# Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube

arXiv: https://arxiv.org/abs/2209.03042 · HTML: https://mlsanity.com/paper/2209.03042/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 45 references that are in the map.
- First posted on arXiv 7 Sep 2022.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [A survey of loss functions for semantic segmentation](https://mlsanity.com/paper/2006.14822/) (2020)
- [Early stopping and non-parametric regression: An optimal data-dependent stopping rule](https://mlsanity.com/paper/1306.3574/) (2013)
- [Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs](https://mlsanity.com/paper/1812.04616/) (2018)
- [Graph Neural Networks for IceCube Signal Classification](https://mlsanity.com/paper/1809.06166/) (2018)
- [Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks](https://mlsanity.com/paper/2002.11867/) (2020)
- [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, 8 of 8)

- [Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics](https://mlsanity.com/paper/2402.12535/) (2024)
- [GraphNeT: Graph neural networks for neutrino telescope event reconstruction](https://mlsanity.com/paper/2210.12194/) (2022)
- [Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere](https://mlsanity.com/paper/2604.19846/) (2026)
- [Neutrino Reconstruction in TRIDENT Based on Graph Neural Network](https://mlsanity.com/paper/2401.15324/) (2024)
- [Learning Efficient Representations of Neutrino Telescope Events](https://mlsanity.com/paper/2410.13148/) (2024)
- [Tagging fully hadronic exotic decays of the vectorlike B quark using a graph neural network](https://mlsanity.com/paper/2505.07769/) (2025)
- [NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes](https://mlsanity.com/paper/2511.13111/) (2025)
- [From IceCube to IT-Sphere: A Hybrid Quantum-Classical GNN for Banking IT Root Cause Analysis](https://mlsanity.com/paper/2609.22822/) (2026)

## Abstract (arXiv)

IceCube, a cubic-kilometer array of optical sensors built to detect atmospheric and astrophysical neutrinos between 1 GeV and 1 PeV, is deployed 1.45 km to 2.45 km below the surface of the ice sheet at the South Pole. The classification and reconstruction of events from the in-ice detectors play a central role in the analysis of data from IceCube. Reconstructing and classifying events is a challenge due to the irregular detector geometry, inhomogeneous scattering and absorption of light in the ice and, below 100 GeV, the relatively low number of signal photons produced per event. To address this challenge, it is possible to represent IceCube events as point cloud graphs and use a Graph Neural Network (GNN) as the classification and reconstruction method. The GNN is capable of distinguishing neutrino events from cosmic-ray backgrounds, classifying different neutrino event types, and reconstructing the deposited energy, direction and interaction vertex. Based on simulation, we provide a comparison in the 1-100 GeV energy range to the current state-of-the-art maximum likelihood techniques used in current IceCube analyses, including the effects of known systematic uncertainties. For neutrino event classification, the GNN increases the signal efficiency by 18% at a fixed false positive rate (FPR), compared to current IceCube methods. Alternatively, the GNN offers a reduction of the FPR by over a factor 8 (to below half a percent) at a fixed signal efficiency. For the reconstruction of energy, direction, and interaction vertex, the resolution improves by an average of 13%-20% compared to current maximum likelihood techniques in the energy range of 1-30 GeV. The GNN, when run on a GPU, is capable of processing IceCube events at a rate nearly double of the median IceCube trigger rate of 2.7 kHz, which opens the possibility of using low energy neutrinos in online searches for transient events.