Bonn 2020 – wissenschaftliches Programm

Die DPG-Frühjahrstagung in Bonn musste abgesagt werden! Lesen Sie mehr ...

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 39: Methods of astroparticle physics III

T 39.5: Vortrag

Dienstag, 31. März 2020, 18:00–18:15, L-3.002

A study of the detectability of the DSNB through high resolution convolutional neural networks for next generation neutrino experiments — •David Maksimovic, Michael Wurm, and Michael Nieslony for the ANNIE collaboration — Johannes Gutenberg-Universität, Mainz, Deutschland

The ANNIE experiment (Accelerator Neutrino Neutron Interaction Experiment) at Fermilab is a 26-ton Gadolinium-loaded water Cherenkov detector. Its scientific aim is to study cross-sections and neutron multiplicity from the interactions of GeV neutrinos in the Booster Neutrino Beam. Moreover, ANNIE serves as test bench for new experimental techniques, e.g. the application of Convolutional Neural Networks (CNN) for event classification based on detector hit maps.
Here, we report on the performance of a CNN being developed to distinguish the signals of positrons emitted in Inverse Beta Decays from a background of neutral current interactions induced by GeV neutrinos. The resulting event classifier is of high relevance for the detection of the Diffuse Supernova Neutrino Background (DSNB) in the current Super-Kamiokande+gadolinium phase as well as for future water-based liquid scintillator experiments like THEIA.