Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks

Abstract

Quantifying image distortions caused by strong gravitational lensing and estimating the corresponding matter distribution in lensing galaxies has been primarily performed by maximum likelihood modeling of observations. This is typically a time and resource-consuming procedure, requiring sophisticated lensing codes, several data preparation steps, and finding the maximum likelihood model parameters in a computationally expensive process with downhill optimizers. Accurate analysis of a single lens can take up to a few weeks and requires the attention of dedicated experts. Tens of thousands of new lenses are expected to be discovered with the upcoming generation of ground and space surveys, the analysis of which can be a challenging task. Here we report the use of deep convolutional neural networks to accurately estimate lensing parameters in an extremely fast and automated way, circumventing the difficulties faced by maximum likelihood methods. We also show that lens removal can be made fast and automated using Independent Component Analysis of multi-filter imaging data. Our networks can recover the parameters of the Singular Isothermal Ellipsoid density profile, commonly used to model strong lensing systems, with an accuracy comparable to the uncertainties of sophisticated models, but about ten million times faster: 100 systems in approximately 1s on a single graphics processing unit. These networks can provide a way for non-experts to obtain lensing parameter estimates for large samples of data. Our results suggest that neural networks can be a powerful and fast alternative to maximum likelihood procedures commonly used in astrophysics, radically transforming the traditional methods of data reduction and analysis.

Accepted for publication in Nature. Under press embargo till 18:00 GMT (1300 US Eastern Time) on Wednesday August 30th

References in corpus (4)

• The Sloan Lens ACS Survey. V. The Full ACS Strong-Lens Sample
• Lens models and magnification maps of the six Hubble Frontier Fields clusters
• The SL2S Galaxy-scale Lens Sample. V. Dark Matter Halos and Stellar IMF of Massive Early-type Galaxies out to Redshift 0.8
• Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in HST Legacy Imaging

Cited by in corpus (38)

• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Deep Reinforcement Learning for Quantum Gate Control
• Deep learning predictions of galaxy merger stage and the importance of observational realism
• Machine learning technique to find quantum many-body ground states of bosons on a lattice
• Photometric Redshifts for Next-Generation Surveys
• Strong lensing time-delay cosmography in the 2020s
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• Nuclear liquid-gas phase transition with machine learning
• 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
• Determining the temperature in heavy-ion collisions with multiplicity distribution
• Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniques
• Quasar microlensing light curve analysis using deep machine learning
• Recovering the CMB Signal with Machine Learning
• A machine learning based approach to gravitational lens identification with the International LOFAR Telescope
• SLITronomy: towards a fully wavelet-based strong lensing inversion technique
• Likelihood-free Inference with Mixture Density Network
• Neural network-based anomaly detection for high-resolution X-ray spectroscopy
• Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers
• A 4% measurement of $H_0$ using the cumulative distribution of strong-lensing time delays in doubly-imaged quasars
• Auto-identification of unphysical source reconstructions in strong gravitational lens modelling
• Machine Learning and Cosmology
• Models of gravitational lens candidates from Space Warps CFHTLS
• A Deep Learning Method for AGILE-GRID GRB Detection
• X-ray Study of Spatial Structures in Tycho's Supernova Remnant Using Unsupervised Deep Learning
• Deep Learning in Wide-field Surveys: Fast Analysis of Strong Lenses in Ground-based Cosmic Experiments
• Targeted Likelihood-Free Inference of Dark Matter Substructure in Strongly-Lensed Galaxies
• Discover the GellMann-Okubo formula with machine learning
• Dark Matter Subhalos, Strong Lensing and Machine Learning
• Hunting for Dark Matter Subhalos in Strong Gravitational Lensing with Neural Networks
• Success of Machine Learning algorithms in Dynamical Mass Measurements of Galaxy Clusters
• Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning
• Differentiable probabilistic programming for strong gravitational lensing
• A New Method for the Reconstruction of Strongly Lensed Galaxies with Resolved Kinematics
• Multi-frequency point source detection with fully convolutional networks: Performance in realistic microwave sky simulations
• Introduction to Machine Learning for Accelerator Physics