Electromagnetic Showers Beyond Shower Shapes

TL;DR

This paper compares traditional shower shape-based classification methods with advanced computer vision techniques using detector images, demonstrating that deep learning models can improve particle identification and infer kinematic properties.

Contribution

It introduces a DenseNet-based deep learning approach that outperforms traditional methods in particle classification and enables direct inference of kinematic properties from calorimeter images.

Findings

Deep learning models match or outperform traditional shower shape methods.

Convolutional neural networks can infer kinematic properties directly from images.

The approach is effective in simplified calorimeter geometries.

Abstract

Correctly identifying the nature and properties of outgoing particles from high energy collisions at the Large Hadron Collider is a crucial task for all aspects of data analysis. Classical calorimeter-based classification techniques rely on shower shapes -- observables that summarize the structure of the particle cascade that forms as the original particle propagates through the layers of material. This work compares shower shape-based methods with computer vision techniques that take advantage of lower level detector information. In a simplified calorimeter geometry, our DenseNet-based architecture matches or outperforms other methods on $e^+$-$\gamma$ and $e^+$-$\pi^+$ classification tasks. In addition, we demonstrate that key kinematic properties can be inferred directly from the shower representation in image format.