Hadron Identification Prospects with Granular Calorimeters

In this work we consider the problem of determining the identity of hadrons at high energies based on the topology of their energy depositions in dense matter, along with the time of the interactions. Using GEANT4 simulations of a homogeneous lead tungstate calorimeter with high transverse and longi...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrea De Vita, Abhishek, Max Aehle, Muhammad Awais, Alessandro Breccia, Riccardo Carroccio, Long Chen, Tommaso Dorigo, Nicolas R. Gauger, Ralf Keidel, Jan Kieseler, Enrico Lupi, Federico Nardi, Xuan Tung Nguyen, Fredrik Sandin, Kylian Schmidt, Pietro Vischia, Joseph Willmore
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Particles
Subjects:
Online Access:https://www.mdpi.com/2571-712X/8/2/58
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164618943528960
author Andrea De Vita
Abhishek
Max Aehle
Muhammad Awais
Alessandro Breccia
Riccardo Carroccio
Long Chen
Tommaso Dorigo
Nicolas R. Gauger
Ralf Keidel
Jan Kieseler
Enrico Lupi
Federico Nardi
Xuan Tung Nguyen
Fredrik Sandin
Kylian Schmidt
Pietro Vischia
Joseph Willmore
author_facet Andrea De Vita
Abhishek
Max Aehle
Muhammad Awais
Alessandro Breccia
Riccardo Carroccio
Long Chen
Tommaso Dorigo
Nicolas R. Gauger
Ralf Keidel
Jan Kieseler
Enrico Lupi
Federico Nardi
Xuan Tung Nguyen
Fredrik Sandin
Kylian Schmidt
Pietro Vischia
Joseph Willmore
author_sort Andrea De Vita
collection DOAJ
description In this work we consider the problem of determining the identity of hadrons at high energies based on the topology of their energy depositions in dense matter, along with the time of the interactions. Using GEANT4 simulations of a homogeneous lead tungstate calorimeter with high transverse and longitudinal segmentation, we investigated the discrimination of protons, positive pions, and positive kaons at 100 GeV. The analysis focuses on the impact of calorimeter granularity by progressively merging detector cells and extracting features like energy deposition patterns and timing information. Two machine learning approaches, XGBoost and fully connected deep neural networks, were employed to assess the classification performance across particle pairs. The results indicate that fine segmentation improves particle discrimination, with higher granularity yielding more detailed characterization of energy showers. Additionally, the results highlight the importance of shower radius, energy fractions, and timing variables in distinguishing particle types. The XGBoost model demonstrated computational efficiency and interpretability advantages over deep learning for tabular data structures, while achieving similar classification performance. This motivates further work required to combine high- and low-level feature analysis, e.g., using convolutional and graph-based neural networks, and extending the study to a broader range of particle energies and types.
format Article
id doaj-art-70a2c6638dec49a9b6078a35ee0f023a
institution OA Journals
issn 2571-712X
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Particles
spelling doaj-art-70a2c6638dec49a9b6078a35ee0f023a2025-08-20T02:21:57ZengMDPI AGParticles2571-712X2025-05-01825810.3390/particles8020058Hadron Identification Prospects with Granular CalorimetersAndrea De Vita0Abhishek1Max Aehle2Muhammad Awais3Alessandro Breccia4Riccardo Carroccio5Long Chen6Tommaso Dorigo7Nicolas R. Gauger8Ralf Keidel9Jan Kieseler10Enrico Lupi11Federico Nardi12Xuan Tung Nguyen13Fredrik Sandin14Kylian Schmidt15Pietro Vischia16Joseph Willmore17Dipartimento di Fisica e Astronomia, Università di Padova, Via F. Marzolo 8, 35131 Padova, ItalyNational Institute of Science Education and Research, Jatni 752050, IndiaScientific Computing, University of Kaiserslautern-Landau (RPTU), Paul-Ehrlich-Straße, 67663 Kaiserslautern, GermanyDipartimento di Fisica e Astronomia, Università di Padova, Via F. Marzolo 8, 35131 Padova, ItalyDipartimento di Fisica e Astronomia, Università di Padova, Via F. Marzolo 8, 35131 Padova, ItalyDipartimento di Fisica e Astronomia, Università di Padova, Via F. Marzolo 8, 35131 Padova, ItalyScientific Computing, University of Kaiserslautern-Landau (RPTU), Paul-Ehrlich-Straße, 67663 Kaiserslautern, GermanyDepartment of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 97187 Luleå, SwedenScientific Computing, University of Kaiserslautern-Landau (RPTU), Paul-Ehrlich-Straße, 67663 Kaiserslautern, GermanyScientific Computing, University of Kaiserslautern-Landau (RPTU), Paul-Ehrlich-Straße, 67663 Kaiserslautern, GermanyInstitute for Experimental Particle Physics, Karlsruhe Institute of Technology, 76131 Karlsruhe, GermanyDipartimento di Fisica e Astronomia, Università di Padova, Via F. Marzolo 8, 35131 Padova, ItalyDipartimento di Fisica e Astronomia, Università di Padova, Via F. Marzolo 8, 35131 Padova, ItalyINFN, Sezione di Padova, Via F. Marzolo 8, 35131 Padova, ItalyDepartment of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 97187 Luleå, SwedenInstitute for Experimental Particle Physics, Karlsruhe Institute of Technology, 76131 Karlsruhe, GermanyDepartment of Physics, Universidad de Oviedo and ICTEA, 33004 Oviedo, SpainINFN, Sezione di Padova, Via F. Marzolo 8, 35131 Padova, ItalyIn this work we consider the problem of determining the identity of hadrons at high energies based on the topology of their energy depositions in dense matter, along with the time of the interactions. Using GEANT4 simulations of a homogeneous lead tungstate calorimeter with high transverse and longitudinal segmentation, we investigated the discrimination of protons, positive pions, and positive kaons at 100 GeV. The analysis focuses on the impact of calorimeter granularity by progressively merging detector cells and extracting features like energy deposition patterns and timing information. Two machine learning approaches, XGBoost and fully connected deep neural networks, were employed to assess the classification performance across particle pairs. The results indicate that fine segmentation improves particle discrimination, with higher granularity yielding more detailed characterization of energy showers. Additionally, the results highlight the importance of shower radius, energy fractions, and timing variables in distinguishing particle types. The XGBoost model demonstrated computational efficiency and interpretability advantages over deep learning for tabular data structures, while achieving similar classification performance. This motivates further work required to combine high- and low-level feature analysis, e.g., using convolutional and graph-based neural networks, and extending the study to a broader range of particle energies and types.https://www.mdpi.com/2571-712X/8/2/58particle detectorscalorimetryparticle identificationphysicsmachine learning
spellingShingle Andrea De Vita
Abhishek
Max Aehle
Muhammad Awais
Alessandro Breccia
Riccardo Carroccio
Long Chen
Tommaso Dorigo
Nicolas R. Gauger
Ralf Keidel
Jan Kieseler
Enrico Lupi
Federico Nardi
Xuan Tung Nguyen
Fredrik Sandin
Kylian Schmidt
Pietro Vischia
Joseph Willmore
Hadron Identification Prospects with Granular Calorimeters
Particles
particle detectors
calorimetry
particle identification
physics
machine learning
title Hadron Identification Prospects with Granular Calorimeters
title_full Hadron Identification Prospects with Granular Calorimeters
title_fullStr Hadron Identification Prospects with Granular Calorimeters
title_full_unstemmed Hadron Identification Prospects with Granular Calorimeters
title_short Hadron Identification Prospects with Granular Calorimeters
title_sort hadron identification prospects with granular calorimeters
topic particle detectors
calorimetry
particle identification
physics
machine learning
url https://www.mdpi.com/2571-712X/8/2/58
work_keys_str_mv AT andreadevita hadronidentificationprospectswithgranularcalorimeters
AT abhishek hadronidentificationprospectswithgranularcalorimeters
AT maxaehle hadronidentificationprospectswithgranularcalorimeters
AT muhammadawais hadronidentificationprospectswithgranularcalorimeters
AT alessandrobreccia hadronidentificationprospectswithgranularcalorimeters
AT riccardocarroccio hadronidentificationprospectswithgranularcalorimeters
AT longchen hadronidentificationprospectswithgranularcalorimeters
AT tommasodorigo hadronidentificationprospectswithgranularcalorimeters
AT nicolasrgauger hadronidentificationprospectswithgranularcalorimeters
AT ralfkeidel hadronidentificationprospectswithgranularcalorimeters
AT jankieseler hadronidentificationprospectswithgranularcalorimeters
AT enricolupi hadronidentificationprospectswithgranularcalorimeters
AT federiconardi hadronidentificationprospectswithgranularcalorimeters
AT xuantungnguyen hadronidentificationprospectswithgranularcalorimeters
AT fredriksandin hadronidentificationprospectswithgranularcalorimeters
AT kylianschmidt hadronidentificationprospectswithgranularcalorimeters
AT pietrovischia hadronidentificationprospectswithgranularcalorimeters
AT josephwillmore hadronidentificationprospectswithgranularcalorimeters