VROOM-SBI: A Fast Simulation-based Bayesian Inference Methodology for Stokes QU -fitting in Radio Interferometry

Bayesian QU -fitting is among the most accurate approaches for line-of-sight Faraday inference, but its per-pixel computational cost has made survey-scale application infeasible. QU -fitting is an alternative to Faraday synthesis with comparable accuracy in recovering line-of-sight Faraday components, but it has historically been computationally prohibitive at the survey scale. Fitting to the Stokes spectra in Q and U through Bayesian inference is effective but slow. We introduce VROOM-SBI , which uses simulation-based inference (SBI), particularly neural posterior estimation (NPE), to speed up inference. Our results are comparable to both Faraday synthesis and QU -fitting and deliver a speedup of ∼500 over classical QU -fitting implementations. We provide an open code repository and tools along with trained models via HuggingFace for the four standard depolarization models in common use, trained on Very Large Array (VLA) L -band frequency coverage.