Calorimeter Shower Superresolution with Conditional Normalizing Flows: Implementation and Statistical Evaluation

2026-03-26

AI Summary

This work addresses the substantial computational cost associated with high-granularity simulation and reconstruction of calorimeter showers in high-energy physics. To this end, we present the first application of a conditional normalizing flow model—originally developed for fast simulation—to the task of calorimeter shower super-resolution, recovering fine-grained structures from coarse-grained readouts. Leveraging the Geant4 Par04 geometry and the CaloChallenge 2022 dataset, we independently reproduce and train the generative model, evaluating its fidelity through a rigorous statistical testing framework that assesses consistency between generated and reference distributions. Our results demonstrate that the model accurately reproduces key physical observables of real data while significantly reducing computational complexity, thereby preserving detector performance at a fraction of the traditional simulation cost.

Abstract

In High Energy Physics, detailed calorimeter simulations and reconstructions are essential for accurate energy measurements and particle identification, but their high granularity makes them computationally expensive. Developing data-driven techniques capable of recovering fine-grained information from coarser readouts, a task known as calorimeter superresolution, offers a promising way to reduce both computational and hardware costs while preserving detector performance. This thesis investigates whether a generative model originally designed for fast simulation can be effectively applied to calorimeter superresolution. Specifically, the model proposed in arXiv:2308.11700 is re-implemented independently and trained on the CaloChallenge 2022 dataset based on the Geant4 Par04 calorimeter geometry. Finally, the model's performance is assessed through a rigorous statistical evaluation framework, following the methodology introduced in arXiv:2409.16336, to quantitatively test its ability to reproduce the reference distributions.

Problem

• calorimeter superresolution
• high energy physics
• computational cost
• fine-grained information
• detector performance

Innovation

• calorimeter superresolution
• conditional normalizing flows
• generative modeling
• statistical evaluation
• high energy physics