Skip to yearly menu bar Skip to main content

Workshop: NeurIPS 2023 Workshop: Machine Learning and the Physical Sciences

Bayesian Imaging for Radio Interferometry with Score-Based Priors

NoĆ© Dia · M. J. Yantovski-Barth · Alexandre Adam · Micah Bowles · Pablo Lemos · Laurence Perreault-Levasseur · Yashar Hezaveh · Anna Scaife


The inverse imaging task in radio interferometry is a key limiting factor to retrieving Bayesian uncertainties in radio astronomy in a computationally effective manner. We use a score-based prior derived from optical images of galaxies to recover images of protoplanetary disks from the DSHARP survey. We demonstrate that our method produces accurate posterior samples despite the misspecified galaxy prior. We show that our approach produces results which are competitive with existing radio interferometry imaging algorithms.

Chat is not available.