A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber

TL;DR

This paper introduces a convolutional neural network capable of pixel-level object identification in liquid argon time projection chamber images, advancing the data reconstruction process for neutrino detectors.

Contribution

It is the first to develop and validate a deep neural network for pixel-level object detection in LArTPC data, enhancing event reconstruction accuracy.

Findings

Successful pixel-level predictions on real MicroBooNE data

Demonstrated network's validity on muon and neutrino interaction samples

Established a foundation for deep learning-based data reconstruction in neutrino experiments

Abstract

We have developed a convolutional neural network (CNN) that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training techniques, and software tools developed to train this network. The goal of this work is to develop a complete deep neural network based data reconstruction chain for the MicroBooNE detector. We show the first demonstration of a network's validity on real LArTPC data using MicroBooNE collection plane images. The demonstration is performed for stopping muon and a $\nu_\mu$ charged current neutral pion data samples.