Digital Pulseshape Analysis by Neural Networks for the Heidelberg-Moscow-Double-Beta-Decay-Experiment

TL;DR

This paper introduces a neural network-based digital pulse shape analysis technique to improve event discrimination in the Heidelberg-Moscow double-beta decay experiment, enhancing sensitivity by better background rejection.

Contribution

It presents a novel neural network approach for pulse shape analysis that utilizes all recorded digital pulse information for improved event classification.

Findings

Enhanced background discrimination in the experiment.

Neural network method outperforms traditional cut-based techniques.

Potential for increased sensitivity in neutrinoless double-beta decay searches.

Abstract

The Heidelberg-Moscow Experiment is presently the most sensitive experiment looking for neutrinoless double-beta decay. Recently the already very low background has been lowered by means of a Digital Pulseshape Analysis using a one parameter cut to distinguish between pointlike events and multiple scattered events. To use all the information contained in a recorded digital pulse, we developed a new technique for event recognition based on neural networks.