Transformer-based machine learning using low-level calorimeter signals for collimated photon identification at collider experiments
Abstract
Electromagnetic calorimeters provide essential information for reconstructing and selecting both Standard Model (SM) and potential beyond the SM physics events at high-energy particle colliders. The fine-grained segmentation of modern calorimeters captures rich information about the internal structure of particle showers, much of which is discarded by conventional high-level reconstruction methods. In this work, we leverage calorimeter cell-level information to classify highly collimated diphoton signatures, arising from the decay of light axion-like particles, from isolated single-photon showers. We systematically compare a range of machine learning architectures, spanning high-level, shower shape variable-based approaches and direct cell-level methods. Cell-level machine learning shows significantly superior classification ability, with a Transformer in particular representing the best performance among six different architectures studied, and an MLP Mixer representing a resource-constrained alternative for potential real-time, trigger-level applications. Beyond classification, the Transformer model developed enables direct invariant mass regression from calorimeter cells, improving the characterization of light resonances and providing an additional handle in reducing the π0 and η fake photon backgrounds. These results demonstrate that cell-level machine learning methods can extend calorimeter-based particle identification and performance well beyond the capabilities of current conventional techniques.
Related
- Application of sequence learning for predicting radiation damage of the CMS electromagnetic calorimeter
- Enhancing electromagnetic calorimeter signal reconstruction with machine learning-based noise discrimination
- Understanding Energy Dependent Hadronic Calorimeter Response from a Machine Learning Perspective
- Calibration of electromagnetic shower features in the CMS calorimeter with machine-learning techniques
- High-charge collimated and energy-selected laser-driven MeV electron beams produced by magnetic selection
BibTeX
@misc{matos2026transformerbased,
title = {{Transformer-based machine learning using low-level calorimeter signals for collimated photon identification at collider experiments}},
author = {Gabriel Matos and Lauren Larson and Abhilasha Dave and Maria Bressan and Azal Amer and Cindy Liu and Nikiforos Nikiforou and Jonathan Long and Timothy Andeen and John Parsons and Julia Gonski},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2607.08175},
eprint = {2607.08175},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.08175},
}
RIS
TY - UNPB
TI - Transformer-based machine learning using low-level calorimeter signals for collimated photon identification at collider experiments
AU - Gabriel Matos
AU - Lauren Larson
AU - Abhilasha Dave
AU - Maria Bressan
AU - Azal Amer
AU - Cindy Liu
AU - Nikiforos Nikiforou
AU - Jonathan Long
AU - Timothy Andeen
AU - John Parsons
AU - Julia Gonski
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2607.08175
UR - https://arxiv.org/abs/2607.08175
AB - Electromagnetic calorimeters provide essential information for reconstructing and selecting both Standard Model (SM) and potential beyond the SM physics events at high-energy particle colliders. The fine-grained segmentation of modern calorimeters captures rich information about the internal structure of particle showers, much of which is discarded by conventional high-level reconstruction methods. In this work, we leverage calorimeter cell-level information to classify highly collimated diphoton signatures, arising from the decay of light axion-like particles, from isolated single-photon showers. We systematically compare a range of machine learning architectures, spanning high-level, shower shape variable-based approaches and direct cell-level methods. Cell-level machine learning shows significantly superior classification ability, with a Transformer in particular representing the best performance among six different architectures studied, and an MLP Mixer representing a resource-constrained alternative for potential real-time, trigger-level applications. Beyond classification, the Transformer model developed enables direct invariant mass regression from calorimeter cells, improving the characterization of light resonances and providing an additional handle in reducing the π^0 and η fake photon backgrounds. These results demonstrate that cell-level machine learning methods can extend calorimeter-based particle identification and performance well beyond the capabilities of current conventional techniques.
ER -