Pulse shape discrimination for event rejection in BEGe-type high-purity germanium detectors

Abstract

High-purity germanium detectors are widely used in rare-event searches due to their excellent energy resolution and extremely high intrinsic (radio)purity. In experiments searching for neutrinoless double beta decay in

Ge such as , pulse shape discrimination is required to suppress multi-site

$$\gamma $$ γ

events. In this work, we investigate whether pulse shape discrimination classifiers trained exclusively on

$$\gamma $$ γ

ray data can be used to identify and reject

$$\alpha $$ α

events, without the need for dedicated

$$\alpha $$ α

training. In detectors such as , the total number of registered

$$\alpha $$ α

events over the experiment lifetime is expected to be insufficient to train dedicated classifiers, while still contributing to the background. Two approaches based on machine learning are studied: a multilayer perceptron and a projective likelihood classifier. The p+ surface of a point-contact semi-planar germanium detector was exposed to

$$^{209}$$ 209

Po and

$$^{210}$$ 210

Po sources deposited on a thin gold foil. Two measurement campaigns were performed, yielding

$$1.36\times 10^{5}$$ 1.36 × 10 5

and

$$1.87\times 10^{6}$$ 1.87 × 10 6

$$\alpha $$ α

events, respectively. Both classification methods achieve efficient separation of single-site and multi-site

$$\gamma $$ γ

events while strongly reducing the

$$\alpha $$ α

component. The multilayer perceptron provides the best overall performance, with a signal-like event survival greater than 80%, a background-like event survival below 20%, and an

$$\alpha $$ α

-rejection factor exceeding

$$2.71\times 10^{4}$$ 2.71 × 10 4

. These results demonstrate that robust pulse shape discrimination for high-purity germanium detectors can be achieved using training information derived solely from

$$\gamma $$ γ

events, providing a promising strategy for next-generation neutrinoless double beta decay searches.