Improving neutrino energy estimation of charged-current interaction events with recurrent neural networks in MicroBooNE

TL;DR

This paper introduces a deep learning approach using recurrent neural networks to improve neutrino energy estimation in the MicroBooNE experiment, achieving better resolution and reduced bias over traditional methods.

Contribution

The paper presents a novel RNN-based neutrino energy estimator that enhances accuracy and reduces bias in LArTPC detector data, validated with MicroBooNE data and simulations.

Findings

Improved energy resolution and reduced bias with RNN approach

Validated method with MicroBooNE data-simulation consistency tests

Enhanced physics sensitivity in neutrino oscillation studies

Abstract

We present a deep learning-based method for estimating the neutrino energy of charged-current neutrino-argon interactions. We employ a recurrent neural network (RNN) architecture for neutrino energy estimation in the MicroBooNE experiment, utilizing liquid argon time projection chamber (LArTPC) detector technology. Traditional energy estimation approaches in LArTPCs, which largely rely on reconstructing and summing visible energies, often experience sizable biases and resolution smearing because of the complex nature of neutrino interactions and the detector response. The estimation of neutrino energy can be improved after considering the kinematics information of reconstructed final-state particles. Utilizing kinematic information of reconstructed particles, the deep learning-based approach shows improved resolution and reduced bias for the muon neutrino Monte Carlo simulation sample compared to the traditional approach. In order to address the common concern about the effectiveness of this method on experimental data, the RNN-based energy estimator is further examined and validated with dedicated data-simulation consistency tests using MicroBooNE data. We also assess its potential impact on a neutrino oscillation study after accounting for all statistical and systematic uncertainties and show that it enhances physics sensitivity. This method has good potential to improve the performance of other physics analyses.