Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning

Abstract

Simulating high-resolution detector responses is a computationally intensive process that has long been challenging in Particle Physics. Despite the ability of generative models to streamline it, full ultra-high-granularity detector simulation still proves to be difficult as it contains correlated and fine-grained information. To overcome these limitations, we propose Intra-Event Aware Generative Adversarial Network (IEA-GAN). IEA-GAN presents a Relational Reasoning Module that approximates an event in detector simulation, generating contextualized high-resolution full detector responses with a proper relational inductive bias. IEA-GAN also introduces a Self-Supervised intra-event aware loss and Uniformity loss, significantly enhancing sample fidelity and diversity. We demonstrate IEA-GAN's application in generating sensor-dependent images for the ultra-high-granularity Pixel Vertex Detector (PXD), with more than 7.5 M information channels at the Belle II Experiment. Applications of this work span from Foundation Models for high-granularity detector simulation, such as at the HL-LHC (High Luminosity LHC), to simulation-based inference and fine-grained density estimation. To our knowledge, IEA-GAN is the first algorithm for faithful ultra-high-granularity full detector simulation with event-based reasoning.

Published at Nature Communications

References in corpus (27)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Conditional Generative Adversarial Nets
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
• NormFace: L2 Hypersphere Embedding for Face Verification
• cGANs with Projection Discriminator
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters
• An empirical study on evaluation metrics of generative adversarial networks
• The Belle II Core Software
• How to GAN LHC Events
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Coupling Learning of Complex Interactions
• Machine Learning and LHC Event Generation
• Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physics
• Score-based Generative Models for Calorimeter Shower Simulation
• Roundtrip: A Deep Generative Neural Density Estimator
• DijetGAN: A Generative-Adversarial Network Approach for the Simulation of QCD Dijet Events at the LHC
• Geometric GAN
• Stochastic Separation Theorems
• Permutation-equivariant neural networks applied to dynamics prediction
• L2LFlows: Generating High-Fidelity 3D Calorimeter Images
• Word Embedding Perturbation for Sentence Classification
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• PE-GAN: Prior Embedding GAN for PXD images at Belle II

Cited by in corpus (11)

• CaloDREAM -- Detector Response Emulation via Attentive flow Matching
• Precision-Machine Learning for the Matrix Element Method
• Normalizing Flows for High-Dimensional Detector Simulations
• Differentiable MadNIS-Lite
• Convolutional L2LFlows: Generating Accurate Showers in Highly Granular Calorimeters Using Convolutional Normalizing Flows
• CaloGraph: Graph-based diffusion model for fast shower generation in calorimeters with irregular geometry
• BitHEP -- The Limits of Low-Precision ML in HEP
• Amplitude Uncertainties Everywhere All at Once
• Extrapolating Jet Radiation with Autoregressive Transformers
• CaloHadronic: a diffusion model for the generation of hadronic showers
• CaloClouds3: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation