SIFARI: Self-Supervised Interferometric Fitting for Astronomical Radio Imaging

2026-09-28

AI Summary

This study addresses the challenges of spatial filtering, complex morphology reconstruction, and uncertainty quantification in radio interferometric imaging by proposing a self-supervised neural network approach. The method models sky brightness as a spatially continuous function, utilizing Fourier features to directly fit visibility data without requiring external training sets or explicit regularization. Furthermore, it incorporates Stochastic Weight Averaging-Gaussian (SWAG) sampling to generate spatially resolved signal-to-noise ratio maps. Experimental results demonstrate that the proposed approach yields a point source response eight times narrower than CLEAN, recovers substantially more extended flux, significantly enhances image fidelity, and reduces noise by 30%.

Abstract

Radio-interferometric images are reconstructed from sparsely sampled visibilities, and CLEAN-based imaging can struggle with spatial filtering, complex morphologies, and uncertainty quantification. Alternative methods that fit visibilities directly can address some of these limitations but often require manual choices of image priors and model hyperparameters. We present SIFARI (Self-Supervised Interferometric Fitting for Astronomical Radio Imaging), a self-supervised neural network workflow that represents sky brightness as a continuous function of position and fits measured visibilities without an external image training set or explicit spatial regularizer. An empirical rule sets the Fourier feature scale from the visibilities before training, controlling how readily the network fits fine structure. Sampling network weights with Stochastic Weight Averaging-Gaussian (SWAG) gives approximate brightness uncertainty estimates, which we combine with a thermal-noise floor to construct spatially resolved signal-to-noise maps. In synthetic ALMA tests, SIFARI yields an effective point-source response about eight times narrower than the natural-weighting CLEAN restoring beam and recovers more extended flux than CLEAN when short baselines are missing. It also achieves higher image fidelity than the restored CLEAN images in all three morphology benchmarks. Applied to ALMA observations of PDS 70, SIFARI recovers the bright outer ring together with faint compact emission in the central cavity. For long-baseline-only WISPIT 2 data, SIFARI supplies a sky model for phase self-calibration where the CLEAN model is inadequate. The restored, self-calibrated SIFARI image has approximately 30% lower RMS noise than the CLEAN image made from the original visibilities without self-calibration.

Problem

• radio-interferometric imaging
• visibility fitting
• uncertainty quantification
• image priors
• complex morphologies

Innovation

• Self-supervised learning
• Radio interferometry
• Neural network
• Uncertainty quantification
• Astronomical imaging