Background rejection in NEXT using deep neural networks

TL;DR

This paper explores the use of deep neural networks to improve background rejection in neutrinoless double beta decay searches with high pressure xenon detectors, achieving better classification than previous methods.

Contribution

It demonstrates that deep learning can effectively distinguish signal from background events based on topological signatures, surpassing prior techniques.

Findings

Deep neural networks outperform previous methods by a factor of 1.2 to 1.6.

Networks trained on thousands of events can classify signals with high accuracy.

Potential exists for further improvements in background rejection.

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.