An Improved Machine Learning Approach for Radio Frequency Interference Mitigation in FAST-SETI Survey Archival Data

TL;DR

This paper introduces an improved machine learning method using DBSCAN to more effectively identify and remove residual radio frequency interference in FAST-SETI survey data, enhancing detection accuracy and computational efficiency.

Contribution

The study applies and demonstrates the effectiveness of the DBSCAN clustering algorithm for residual RFI mitigation in SETI data, outperforming previous methods in removal rate and speed.

Findings

Successfully removed 77.87% of residual RFI

Achieved 7.44% higher removal rate than previous methods

Reduced execution time by 24.85%

Abstract

The search for extraterrestrial intelligence (SETI) commensal surveys aim to scan the sky to detect technosignatures from extraterrestrial life. A major challenge in SETI is the effective mitigation of radio frequency interference (RFI), a critical step that is particularly vital for the highly sensitive Five-hundred-meter Aperture Spherical radio Telescope (FAST). While initial RFI mitigation (e.g., removal of persistent and drifting narrowband RFI) are essential, residual RFI often persists, posing significant challenges due to its complex and various nature. In this paper, we propose and apply an improved machine learning approach, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, to identify and mitigate residual RFI in FAST-SETI commensal survey archival data from July 2019. After initial RFI mitigation, we successfully identify and remove 36977 residual RFIs (accounting for $\sim$ 77.87\%) within approximately 1.678 seconds using the DBSCAN algorithm. This result shows that we have achieved a 7.44\% higher removal rate than previous machine learning methods, along with a 24.85\% reduction in execution time. We finally find interesting candidate signals consistent with previous studies, and retain one candidate signal following further analysis. Therefore, DBSCAN algorithm can mitigate more residual RFI with higher computational efficiency while preserving the candidate signals that we are interested in.