RFI-DRUnet: Restoring dynamic spectra corrupted by radio frequency interference -- Application to pulsar observations
Xiao Zhang, Ismaël Cognard, Nicolas Dobigeon
TL;DR
This work reframes radio frequency interference mitigation in pulsar observations as a restoration problem rather than a pure detection task. It introduces RFI-DRUnet, a DRUNet-inspired deep network trained on a physics- and statistics-based data-generation framework that separately simulates pulsar signals and RFI before combining them into realistic, labeled dynamic spectra. Across extensive synthetic experiments, the method achieves high-quality restoration and competitive RFI detection, and importantly, enables pulsar TOA estimation with accuracy close to that obtained from pristine, RFI-free data. The study demonstrates the practical value of restoring corrupted dynamic spectra for precision pulsar timing and outlines future directions for incorporating phase information and real-time deployment.
Abstract
Radio frequency interference (RFI) have been an enduring concern in radio astronomy, particularly for the observations of pulsars which require high timing precision and data sensitivity. In most works of the literature, RFI mitigation has been formulated as a detection task that consists of localizing possible RFI in dynamic spectra. This strategy inevitably leads to a potential loss of information since parts of the signal identified as possibly RFI-corrupted are generally not considered in the subsequent data processing pipeline. Conversely, this work proposes to tackle RFI mitigation as a joint detection and restoration that allows parts of the dynamic spectrum affected by RFI to be not only identified but also recovered. The proposed supervised method relies on a deep convolutional network whose architecture inherits the performance reached by a recent yet popular image-denoising network. To train this network, a whole simulation framework is built to generate large data sets according to physics-inspired and statistical models of the pulsar signals and of the RFI. The relevance of the proposed approach is quantitatively assessed by conducting extensive experiments. In particular, the results show that the restored dynamic spectra are sufficiently reliable to estimate pulsar times-of-arrivals with an accuracy close to the one that would be obtained from RFI-free signals.