Image and Point-cloud Classification for Jet Analysis in High-Energy Physics: A survey

TL;DR

This survey comprehensively maps the use of ML and DL for jet analysis in high-energy physics, detailing Jet representations as images and point clouds, representative datasets and preprocessing pipelines, and a wide spectrum of models from MLPs to GNNs and Transformers. It documents state-of-the-art architectures (e.g., ParticleNet, LorentzNet, ParT, PartT) and their performance on Jet tagging and classification tasks, while discussing datasets, evaluation metrics, and real-world considerations such as systematics and simulation biases. The paper highlights future directions including quantum ML, federated learning, and interpretable, uncertainty-aware models, aiming to guide researchers toward robust, scalable, and physics-informed AI approaches for upcoming colliders and datasets. Overall, it positions Jet DL as a mature and rapidly evolving area with significant potential for improving signal discrimination, detector-level analyses, and fast simulation in HL-LHC and future hadron colliders.

Abstract

Nowadays, there has been a growing trend in the field of high-energy physics (HEP), in both its experimental and phenomenological studies, to incorporate machine learning (ML) and its specialized branch, deep learning (DL). This review paper provides a thorough illustration of these applications using different ML and DL approaches. The first part of the paper examines the basics of various particle physics types and establishes guidelines for assessing particle physics alongside the available learning models. Next, a detailed classification is provided for representing Jets that are reconstructed in high-energy collisions, mainly in proton-proton collisions at well-defined beam energies. This section covers various datasets, preprocessing techniques, and feature extraction and selection methods. The presented techniques can be applied to future hadron-hadron colliders (HHC), such as the high-luminosity LHC (HL-LHC) and the future circular collider - hadron-hadron (FCChh). The authors then explore several AI techniques analyses designed specifically for both image and point-cloud (PC) data in HEP. Additionally, a closer look is taken at the classification associated with Jet tagging in hadron collisions. In this review, various state-of-the-art (SOTA) techniques in ML and DL are examined, with a focus on their implications for HEP demands. More precisely, this discussion addresses various applications in extensive detail, such as Jet tagging, Jet tracking, particle classification, and more. The review concludes with an analysis of the current state of HEP using DL methodologies. It highlights the challenges and potential areas for future research, which are illustrated for each application.

Figures (18)

• Figure 1: Mind-map of the proposed review.
• Figure 2: Visualization of decay involving a reconstructed Jet and a secondary vertex, showcasing various noteworthy features novak2020sissa.
• Figure 3: Jet images summed online and categorized into different channels employed in the analysis within the 100-200 GeV $p_T$ range.
• Figure 4: Taxonomy of ML and DL-based HEP techniques for Jet classification, with associated preprocessing, metrics, simulation tools and datasets.
• Figure 5: (a) Diagram illustrating the localized explanation of an event classifier with the SHAP method. (b) Localized SHAP explanation represented using a waterfall plot. It can be observed that the SHAP values are associated with individual event features. The classifier's prediction (XGBoost) is $f(x) = 1.218$, while the base value is $E[f(x)] = 0.123$. In this context, the feature "m_wwbb" contributes positively with a SHAP value of +0.77, increasing the prediction, whereas the feature "m_wbb" has a SHAP value of -0.6, reducing the prediction.