Enhancing electromagnetic calorimeter signal reconstruction with machine learning-based noise discrimination
5 affiliations
- 1Saha Institute of Nuclear Physics- a CI of Homi Bhabha National Institute (Training School Complex, Anushaktinagar, Mumbai 400094, India)
- 2Institut Polytechnique de Paris
- 3Stony Brook University-SUNY
- 4University of Virginia
- 5Tata Institute of Fundamental Research
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 calorimeter 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 and the energy deposit pattern. In this paper, we investigate graph neural network (GNN) based algorithms as an alternative to rigid energy thresholds. The proposed approach exploits the full pulse-shape information together with the correlations among energy deposits in individual cells within an electromagnetic cluster. The study is performed using a standalone Geant4 simulation of an 11× 11 11 × 11 matrix of lead tungstate crystals. To simulate it in a more realistic way, we demonstrate that the machine learning based method significantly outperforms a simple threshold based strategy, achieving an improvement in the calorimeter energy resolution of up to 82% 82 % and recovering up to 83% 83 % of true signal cells within the calorimeter grid.
Related
- Application of sequence learning for predicting radiation damage of the CMS electromagnetic calorimeter
- Calibration of electromagnetic shower features in the CMS calorimeter with machine-learning techniques
- Kinematic Fitting of electromagnetic calorimeter data - an improved method
- Time-over-threshold versus pulse-height energy reconstruction in a PbWO4 calorimeter read out by SiPMs
- Understanding Energy Dependent Hadronic Calorimeter Response from a Machine Learning Perspective
BibTeX
@article{gupta2026enhancing,
title = {{Enhancing electromagnetic calorimeter signal reconstruction with machine learning-based noise discrimination}},
author = {Suman Das Gupta and Shamik Ghosh and Laltu Gazi and Shubham Dutta and Alexander Ledovskoy and Satyaki Bhattacharya and Shilpi Jain},
journal = {The European Physical Journal C},
year = {2026},
month = sep,
doi = {10.1140/epjc/s10052-026-16346-z},
url = {https://link.springer.com/10.1140/epjc/s10052-026-16346-z},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Enhancing electromagnetic calorimeter signal reconstruction with machine learning-based noise discrimination
AU - Suman Das Gupta
AU - Shamik Ghosh
AU - Laltu Gazi
AU - Shubham Dutta
AU - Alexander Ledovskoy
AU - Satyaki Bhattacharya
AU - Shilpi Jain
PY - 2026
DA - 2026/09/30
JO - The European Physical Journal C
DO - 10.1140/epjc/s10052-026-16346-z
UR - https://link.springer.com/10.1140/epjc/s10052-026-16346-z
AB - 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 calorimeter 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 and the energy deposit pattern. In this paper, we investigate graph neural network (GNN) based algorithms as an alternative to rigid energy thresholds. The proposed approach exploits the full pulse-shape information together with the correlations among energy deposits in individual cells within an electromagnetic cluster. The study is performed using a standalone Geant4 simulation of an 11× 11 11 × 11 matrix of lead tungstate crystals. To simulate it in a more realistic way, we demonstrate that the machine learning based method significantly outperforms a simple threshold based strategy, achieving an improvement in the calorimeter energy resolution of up to 82% 82 % and recovering up to 83% 83 % of true signal cells within the calorimeter grid.
SN - 1434-6052
ER -