Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks

Abstract

We use convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to estimate the parameters of strong gravitational lenses from interferometric observations. We explore multiple strategies and find that the best results are obtained when the effects of the dirty beam are first removed from the images with a deconvolution performed with an RNN-based structure before estimating the parameters. For this purpose, we use the recurrent inference machine (RIM) introduced in Putzky & Welling (2017). This provides a fast and automated alternative to the traditional CLEAN algorithm. We obtain the uncertainties of the estimated parameters using variational inference with Bernoulli distributions. We test the performance of the networks with a simulated test dataset as well as with five ALMA observations of strong lenses. For the observed ALMA data we compare our estimates with values obtained from a maximum-likelihood lens modeling method which operates in the visibility space and find consistent results. We show that we can estimate the lensing parameters with high accuracy using a combination of an RNN structure performing image deconvolution and a CNN performing lensing analysis, with uncertainties less than a factor of two higher than those achieved with maximum-likelihood methods. Including the deconvolution procedure performed by RIM, a single evaluation can be done in about a second on a single GPU, providing a more than six orders of magnitude increase in analysis speed while using about eight orders of magnitude less computational resources compared to maximum-likelihood lens modeling in the uv-plane. We conclude that this is a promising method for the analysis of mm and cm interferometric data from current facilities (e.g., ALMA, JVLA) and future large interferometric observatories (e.g., SKA), where an analysis in the uv-plane could be difficult or unfeasible.

arXiv commentTo be submitted to ApJ

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Recurrent Inference Machines for Solving Inverse Problems
• ALMA imaging of SDP.81 - I. A pixelated reconstruction of the far-infrared continuum emission

Cited by in corpus (20)

• Machine learning and the physical sciences
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
• The use of convolutional neural networks for modelling large optically-selected strong galaxy-lens samples
• Direct Detection of Dark Matter Substructure in Strong Lens Images with Convolutional Neural Networks
• Deep Learning-based Imaging in Radio Interferometry
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting
• Extracting the Subhalo Mass Function from Strong Lens Images with Image Segmentation
• Decoding Dark Matter Substructure without Supervision
• Machine Learning and Cosmology
• Reconstructing Cosmic Polarization Rotation with ResUNet-CMB
• Deep Learning in Wide-field Surveys: Fast Analysis of Strong Lenses in Ground-based Cosmic Experiments
• Deep Learning Blazar Classification based on Multi-frequency Spectral Energy Distribution Data
• Peculiar Velocity Estimation from Kinetic SZ Effect using Deep Neural Networks
• Dark Matter Subhalos, Strong Lensing and Machine Learning
• A proof-of-concept neural network for inferring parameters of a black hole from partial interferometric images of its shadow
• A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling
• VLBInet: Radio Interferometry Data Classification for EHT with Neural Networks