Abstract
We present the first application of three-dimensional convolutional Generative Adversarial Network to High Energy Physics simulation. We generate three-dimensional images of particles depositing energy in high granularity calorimeters. This is the first time such an approach is taken in HEP where most of data is three-dimensional in nature but it is customary to convert it into two-dimensional slices. The present work proves the success of using three dimensional convolutional GAN. Energy showers are well reproduced in all dimensions and show a good agreement with standard techniques (Geant4 detailed simulation). We also demonstrate the ability to condition training on several parameters such as particle type and energy. 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.
Highlights
We present the first application of three-dimensional convolutional Generative Adversarial Network to High Energy Physics simulation
This work aims at proving that deep learning techniques represent a valid fast alternative to standard Monte Carlo approaches
High Energy Physics (HEP) software and simulation software, in particular, are going through an important phase of restructuring and optimisation for new computing architectures, in order to cope with the expected High Luminosity LHC computing needs [1]
Summary
High Energy Physics (HEP) software and simulation software, in particular, are going through an important phase of restructuring and optimisation for new computing architectures, in order to cope with the expected High Luminosity LHC computing needs [1]. Input data set The data set that we use for our studies, was produced in the context of the CLIC detector design [10] and it is available under the DD4hep software framework [11] It consists of energy showers generated with the Geant software [13] inside the CLIC electromagnetic and hadronic calorimeters detector prototype [10]. This is an example of generation highly granular calorimeters and it represents a demanding use case simulation will have to face during High Luminosity LHC runs This data set was produced in an effort to provide the HEP community with a common benchmark to perform tests, development and optimization of different machine learning techniques. The energy of the incoming particle is sampled from a uniform [0-500 GeV] spectrum
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
