Separation of a single photon and products of the $\pi^0,\eta, K^0_s$ meson neutral decay channels in the CMS electromagnetic calorimeter using neural network

TL;DR

This paper presents a neural network method to distinguish single photons from meson decay products in the CMS electromagnetic calorimeter, improving particle identification in high-energy physics experiments.

Contribution

It introduces a neural network approach for separating photons from meson decay products using CMS calorimeter data, with detailed performance metrics across different energies and detector regions.

Findings

High rejection rates for mesons at various photon efficiencies.

Effective separation achieved in both Barrel and Endcap regions.

Performance varies with photon energy and detector region.

Abstract

The artificial neural network approach is used for separation of signals from a single photon $\gamma$ and products of the $\pi^0,\eta, K^0_s$ meson neutral decay channels on the basis of the data from the CMS electromagnetic calorimeter alone. Rejection values for the three types of mesons as a function of single photon selection efficiencies are obtained for two Barrel and one Endcap pseudorapidity regions and initial $\Et$ of 20, 40, 60 and 100 GeV.