29 July 2019 to 2 August 2019
Northeastern University
US/Eastern timezone

Deep Learning for Event Reconstruction at DUNE

31 Jul 2019, 14:20
20m
Shillman 425 (Northeastern University)

Shillman 425

Northeastern University

Oral Presentation Computing, Analysis Tools, & Data Handling Computing, Analysis Tools, & Data Handling

Speaker

Jianming Bian (University of California Irvine (US))

Description

DUNE is the next-generation neutrino experiment will play a decisive role to measure neutrino CP violation and mass hierarchy. DUNE far detectors will use liquid argon time projection chamber (LArTPC) technology which provides an excellent spatial resolution, high neutrino detection efficiency, and superb background rejection. To successfully accomplish the role of DUNE, the reconstruction of neutrino event is crucial. However, precise reconstruction can be limited by missing energy, detector response, invisible energy, and hadron identities. To address these issues, we developed deep learning methods, Convolutional Neural Networks (CNNs), to reconstruct neutrino events directly from pixel images of interactions in the detector. In this talk, we will focus on developments of CNNs to reconstruct the neutrino energies and interaction vertices.

Primary authors

Ilsoo Seong (University of California Irvine (US)) Jianming Bian (University of California Irvine (US))

Presentation Materials