Deep Generative Models for Fast Photon Shower Simulation in ATLAS



Aad, G, Abbott, B, Abbott, DC, Abud, A Abed, Abeling, K, Abhayasinghe, DK, Abidi, SH, Aboulhorma, A, Abramowicz, H, Abreu, H
et al (show 2852 more authors) (2024) Deep Generative Models for Fast Photon Shower Simulation in ATLAS. Computing and Software for Big Science, 8 (1). 7-.

Access the full-text of this item by clicking on the Open Access link.

Abstract

<jats:title>Abstract</jats:title><jats:p>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 <jats:sc>geant4</jats:sc>. 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.</jats:p>

Item Type: Article
Divisions: Faculty of Science and Engineering > School of Physical Sciences
Depositing User: Symplectic Admin
Date Deposited: 18 Mar 2024 10:04
Last Modified: 18 Mar 2024 10:05
DOI: 10.1007/s41781-023-00106-9
Open Access URL: https://link.springer.com/article/10.1007/s41781-0...
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3179613