Enhancing Electromagnetic Calorimeter Signal Reconstruction with Machine Learning-Based Noise Discrimination

2025/09/14 by Suman Das Gupta, Gupta, Suman Das, Shamik Ghosh +11
Physics and Astronomy · #Calorimeter (particle physics) #Data Analysis #Energy (signal processing) #FOS: Physical sciences #High Energy Physics - Experiment (hep-ex) #Instrumentation and Detectors (physics.ins-det) #Noise (video) #Particle Detector Development and Performance #Radiation Detection and Scintillator Technologies #Resolution (logic) #SIGNAL (programming language) #Set (abstract data type) #Signal-to-noise ratio (imaging) #Statistics and Probability (physics.data-an) #Superconducting and THz Device Technology

paper · pdf · doi:10.48550/arxiv.2509.11291

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/09/14 · openalex created_date 2025/10/12 · openalex updated_date 2026/08/05

Abstract

Calorimeters operating in high-radiation environments are susceptible to damage, leading to increased noise that can significantly degrade energy resolution. A common way to mitigate noise is to apply a higher energy threshold on the cells, typically set a few standard deviations above the noise level. However, this method risks discarding cells with genuine energy deposits, worsening the energy resolution. In this paper we explore various machine learning (ML) algorithms that can replace a rigid threshold on the reconstructed cell energy and we demonstrate the improvement in calorimetric energy reconstruction and energy resolution that these ML methods can achieve in such challenging conditions.

Citations

• Dynamic Graph CNN for Learning on Point Clouds
• Dynamic Graph CNN for Learning on Point Clouds
• Graph Attention Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• ImageNet classification with deep convolutional neural networks
• A Comprehensive Survey on Graph Neural Networks

Related

• Cluster Reconstruction in Electromagnetic Calorimeters Using Machine Learning Methods
• Electron Energy Regression in the CMS High-Granularity Calorimeter Prototype
• Perspectives on the Calibration of CNN Energy Reconstruction in Highly Granular Calorimeters
• Machine Learning for the Cluster Reconstruction in the CALIFA Calorimeter at R3B
• Machine-learning correction for the calorimeter saturation of cosmic-rays ions with the Dark Matter Particle Explorer: towards the PeV scale