Denoising Graph Super-Resolution towards Improved Collider Event Reconstruction

2024-09-24

arXiv.org

AI Summary

To address the limited spatial resolution and noise contamination in calorimeters at high-energy colliders, this work proposes a graph-structured super-resolution method that jointly performs upsampling and denoising of detector data in software. The approach innovatively integrates graph-based super-resolution with particle-flow reconstruction into an interpretable, end-to-end particle-flow model: first, a graph neural network models sparse calorimeter responses and reconstructs fine-grained spatial structures via super-resolution; then, particle-flow graphs are constructed and embedded within an LHC-like reconstruction pipeline to enable physics-constrained joint optimization. Experiments demonstrate that, without hardware modifications, the method significantly improves both energy and position reconstruction accuracy. It thus provides an efficient, low-cost software upgrade pathway for current and future collider experiments.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurately reconstructing particles from detector data is a critical challenge in experimental particle physics, where the spatial resolution of calorimeters has a crucial impact. This study explores the integration of super-resolution techniques into an LHC-like reconstruction pipeline to effectively enhance the granularity of calorimeter data and suppress noise. We find that this software preprocessing step can significantly improve reconstruction quality without physical changes to detectors. To demonstrate the impact of our approach, we propose a novel particle flow model that offers enhanced particle reconstruction quality and interpretability. These advancements underline the potential of super-resolution to impact both current and future particle physics experiments.

Problem

• Enhancing calorimeter granularity via super-resolution techniques
• Suppressing noise in collider event reconstruction
• Improving particle reconstruction quality without detector modifications

Innovation

• Transformer-based particle flow model
• Super-resolution enhances calorimeter granularity
• Software preprocessing improves reconstruction quality