Precise Simulation of Electromagnetic Calorimeter Showers Using a Wasserstein Generative Adversarial Network

  title={Precise Simulation of Electromagnetic Calorimeter Showers Using a Wasserstein Generative Adversarial Network},
  author={Martin Erdmann and Jonas Glombitza and Thorben Quast},
  journal={Computing and Software for Big Science},
Simulations of particle showers in calorimeters are computationally time-consuming, as they have to reproduce both energy depositions and their considerable fluctuations. A new approach to ultra-fast simulations is generative models where all calorimeter energy depositions are generated simultaneously. We use GEANT4 simulations of an electron beam impinging on a multi-layer electromagnetic calorimeter for adversarial training of a generator network and a critic network guided by the Wasserstein… Expand
Fast simulation of the ILD electromagnetic calorimeter with Deep Learning
The ability to perform precise detector simulations is crucial in high energy physics. However, traditional techniques relying on Monte Carlo methods are computationally intensive and time consuming.Expand
Fast and Accurate Electromagnetic and Hadronic Showers from Generative Models
Generative machine learning models offer a promising way to efficiently amplify classical Monte Carlo generators’ statistics for event simulation and generation in particle physics. Given the alreadyExpand
Fast Simulation of a High Granularity Calorimeter by Generative Adversarial Networks
We present the 3DGAN for the simulation of a future high granularity calorimeter output as three-dimensional images. We prove the efficacy of Generative Adversarial Networks (GANs) for generatingExpand
Validation of Deep Convolutional Generative Adversarial Networks for High Energy Physics Calorimeter Simulations
It is proved that the new neural network architecture reaches a higher level of accuracy with respect to the 3D convolutional GAN while reducing the necessary computational resources. Expand
Fast Data-Driven Simulation of Cherenkov Detectors Using Generative Adversarial Networks
This work generates high-level reconstructed observables using a generative neural network to bypass low level details of event generation and simulation of detector responses, and demonstrates that this approach provides high-fidelity results. Expand
Conditional Wasserstein Generative Adversarial Networks for Fast Detector Simulation
This work investigates the use of conditional Wasserstein Generative Adversarial Networks to simulate both hadronization and the detector response to jets, and demonstrates that the model produces accurate conditional reconstructed jet transverse momentum (pT) distributions over a wide range of pT for the input parton jet. Expand
Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
This work investigates 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 and achieves an accurate simulation of differential distributions including for the first time the shape of the minimum-ionizing-particle peak. Expand
Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
The new Feature-Augmented and Transformed GAN (FAT-GAN) is able to faithfully reproduce the distribution of final state electron momenta in inclusive electron scattering, without the need for input derived from domain-based theoretical assumptions. Expand
CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
It is demonstrated that normalizing flows can reproduce many-channel calorimeter showers with extremely high fidelity, providing a fresh alternative to computationally expensive Geant4 simulations, as well as other state-of-the-art fast simulation frameworks based on GANs and VAEs. Expand
Generative Adversarial Networks for Fast Simulation: distributed training and generalisation
In High Energy Physics, the Monte Carlo simulation of the detector response to the particles traversing it is one of the most computing intensive tasks. For some applications, a certain level ofExpand


Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters.
A deep neural network-based generative model is introduced to enable high-fidelity, fast, electromagnetic calorimeter simulation and opens the door to a new era of fast simulation that could save significant computing time and disk space, while extending the reach of physics searches and precision measurements at the LHC and beyond. Expand
CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
CaloGAN, a new fast simulation technique based on generative adversarial networks (GANs) is introduced, which is applied to the modeling of electromagnetic showers in a longitudinally segmented calorimeter and achieves speedup factors comparable to or better than existing full simulation techniques. Expand
Generating and Refining Particle Detector Simulations Using the Wasserstein Distance in Adversarial Networks
With this method, it is demonstrated that training a deep network with refined data-like signal traces leads to a more precise energy reconstruction of data events compared to training with the originally simulated traces. Expand
Calorimetry with Deep Learning : Particle Classification , Energy Regression , and Simulation for High-Energy Physics
We present studies of the application of Deep Neural Networks and Convolutional Neural Networks for the classification, energy regression, and simulation of particles produced in high-energy particleExpand
Gflash as a Parameterized Calorimeter Simulation for the CMS Experiment
Gflash is a parameterized simulation of electromagnetic and hadronic showers. It uses parameterizations of longitudinal and lateral shower profiles in homogeneous or sampling calorimeters taking intoExpand
Geant4 - A simulation toolkit
Geant4 is a toolkit for simulating the passage of particles through matter. It includes a complete range of functionality including tracking, geometry, physics models and hits. The physics processesExpand
Position resolution and particle identification with the ATLAS EM calorimeter
In the years between 2000 and 2002 several pre-series and series modules of the ATLAS EM barrel and end-cap calorimeter were exposed to electron, photon and pion beams. The performance of theExpand
Construction and beam-tests of silicon-tungsten prototype modules for the CMS High Granularity Calorimeter for HL-LHC
As part of its HL-LHC upgrade program, CMS is developing a High Granularity Calorimeter (HGCAL) to replace the existing endcap calorimeters. The HGCAL will be realised as a sampling calorimeter,Expand
Construction and first beam-tests of silicon-tungsten prototype modules for the CMS High Granularity Calorimeter for HL-LHC
The High Granularity Calorimeter (HGCAL) is the technology choice of the CMS collaboration for the endcap calorimetry upgrade planned to cope with the harsh radiation and pileup environment at theExpand
Learning from Simulated and Unsupervised Images through Adversarial Training
This work develops a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors, and makes several key modifications to the standard GAN algorithm to preserve annotations, avoid artifacts, and stabilize training. Expand