Autoencoding Labeled Interpolator, Inferring Parameters From Image, And Image From Parameters
This work addresses a bottleneck in astrophysics research by enabling faster parameter estimation and model validation for black hole observations, though it is incremental as it extends existing autoencoder methods.
The study tackled the computational expense of generating synthetic black hole images for fitting models to Event Horizon Telescope observations by developing a generative machine learning tool based on a variational autoencoder. The tool successfully interpolates between training images and retrieves physical parameters, reducing computational costs to facilitate parameter estimation and model validation.
The Event Horizon Telescope (EHT) provides an avenue to study black hole accretion flows on event-horizon scales. Fitting a semi-analytical model to EHT observations requires the construction of synthetic images, which is computationally expensive. This study presents an image generation tool in the form of a generative machine learning model, which extends the capabilities of a variational autoencoder. This tool can rapidly and continuously interpolate between a training set of images and can retrieve the defining parameters of those images. Trained on a set of synthetic black hole images, our tool showcases success in both interpolating black hole images and their associated physical parameters. By reducing the computational cost of generating an image, this tool facilitates parameter estimation and model validation for observations of black hole system.