English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Convolutional neural networks (CNNs) have seen extensive applications inscientific data analysis, including in neutrino telescopes. However, the datafrom these experiments present numerous challenges to CNNs, such as non-regulargeometry, sparsity, and high dimensionality. Consequently, CNNs are highlyinefficient on neutrino telescope data, and require significant pre-processingthat results in information loss. We propose sparse submanifold convolutions(SSCNNs) as a solution to these issues and show that the SSCNN eventreconstruction performance is comparable to or better than traditional andmachine learning algorithms. Additionally, our SSCNN runs approximately 16times faster than a traditional CNN on a GPU. As a result of this speedup, itis expected to be capable of handling the trigger-level event rate ofIceCube-scale neutrino telescopes. These networks could be used to improve thefirst estimation of the neutrino energy and direction to seed more advancedreconstructions, or to provide this information to an alert-sending system toquickly follow-up interesting events.

Trigger-Level Event Reconstruction for Neutrino Telescopes Using Sparse Submanifold Convolutional Neural Networks