Home > Research > Publications & Outputs > Deep neural network for pixel-level electromagn...

Associated organisational unit

Electronic data

  • 1808.07269v1

    Rights statement: © 2019 American Physical Society

    Accepted author manuscript, 3.39 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License


Text available via DOI:

View graph of relations

Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Article number092001
<mark>Journal publication date</mark>7/05/2019
<mark>Journal</mark>Physical Review D
Issue number9
Number of pages20
Publication StatusPublished
<mark>Original language</mark>English


We have developed a convolutional neural network 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.

Bibliographic note

© 2019 American Physical Society