ML for the hKLM at the 2nd Detector

TL;DR

This research applies Graph Neural Networks to improve energy measurement and particle identification in a proposed detector for the Electron Ion Collider, demonstrating superior performance over classical methods.

Contribution

The paper introduces GNN-based methods for detector data analysis, a faster scintillator simulation parameterization, and an integrated optimization framework for detector design tradeoffs.

Findings

GNN outperforms classical methods in particle identification and energy prediction.

A 20-fold speed-up in scintillator photon simulation was achieved.

Optimization quantifies tradeoffs in detector design parameters.

Abstract

The present research applies Graph Neural-Networks (GNNs) for energy measurement and particle identification tasks for a proposed second detector at the future Electron Ion Collider (EIC). In particular, an iron-scintillator sampling calorimeter would provide neutral hadron ($K_L$ and neutron) energy measurements and identification, as well as separation of muons from hadrons. Using detector simulations, particle hits in the detector are represented as graphs, and a GNN is trained for either classification or prediction. Furthermore, we developed a parameterization of the scintillator optical photon simulation that yields a 20-fold speed up compared to the default simulation. We find that the GNN method outperforms classical methods at the same tasks, and we report projections for the energy and timing resolution, and identification accuracy of the calorimeter. We also present an integration of the GNN method into a Multi-Objective Optimization framework, enabled by an automated pipeline of data generation, GNN training, and detector performance evaluation. We utilize the optimization to quantify the tradeoffs between different performance metrics at high and low energies when changing the detector design parameters, such as the iron/scintillator thickness.