A Machine-Learning-Based Direction-of-Origin Filter for the Identification of Radio Frequency Interference in the Search for Technosignatures

TL;DR

This paper introduces a CNN-based direction-of-origin filter that significantly improves radio frequency interference identification in the search for technosignatures, reducing false positives and the need for manual inspection.

Contribution

It presents a novel CNN approach for DoO filtering that outperforms existing methods in accuracy and efficiency, enhancing RFI mitigation in technosignature searches.

Findings

CNN achieves 99.15% precision and 97.81% recall.

Reduces signals needing visual inspection by a factor of 6-16.

Outperforms baseline correlation and existing DoO filters.

Abstract

Radio frequency interference (RFI) mitigation remains a major challenge in the search for radio technosignatures. Typical mitigation strategies include a direction-of-origin (DoO) filter, where a signal is classified as RFI if it is detected in multiple directions on the sky. These classifications generally rely on estimates of signal properties, such as frequency and frequency drift rate. Convolutional neural networks (CNNs) offer a promising complement to existing filters because they can be trained to analyze dynamic spectra directly, instead of relying on inferred signal properties. In this work, we compiled several data sets consisting of labeled pairs of images of dynamic spectra, and we designed and trained a CNN that can determine whether or not a signal detected in one scan is also present in another scan. This CNN-based DoO filter outperforms both a baseline 2D correlation model as well as existing DoO filters over a range of metrics, with precision and recall values of 99.15% and 97.81%, respectively. We found that the CNN reduces the number of signals requiring visual inspection after the application of traditional DoO filters by a factor of 6-16 in nominal situations.