Suppressing Background Radiation Using Poisson Principal Component Analysis

TL;DR

This paper explores the use of Poisson PCA, a variant of principal component analysis tailored for Poisson-distributed data, to improve background radiation modeling and threat detection sensitivity in gamma-ray spectrometry, especially at low photon counts.

Contribution

It introduces Poisson PCA for background radiation modeling and compares its performance to standard PCA, demonstrating potential improvements in nuclear threat detection.

Findings

Poisson PCA outperforms standard PCA at low photon counts.

Poisson PCA provides a more accurate background model in nuclear threat detection.

Enhanced detection sensitivity and specificity are achieved with Poisson PCA.

Abstract

Performance of nuclear threat detection systems based on gamma-ray spectrometry often strongly depends on the ability to identify the part of measured signal that can be attributed to background radiation. We have successfully applied a method based on Principal Component Analysis (PCA) to obtain a compact null-space model of background spectra using PCA projection residuals to derive a source detection score. We have shown the method's utility in a threat detection system using mobile spectrometers in urban scenes (Tandon et al 2012). While it is commonly assumed that measured photon counts follow a Poisson process, standard PCA makes a Gaussian assumption about the data distribution, which may be a poor approximation when photon counts are low. This paper studies whether and in what conditions PCA with a Poisson-based loss function (Poisson PCA) can outperform standard Gaussian PCA in modeling background radiation to enable more sensitive and specific nuclear threat detection.