Semantic Segmentation with a Sparse Convolutional Neural Network for Event Reconstruction in MicroBooNE

Blake, A. and Devitt, D. and Nowak, J. and Thorpe, C. (2021) Semantic Segmentation with a Sparse Convolutional Neural Network for Event Reconstruction in MicroBooNE. Physical Review D, 103 (5): 052012. ISSN 1550-7998

Text (Sparse_SSNet_Paper_v7)
Sparse_SSNet_Paper_v7.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.
Download (2MB)

Abstract

We present the performance of a semantic segmentation network, SparseSSNet, that provides pixel-level classification of MicroBooNE data. The MicroBooNE experiment employs a liquid argon time projection chamber for the study of neutrino properties and interactions. SparseSSNet is a submanifold sparse convolutional neural network, which provides the initial machine learning based algorithm utilized in one of MicroBooNE's $\nu_e$-appearance oscillation analyses. The network is trained to categorize pixels into five classes, which are re-classified into two classes more relevant to the current analysis. The output of SparseSSNet is a key input in further analysis steps. This technique, used for the first time in liquid argon time projection chambers data and is an improvement compared to a previously used convolutional neural network, both in accuracy and computing resource utilization. The accuracy achieved on the test sample is $\geq 99\%$. For full neutrino interaction simulations, the time for processing one image is $\approx$ 0.5 sec, the memory usage is at 1 GB level, which allows utilization of most typical CPU worker machine.