Background rejection in NEXT using deep neural networks

Abstract

We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.

21 pages, 9 figures; formatting changes

References in corpus (7)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• Double Beta Decay, Majorana Neutrinos, and Neutrino Mass
• Initial results of NEXT-DEMO, a large-scale prototype of the NEXT-100 experiment
• Characterisation of NEXT-DEMO using xenon K${}_{\alpha }$ X-rays
• Phenomenology of neutrinoless double beta decay
• Discovery potential of xenon-based neutrinoless double beta decay experiments in light of small angular scale CMB observations

Cited by in corpus (2)

• Radiopurity assessment of the tracking readout for the NEXT double beta decay experiment
• Radiopurity assessment of the energy readout for the NEXT double beta decay experiment