Filters








1,763 Hits in 5.6 sec

Deep Generative Models for Fast Shower Simulation in ATLAS

Dalila Salamani, Stefan Gadatsch, Tobias Golling, Graeme Andrew Stewart, Aishik Ghosh, David Rousseau, Ahmed Hasib, Jana Schaarschmidt
2018 2018 IEEE 14th International Conference on e-Science (e-Science)  
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  ...  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  ...  E = ∑ i∈layers ∑ j∈cells E ij . (3) Conclusions We present the first application of generative models for simulating particle showers in the ATLAS calorimeter.  ... 
doi:10.1109/escience.2018.00091 dblp:conf/eScience/SalamaniGGSGRHS18 fatcat:imbn4qtn6fdmzmhep3g6ncr2ny

Fast simulation methods in ATLAS: from classical to generative models

Aishik Ghosh, Dalila Salamani, David Rousseau, Gilles Louppe, Graeme A Stewart, Hasib Ahmed, Heather Gray, Jana Schaarschmidt, John Derek Chapman, Johnny Raine, Kyle Stuart Cranmer, Stefan Gadatsch (+3 others)
2019 Zenodo  
In this talk, we will describe the new tools for fast production of simulated events and an exploratory analysis of the deep learning methods.  ...  Two different approaches, using Variational Auto-Encoders (VAEs) or Generative Adversarial Networks (GANs), are trained to model the shower simulation.  ...  hits used by FCS) ATL-SOFT-PUB-2018-001 Johnny Raine (UniGe) Fast Simulation in ATLAS 4 th November, 2019 10 / 15 Fast Simulation Generative Models GAN Generator Discriminator E Discriminator  ... 
doi:10.5281/zenodo.3599704 fatcat:pnf63xajjvc4rpwblyurae3nka

Fast simulation methods in ATLAS: from classical to generative models

John Chapman, Kyle Cranmer, Stefan Gadatsch, Tobias Golling, Aishik Ghosh, Heather M. Gray, Tommaso Lari, Vincent R. Pascuzzi, John A. Raine, David Rousseau, Dalila Salamani, Jana Schaarschmidt (+6 others)
2020 EPJ Web of Conferences  
In this talk, we will describe the new tools for fast production of simulated events and an exploratory analysis of the deep learning methods.  ...  Two different approaches, using Variational Auto-Encoders (VAEs) or Generative Adversarial Networks (GANs), are trained to model the shower simulation.  ...  ATLAS is investigating whether deep neural networks can be used for simulation by training a network to approximate the showering from Geant4.  ... 
doi:10.1051/epjconf/202024502035 fatcat:plesfaep4za3ncjo2gvudafbri

Generative models for fast simulation

S. Vallecorsa
2018 Journal of Physics, Conference Series  
The need for simulated events, expected in the future for LHC experiments and their High Luminosity upgrades, is increasing dramatically and requires new fast simulation solutions.  ...  We will present the first three-dimensional images of energy showers in a high granularity calorimeter, obtained using Generative Adversarial Networks.  ...  Both the ATLAS and CMS experiments, for example, use pre-simulated EM-showers libraries to replace the detailed simulation of their forward calorimeters [9] [10] .  ... 
doi:10.1088/1742-6596/1085/2/022005 fatcat:pm6a6byiyzbz7dkurazn63ezym

Learning high-level structures in HEP data with novel Deep Auto-Regressive Networks for Fast Simulation

Anna Zaborowska, Ioana Ifrim, Witold Pokorski
2019 Zenodo  
In High Energy Physics, simulation activity is a key element for theoretical models evaluation and detector design choices.  ...  A novel Deep Learning architecture is proposed in this research based on autoregressive connections to model the simulation output by decomposing the event distribution as a product of conditionals.  ...  2018 estimates: MC fast calo sim + standard reco MC fast calo sim + fast reco Generators speed up x2 Flat budget model (+20%/year) ATLAS Preliminary -Using the Geant4 full simulation toolkit  ... 
doi:10.5281/zenodo.3599392 fatcat:bn5fkfjrizfytjy3rypiag5vsa

SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics [article]

Atul Kumar Sinha, Daniele Paliotta, Bálint Máté, Sebastian Pina-Otey, John A. Raine, Tobias Golling, François Fleuret
2022 arXiv   pre-print
Deep learning methods have gained popularity in high energy physics for fast modeling of particle showers in detectors.  ...  Our contribution is SUPA, the SUrrogate PArticle propagation simulator, an algorithm and software package for generating data by simulating simplified particle propagation, scattering and shower development  ...  The authors would like to acknowledge funding through the SNSF Sinergia grant called Robust Deep Density Models for High-Energy Particle Physics and Solar Flare Analysis (RODEM) with funding number CRSII5  ... 
arXiv:2202.05012v1 fatcat:24ox556mdzhxnnhbnidjvjypam

Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters

Michela Paganini, Luke de Oliveira, Benjamin Nachman
2018 Physical Review Letters  
We therefore introduce a deep neural network-based generative model to enable high-fidelity, fast, electromagnetic calorimeter simulation.  ...  The modeling of detectors and the precise description of particle cascades as they interact with the material in the calorimeter are the most computationally demanding steps in the simulation pipeline.  ...  We therefore introduce a deep learning model, named CaloGAN, for a highfidelity fast simulation of particle showers in electromagnetic calorimeters.  ... 
doi:10.1103/physrevlett.120.042003 pmid:29437460 fatcat:e6sxsqze7baahfaottkkion2ru

Three dimensional Generative Adversarial Networks for fast simulation

F Carminati, A Gheata, G Khattak, P Mendez Lorenzo, S Sharan, S Vallecorsa
2018 Journal of Physics, Conference Series  
Energy showers are well reproduced in all dimensions and show a good agreement with standard techniques (Geant4 detailed simulation).  ...  This work aims at proving that deep learning techniques represent a valid fast alternative to standard Monte Carlo approaches. It is part of the GeantV project.  ...  This study is a first proof of concept for a much larger plan intended to provide a generic Deep Learning tool for fast simulation, to be integrated in existing simulation software, such as Geant4, or  ... 
doi:10.1088/1742-6596/1085/3/032016 fatcat:3nqv5olc7ngefdwwzc6dh4ygw4

AtlFast3: the next generation of fast simulation in ATLAS [article]

ATLAS Collaboration
2022 arXiv   pre-print
Here, AtlFast3, the next generation of high-accuracy fast simulation in ATLAS is introduced.  ...  Over the past decade, ATLAS has developed and utilized tools that replace the most CPU-intensive component of the simulation -- the calorimeter shower simulation -- with faster simulation methods.  ...  Acknowledgements We thank CERN for the very successful operation of the LHC, as well as the support staff from our institutions without whom ATLAS could not be operated efficiently.  ... 
arXiv:2109.02551v2 fatcat:2llqhob5u5ge7bchdfcbtq4zfy

3D convolutional GAN for fast simulation

Sofia Vallecorsa, Federico Carminati, Gulrukh Khattak, A. Forti, L. Betev, M. Litmaath, O. Smirnova, P. Hristov
2019 EPJ Web of Conferences  
The need for simulated events, expected in the future for LHC experiments and their High Luminosity upgrades, is increasing dramatically and requires new fast simulation solutions.  ...  Finally we show how this tool could be generalized to describe a whole class of calorimeters, opening the way to a generic machine learning based fast simulation approach.  ...  Our proposal is to leverage state of the art deep learning algorithms to design a generic, fast simulation tool.  ... 
doi:10.1051/epjconf/201921402010 fatcat:pruecy6e2fe5pewvlszcxnzd5e

Fast Simulation of a High Granularity Calorimeter by Generative Adversarial Networks [article]

Gul Rukh Khattak, Sofia Vallecorsa, Federico Carminati, Gul Muhammad Khan
2021 arXiv   pre-print
The same concept is extended to generate showers for other particles (photons and neutral pions) depositing most of their energies in electromagnetic interactions.  ...  In addition, the generation of charged pion showers is also explored, a more accurate effort would require additional data from other detectors not included in the scope of the current work.  ...  We thank Matt Zhang from the University of Illinois at Urbana-Champaign for help regarding the Triforce [19] model.  ... 
arXiv:2109.07388v1 fatcat:w5a735nlorgldatwjxrrt5jhwq

Fast simulation of a high granularity calorimeter by generative adversarial networks

Gul Rukh Khattak, Sofia Vallecorsa, Federico Carminati, Gul Muhammad Khan
2022 European Physical Journal C: Particles and Fields  
The same concept is extended to generate showers for other particles depositing most of their energies in electromagnetic interactions (photons and neutral pions).  ...  In addition, the generation of charged pion showers is also explored, a more accurate effort would require additional data from other detectors not included in the scope of the current work.  ...  We thank Matt Zhang from the University of Illinois at Urbana-Champaign for help regarding the Triforce [19] model.  ... 
doi:10.1140/epjc/s10052-022-10258-4 fatcat:4fd3jt762ragrmrpk7lpsoeuju

CaloGAN: Simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks

Michela Paganini, Luke de Oliveira, Benjamin Nachman
2018 Physical Review D  
We introduce CaloGAN, a new fast simulation technique based on generative adversarial networks (GANs).  ...  We apply these neural networks to the modeling of electromagnetic showers in a longitudinally segmented calorimeter, and achieve speedup factors comparable to or better than existing full simulation techniques  ...  We introduce a Deep Learning model to enable highfidelity fast simulation of particle showers in electromagnetic calorimeters.  ... 
doi:10.1103/physrevd.97.014021 fatcat:efbdydu6pzhc7khbohuxfg6rsm

GeantV alpha release

G Amadio, Ananya, J Apostolakis, M Bandieramonte, S Behera, A Bhattacharyya, R Brun, P Canal, F Carminati, G Cosmo, V Drogan, L Duhem (+27 others)
2018 Journal of Physics, Conference Series  
Electromagnetic physics models were adapted for the specific GeantV requirements, aiming for the full demonstration of shower physics performance in the alpha release at the end of 2017.  ...  in general.  ...  Table 1 presents such a comparison for electron-induced showers in the ATLAS simplified calorimeter, while Figure 5 presents the validation of different options of the multiple scattering model in two  ... 
doi:10.1088/1742-6596/1085/3/032037 fatcat:dm6te42hbbhl7bpke5d4z5kwfy

Detector Simulation [chapter]

J. Apostolakis
2020 Particle Physics Reference Library  
This chapter provides an overview of particle and radiation transport simulation, as it is used in the simulation of detectors in High Energy and Nuclear Physics (HENP) experiments and, briefly, in other  ...  Simulating the generation of particles in an initial collision, the interaction of these primaries and their daughter particles with the material of a detector and the response of the detector is a key  ...  generate a library of pre-simulated showers at set energies for use in recreating realistic showers.  ... 
doi:10.1007/978-3-030-35318-6_11 fatcat:b6fkcky7hzfuxknk6qayown3b4
« Previous Showing results 1 — 15 out of 1,763 results