Dortmund 2021 – scientific programme

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

T: Fachverband Teilchenphysik

T 47: Experimental techniques in astroparticle physics II

T 47.7: Talk

Tuesday, March 16, 2021, 17:30–17:45, Tv

Application of graph neural networks to classification and reconstruction tasks in KM3NeT — •Daniel Guderian and Alexander Kappes for the KM3NeT collaboration — WWU Münster

The KM3NeT neutrino telescope consists of a network of large-volume Cherenkov detectors at the bottom of the Mediterranean Sea, destined to search for neutrino interactions in water. With its two different sites, ORCA and ARCA, specializing in lower and higher neutrino energies, respectively, it aims at studying physics spanning from the determination of the neutrino mass hierarchy to detection of neutrinos from astrophysical objects. Currently under construction, data from the first deployed detector units, each holding 18 optical modules for the Cherenkov light detection, is available for analysis.

This talk presents results from studies on event classification and reconstruction for the ORCA detector, consisting of four detector units, based on graph neural networks.