Trigger-Level Event Reconstruction for Neutrino Telescopes Using Sparse Submanifold Convolutional Neural Networks
This work addresses the challenge of real-time event reconstruction for neutrino telescopes like IceCube, enabling faster trigger-level processing to improve energy and direction estimates for alerts, though it is incremental as it builds on existing CNN methods.
The paper tackled the inefficiency of CNNs in neutrino telescope data analysis due to non-regular geometry and sparsity by proposing sparse submanifold convolutions (SSCNNs), achieving comparable or better event reconstruction performance and running approximately 16 times faster than traditional CNNs on a GPU.
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.