Graph Neural Networks for Reconstruction

US/Central
Description

Recorded Meeting Video: https://youtu.be/DQAogJX5shk

    • 12:00 12:30
      Graph Neural Networks for Reconstruction in DUNE 30m

      The Deep Underground Neutrino Experiment is a next-generation long-baseline neutrino oscillation experiment, designed to measure current unknowns in neutrino oscillation phenomenology. Its high-resolution detectors benefit from ML-based reconstruction techniques, which currently provide the backbone of its projected sensitivity to primary physics goals. This talk will discuss the development of graph neural network (GNN) based low-level reconstruction techniques, using an attention message-passing network to classify the relationships between detector hits into different particle types. The current benchmark achieves 84% accuracy in graph edge classification, with more advanced techniques currently in development.

      Speaker: Jeremy Hewes (University of Cincinnati)
    • 12:30 13:00
      Graph Neural Networks for Reconstruction at the LHC 30m
      Speaker: Savannah Thais (Yale University)