Towards Optimal Signal Extraction for Imaging X-ray Polarimetry

TL;DR

This paper introduces a deep learning-based optimal signal extraction method for imaging X-ray polarimetry, improving sensitivity and robustness over previous heuristic approaches.

Contribution

It develops a neural network ensemble to select events and measure angles, optimizing polarization signal extraction and reducing reliance on heuristic weighting schemes.

Findings

Achieves ~10% sensitivity improvement (MDP99) over previous methods.

Effectively filters non-conversion events with little polarization sensitivity.

Demonstrates robustness on complex astrophysical spectra.

Abstract

We describe an optimal signal extraction process for imaging X-ray polarimetry using an ensemble of deep neural networks. The initial photo-electron angle, used to recover the polarization, has errors following a von Mises distribution. This is complicated by events converting outside of the fiducial gas volume, whose tracks have little polarization sensitivity. We train a deep ensemble of convolutional neural networks to select against these events and to measure event angles and errors for the desired gas conversion tracks. We show how the expected modulation amplitude from each event gives an optimal weighting to maximize signal-to-noise ratio of the recovered polarization. Applying this weighted maximum likelihood event analysis yields sensitivity (MDP99) improvements of ~10% over earlier heuristic weighting schemes and mitigates the need to adjust said weighting for the source spectrum. We apply our new technique to a selection of astrophysical spectra, including complex extreme examples, and compare the polarization recovery to the current state of the art.