Development and Explainability of Models for Machine-Learning-Based Reconstruction of Signals in Particle Detectors

Kalina Dimitrova; Venelin Kozhuharov; Peicho Petkov

doi:10.3390/particles8020048

Development and Explainability of Models for Machine-Learning-Based Reconstruction of Signals in Particle Detectors

Instrumentation and Detectors 2025-04-25 v1 High Energy Physics - Experiment Computational Physics

Authors: Kalina Dimitrova , Venelin Kozhuharov , Peicho Petkov

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

Machine learning methods are being introduced at all stages of data reconstruction and analysis in various high-energy physics experiments. We present the development and application of convolutional neural networks with modified autoencoder architecture for the reconstruction of the pulse arrival time and amplitude in individual scintillating crystals in electromagnetic calorimeters and other detectors. The network performance is discussed as well as the application of xAI methods for further investigation of the algorithm and improvement of the output accuracy.

Keywords

machine learning convolutional neural networks autoencoder pulse arrival time amplitude reconstruction explainable AI electromagnetic calorimeter

Cite

@article{arxiv.2504.17272,
  title  = {Development and Explainability of Models for Machine-Learning-Based Reconstruction of Signals in Particle Detectors},
  author = {Kalina Dimitrova and Venelin Kozhuharov and Peicho Petkov},
  journal= {arXiv preprint arXiv:2504.17272},
  year   = {2025}
}

Comments

This article was published in Particles, 2025, 8, 48, DOI: 10.3390/particles8020048

Development and Explainability of Models for Machine-Learning-Based Reconstruction of Signals in Particle Detectors

Abstract

Keywords

Cite

Comments

Related papers