Cargando…

Deep generative models for fast shower simulation in ATLAS

The need for large scale and high fidelity simulated samples for the extensive physics program 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 Auto-Encoders and Genera...

Descripción completa

Detalles Bibliográficos
Autor principal: Gadatsch, Stefan
Lenguaje:eng
Publicado: 2018
Materias:
Acceso en línea:http://cds.cern.ch/record/2650726
_version_ 1780960822702374912
author Gadatsch, Stefan
author_facet Gadatsch, Stefan
author_sort Gadatsch, Stefan
collection CERN
description The need for large scale and high fidelity simulated samples for the extensive physics program 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 Auto-Encoders and Generative Adversarial Networks are investigated for modeling the response of the ATLAS electromagnetic calorimeter for photons in a central calorimeter region over a range of energies. The properties of synthesized showers are compared to showers from a full detector simulation using Geant4. This feasibility study demonstrates the potential of using such algorithms for fast calorimeter simulation for the ATLAS experiment in the future and opens the possibility to complement current simulation techniques. To employ generative models for physics analyses, it is required to incorporate additional particle types and regions of the calorimeter and enhance the quality of the synthesised showers.
id cern-2650726
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2018
record_format invenio
spelling cern-26507262019-09-30T06:29:59Zhttp://cds.cern.ch/record/2650726engGadatsch, StefanDeep generative models for fast shower simulation in ATLASParticle Physics - ExperimentThe need for large scale and high fidelity simulated samples for the extensive physics program 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 Auto-Encoders and Generative Adversarial Networks are investigated for modeling the response of the ATLAS electromagnetic calorimeter for photons in a central calorimeter region over a range of energies. The properties of synthesized showers are compared to showers from a full detector simulation using Geant4. This feasibility study demonstrates the potential of using such algorithms for fast calorimeter simulation for the ATLAS experiment in the future and opens the possibility to complement current simulation techniques. To employ generative models for physics analyses, it is required to incorporate additional particle types and regions of the calorimeter and enhance the quality of the synthesised showers.ATL-SOFT-SLIDE-2018-1030oai:cds.cern.ch:26507262018-12-10
spellingShingle Particle Physics - Experiment
Gadatsch, Stefan
Deep generative models for fast shower simulation in ATLAS
title Deep generative models for fast shower simulation in ATLAS
title_full Deep generative models for fast shower simulation in ATLAS
title_fullStr Deep generative models for fast shower simulation in ATLAS
title_full_unstemmed Deep generative models for fast shower simulation in ATLAS
title_short Deep generative models for fast shower simulation in ATLAS
title_sort deep generative models for fast shower simulation in atlas
topic Particle Physics - Experiment
url http://cds.cern.ch/record/2650726
work_keys_str_mv AT gadatschstefan deepgenerativemodelsforfastshowersimulationinatlas