A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling
arXiv:1911.03867
Abstract
Upcoming large astronomical surveys are expected to capture an unprecedented number of strong gravitational lensing systems. Deep learning is emerging as a promising practical tool for the detection and quantification of these galaxy-scale image distortions. The absence of large quantities of representative data from current astronomical surveys motivates the development of a robust forward-modeling approach using synthetic lensing images. Using a mock sample of strong lenses created upon a state-of-the-art extragalactic catalogs, we train a modular deep learning pipeline for uncertainty-quantified detection and modeling with intermediate image processing components for denoising and deblending the lensing systems. We demonstrate a high degree of interpretability and controlled systematics due to domain-specific task modules trained with different stages of synthetic image generation. For lens detection and modeling, we obtain semantically meaningful latent spaces that separate classes of strong lens images and yield uncertainty estimates that explain the origin of misclassified images and provide probabilistic predictions for the lens parameters. Validation of the inference pipeline has been carried out using images from the Subaru telescope's Hyper Suprime-Cam camera, and LSST DESC simulated DC2 sky survey catalogues.
References in corpus (17)
- Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
- Inference of the Cold Dark Matter substructure mass function at z=0.2 using strong gravitational lenses
- Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
- The Strong Gravitational Lens Finding Challenge
- Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
- The BOSS Emission-Line Lens Survey. IV. : Smooth Lens Models for the BELLS GALLERY Sample
- Models of the Cosmic Horseshoe Gravitational Lens
- A Deep Journey into Super-resolution: A survey
- 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
- Probing the nature of dark matter by forward modeling flux ratios in strong gravitational lenses
- Uncertainty in the Variational Information Bottleneck
- Testing Star Formation Laws in a Starburst Galaxy At Redshift 3 Resolved with ALMA
- The use of convolutional neural networks for modelling large optically-selected strong galaxy-lens samples
- A Neural Network Gravitational Arc Finder based on the Mediatrix filamentation Method
- Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks
- Models of gravitational lens candidates from Space Warps CFHTLS