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

arXiv: https://arxiv.org/abs/2303.08812 · HTML: https://mlsanity.com/paper/2303.08812/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 34 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 5 of 5)

- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1706.01307/) (2017)
- [A Convolutional Neural Network Neutrino Event Classifier](https://mlsanity.com/paper/1604.01444/) (2016)
- [Scalable Deep Convolutional Neural Networks for Sparse, Locally Dense Liquid Argon Time Projection Chamber Data](https://mlsanity.com/paper/1903.05663/) (2019)
- [A Convolutional Neural Network based Cascade Reconstruction for the IceCube Neutrino Observatory](https://mlsanity.com/paper/2101.11589/) (2021)

## Built on by (most cited first, 4 of 4)

- [Neutrino Reconstruction in TRIDENT Based on Graph Neural Network](https://mlsanity.com/paper/2401.15324/) (2024)
- [Enhancing Events in Neutrino Telescopes through Deep Learning-Driven Super-Resolution](https://mlsanity.com/paper/2408.08474/) (2024)
- [Learning Efficient Representations of Neutrino Telescope Events](https://mlsanity.com/paper/2410.13148/) (2024)
- [Sun sensor calibration algorithms: A systematic mapping and survey](https://mlsanity.com/paper/2507.21541/) (2025)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have seen extensive applications in scientific data analysis, including in neutrino telescopes. However, the data from these experiments present numerous challenges to CNNs, such as non-regular geometry, sparsity, and high dimensionality. Consequently, CNNs are highly inefficient on neutrino telescope data, and require significant pre-processing that results in information loss. We propose sparse submanifold convolutions (SSCNNs) as a solution to these issues and show that the SSCNN event reconstruction performance is comparable to or better than traditional and machine learning algorithms. Additionally, our SSCNN runs approximately 16 times faster than a traditional CNN on a GPU. As a result of this speedup, it is expected to be capable of handling the trigger-level event rate of IceCube-scale neutrino telescopes. These networks could be used to improve the first estimation of the neutrino energy and direction to seed more advanced reconstructions, or to provide this information to an alert-sending system to quickly follow-up interesting events.