# Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines

## TL;DR

This paper introduces a machine learning approach using Recurrent Inference Machines to accurately reconstruct background sources in gravitational lensing, improving over traditional methods by learning priors from data and enabling automated analysis.

## Contribution

The novel integration of RIM with a CNN for fully automated reconstruction of lensed sources and lens mass distribution from telescope images.

## Key findings

- Outperforms linear inversion methods in source reconstruction accuracy.
- Learns source priors implicitly from training data.
- Enables automated reconstruction of lensing systems.

## Abstract

We present a machine learning method for the reconstruction of the undistorted images of background sources in strongly lensed systems. This method treats the source as a pixelated image and utilizes the Recurrent Inference Machine (RIM) to iteratively reconstruct the background source given a lens model. Our architecture learns to minimize the likelihood of the model parameters (source pixels) given the data using the physical forward model (ray tracing simulations) while implicitly learning the prior of the source structure from the training data. This results in better performance compared to linear inversion methods, where the prior information is limited to the 2-point covariance of the source pixels approximated with a Gaussian form, and often specified in a relatively arbitrary manner. We combine our source reconstruction network with a convolutional neural network that predicts the parameters of the mass distribution in the lensing galaxies directly from telescope images, allowing a fully automated reconstruction of the background source images and the foreground mass distribution.