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

Adams, C. and Alrashed, M. and An, R. and Anthony, J. and Asaadi, J. and Ashkenazi, A. and Auger, M. and Balasubramanian, S. and Baller, B. and Barnes, C. and Barr, G. and Bass, M. and Bay, F. and Bhat, A. and Bhattacharya, K. and Bishai, M. and Blake, A. and Bolton, T. and Camilleri, L. and Caratelli, D. and Terrazas, I. Caro and Fernandez, R. Castillo and Cavanna, F. and Cerati, G. and Church, E. and Cianci, D. and Cohen, E. and Collin, G. H. and Conrad, J. M. and Convery, M. and Cooper-Troendle, L. and Crespo-Anadon, J. I. and Tutto, M. Del and Devitt, D. and Diaz, A. and Duffy, K. and Dytman, S. and Eberly, B. and Ereditato, A. and Sanchez, L. Escudero and Esquivel, J. and Fadeeva, A. A. and Fitzpatrick, R. S. and Fleming, B. T. and Franco, D. and Furmanski, A. P. and Garcia-Gamez, D. and Garvey, G. T. and Lister, A. and Nowak, J. (2019) Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber. Physical Review D, 99 (9). ISSN 1550-7998

[img]
Preview
PDF (1808.07269v1)
1808.07269v1.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.

Download (3MB)

Abstract

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.

Item Type:
Journal Article
Journal or Publication Title:
Physical Review D
Additional Information:
© 2019 American Physical Society
Subjects:
ID Code:
131237
Deposited By:
Deposited On:
12 Feb 2019 11:30
Refereed?:
Yes
Published?:
Published
Last Modified:
20 Sep 2020 05:00