Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
Authors:
- Erik BuhmannEBErik Buhmann
- Sascha DiefenbacherSDSascha Diefenbacher
- Engin ErenEEEngin Eren
- Frank GaedeFGFrank Gaede
- Gregor KasieczkaGKGregor Kasieczka
- Anatolii KorolAKAnatolii Korol
- Katja KrügerKKKatja Krüger
Preprint
Abstract
Accurate simulation of physical processes is crucial for the success of modern particle physics. However, simulating the development and interaction of particle showers with calorimeter detectors is a time consuming process and drives the computing needs of large experiments at the LHC and future colliders. Recently, generative machine learning models based on deep neural networks have shown promise in speeding up this task by several orders of magnitude. We investigate the use of a new architecture -- the Bounded Information Bottleneck Autoencoder -- for modelling electromagnetic showers in the central region of the Silicon-Tungsten calorimeter of the proposed International Large Detector. Combined with a novel second post-processing network, this approach achieves an accurate simulation of differential distributions including for the first time the shape of the minimum-ionizing-particle peak compared to a full GEANT4 simulation for a high-granularity calorimeter with 27k simulated channels. The results are validated by comparing to established architectures. Our results further strengthen the case of using generative networks for fast simulation and demonstrate that physically relevant differential distributions can be described with high accuracy.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Tag N’ Train: a technique to train improved classifiers on unlabeled dataJournal of High Energy Physics, 2021
- Using neural networks for efficient evaluation of high multiplicity scattering amplitudesJournal of High Energy Physics, 2020
- DijetGAN: a Generative-Adversarial Network approach for the simulation of QCD dijet events at the LHCJournal of High Energy Physics, 2019
- Variational autoencoders for new physics mining at the Large Hadron ColliderJournal of High Energy Physics, 2019
- Precise Simulation of Electromagnetic Calorimeter Showers Using a Wasserstein Generative Adversarial NetworkComputing and Software for Big Science, 2019
- Deep learning as a parton showerJournal of High Energy Physics, 2018
- Fast and Accurate Simulation of Particle Detectors Using Generative Adversarial NetworksComputing and Software for Big Science, 2018
- Generating and Refining Particle Detector Simulations Using the Wasserstein Distance in Adversarial NetworksComputing and Software for Big Science, 2018
- Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics SynthesisComputing and Software for Big Science, 2017
- Geant4—a simulation toolkitNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2003