On the Use of Neural Networks for Energy Reconstruction in High-granularity Calorimeters

TL;DR

This paper compares neural network approaches, CNN and GNN, to traditional methods for energy reconstruction in high-granularity calorimeters, showing significant improvements and insights into the physics of shower development.

Contribution

It demonstrates the effectiveness of CNN and GNN models for energy regression in calorimeters and explores their ability to leverage physics-based latent features.

Findings

CNN outperforms traditional methods in energy resolution for pions and jets.

GNN with edge convolution assesses timing information's role in shower development.

Neural networks maintain good performance for electrons and photons.

Abstract

We contrasted the performance of deep neural networks - Convolutional Neural Network (CNN) and Graph Neural Network (GNN) - to current state of the art energy regression methods in a finely 3D-segmented calorimeter simulated by GEANT4. This comparative benchmark gives us some insight to assess the particular latent signals neural network methods exploit to achieve superior resolution. A CNN trained solely on a pure sample of pions achieved substantial improvement in the energy resolution for both single pions and jets over the conventional approaches. It maintained good performance for electron and photon reconstruction. We also used the Graph Neural Network (GNN) with edge convolution to assess the importance of timing information in the shower development for improved energy reconstruction. We implement a simple simulation based correction to the energy sum derived from the fraction of energy deposited in the electromagnetic shower component. This serves as an approximate dual-readout analogue for our benchmark comparison. Although this study does not include the simulation of detector effects, such as electronic noise, the margin of improvement seems robust enough to suggest these benefits will endure in real-world application. We also find reason to infer that the CNN/GNN methods leverage latent features that concur with our current understanding of the physics of calorimeter measurement.