Vertex and Energy Reconstruction in JUNO with Machine Learning Methods

TL;DR

This paper explores machine learning techniques such as DNNs, CNNs, and Graph Neural Networks to improve vertex and energy reconstruction in JUNO, achieving the precision needed for neutrino physics goals.

Contribution

It systematically compares various machine learning models for event reconstruction in JUNO, demonstrating their effectiveness in meeting experimental accuracy requirements.

Findings

ML models achieve 3% energy resolution at 1 MeV

ML models reach 10 cm vertex resolution at 1 MeV

DeepSphere GNN performs comparably to CNNs in reconstruction tasks

Abstract

The Jiangmen Underground Neutrino Observatory (JUNO) is an experiment designed to study neutrino oscillations. Determination of neutrino mass ordering and precise measurement of neutrino oscillation parameters $\sin^2 2\theta_{12}$, $\Delta m^2_{21}$ and $\Delta m^2_{32}$ are the main goals of the experiment. A rich physical program beyond the oscillation analysis is also foreseen. The ability to accurately reconstruct particle interaction events in JUNO is of great importance for the success of the experiment. In this work we present a few machine learning approaches applied to the vertex and the energy reconstruction. Multiple models and architectures were compared and studied, including Boosted Decision Trees (BDT), Deep Neural Networks (DNN), a few kinds of Convolution Neural Networks (CNN), based on ResNet and VGG, and a Graph Neural Network based on DeepSphere. Based on a study, carried out using the dataset, generated by the official JUNO software, we demonstrate that machine learning approaches achieve the necessary level of accuracy for reaching the physical goals of JUNO: $\sigma_E=3\%$ at $E_\text{vis}=1~\text{MeV}$ for the energy and $\sigma_{x,y,z}=10~\text{cm}$ at $E_\text{vis}=1~\text{MeV}$ for the position.