# A deep ensemble approach to X-ray polarimetry

arXiv: https://arxiv.org/abs/2111.03047 · HTML: https://mlsanity.com/paper/2111.03047/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Deep Ensembles: A Loss Landscape Perspective](https://mlsanity.com/paper/1912.02757/) (2019)
- [Deep Ensembles from a Bayesian Perspective](https://mlsanity.com/paper/2105.13283/) (2021)
- [HexagDLy - Processing hexagonally sampled data with CNNs in PyTorch](https://mlsanity.com/paper/1903.01814/) (2019)
- [Inferring astrophysical X-ray polarization with deep learning](https://mlsanity.com/paper/2005.08126/) (2020)
- [Deep Ensemble Analysis for Imaging X-ray Polarimetry](https://mlsanity.com/paper/2007.03828/) (2020)

## Abstract (arXiv)

X-ray polarimetry will soon open a new window on the high energy universe with the launch of NASA's Imaging X-ray Polarimetry Explorer (IXPE). Polarimeters are currently limited by their track reconstruction algorithms, which typically use linear estimators and do not consider individual event quality. We present a modern deep learning method for maximizing the sensitivity of X-ray telescopic observations with imaging polarimeters, with a focus on the gas pixel detectors (GPDs) to be flown on IXPE. We use a weighted maximum likelihood combination of predictions from a deep ensemble of ResNets, trained on Monte Carlo event simulations. We derive and apply the optimal event weighting for maximizing the polarization signal-to-noise ratio (SNR) in track reconstruction algorithms. For typical power-law source spectra, our method improves on the current state of the art, providing a ~40% decrease in required exposure times for a given SNR.