Using Geometric Deep Learning for the Detection of the Diffuse Supernova Neutrino Background in Water-Cherenkov Detectors
Abstract
The study of the Diffuse Supernova Neutrino Background (DSNB) is an essential approach to improve our understanding of the formation of Core-Collapse Supernovae, as well as investigating fundamental neutrino properties. The detection of the DSNB flux however is a difficult task, as it requires the disentanglement of its signal with many competitive backgrounds in the low energy range. The main DSNB detection channel is the Inverse Beta Decay (IBD), which is characterised by a distinct, time-separated two-signal signature. This work introduces the use of Graph Neural Networks (GNNs) to handle critical detection and reconstruction tasks for the DSNB through the IBD channel. In particular, we present a model to recover the energy of the first signal from a low energy positron. Additionally, we develop a signal-to-background classifier optimised for the secondary signal, which corresponds to the characteristic photon emission following a neutron capture event. We test our models on two simulations in a Hyper-Kamiokande-like water Cherenkov detector geometry, and show that we obtain performances that are comparable to the state of the art.
Related
- Gamma Neutron Radioactive Source Identification in Water Cherenkov Detectors
- A density-regulated non-phantom dark-energy background tested with DESI DR2 and three supernova compilations
- Search for Diffuse Supernova Neutrino Background of All Flavors with PandaX-4T
- Probing Scalar-Induced First-Order Phase Transitions with the Diffuse Supernova Neutrino Background
- A Two-Parameter Framework for the Diffuse Supernova Neutrino Background
BibTeX
@misc{melennec2026using,
title = {{Using Geometric Deep Learning for the Detection of the Diffuse Supernova Neutrino Background in Water-Cherenkov Detectors}},
author = {Matthieu Melennec and Andrew D Santos and Thomas Mueller and Frédéric Magniette},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.12042},
eprint = {2610.12042},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05829961v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Using Geometric Deep Learning for the Detection of the Diffuse Supernova Neutrino Background in Water-Cherenkov Detectors
AU - Matthieu Melennec
AU - Andrew D Santos
AU - Thomas Mueller
AU - Frédéric Magniette
PY - 2026
DA - 2026/10/08
PB - HAL
DO - 10.48550/arxiv.2610.12042
UR - https://hal.science/hal-05829961v1
AB - The study of the Diffuse Supernova Neutrino Background (DSNB) is an essential approach to improve our understanding of the formation of Core-Collapse Supernovae, as well as investigating fundamental neutrino properties. The detection of the DSNB flux however is a difficult task, as it requires the disentanglement of its signal with many competitive backgrounds in the low energy range. The main DSNB detection channel is the Inverse Beta Decay (IBD), which is characterised by a distinct, time-separated two-signal signature. This work introduces the use of Graph Neural Networks (GNNs) to handle critical detection and reconstruction tasks for the DSNB through the IBD channel. In particular, we present a model to recover the energy of the first signal from a low energy positron. Additionally, we develop a signal-to-background classifier optimised for the secondary signal, which corresponds to the characteristic photon emission following a neutron capture event. We test our models on two simulations in a Hyper-Kamiokande-like water Cherenkov detector geometry, and show that we obtain performances that are comparable to the state of the art.
ER -