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

Abstract

Physicists at the Large Hadron Collider (LHC) rely on detailed simulations of particle collisions to build expectations of what experimental data may look like under different theory modeling assumptions. Petabytes of simulated data are needed to develop analysis techniques, though they are expensive to generate using existing algorithms and computing resources. 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 neural network-based generative model to enable high-fidelity, fast, electromagnetic calorimeter simulation. There are still challenges for achieving precision across the entire phase space, but our current solution can reproduce a variety of particle shower properties while achieving speed-up factors of up to 100,000$\times$. This 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.

6 pages, 3 figures; version accepted by Physical Review Letters (PRL)

References in corpus (7)

• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
• PYTHIA 6.4 Physics and Manual
• Big-Bang Nucleosynthesis
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit

Cited by in corpus (124)

• Machine learning and the physical sciences
• Fast inference of deep neural networks in FPGAs for particle physics
• Jet Substructure at the Large Hadron Collider: A Review of Recent Advances in Theory and Machine Learning
• Anomaly Detection with Density Estimation
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• Energy Flow Networks: Deep Sets for Particle Jets
• Learning New Physics from a Machine
• How to GAN LHC Events
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Energy flow polynomials: A complete linear basis for jet substructure
• Machine and Deep Learning Applications in Particle Physics
• Pulling Out All the Tops with Computer Vision and Deep Learning
• The Metric Space of Collider Events
• Fast approximate simulation of seismic waves with deep learning
• Precise simulation of electromagnetic calorimeter showers using a Wasserstein Generative Adversarial Network
• AtlFast3: the next generation of fast simulation in ATLAS
• Machine Learning and LHC Event Generation
• JUNIPR: a Framework for Unsupervised Machine Learning in Particle Physics
• Learning to Classify from Impure Samples with High-Dimensional Data
• Regressive and generative neural networks for scalar field theory
• Score-based Generative Models for Calorimeter Shower Simulation
• Invertible Networks or Partons to Detector and Back Again
• CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flows
• Neural Networks for Full Phase-space Reweighting and Parameter Tuning
• Fast and accurate simulation of particle detectors using generative adversarial networks
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• How to GAN away Detector Effects
• Ultra-High-Energy Cosmic Rays: The Intersection of the Cosmic and Energy Frontiers
• Unfolding with Generative Adversarial Networks
• Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)
• Understanding Event-Generation Networks via Uncertainties
• Applications and Techniques for Fast Machine Learning in Science
• Event Generators for High-Energy Physics Experiments
• Decoding Photons: Physics in the Latent Space of a BIB-AE Generative Network
• GANplifying Event Samples
• Generative Networks for Precision Enthusiasts
• A Neural Resampler for Monte Carlo Reweighting with Preserved Uncertainties
• Fast Point Cloud Generation with Diffusion Models in High Energy Physics
• CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• An operational definition of quark and gluon jets
• Evaluating generative models in high energy physics
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Software and computing for Run 3 of the ATLAS experiment at the LHC
• Supervised deep learning in high energy phenomenology: a mini review
• Lund jet images from generative and cycle-consistent adversarial networks
• Phase Space Sampling and Inference from Weighted Events with Autoregressive Flows
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• Calomplification -- The Power of Generative Calorimeter Models
• L2LFlows: Generating High-Fidelity 3D Calorimeter Images
• Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks
• DCTRGAN: Improving the Precision of Generative Models with Reweighting
• Learning to Simulate High Energy Particle Collisions from Unlabeled Data
• How to Understand Limitations of Generative Networks
• GANs for generating EFT models
• Binary JUNIPR: an interpretable probabilistic model for discrimination
• CaloScore v2: Single-shot Calorimeter Shower Simulation with Diffusion Models
• Electromagnetic Showers Beyond Shower Shapes
• Deep generative models for fast photon shower simulation in ATLAS
• LHC analysis-specific datasets with Generative Adversarial Networks
• Towards a Deep Learning Model for Hadronization
• Inductive Simulation of Calorimeter Showers with Normalizing Flows
• The MadNIS Reloaded
• Cherenkov Detectors Fast Simulation Using Neural Networks
• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• PC-Droid: Faster diffusion and improved quality for particle cloud generation
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physics
• Lorentz group equivariant autoencoders
• Explainable machine learning of the underlying physics of high-energy particle collisions
• CaloFlow for CaloChallenge Dataset 1
• Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning
• How to GAN Event Subtraction
• Machine Learning Templates for QCD Factorization in the Search for Physics Beyond the Standard Model
• CaloDREAM -- Detector Response Emulation via Attentive flow Matching
• Particle-based Fast Jet Simulation at the LHC with Variational Autoencoders
• Precision-Machine Learning for the Matrix Element Method
• Designing quantum many-body matter with conditional generative adversarial networks
• Classification and Recovery of Radio Signals from Cosmic Ray Induced Air Showers with Deep Learning
• Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
• Normalizing Flows for High-Dimensional Detector Simulations
• A high-granularity calorimeter insert based on SiPM-on-tile technology at the future Electron-Ion Collider
• Parameter Estimation using Neural Networks in the Presence of Detector Effects
• Parametrizing the Detector Response with Neural Networks
• Calorimeter shower superresolution
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• Differentiable MadNIS-Lite
• Learning Multivariate New Physics
• CaloShowerGAN, a Generative Adversarial Networks model for fast calorimeter shower simulation
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• Uncertainties associated with GAN-generated datasets in high energy physics
• Accurate Surrogate Amplitudes with Calibrated Uncertainties
• CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
• Simulating the Time Projection Chamber responses at the MPD detector using Generative Adversarial Networks
• Anomaly detection with flow-based fast calorimeter simulators
• CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation
• Deep Learning Jet Substructure from Two-Particle Correlation
• OASIS: Optimal Analysis-Specific Importance Sampling for event generation
• A Data-driven Event Generator for Hadron Colliders using Wasserstein Generative Adversarial Network
• Effectiveness of denoising diffusion probabilistic models for fast and high-fidelity whole-event simulation in high-energy heavy-ion experiments
• Variational Autoencoders for Jet Simulation
• Unsupervised and lightly supervised learning in particle physics
• How to GAN Event Unweighting
• Advancing Set-Conditional Set Generation: Diffusion Models for Fast Simulation of Reconstructed Particles
• Leveraging Staggered Tessellation for Enhanced Spatial Resolution in High-Granularity Calorimeters
• Unifying Simulation and Inference with Normalizing Flows
• Parnassus: An Automated Approach to Accurate, Precise, and Fast Detector Simulation and Reconstruction
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Towards Reliable Neural Generative Modeling of Detectors
• Pores for thought: The use of generative adversarial networks for the stochastic reconstruction of 3D multi-phase electrode microstructures with periodic boundaries
• Synthesis of pulses from particle detectors with a Generative Adversarial Network (GAN)
• Extrapolating Jet Radiation with Autoregressive Transformers
• How good is my GAN?
• BitHEP -- The Limits of Low-Precision ML in HEP
• The use of Generative Adversarial Networks to characterise new physics in multi-lepton final states at the LHC
• Amplitude Uncertainties Everywhere All at Once
• Deep learning based track reconstruction on CEPC luminometer
• Reconstructing Sparticle masses at the LHC using Generative Machine Learning
• CaloHadronic: a diffusion model for the generation of hadronic showers
• CaloClouds3: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation
• Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System
• ParaFlow: fast calorimeter simulations parameterized in upstream material configurations
• Global Optimisation of Black-Box Functions with Generative Models in the Wasserstein Space
• A deep learning approach for predicting multiple observables in Au+Au collisions at RHIC
• Ultra Fast Calorimeter Simulation with Generative Machine Learning on FPGAs