Saved in:
Bibliographic Details
Main Authors: Hirvonen, H., Eskola, K. J., Niemi, H.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.02602
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929302097887232
author Hirvonen, H.
Eskola, K. J.
Niemi, H.
author_facet Hirvonen, H.
Eskola, K. J.
Niemi, H.
contents We demonstrate how deep convolutional neural networks can be trained to predict 2+1 D hydrodynamic simulation results for flow coefficients, mean-transverse-momentum and charged particle multiplicity from the initial energy density profile. We show that this method provides results that are accurate enough, so that one can use neural networks to reliably estimate multi-particle flow correlators. Additionally, we train networks that can take any model parameter as an additional input and demonstrate with a few examples that the accuracy remains good. The usage of neural networks can reduce the computation time needed in performing Bayesian analyses with multi-particle flow correlators by many orders of magnitude.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02602
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep learning for flow observables in high energy heavy-ion collisions
Hirvonen, H.
Eskola, K. J.
Niemi, H.
High Energy Physics - Phenomenology
Nuclear Theory
We demonstrate how deep convolutional neural networks can be trained to predict 2+1 D hydrodynamic simulation results for flow coefficients, mean-transverse-momentum and charged particle multiplicity from the initial energy density profile. We show that this method provides results that are accurate enough, so that one can use neural networks to reliably estimate multi-particle flow correlators. Additionally, we train networks that can take any model parameter as an additional input and demonstrate with a few examples that the accuracy remains good. The usage of neural networks can reduce the computation time needed in performing Bayesian analyses with multi-particle flow correlators by many orders of magnitude.
title Deep learning for flow observables in high energy heavy-ion collisions
topic High Energy Physics - Phenomenology
Nuclear Theory
url https://arxiv.org/abs/2404.02602