Dortmund 2021 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

T: Fachverband Teilchenphysik

T 67: Neutrino astronomy III

T 67.9: Talk

Wednesday, March 17, 2021, 18:00–18:15, Tq

Particle identification by high resolution convolutional neural networks for the DSNB detection in next generation neutrino experiments — •David Maksimovic, Michael Nieslony, and Michael Wurm — Johannes Gutenberg-Universität, Mainz, DE

An important physics goal of next generation neutrino experiments is the search for the Diffuse Supernova Neutrino Background (DSNB), which is an isotropic neutrino signal composed of all the supernova explosions that occurred throughout the observable universe. Through the addition of Gadolinium to water Cherenkov detectors, many of the single-event backgrounds that were problematic in earlier analyses can be suppressed, generating a possible detection window from 10 to 30 MeV. Within this window, neutral current (NC) events of atmospheric neutrinos are the main remaining background. This talk presents the application of convolutional neural networks (CNN) for the identification and rejection of such atmospheric NC background events in future DSNB searches. The developed CNNs show very promising results and could prove to be of high relevance for measuring this signal in next generation neutrino experiments.