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.

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

References in corpus (15)

• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• The Sloan Lens ACS Survey. V. The Full ACS Strong-Lens Sample
• The population of galaxy-galaxy strong lenses in forthcoming optical imaging surveys
• A Bayesian analysis of regularised source inversions in gravitational lensing
• Semi-linear gravitational lens inversion
• Lens models and magnification maps of the six Hubble Frontier Fields clusters
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• The Third Gravitational Lensing Accuracy Testing (GREAT3) Challenge Handbook
• The SL2S Galaxy-scale Lens Sample. V. Dark Matter Halos and Stellar IMF of Massive Early-type Galaxies out to Redshift 0.8
• Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes
• Finding strong lenses in CFHTLS using convolutional neural networks
• The SL2S Galaxy-scale Lens Sample. III. Lens Models, Surface Photometry and Stellar Masses for the final sample
• Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in HST Legacy Imaging
• A Systematic Review of Strong Gravitational Lens Modeling Software

Cited by in corpus (161)

• Machine learning and the physical sciences
• A trans-disciplinary review of deep learning research for water resources scientists
• A New Era in the Quest for Dark Matter
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Lenstronomy: multi-purpose gravitational lens modelling software package
• Seeing Permeability From Images: Fast Prediction with Convolutional Neural Networks
• Learning to Predict the Cosmological Structure Formation
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• AI Poincaré: Machine Learning Conservation Laws from Trajectories
• Is every strong lens model unhappy in its own way? Uniform modelling of a sample of 13 quadruply+ imaged quasars
• 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
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• Finding high-redshift strong lenses in DES using convolutional neural networks
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Radio Galaxy Zoo: ClaRAN - A Deep Learning Classifier for Radio Morphologies
• Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data
• Strong lensing time-delay cosmography in the 2020s
• Reconstructing Functions and Estimating Parameters with Artificial Neural Networks: A Test with the Hubble Parameter and SNe Ia
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• Machine Learning Bell Nonlocality in Quantum Many-body Systems
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• HOLISMOKES -- I. Highly Optimised Lensing Investigations of Supernovae, Microlensing Objects, and Kinematics of Ellipticals and Spirals
• STRIDES: Automated uniform models for 30 quadruply imaged quasars
• Machine Learning meets Quantum Foundations: A Brief Survey
• Extensive Studies of the Neutron Star Equation of State from the Deep Learning Inference with the Observational Data Augmentation
• Multi-scale Convolutional Neural Networks for Inverse Problems
• Nuclear liquid-gas phase transition with machine learning
• Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Fast Point Spread Function Modeling with Deep Learning
• Automated galaxy-galaxy strong lens modelling: no lens left behind
• Time Delay Lens Modelling Challenge
• Unsupervised Learning of Non-Hermitian Topological Phases
• Recovery of TESS Stellar Rotation Periods Using Deep Learning
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• The use of convolutional neural networks for modelling large optically-selected strong galaxy-lens samples
• Line-of-sight effects in strong gravitational lensing
• Using convolutional neural networks to predict galaxy metallicity from three-color images
• Deep Learning the Morphology of Dark Matter Substructure
• HOLISMOKES -- IV. Efficient mass modeling of strong lenses through deep learning
• Direct Detection of Dark Matter Substructure in Strong Lens Images with Convolutional Neural Networks
• Differentiable Strong Lensing: Uniting Gravity and Neural Nets through Differentiable Probabilistic Programming
• Statistical strong lensing. I. Constraints on the inner structure of galaxies from samples of a thousand lenses
• Sensitivity of strong lensing observations to dark matter substructure: a case study with Euclid
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• Analyzing γ-rays of the Galactic Center with Deep Learning
• Machine Learning for Observational Cosmology
• 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
• TDCOSMO X. Automated Modeling of 9 Strongly Lensed Quasars and Comparison Between Lens Modeling Software
• Scientific intuition inspired by machine learning generated hypotheses
• Deep Horizon; a machine learning network that recovers accreting black hole parameters
• Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting
• Strong Lensing by Galaxies
• Estimating the warm dark matter mass from strong lensing images with truncated marginal neural ratio estimation
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Extracting the Subhalo Mass Function from Strong Lens Images with Image Segmentation
• 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
• Cataloging Accreted Stars within Gaia DR2 using Deep Learning
• Artificial Neural Network Based Computation for Out-of-Time-Ordered Correlators
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• A machine learning based approach to gravitational lens identification with the International LOFAR Telescope
• SLITronomy: towards a fully wavelet-based strong lensing inversion technique
• Gravitational Lenses as High-Resolution Telescopes
• Applications of deep learning to relativistic hydrodynamics
• LeHaMoC: a versatile time-dependent lepto-hadronic modeling code for high-energy astrophysical sources
• Likelihood-free Inference with Mixture Density Network
• Neural network-based anomaly detection for high-resolution X-ray spectroscopy
• Identification of Galaxy-Galaxy Strong Lens Candidates in the DECam Local Volume Exploration Survey Using Machine Learning
• 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
• Streamlined Lensed Quasar Identification in Multiband Images via Ensemble Networks
• Auto-identification of unphysical source reconstructions in strong gravitational lens modelling
• Deep-CEE I: Fishing for Galaxy Clusters with Deep Neural Nets
• HOLISMOKES -- IX. Neural network inference of strong-lens parameters and uncertainties from ground-based images
• Decoding Dark Matter Substructure without Supervision
• DECORAS: detection and characterization of radio-astronomical sources using deep learning
• HOLISMOKES -- X. Comparison between neural network and semi-automated traditional modeling of strong lenses
• An extended catalog of galaxy-galaxy strong gravitational lenses discovered in DES using convolutional neural networks
• Applications of deep learning to relativistic hydrodynamics
• LeMoN: Lens Modelling with Neural networks -- I. Automated modelling of strong gravitational lenses with Bayesian Neural Networks
• Machine Learning and Cosmology
• Strong-lensing source reconstruction with variationally optimised Gaussian processes
• Quantifying the structure of strong gravitational lens potentials with uncertainty-aware deep neural networks
• A Framework for Obtaining Accurate Posteriors of Strong Gravitational Lensing Parameters with Flexible Priors and Implicit Likelihoods using Density Estimation
• Models of gravitational lens candidates from Space Warps CFHTLS
• PGNets: Planet mass prediction using convolutional neural networks for radio continuum observations of protoplanetary disks
• Application of the independent component analysis to the iKAGRA data
• A Deep Learning Method for AGILE-GRID GRB Detection
• HOLISMOKES -- XI. Evaluation of supervised neural networks for strong-lens searches in ground-based imaging surveys
• Deep learning the astrometric signature of dark matter substructure
• Finding quadruply imaged quasars with machine learning. I. Methods
• Application of Deep Learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM TTE Data
• Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines
• AI-driven spatio-temporal engine for finding gravitationally lensed type Ia supernovae
• Learning neutrino effects in Cosmology with Convolutional Neural Networks
• 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
• Modeling lens potentials with continuous neural fields in galaxy-scale strong lenses
• Neural network-based preprocessing to estimate the parameters of the X-ray emission of a single-temperature thermal plasma
• Targeted Likelihood-Free Inference of Dark Matter Substructure in Strongly-Lensed Galaxies
• HOLISMOKES XIII: Strong-lens candidates at all mass scales and their environments from the Hyper-Suprime Cam and deep learning
• Simple lessons from complex learning: what a neural network model learns about cosmic structure formation
• Developing a Victorious Strategy to the Second Strong Gravitational Lensing Data Challenge
• Euclid preparation. LI. Forecasting the recovery of galaxy physical properties and their relations with template-fitting and machine-learning methods
• Deep Learning Blazar Classification based on Multi-frequency Spectral Energy Distribution Data
• Discover the GellMann-Okubo formula with machine learning
• Random telegraph signal analysis with a recurrent neural network
• Anisotropic strong lensing as a probe of dark matter self-interactions
• Cosmological joint analysis with cosmic growth and expansion rate
• Lessons from a blind study of simulated lenses: image reconstructions do not always reproduce true convergence
• Peculiar Velocity Estimation from Kinetic SZ Effect using Deep Neural Networks
• Lens Modeling of STRIDES Strongly Lensed Quasars using Neural Posterior Estimation
• AGNet: Weighing Black Holes with Deep Learning
• Probing Neural Networks for the Gamma/Hadron Separation of the Cherenkov Telescope Array
• Machine learning and Kolmogorov analysis to reveal gravitational lenses
• Dark Matter Subhalos, Strong Lensing and Machine Learning
• Hunting for Dark Matter Subhalos in Strong Gravitational Lensing with Neural Networks
• Searching for Sub-Second Stellar Variability with Wide-Field Star Trails and Deep Learning
• A proof-of-concept neural network for inferring parameters of a black hole from partial interferometric images of its shadow
• YOLO-CL cluster detection in the Rubin/LSST DC2 simulation
• Measuring the Substructure Mass Power Spectrum of 23 SLACS Strong Galaxy-Galaxy Lenses with Convolutional Neural Networks
• A Bayesian neural network predicts the dissolution of compact planetary systems
• A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling
• Accelerating lensed quasar discovery and modeling with physics-informed variational autoencoders
• A new strategy for matching observed and simulated lensing galaxies
• Search for glitches of gamma-ray pulsars with deep learning
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• A compact group lens modeled with GIGA-Lens: Enhanced inference for complex systems
• Phased Microphone Array for Sound Source Localization with Deep Learning
• Datacube segmentation via Deep Spectral Clustering
• Machine Learning Promoting Extreme Simplification of Spectroscopy Equipment
• Measuring the spectral index of turbulent gas with deep learning from projected density maps
• Lenses In VoicE (LIVE): Searching for strong gravitational lenses in the VOICE@VST survey using Convolutional Neural Networks
• Understanding the predication mechanism of deep learning through error propagation among parameters in strong lensing case
• Optical deep learning nano-profilometry
• Success of Machine Learning algorithms in Dynamical Mass Measurements of Galaxy Clusters
• Deep inference of simulated strong lenses in ground-based surveys
• Neural Scaling Laws for Deep Regression
• Genetic-algorithm-optimized neural networks for gravitational wave classification
• Femtosecond pulse parameter estimation from photoelectron momenta using machine learning
• Gaia GraL: Gaia gravitational lens systems IX. Using XGBoost to explore the Gaia Focused Product Release GravLens catalogue
• Constraining primordial non-Gaussianity using Neural Networks
• A short review on joint weak and strong cluster lens-mass reconstruction
• From Dark Matter Minihalos to Large-Scale Radiative Feedback: A Self-Consistent 3D Simulation of the First Stars and Galaxies using Neural Networks
• Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra
• Machine Learning for Nanohertz Gravitational Wave Detection and Parameter Estimation with Pulsar Timing Array
• Enhancing Gravitational Lens Study with Deep Learning: A Study on Effects of Dropout Regularization
• Multi-frequency point source detection with fully convolutional networks: Performance in realistic microwave sky simulations
• A New Method for the Reconstruction of Strongly Lensed Galaxies with Resolved Kinematics
• Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning
• Determining the Dark Matter distribution in galaxies with Deep Learning
• Introduction to Machine Learning for Accelerator Physics
• Differentiable probabilistic programming for strong gravitational lensing