Deep Generative Models for Fast Photon Shower Simulation in ATLAS
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10494659" target="_blank" >RIV/00216208:11320/24:10494659 - isvavai.cz</a>
Alternative codes found
RIV/68378271:_____/24:00616540
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=mxswPvBgpw" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=mxswPvBgpw</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s41781-023-00106-9" target="_blank" >10.1007/s41781-023-00106-9</a>
Alternative languages
Result language
angličtina
Original language name
Deep Generative Models for Fast Photon Shower Simulation in ATLAS
Original language description
The need for large-scale production of highly accurate simulated event samples for the extensive physics programme of theATLAS experiment at the Large Hadron Collider motivates the development of new simulation techniques. Building on therecent success of deep learning algorithms, variational autoencoders and generative adversarial networks are investigated formodelling the response of the central region of the ATLAS electromagnetic calorimeter to photons of various energies. Theproperties of synthesised showers are compared with showers from a full detector simulation using geant4. Both variationalautoencoders and generative adversarial networks are capable of quickly simulating electromagnetic showers with correcttotal energies and stochasticity, though the modelling of some shower shape distributions requires more refinement. Thisfeasibility study demonstrates the potential of using such algorithms for ATLAS fast calorimeter simulation in the futureand shows a possible way to complement current simulation techniques.
Czech name
—
Czech description
—
Classification
Type
J<sub>SC</sub> - Article in a specialist periodical, which is included in the SCOPUS database
CEP classification
—
OECD FORD branch
10300 - Physical sciences
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Computing and Software for Big Science
ISSN
2510-2036
e-ISSN
2510-2044
Volume of the periodical
8
Issue of the periodical within the volume
Mar
Country of publishing house
CH - SWITZERLAND
Number of pages
40
Pages from-to
7
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-85189330049