Deep Generative Models for Fast Photon Shower Simulation in ATLAS

The ATLAS collaboration

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

The need for large-scale production of highly accurate simulated event samples for the extensive physics programme of the ATLAS experiment at the Large Hadron Collider motivates the development of new simulation techniques. Building on the recent success of deep learning algorithms, variational autoencoders and generative adversarial networks are investigated for modelling the response of the central region of the ATLAS electromagnetic calorimeter to photons of various energies. The properties of synthesised showers are compared with showers from a full detector simulation using geant4. Both variational autoencoders and generative adversarial networks are capable of quickly simulating electromagnetic showers with correct total energies and stochasticity, though the modelling of some shower shape distributions requires more refinement. This feasibility study demonstrates the potential of using such algorithms for ATLAS fast calorimeter simulation in the future and shows a possible way to complement current simulation techniques.

Original languageEnglish
Article number7
JournalComputing and Software for Big Science
Volume8
Issue number1
DOIs
StatePublished - Dec 2024

Funding

FundersFunder number
BSF-NSF
Australian Research Council
La Caixa Banking Foundation
Centre National pour la Recherche Scientifique et Technique
Fundação para a Ciência e a Tecnologia
Narodowe Centrum Nauki
National Science Foundation
CEA-DRF
Science and Technology Facilities Council
H2020 Marie Skłodowska-Curie Actions
Japan Society for the Promotion of Science
INFN-CNAF
Nederlandse Organisatie voor Wetenschappelijk Onderzoek
Ministerio de Ciencia e Innovación
Ministry of Science and Technology, Taiwan
Israel Science Foundation
Wallenberg Foundation
Leverhulme Trust
PROMETEO
Staatssekretariat für Bildung, Forschung und Innovation
Javna Agencija za Raziskovalno Dejavnost RS
Engineering Research Centers
Generalitat de Catalunya
Instituto Nazionale di Fisica Nucleare
Bundesministerium für Wissenschaft, Forschung und Wirtschaft
Austrian Science Fund
Narodowa Agencja Wymiany Akademickiej
Alabama Space Grant Consortium
Agencia Nacional de Investigación y Desarrollo
Bundesministerium für Bildung und Forschung
Canada Foundation for Innovation
Helmholtz-Gemeinschaft
Danmarks Grundforskningsfond
Conselho Nacional de Desenvolvimento Científico e Tecnológico
Karlsruhe Institute of Technology
Canarie
GridKA
Vermont Agency of Natural Resources
Göran Gustafssons Stiftelser
MIZŠ
California Department of Fish and Game
Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja
U.S. Department of Energy
European Cooperation in Science and Technology
EU-ESF
RGC
National Research Council
Fundação de Amparo à Pesquisa do Estado de São Paulo
Institutul de Fizică Atomică
Natural Sciences and Engineering Research Council of Canada
Nella and Leon Benoziyo Center for Neurological Diseases, Weizmann Institute of Science
GenT Programmes Generalitat Valenciana, Spain
Irish Rugby Football Union
Cantons of Bern and Geneva
Chinese Academy of Sciences
Defence Science Institute
Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Compute Canada
MNE
Agencia Nacional de Promoción Científica y Tecnológica
Royal Society
Minerva Foundation
National Research Foundation
European Regional Development Fund
CERN
Ministerstvo Školství, Mládeže a Tělovýchovy
Brookhaven National Laboratory
Alexander von Humboldt-Stiftung
Multiple Sclerosis Scientific Research Foundation
Horizon 2020
British Columbia Knowledge Development Fund
Ministry of Education, Culture, Sports, Science and Technology
National Natural Science Foundation of China
NDGFCC-IN2P3
Norwegian Financial Mechanism2014-2021
UNCESCI/013
DNSRCIN2P3-CNRS
CRC Health Group21/SCI/017
CRC Health Group

    Fingerprint

    Dive into the research topics of 'Deep Generative Models for Fast Photon Shower Simulation in ATLAS'. Together they form a unique fingerprint.

    Cite this