, Tony; Youssef, Ahmed; Zupan, Jure

doi:10.21468/SciPostPhys.14.3.027

SciPost Physics

Modeling hadronization using machine learning

Phil Ilten, Tony Menzo, Ahmed Youssef, Jure Zupan

SciPost Phys. 14, 027 (2023) · published 2 March 2023

doi: 10.21468/SciPostPhys.14.3.027
pdf
Submissions/Reports

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.

TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.14.3.027
TI  - Modeling hadronization using machine learning
PY  - 2023/03/02
UR  - https://scipost.org/SciPostPhys.14.3.027
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 14
IS  - 3
SP  - 027
A1  - Ilten, Philip
AU  - Menzo, Tony
AU  - Youssef, Ahmed
AU  - Zupan, Jure
AB  - 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.
ER  -

@Article{10.21468/SciPostPhys.14.3.027,
	title={{Modeling hadronization using machine learning}},
	author={Phil Ilten and Tony Menzo and  Ahmed Youssef and  Jure Zupan},
	journal={SciPost Phys.},
	volume={14},
	pages={027},
	year={2023},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.14.3.027},
	url={https://scipost.org/10.21468/SciPostPhys.14.3.027},
}

Cited by 7

Authors / Affiliation: mappings to Contributors and Organizations

See all Organizations.

¹ University of Cincinnati [UC]

Funders for the research work leading to this publication