Physics Validation of Novel Convolutional 2D Architectures for Speeding Up High Energy Physics Simulations

EPJ Web of Conferences, vol. 251, pp. 03042

Abstract

The precise simulation of particle transport through detectors remains a key element for the successful interpretation of high energy physics results. However, Monte Carlo based simulation is extremely demanding in terms of computing resources. This challenge motivates investigations of faster, alternative approaches for replacing the standard Monte Carlo technique. We apply Generative Adversarial Networks (GANs), a deep learning technique, to replace the calorimeter detector simulations and speeding up the simulation time by orders of magnitude. We follow a previous approach which used three-dimensional convolutional neural networks and develop new two-dimensional convolutional networks to solve the same 3D image generation problem faster. Additionally, we increased the number of parameters and the neural networks representational power, obtaining a higher accuracy. We compare our best convolutional 2D neural network architecture and evaluate it versus the previous 3D architecture and Geant4 data. Our results demonstrate a high physics accuracy and further consolidate the use of GANs for fast detector simulations.

Authors 4

1. Florian Rehm Aachen

   European Organization for Nuclear Research · RWTH Aachen University

   Affiliation as printed

   CERN, Esplanade des Particules 1, Geneva, Switzerland

   RWTH Aachen University, Templergraben 55, Aachen, Germany

2. Sofia Vallecorsa

   European Organization for Nuclear Research

   Affiliation as printed

   CERN, Esplanade des Particules 1, Geneva, Switzerland

3. K. Borras Aachen

   Deutsches Elektronen-Synchrotron DESY · RWTH Aachen University

   Affiliation as printed

   DESY, Notkestraße 85, Hamburg, Germany

   RWTH Aachen University, Templergraben 55, Aachen, Germany

4. Dirk Krücker

   Deutsches Elektronen-Synchrotron DESY

   Affiliation as printed

   DESY, Notkestraße 85, Hamburg, Germany