Semi-Supervised Rotation Measure Deconvolution and its application to MeerKAT observations of galaxy clusters

Abstract: Faraday rotation contains information about the magnetic field structure along the line of sight and is an important instrument in the study of cosmic magnetism. Traditional Faraday spectrum deconvolution methods such as RMCLEAN face challenges in resolving complex Faraday dispersion functions and handling large datasets. We develop a deep learning deconvolution model to enhance the accuracy and efficiency of extracting Faraday rotation measures from radio astronomical data, specifically targeting data from the MeerKAT Galaxy Cluster Legacy Survey (MGCLS). We use semi-supervised learning, where the model simultaneously recreates the data and minimizes the difference between the output and the true signal of synthetic data. Performance comparisons with RMCLEAN were conducted on simulated as well as real data for the galaxy cluster Abell 3376. Our semi-supervised model is able to recover the Faraday dispersion with great accuracy, particularly for complex or high-RM signals, maintaining sensitivity across a broad RM range. The computational efficiency of this method is significantly improved over traditional methods. Applied to observations of Abell 3376, we find detailed magnetic field structures in the radio relics, and several AGN. We also apply our model to MeerKAT data of Abell 85, Abell 168, Abell 194, Abell 3186 and Abell 3667.