Interpretable Faraday Complexity Classification

Abstract

Faraday complexity describes whether a spectropolarimetric observation has simple or complex magnetic structure. Quickly determining the Faraday complexity of a spectropolarimetric observation is important for processing large, polarised radio surveys. Finding simple sources lets us build rotation measure grids, and finding complex sources lets us follow these sources up with slower analysis techniques or further observations. We introduce five features that can be used to train simple, interpretable machine learning classifiers for estimating Faraday complexity. We train logistic regression and extreme gradient boosted tree classifiers on simulated polarised spectra using our features, analyse their behaviour, and demonstrate our features are effective for both simulated and real data. This is the first application of machine learning methods to real spectropolarimetry data. With 95 per cent accuracy on simulated ASKAP data and 90 per cent accuracy on simulated ATCA data, our method performs comparably to state-of-the-art convolutional neural networks while being simpler and easier to interpret. Logistic regression trained with our features behaves sensibly on real data and its outputs are useful for sorting polarised sources by apparent Faraday complexity.

arXiv commentAccepted for publication in PASA

References in corpus (11)

• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• Complex Faraday depth structure of Active Galactic Nuclei as revealed by broadband radio polarimetry
• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• Comparison of algorithms for determination of rotation measure and Faraday structure I. 1100 - 1400 MHz
• A Broadband Polarization Catalog of Extragalactic Radio Sources
• Broadband Radio Polarimetry and Faraday Rotation of 563 Extragalactic Radio Sources
• Broadband, radio spectro-polarimetric study of 100 radiative-mode and jet-mode AGN
• Spectropolarimetry with the Allen Telescope Array: Faraday Rotation toward Bright Polarized Radio Galaxies
• A Broadband Spectro-polarimetric View of the NVSS Rotation Measure Catalogue I: Breaking the nπ-ambiguity
• Heightened Faraday Complexity in the inner 1 kpc of the Galactic Centre
• Performance test of QU-fitting in cosmic magnetism study

Cited by in corpus (8)

• RMTable2023 and PolSpectra2023: standards for reporting polarization and Faraday rotation measurements of radio sources
• A Radio Polarisation Study of Magnetic Fields in the Small Magellanic Cloud
• Full Resolution Deconvolution of Complex Faraday Spectra
• The Global Magneto-Ionic Medium Survey (GMIMS): The brightest polarized region in the Southern sky at 75cm and its implications for Radio Loop II
• Faraday moments of the Southern Twenty-centimeter All-sky Polarization Survey (STAPS)
• The Galactic latitude dependency of Faraday complexity in the S-PASS/ATCA RM catalogue
• Wavelets and sparsity for Faraday tomography
• Semi-Supervised Rotation Measure Deconvolution and its application to MeerKAT observations of galaxy clusters