Supervised Neural Networks for RFI Flagging

TL;DR

This paper explores neural network methods for detecting radio frequency interference in radio astronomy data, demonstrating high accuracy in flagging contaminated signals using a simple neural network model.

Contribution

It introduces a neural network approach for RFI detection that achieves high accuracy, using features from polarization and Stokes visibilities, and compares favorably to existing techniques.

Findings

Achieved an F1-score of 0.75 in RFI flagging.

Recall of 0.69 and Precision of 0.83 demonstrate effective detection.

Single-layer neural network can predict RFI with high accuracy.

Abstract

Neural network (NN) based methods are applied to the detection of radio frequency interference (RFI) in post-correlation,post-calibration time/frequency data. While calibration doesaffect RFI for the sake of this work a reduced dataset inpost-calibration is used. Two machine learning approachesfor flagging real measurement data are demonstrated usingthe existing RFI flagging technique AOFlagger as a groundtruth. It is shown that a single layer fully connects networkcan be trained using each time/frequency sample individuallywith the magnitude and phase of each polarization and Stokesvisibilities as features. This method was able to predict aBoolean flag map for each baseline to a high degree of accuracy achieving a Recall of 0.69 and Precision of 0.83 and anF1-Score of 0.75.