Performance of the Segment Anything Model in Various RFI/Events Detection in Radio Astronomy

Abstract

The emerging era of big data in radio astronomy demands more efficient and higher-quality processing of observational data. While deep learning methods have been applied to tasks such as automatic radio frequency interference (RFI) detection, these methods often face limitations, including dependence on training data and poor generalization, which are also common issues in other deep learning applications within astronomy. In this study, we investigate the use of the open-source image recognition and segmentation model, Segment Anything Model (SAM), and its optimized version, HQ-SAM, due to their impressive generalization capabilities. We evaluate these models across various tasks, including RFI detection and solar radio burst (SRB) identification. For RFI detection, HQ-SAM (SAM) shows performance that is comparable to or even superior to the SumThreshold method, especially with large-area broadband RFI data. In the search for SRBs, HQ-SAM demonstrates strong recognition abilities for Type II and Type III bursts. Overall, with its impressive generalization capability, SAM (HQ-SAM) can be a promising candidate for further optimization and application in RFI and event detection tasks in radio astronomy.

19 pages, 18 figures, 7 tables. Accepted for publication in PASA

References in corpus (9)

• Segment Anything in Medical Images
• Cosmology at Low Frequencies: The 21 cm Transition and the High-Redshift Universe
• Post-correlation radio frequency interference classification methods
• The low-frequency environment of the Murchison Widefield Array: radio-frequency interference analysis and mitigation
• Optimizing Sparse RFI Prediction using Deep Learning
• HIDE & SEEK: End-to-End Packages to Simulate and Process Radio Survey Data
• Improved Type III solar radio burst detection using congruent deep learning models
• The Intensity of Diffuse Galactic Emission Reflected by Meteor Trails
• Enhanced Bayesian RFI Mitigation and Transient Flagging Using Likelihood Reweighting