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

TL;DR

This paper introduces IEA-GAN, a novel generative model that uses relational reasoning and self-supervised losses to efficiently produce ultra-high-resolution detector simulations with correlated, fine-grained information.

Contribution

We propose IEA-GAN, the first algorithm for faithful ultra-high-granularity detector simulation incorporating event-based relational reasoning and self-supervised intra-event aware learning.

Findings

Successfully generated sensor-dependent images with over 7.5 million channels.

Enhanced sample fidelity and diversity through new loss functions.

Applicable to high-granularity detectors like Belle II and HL-LHC.

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.