Deep Image Reconstruction for Background Subtraction in Heavy-Ion Collisions

TL;DR

DeepSub introduces a novel machine learning approach using Swin Transformer layers to effectively subtract heavy-ion backgrounds, enabling more precise jet measurements in complex collision environments.

Contribution

This paper presents the first ML-based full-event background subtraction method for heavy-ion collisions, improving accuracy over traditional techniques.

Findings

DeepSub accurately reproduces jet $p_T$ and mass.

It outperforms existing methods in jet substructure observables.

Enables precision measurements in previously inaccessible regimes.

Abstract

Jet reconstruction in an ultra-relativistic heavy-ion collision suffers from a notoriously large, fluctuating thermal background. Traditional background subtraction methods struggle to remove this soft background while preserving the jet's hard substructure. In this Letter, we present DeepSub, the first machine learning-based approach for full-event background subtraction. DeepSub utilizes a model based on Swin Transformer layers to denoise jet images and disentangle hard jets from the heavy-ion background. DeepSub significantly outperforms existing subtraction techniques by reproducing key jet observables such as jet $p_\mathrm{T}$ and mass, and substructure observables such as girth and the energy correlation function, at the sub-percent to percent level. As such, DeepSub paves the way for precision heavy-ion measurements in hitherto inaccessible kinematic regimes.