High Level Reconstruction with Deep Learning using ILD Full Simulation

TL;DR

This paper explores deep learning techniques for event reconstruction in electron-positron Higgs factories, focusing on jet flavor tagging and particle flow to enhance physics performance.

Contribution

It introduces novel deep learning algorithms for jet flavor tagging and particle flow using full simulation data, incorporating particle transformer, GravNet, and Object Condensation methods.

Findings

Particle transformer effectively identifies jet flavor including strange tagging.

Modified GravNet and Object Condensation improve calorimeter hit clustering.

Enhanced track-cluster assignment boosts jet energy resolution.

Abstract

Deep learning can give a significant impact on physics performance of electron-positron Higgs factories such as ILC and FCCee. We are working on two topics on event reconstruction to apply deep learning. The first is jet flavor tagging, in which we apply particle transformer to ILD full simulation to obtain jet flavor, including strange tagging. The second is particle flow, which clusters calorimeter hits and assigns tracks to them to improve jet energy resolution. We modified the algorithm developed in context of CMS HGCAL based on GravNet and Object Condensation techniques and add a track-cluster assignment function into the network. The overview and performance of these algorithms are described.