Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors

Deep-learning tools are being used extensively in high energy physics and are becoming central in the reconstruction of neutrino interactions in particle detectors. In this work, we report on the performance of a graph neural network in assisting with particle set event reconstruction. The three-dimensional reconstruction of particle tracks produced in neutrino interactions can be subject to ambiguities due to high multiplicity signatures in the detector or leakage of signal between neighboring active detector volumes. Graph neural networks potentially have the capability of identifying all these features to boost the reconstruction performance. As an example case study, we tested a graph neural network, inspired by the graphsage algorithm, on a novel 3D-granular plastic-scintillator detector, that will be used to upgrade the near detector of the T2K experiment. The developed neural network has been trained and tested on diverse neutrino interaction samples, showing very promising results: the classification of particle track voxels produced in the detector can be done with efficiencies and purities of 94%–96% per event and most of the ambiguities can be identified and rejected, while being robust against systematic effects.D. Douqa and F. Sánchez acknowledge the Swiss National Foundation Grant No. 200021_85012. C. Jesús-Valls and T. Lux acknowledge funding from the Spanish Ministerio de Economía y Competitividad (SEIDIMINECO) under Grants No. FPA2016-77347-C2-2-P and SEV-2016-0588. S. Pina-Otey acknowledges the support of the Industrial Doctorates Plan of the Secretariat of Universities and Research of the Department of Business and Knowledge of the Generalitat of Catalonia. IFAE is partially funded by the CERCA program of the Generalitat de Catalunya. The authors also thank T. Jiang, T. Zhao, and D. Wang for their implementation of GraphSAGE, on which the software of this paper was based. This work was initiated in the framework of the T2K Near Detector upgrade project, fruitful discussions in this context with our colleagues are gratefully acknowledged. The authors acknowledge the T2K Collaboration for providing the neutrino interaction and detector simulation software