Home > Research > Publications & Outputs > Deep Generative Models for Fast Photon Shower S...

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Deep Generative Models for Fast Photon Shower Simulation in ATLAS

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Deep Generative Models for Fast Photon Shower Simulation in ATLAS. / The ATLAS collaboration ; Sanderswood, Izaac; Yexley, Melissa.
In: Computing and Software for Big Science, Vol. 8, No. 1, 7, 05.03.2024.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

The ATLAS collaboration, Sanderswood, I & Yexley, M 2024, 'Deep Generative Models for Fast Photon Shower Simulation in ATLAS', Computing and Software for Big Science, vol. 8, no. 1, 7. https://doi.org/10.1007/s41781-023-00106-9

APA

Vancouver

The ATLAS collaboration, Sanderswood I, Yexley M. Deep Generative Models for Fast Photon Shower Simulation in ATLAS. Computing and Software for Big Science. 2024 Mar 5;8(1):7. doi: 10.1007/s41781-023-00106-9

Author

The ATLAS collaboration ; Sanderswood, Izaac ; Yexley, Melissa. / Deep Generative Models for Fast Photon Shower Simulation in ATLAS. In: Computing and Software for Big Science. 2024 ; Vol. 8, No. 1.

Bibtex

@article{9d5c2332626b48c39b5d6f04b35b1668,
title = "Deep Generative Models for Fast Photon Shower Simulation in ATLAS",
abstract = "AbstractThe 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.",
keywords = "Nuclear and High Energy Physics, Computer Science (miscellaneous), Software",
author = "{The ATLAS collaboration} and A.E. Barton and I.A. Bertram and G. Borissov and E.V. Bouhova-Thacker and James Ferrando and H. Fox and R.C.W. Henderson and R.W.L. Jones and V. Kartvelishvili and P.A. Love and L. Meng and D. Muenstermann and K. Rybacki and Izaac Sanderswood and M. Smizanska and S. Spinali and A.M. Wharton and Melissa Yexley",
year = "2024",
month = mar,
day = "5",
doi = "10.1007/s41781-023-00106-9",
language = "English",
volume = "8",
journal = "Computing and Software for Big Science",
issn = "2510-2036",
publisher = "Springer Science and Business Media LLC",
number = "1",

}

RIS

TY - JOUR

T1 - Deep Generative Models for Fast Photon Shower Simulation in ATLAS

AU - The ATLAS collaboration

AU - Barton, A.E.

AU - Bertram, I.A.

AU - Borissov, G.

AU - Bouhova-Thacker, E.V.

AU - Ferrando, James

AU - Fox, H.

AU - Henderson, R.C.W.

AU - Jones, R.W.L.

AU - Kartvelishvili, V.

AU - Love, P.A.

AU - Meng, L.

AU - Muenstermann, D.

AU - Rybacki, K.

AU - Sanderswood, Izaac

AU - Smizanska, M.

AU - Spinali, S.

AU - Wharton, A.M.

AU - Yexley, Melissa

PY - 2024/3/5

Y1 - 2024/3/5

N2 - AbstractThe 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.

AB - AbstractThe 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.

KW - Nuclear and High Energy Physics

KW - Computer Science (miscellaneous)

KW - Software

U2 - 10.1007/s41781-023-00106-9

DO - 10.1007/s41781-023-00106-9

M3 - Journal article

VL - 8

JO - Computing and Software for Big Science

JF - Computing and Software for Big Science

SN - 2510-2036

IS - 1

M1 - 7

ER -