Detecting Radio Frequency Interference in radio-antenna arrays with the Recurrent Neural Network algorithm

TL;DR

This paper presents a recurrent neural network with LSTM cells for automatic detection of radio frequency interference in radio astronomy data, achieving high true positive and negative rates but with room for improvement in overall efficiency.

Contribution

The study introduces an RNN-based method for RFI detection in radio-astronomical data, demonstrating promising accuracy with potential for further refinement.

Findings

True positive rate ~99.9%

True negative rate ~97.9%

Overall efficiency ~30%

Abstract

Signal artefacts due to Radio Frequency Interference (RFI) are a common nuisance in radio astronomy. Conventionally, the RFI-affected data are tagged by an expert data analyst in order to warrant data quality. In view of the increasing data rates obtained with interferometric radio telescope arrays, automatic data filtering procedures are mandatory. Here, we present results from the implementation of a RFI-detecting recurrent neural network (RNN) employing long-short term memory (LSTM) cells. For the training of the algorithm, a discrete model was used that distinguishes RFI and non-RFI data, respectively, based on the amplitude information from radio interferometric observations with the GMRT at $610\, \mathrm{MHz}$. The performance of the RNN is evaluated by analyzing a confusion matrix. The true positive and true negative rates of the network are $\approx 99.9\,\%$ and $\approx 97.9\,\%$, respectively. However, the overall efficiency of the network is $\approx 30\%$ due to the fact that a large amount non-RFI data are classified as being contaminated by RFI. Matthews correlation coefficient is ~0.42 suggesting that a still more refined training model is required.