Using Artificial Intelligence in the Reconstruction of Signals from the PADME Electromagnetic Calorimeter

TL;DR

This paper presents a machine learning algorithm designed to improve the reconstruction of overlapping signals in the PADME electromagnetic calorimeter, enhancing the accuracy of energy and timing measurements crucial for dark photon searches.

Contribution

The paper introduces a novel regression machine learning algorithm tailored for disentangling overlapping signals in the PADME calorimeter, achieving high efficiency and sub-nanosecond timing resolution.

Findings

High efficiency in signal disentanglement

Sub-nanosecond timing resolution achieved

Improved accuracy in energy measurement

Abstract

The PADME apparatus was built at the Frascati National Laboratory of INFN to search for a dark photon ($A'$) produced via the process $e^+ e^- \rightarrow A' \gamma$. The central component of the PADME detector is an electromagnetic calorimeter composed of 616 BGO crystals dedicated to the measurement of the energy and position of the final state photons. The high beam particle multiplicity over a short bunch duration requires reliable identification and measurement of overlapping signals. A regression machine-learning-based algorithm has been developed to disentangle with high efficiency close-in-time events and precisely reconstruct the amplitude of the hits and the time with sub-nanosecond resolution. The performance of the algorithm and the sequence of improvements leading to the achieved results are presented and discussed.