Applying Bayesian Neural Networks to Event Reconstruction in Reactor Neutrino Experiments

TL;DR

This paper demonstrates that Bayesian neural networks can significantly improve energy resolution in event reconstruction for reactor neutrino experiments, especially at higher energies, compared to traditional maximum likelihood methods.

Contribution

The study introduces the application of Bayesian neural networks to event reconstruction in reactor neutrino experiments, showing notable improvements in energy resolution over standard methods.

Findings

BNN improves energy resolution significantly.

High-energy electron reconstruction benefits more from BNN.

Uncertainty in vertex position remains unchanged.

Abstract

A toy detector has been designed to simulate central detectors in reactor neutrino experiments in the paper. The electron samples from the Monte-Carlo simulation of the toy detector have been reconstructed by the method of Bayesian neural networks (BNN) and the standard algorithm, a maximum likelihood method (MLD), respectively. The result of the event reconstruction using BNN has been compared with the one using MLD. Compared to MLD, the uncertainties of the electron vertex are not improved, but the energy resolutions are significantly improved using BNN. And the improvement is more obvious for the high energy electrons than the low energy ones.