Robust and Generalizable Background Subtraction on Images of Calorimeter Jets using Unsupervised Generative Learning

TL;DR

This paper presents an unsupervised generative learning approach for background subtraction in calorimeter jet images, outperforming traditional methods and demonstrating robustness in realistic, modified scenarios, thus enabling more precise physics measurements.

Contribution

Introduces the first unsupervised unpaired generative model for full detector jet background subtraction in high-energy physics.

Findings

Outperforms conventional subtraction algorithms in fidelity.

Maintains high fidelity on modified jet signals in out-of-distribution tests.

Demonstrates robustness and potential for application in real experimental data.

Abstract

Accurate separation of signal from background is one of the main challenges for precision measurements across high-energy and nuclear physics. Conventional supervised learning methods are insufficient here because the required paired signal and background examples are impossible to acquire in real experiments. Here, we introduce an unsupervised unpaired image-to-image translation neural network that learns to separate the signal and background from the input experimental data using cycle-consistency principles. We demonstrate the efficacy of this approach using images composed of simulated calorimeter data from the sPHENIX experiment, where physics signals (jets) are immersed in the extremely dense and fluctuating heavy-ion collision environment. Our method outperforms conventional subtraction algorithms in fidelity and overcomes the limitations of supervised methods. Furthermore, we evaluated the model's robustness in an out-of-distribution test scenario designed to emulate modified jets as in real experimental data. The model, trained on a simpler dataset, maintained its high fidelity on a more realistic, highly modified jet signal. This work represents the first use of unsupervised unpaired generative models for full detector jet background subtraction and offers a path for novel applications in real experimental data, enabling high-precision analyses across a wide range of imaging-based experiments.