Neutrino Interaction Vertex Reconstruction in DUNE with Pandora Deep Learning

TL;DR

This paper presents a deep learning-based method for neutrino interaction vertex reconstruction in DUNE, significantly improving accuracy over previous techniques by integrating a U-ResNet neural network into the Pandora reconstruction framework.

Contribution

The paper introduces a novel vertex-finding procedure using U-ResNet neural networks integrated into Pandora, enhancing vertex reconstruction efficiency in neutrino detectors.

Findings

Over 20% increase in sub-1 cm vertex reconstruction efficiency

Seamless integration of deep learning into existing pattern recognition algorithms

Outperforms previous BDT-based vertex-finding solutions

Abstract

The Pandora Software Development Kit and algorithm libraries perform reconstruction of neutrino interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at the Deep Underground Neutrino Experiment, which will operate four large-scale liquid argon time projection chambers at the far detector site in South Dakota, producing high-resolution images of charged particles emerging from neutrino interactions. While these high-resolution images provide excellent opportunities for physics, the complex topologies require sophisticated pattern recognition capabilities to interpret signals from the detectors as physically meaningful objects that form the inputs to physics analyses. A critical component is the identification of the neutrino interaction vertex. Subsequent reconstruction algorithms use this location to identify the individual primary particles and ensure they each result in a separate reconstructed particle. A new vertex-finding procedure described in this article integrates a U-ResNet neural network performing hit-level classification into the multi-algorithm approach used by Pandora to identify the neutrino interaction vertex. The machine learning solution is seamlessly integrated into a chain of pattern-recognition algorithms. The technique substantially outperforms the previous BDT-based solution, with a more than 20\% increase in the efficiency of sub-1\,cm vertex reconstruction across all neutrino flavours.