Development of particle flow algorithms based on Neural Network techniques for the IDEA calorimeter at future colliders

Abstract

IDEA (Innovative Detector for an Electron-positron Accelerator) is an innovative general-purpose detector concept, designed to study electron-positron collisions at future e+e− circular colliders. The detector will be equipped with a dual read-out calorimeter able to measure separately the hadronic component and the electromagnetic component of the showers initiated by the impinging hadrons. Particle flow algorithms (PFAs) have become the paradigm of detector design for the high energy frontier and this work focuses on a project to build a particle flow algorithm for the IDEA detector using Machine Learning (ML) techniques. ML is used for particle reconstruction and identification profiting of the high granularity of the fiber-based dual-readout calorimeter. Neural Networks (NN) are built for electron reconstruction inside the calorimeter. The performance of several NN architectures is shown, with particular attention to the layer setup and the activation function choices. The performance is evaluated on the energy resolution function of the reconstructed particles. The algorithm is trained using both parallel CPUs and GPU, and the time performance and the memory usage of the two approaches are systematically compared.