Pulse Shape Discrimination Algorithms: Survey and Benchmark

TL;DR

This paper surveys and benchmarks pulse shape discrimination algorithms for radiation detection, comparing traditional and deep learning methods on standardized datasets with open-source tools.

Contribution

It provides a comprehensive evaluation of nearly sixty PSD algorithms, highlighting deep learning's superior performance and releasing open-source datasets and code.

Findings

Deep learning models, especially MLPs, outperform traditional methods.

Hybrid approaches combining features and neural regression show strong results.

The open-source toolbox and datasets facilitate reproducibility and further research.

Abstract

This review presents a comprehensive survey and benchmark of pulse shape discrimination (PSD) algorithms for radiation detection, classifying nearly sixty methods into statistical (time-domain, frequency-domain, neural network-based) and prior-knowledge (machine learning, deep learning) paradigms. We implement and evaluate all algorithms on two standardized datasets: an unlabeled set from a 241Am-9Be source and a time-of-flight labeled set from a 238Pu-9Be source, using metrics including Figure of Merit (FOM), F1-score, ROC-AUC, and inter-method correlations. Our analysis reveals that deep learning models, particularly Multi-Layer Perceptrons (MLPs) and hybrid approaches combining statistical features with neural regression, often outperform traditional methods. We discuss architectural suitabilities, the limitations of FOM, alternative evaluation metrics, and performance across energy thresholds. Accompanying this work, we release an open-source toolbox in Python and MATLAB, along with the datasets, to promote reproducibility and advance PSD research.