Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 20 min ago
PreprintCC BY 4.0HAL

Using Graph Neural Networks for the segmentation of overlapping objects in high granularity calorimeters

  • Matthieu Melennec
  • Frédéric Magniette
Open at sourcePDFDOICite

Abstract

High-granularity calorimeters at the High-Luminosity LHC require novel algorithms to resolve overlapping particle showers. We present an optimised Graph Neural Network (GNN) segmentation block that predicts node-level energy fractions to disentangle overlapping two-photon showers. By accelerating graph construction and convolution operations, our pipeline achieves competitive separation efficiency with significantly reduced algorithmic complexity.

Related

  1. End-to-end Particle Reconstruction with Transformers in High-Granularity Calorimeters
    Qiming Bao, Haotian Bi, Benedikt Maier +2
    arXivPreprintCC BY 4.0Full textApplied physics & instrumentationHigh-energy & particle physicsarXiv
  2. Optimising Geometric Deep Learning for Varied Reconstruction Tasks in High Granularity Calorimeters
    Matthieu Melennec, Frédéric Magniette
    HALPreprintCC BY 4.0Full textHigh-energy & particle physicsHALarXiv
  3. Task-preserving neural segmentation of overlapping shocks and vortex cores in compressible flows
    Ehsan Roohi
    arXivPreprintCC BY 4.0Full textComputational physicsFluid dynamicsarXiv
  4. Real-Time SiPM Pulse Deconvolution for a High-granularity Dual-readout Calorimeter with Neutral Networks
    Spencer Allen, Matteo Cremonesi, Jordan Damgov +6
    arXivPreprintarXiv licenceFull textApplied physics & instrumentationComputational physicsarXiv
  5. Precise measurement of the thermal quenching factor of alpha particles in Li2MoO4 cryogenic calorimeters
    M Girola, R Serino, M Biassoni +7
    HALPreprintCC BY 4.0Full textApplied physics & instrumentationHALarXiv

Cite

BibTeXRIS
BibTeX
@misc{melennec2026using,
  title = {{Using Graph Neural Networks for the segmentation of overlapping objects in high granularity calorimeters}},
  author = {Matthieu Melennec and Frédéric Magniette},
  howpublished = {HAL},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.34500},
  eprint = {2609.34500},
  archivePrefix = {arXiv},
  url = {https://hal.science/hal-05781887v1},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Using Graph Neural Networks for the segmentation of overlapping objects in high granularity calorimeters
AU  - Matthieu Melennec
AU  - Frédéric Magniette
PY  - 2026
DA  - 2026/09/29
PB  - HAL
DO  - 10.48550/arxiv.2609.34500
UR  - https://hal.science/hal-05781887v1
AB  - High-granularity calorimeters at the High-Luminosity LHC require novel algorithms to resolve overlapping particle showers. We present an optimised Graph Neural Network (GNN) segmentation block that predicts node-level energy fractions to disentangle overlapping two-photon showers. By accelerating graph construction and convolution operations, our pipeline achieves competitive separation efficiency with significantly reduced algorithmic complexity.
ER  -