Cluster Reconstruction in Electromagnetic Calorimeters Using Machine Learning Methods

TL;DR

This paper presents a machine learning approach using convolutional neural networks with autoencoder architecture to accurately reconstruct particle impact points and energies in electromagnetic calorimeters, enhancing event reconstruction in high energy physics.

Contribution

It introduces a novel CNN-based autoencoder method for cluster reconstruction in segmented detectors, improving position and energy accuracy in particle detection.

Findings

Reconstructs impact points within the same segment as true positions

Determines particle energy with high precision

Applicable to overlapping signal separation in event analysis

Abstract

Machine-learning-based methods can be developed for the reconstruction of clusters in segmented detectors for high energy physics experiments. Convolutional neural networks with autoencoder architecture trained on labeled data from a simulated dataset reconstruct events by providing information about the hit point and energy of each particle that has entered the detector. The correct reconstruction of the positionand the energy of the incident particles is crucial for the accurate events reconstruction. The presented method shows the ability to reconstruct the impact point within the same segment as the true position and determines the particle energy with good precision. It can be applied in a wide range of cases of event reconstruction where the good separation of overlapping signals plays a key role in the data analysis.