IRIS: A Bayesian Approach for Image Reconstruction in Radio Interferometry with expressive Score-Based priors

2025-01-05

AI Summary

High-fidelity reconstruction of protoplanetary disk brightness distributions from noisy radio interferometric visibility data remains challenging. This paper introduces the first Bayesian framework that transfers an optically pre-trained score-based generative model (NCSNv2) to radio interferometric imaging, enabling cross-modal prior embedding and calibrated posterior sampling. Our method integrates a Gaussian likelihood model in the uv domain with coverage calibration via posterior predictive checks to ensure statistical reliability of the inferred posterior. Evaluated on ALMA DSHARP simulation data, our approach yields physically more plausible and structurally richer posterior samples compared to conventional algorithms, while demonstrating robustness to domain shift in the prior. This work establishes a calibrated, transferable, generative Bayesian paradigm for astronomical image reconstruction.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Inferring sky surface brightness distributions from noisy interferometric data in a principled statistical framework has been a key challenge in radio astronomy. In this work, we introduce Imaging for Radio Interferometry with Score-based models (IRIS). We use score-based models trained on optical images of galaxies as an expressive prior in combination with a Gaussian likelihood in the uv-space to infer images of protoplanetary disks from visibility data of the DSHARP survey conducted by ALMA. We demonstrate the advantages of this framework compared with traditional radio interferometry imaging algorithms, showing that it produces plausible posterior samples despite the use of a misspecified galaxy prior. Through coverage testing on simulations, we empirically evaluate the accuracy of this approach to generate calibrated posterior samples.

Problem

• Radio Astronomy
• Noise Reduction
• Protoplanetary Disk Observation

Innovation

• IRIS method
• Bayesian approach
• radio telescope imaging