CaloHadronic: a diffusion model for the generation of hadronic showers

2025-06-26

AI Summary

Low accuracy and slow speed in simulating hadronic showers in high-granularity imaging calorimeters hinder large-scale high-energy physics experiments. Method: We propose the first end-to-end machine learning framework for jointly generating full electromagnetic and hadronic showers. Our approach introduces a diffusion-based point cloud generation architecture that uniquely integrates Transformer attention mechanisms with geometry-agnostic modeling, overcoming the limitations of conventional fixed-topology designs and enabling holistic shower generation across both electromagnetic and hadronic calorimeter configurations. Contributions/Results: (1) First unified generative model for electromagnetic and hadronic showers; (2) Significant improvements in fidelity and efficiency—key hadronic shower observables exhibit >30% lower error versus Geant4, while generation speed is accelerated by four orders of magnitude; (3) A scalable, high-fidelity alternative simulation paradigm for next-generation particle physics experiments.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Simulating showers of particles in highly-granular calorimeters is a key frontier in the application of machine learning to particle physics. Achieving high accuracy and speed with generative machine learning models can enable them to augment traditional simulations and alleviate a major computing constraint. Recent developments have shown how diffusion based generative shower simulation approaches that do not rely on a fixed structure, but instead generate geometry-independent point clouds, are very efficient. We present a transformer-based extension to previous architectures which were developed for simulating electromagnetic showers in the highly granular electromagnetic calorimeter of the International Large Detector, ILD. The attention mechanism now allows us to generate complex hadronic showers with more pronounced substructure across both the electromagnetic and hadronic calorimeters. This is the first time that machine learning methods are used to holistically generate showers across the electromagnetic and hadronic calorimeter in highly granular imaging calorimeter systems.

Problem

• Generate hadronic showers using diffusion models
• Improve accuracy and speed in particle shower simulation
• Simulate showers across electromagnetic and hadronic calorimeters

Innovation

• Diffusion model for hadronic shower generation
• Transformer-based architecture for complex showers
• Geometry-independent point clouds for efficiency