Million Points of Light (MPoL): a PyTorch library for radio interferometric imaging and inference

TL;DR

MPoL is a PyTorch-based library that enables flexible, differentiable modeling and inference of radio interferometric data for high-resolution astronomical imaging.

Contribution

It introduces a modular, neural network-based framework for radio interferometric imaging and calibration, leveraging autodifferentiation and optimization techniques.

Findings

Supports simultaneous image synthesis and calibration

Provides a flexible, neural network-based modeling approach

Enables efficient inference using industry-grade optimizers

Abstract

Astronomical radio interferometers achieve exquisite angular resolution by cross-correlating signal from a cosmic source simultaneously observed by distant pairs of radio telescopes to produce a Fourier-type measurement called a visibility. Million Points of Light (MPoL) is a Python library supporting feed-forward modeling of interferometric visibility datasets for synthesis imaging and parametric Bayesian inference, built using the autodifferentiable machine learning framework PyTorch. Neural network components provide a rich set of modular and composable building blocks that can be used to express the physical relationships between latent model parameters and observed data following the radio interferometric measurement equation. Industry-grade optimizers make it straightforward to simultaneously solve for the synthesized image and calibration parameters using stochastic gradient descent.