Inferring astrophysical X-ray polarization with deep learning

@article{Moriakov2020InferringAX,
  title={Inferring astrophysical X-ray polarization with deep learning},
  author={Nikita Moriakov and Ashwin Samudre and Michela Negro and Fabian Gieseke and Sydney Otten and Luc Hendriks},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.08126}
}
We investigate the use of deep learning in the context of X-ray polarization detection from astrophysical sources as will be observed by the Imaging X-ray Polarimetry Explorer (IXPE), a future NASA selected space-based mission expected to be operative in 2021. In particular, we propose two models that can be used to estimate the impact point as well as the polarization direction of the incoming radiation. The results obtained show that data-driven approaches depict a promising alternative to… 

Figures from this paper

A deep ensemble approach to X-ray polarimetry

TLDR
This work derives and applies the optimal event weighting for maximizing the polarization signal-to-noise ratio (SNR) in track reconstruction algorithms, providing a ∼ 40% decrease in required exposure times for a given SNR.

A deep ensemble approach to X-ray polarimetry

TLDR
This work derives and applies the optimal event weighting for maximizing the polarization signal-to-noise ratio (SNR) in track reconstruction algorithms, providing a ∼ 40% decrease in required exposure times for a given SNR.

Deep Ensemble Analysis for Imaging X-ray Polarimetry

TLDR
This work proposes a method for enhancing the sensitivity of X-ray telescopic observations with imaging polarimeters by using a weighted maximum likelihood combination of predictions from a deep ensemble of ResNet convolutional neural networks, trained on Monte Carlo event simulations.

HexCNN: A Framework for Native Hexagonal Convolutional Neural Networks

TLDR
Experimental results show that compared with the state-of-the-art models, which imitate hexagonal processing but using rectangle-shaped filters, HexCNN reduces the training time and saves the memory space cost, and outperforms existing hexagonal CNN methods substantially.

References

SHOWING 1-10 OF 17 REFERENCES

An Overview of X-Ray Polarimetry of Astronomical Sources

We review the history of astronomical X-ray polarimetry based on the author’s perspective, beginning with early sounding-rocket experiments by Robert Novick at Columbia University and his team, of

An efficient photoelectric X-ray polarimeter for the study of black holes and neutron stars

TLDR
The development of an instrument that makes X-ray polarimetry possible is reported, and the factor of 100 improvement in sensitivity that is achieved will allow direct exploration of the most dramatic objects of theX-ray sky.

Very Deep Convolutional Networks for Large-Scale Image Recognition

TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

HexagDLy - Processing hexagonally sampled data with CNNs in PyTorch

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

TLDR
A new theoretical framework is developed casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes, which mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy.

Weight Uncertainty in Neural Networks

TLDR
This work introduces a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop, and shows how the learnt uncertainty in the weights can be used to improve generalisation in non-linear regression problems.

Deep Residual Learning for Image Recognition

TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift

TLDR
A large-scale benchmark of existing state-of-the-art methods on classification problems and the effect of dataset shift on accuracy and calibration is presented, finding that traditional post-hoc calibration does indeed fall short, as do several other previous methods.

Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks

TLDR
It is demonstrated that TreeNets can improve ensemble performance and that diverse ensembles can be trained end-to-end under a unified loss, achieving significantly higher "oracle" accuracies than classical ensembled.

HexaConv

TLDR
It is found that, due to the reduced anisotropy of hexagonal filters, planar HexaConv provides better accuracy than planar convolution with square filters, given a fixed parameter budget, and the increased degree of symmetry of the hexagonal grid increases the effectiveness of group convolutions, by allowing for more parameter sharing.