Three-dimensional convolutional neural networks for neutrinoless double-beta decay signal/background discrimination in high-pressure gaseous Time Projection Chamber

TL;DR

This paper demonstrates that 3D convolutional neural networks effectively discriminate neutrinoless double-beta decay signals from background in high-pressure gaseous TPCs, outperforming previous methods and showing robustness under various conditions.

Contribution

The study adapts 3D CNNs for event classification in TPCs, showing significant accuracy improvements and robustness over prior approaches.

Findings

3D CNNs outperform previous classifiers in accuracy.

Network depth and 3D structure enhance discrimination power.

Models remain stable under different spatial granularities and noise conditions.

Abstract

In the search for neutrinoless double-beta decay, the high-pressure gaseous Time Projection Chamber has a distinct advantage, because the ionization charge tracks produced by particle interactions are extended and the detector captures the full three-dimensional charge distribution with appropriate charge readout systems. Such information of tracks provides a crucial extra-handle for discriminating signal events against backgrounds. In this paper, we constructed a toy model to demonstrate where the discrimination power comes from and how much of it the neural network models have already harnessed. Then we adapted 3-dimensional convolutional and residual neural networks on the simulated double-beta and background charge tracks and tested their capabilities in classifying these two types of events. We show that both the 3D structure and the overall depth of the neural networks significantly improve the accuracy of the classifier and lead to results better than previous works. We also studied their performance under various spatial granularities as well as different diffusion and noise conditions. The results indicate that the methods are stable and generalize well despite varying experimental conditions.