Deep learning in the DUNE far detectors

by Leigh Howard Whitehead (University of Cambridge (GB))

Friday 11 Dec 2020, 12:30 → 14:00 Europe/London

https://zoom.us/j/304578256

Abstract: The Deep Underground Neutrino Experiment is a next-generation long-baseline neutrino oscillation experiment that aims to measure CP-violation in the neutrino sector as part of a wider physics programme. A key component of these analyses is the ability to accurately identify electron neutrino and muon neutrino interactions. For this purpose, a convolutional neural network algorithm has been developed to select electron and muon (anti)neutrino candidates, with peak selection efficiencies of 90% (94%) and 96% (97%), respectively. Furthermore, deep-learning-based approaches for neutrino energy reconstruction and fast simulations will be discussed.

Connections will begin at 12:30 with the seminar beginning at 13:00.