Home > Research > Publications & Outputs > Semantic Segmentation with a Sparse Convolution...

Associated organisational unit

Electronic data

  • Sparse_SSNet_Paper_v7

    Rights statement: © 2021 American Physical Society

    Accepted author manuscript, 2.25 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License


Text available via DOI:

View graph of relations

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

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Article number052012
<mark>Journal publication date</mark>26/03/2021
<mark>Journal</mark>Physical Review D
Issue number5
Number of pages15
Publication StatusPublished
<mark>Original language</mark>English


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.

Bibliographic note

© 2021 American Physical Society