Dortmund 2021 – scientific programme

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

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 2: AKPIK II: Deep Learning

AKPIK 2.6: Talk

Wednesday, March 17, 2021, 17:15–17:30, AKPIKa

Event reconstruction in JUNO-TAO using Deep Learning — •Vidhya Thara Hariharan — Institute for Experimental Physics, University of Hamburg

The primary goal of JUNO is to resolve the neutrino mass hierarchy using precision spectral measurements of reactor antineutrino oscillations. To achieve this goal a precise knowledge of the unoscillated reactor spectrum is required in order to constrain its fine structure. To account for this, TAO (Taishan Antineutrino Observatory), a ton-level, high energy resolution liquid scintillator detector with a baseline of about 30 m, is set up as a reference detector to JUNO. The 20% increase in the coverage of photosensors, the installation of Silicon Photomultipliers (SiPMs) instead of PMTs, the smaller dimension and the low temperature at -51^∘C, would enable TAO to achieve a photoelectron yield of 4500 p.e./MeV as compared to 1200 p.e./MeV in JUNO. This would in turn help TAO to achieve an energy resolution of 1.5/E(MeV). The measurement of the reactor antineutrino spectrum with this energy resolution will provide a model-independent reference spectrum for JUNO.

The reconstruction can be performed using several approaches. However previous studies have proved Deep Learning yields competitive reconstruction results. Hence this work aims at demonstrating the general applicability of Graph neural networks (GNNs) to reconstruct vertex and energy and later at studying the directionality.