Classifying Complex Faraday Spectra with Convolutional Neural Networks

TL;DR

This paper develops a convolutional neural network to classify Faraday spectra as simple or complex, achieving high accuracy in identifying multiple or thick sources in radio polarization data, aiding future large-scale surveys.

Contribution

The paper introduces a CNN trained specifically for classifying complex Faraday spectra, improving detection accuracy for upcoming radio polarization surveys.

Findings

CNN identifies two-component sources with 99% accuracy under specified conditions.

False positive rate for misclassifying simple sources as complex is below 0.3%.

Method shows promise for analyzing large-scale polarization survey data.

Abstract

Advances in radio spectro-polarimetry offer the possibility to disentangle complex regions where relativistic and thermal plasmas mix in the interstellar and intergalactic media. Recent work has shown that apparently simple Faraday Rotation Measure (RM) spectra can be generated by complex sources. This is true even when the distribution of RMs in the complex source greatly exceeds the errors associated with a single component fit to the peak of the Faraday spectrum. We present a convolutional neural network (CNN) that can differentiate between simple Faraday thin spectra and those that contain multiple or Faraday thick sources. We demonstrate that this CNN, trained for the upcoming Polarisation Sky Survey of the Universe's Magnetism (POSSUM) early science observations, can identify two component sources 99% of the time, provided that the sources are separated in Faraday depth by $>$10% of the FWHM of the Faraday Point Spread Function, the polarized flux ratio of the sources is $>$0.1, and that the Signal-to-Noise radio (S/N) of the primary component is $>$5. With this S/N cut-off, the false positive rate (simple sources mis-classified as complex) is $<$0.3%. Work is ongoing to include Faraday thick sources in the training and testing of the CNN.