Pulse Pileup Rejection Methods Using a Two-Component Gaussian Mixture Model for Fast Neutron Detection with Pulse Shape Discriminating Scintillator

TL;DR

This paper introduces a two-component Gaussian mixture model for pulse shape discrimination in scintillators, effectively identifying and removing pileup events in neutron detection to improve analysis accuracy.

Contribution

It proposes a novel anomaly score based on an unsupervised two-component model for fast neutron detection, enhancing pileup rejection capabilities.

Findings

The G score effectively identifies pileup events.

Machine learning methods improve classification accuracy.

The model is applicable across various energy ranges.

Abstract

Pulse shape discriminating scintillator materials in many cases allow the user to identify two basic kinds of pulses arising from two kinds of particles: neutrons and gammas. An uncomplicated solution for building a classifier consists of a two-component mixture model learned from a collection of pulses from neutrons and gammas at a range of energies. Depending on the conditions of data gathered to be classified, multiple classes of events besides neutrons and gammas may occur, most notably pileup events. All these kinds of events are anomalous and, in cases where the class of the particle is in doubt, it is preferable to remove them from the analysis. This study compares the performance of several machine learning and analytical methods for using the scores from the two-component model to identify anomalous events and in particular to remove pileup events. A specific outcome of this study is to propose a novel anomaly score, denoted G, from an unsupervised two-component model that is conveniently distributed on the interval [-1,1].