Machine Learning approach to boosting neutral particles identification in the LHCb calorimeter

TL;DR

This paper introduces a machine learning method for improved identification of neutral particles like photons and neutral pions in the LHCb calorimeter, surpassing traditional geometric shape-based techniques.

Contribution

It presents a novel machine learning approach that uses primary calorimeter cell energies to enhance particle separation performance without energy dependence.

Findings

Improved separation of photons and neutral pions.

No significant energy dependence in identification performance.

Enhanced accuracy over traditional geometric methods.

Abstract

We present a new approach to identification of boosted neutral particles using Electromagnetic Calorimeter (ECAL) of the LHCb detector. The identification of photons and neutral pions is currently based on the geometric parameters which characterise the expected shape of energy deposition in the calorimeter. This allows to distinguish single photons in the electromagnetic calorimeter from overlapping photons produced from high momentum $\pi^0$ decays. The novel approach proposed here is based on applying machine learning techniques to primary calorimeter information, that are energies collected in individual cells around the energy cluster. This method allows to improve separation performance of photons and neutral pions and has no significant energy dependence.