CNNs for enhanced background discrimination in DSNB searches in large-scale water-Gd detectors. (arXiv:2104.13426v1 [physics.ins-det])
<a href="http://arxiv.org/find/physics/1/au:+Maksimovic_D/0/1/0/all/0/1">David Maksimović</a>, <a href="http://arxiv.org/find/physics/1/au:+Nieslony_M/0/1/0/all/0/1">Michael Nieslony</a>, <a href="http://arxiv.org/find/physics/1/au:+Wurm_M/0/1/0/all/0/1">Michael Wurm</a>
Gadolinium-loading of large water Cherenkov detectors is a prime method for
the detection of the Diffuse Supernova Neutrino Background (DSNB). While the
enhanced neutron tagging capability greatly reduces single-event backgrounds,
correlated events mimicking the IBD coincidence signature remain a potentially
harmful background. Neutral-Current (NC) interactions of atmospheric neutrinos
potentially dominate the DSNB signal especially in the low-energy range of the
observation window that reaches from about 12 to 30 MeV.
The present paper investigates a novel method for the discrimination of this
background. Convolutional Neural Networks (CNNs) offer the possibility for a
direct analysis and classification of the PMT hit patterns of the prompt
events. Based on the events generated in a simplified SuperKamiokande-like
detector setup, we find that a trained CNN can maintain a signal efficiency of
96 % while reducing the residual NC background to 2 % of the original rate.
Comparing to recent predictions of the DSNB signal and measurements of the NC
background levels in Super-Kamiokande, the corresponding signal-to-background
ratio is about 4:1, providing excellent conditions for a DSNB discovery.
Gadolinium-loading of large water Cherenkov detectors is a prime method for
the detection of the Diffuse Supernova Neutrino Background (DSNB). While the
enhanced neutron tagging capability greatly reduces single-event backgrounds,
correlated events mimicking the IBD coincidence signature remain a potentially
harmful background. Neutral-Current (NC) interactions of atmospheric neutrinos
potentially dominate the DSNB signal especially in the low-energy range of the
observation window that reaches from about 12 to 30 MeV.
The present paper investigates a novel method for the discrimination of this
background. Convolutional Neural Networks (CNNs) offer the possibility for a
direct analysis and classification of the PMT hit patterns of the prompt
events. Based on the events generated in a simplified SuperKamiokande-like
detector setup, we find that a trained CNN can maintain a signal efficiency of
96 % while reducing the residual NC background to 2 % of the original rate.
Comparing to recent predictions of the DSNB signal and measurements of the NC
background levels in Super-Kamiokande, the corresponding signal-to-background
ratio is about 4:1, providing excellent conditions for a DSNB discovery.
http://arxiv.org/icons/sfx.gif
