Fast Point Spread Function Modeling with Deep Learning

Abstract

Modeling the Point Spread Function (PSF) of wide-field surveys is vital for many astrophysical applications and cosmological probes including weak gravitational lensing. The PSF smears the image of any recorded object and therefore needs to be taken into account when inferring properties of galaxies from astronomical images. In the case of cosmic shear, the PSF is one of the dominant sources of systematic errors and must be treated carefully to avoid biases in cosmological parameters. Recently, forward modeling approaches to calibrate shear measurements within the Monte-Carlo Control Loops ($MCCL$) framework have been developed. These methods typically require simulating a large amount of wide-field images, thus, the simulations need to be very fast yet have realistic properties in key features such as the PSF pattern. Hence, such forward modeling approaches require a very flexible PSF model, which is quick to evaluate and whose parameters can be estimated reliably from survey data. We present a PSF model that meets these requirements based on a fast deep-learning method to estimate its free parameters. We demonstrate our approach on publicly available SDSS data. We extract the most important features of the SDSS sample via principal component analysis. Next, we construct our model based on perturbations of a fixed base profile, ensuring that it captures these features. We then train a Convolutional Neural Network to estimate the free parameters of the model from noisy images of the PSF. This allows us to render a model image of each star, which we compare to the SDSS stars to evaluate the performance of our method. We find that our approach is able to accurately reproduce the SDSS PSF at the pixel level, which, due to the speed of both the model evaluation and the parameter estimation, offers good prospects for incorporating our method into the $MCCL$ framework.

25 pages, 8 figures, 1 table

References in corpus (9)

• The NumPy array: a structure for efficient numerical computation
• The Gaia mission
• Gaia Data Release 1. Summary of the astrometric, photometric, and survey properties
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• H0LiCOW IV. Lens mass model of HE 0435-1223 and blind measurement of its time-delay distance for cosmology
• Optimal Surveys for Weak Lensing Tomography
• PSF calibration requirements for dark energy from cosmic shear
• Integrated approach to cosmology: Combining CMB, large-scale structure and weak lensing

Cited by in corpus (29)

• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• Cosmological constraints from noisy convergence maps through deep learning
• Spatially-Variant CNN-based Point Spread Function Estimation for Blind Deconvolution and Depth Estimation in Optical Microscopy
• prose: A Python framework for modular astronomical images processing
• Optical Aberration Correction in Postprocessing using Imaging Simulation
• On the dissection of degenerate cosmologies with machine learning
• Separating the EoR Signal with a Convolutional Denoising Autoencoder: A Deep-learning-based Method
• Deep Learning Based Detection of Cosmological Diffuse Radio Sources
• Monte Carlo Control Loops for cosmic shear cosmology with DES Year 1
• Point spread function modelling for astronomical telescopes: a review focused on weak gravitational lensing studies
• Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size
• A Method To Characterize the Wide-Angle Point Spread Function of Astronomical Images
• Euclid: Nonparametric point spread function field recovery through interpolation on a graph Laplacian
• Galaxy shape measurement with convolutional neural networks
• Multi-CCD Point Spread Function Modelling
• The PAU survey: Estimating galaxy photometry with deep learning
• Learning to do multiframe wavefront sensing unsupervisedly: applications to blind deconvolution
• Rethinking data-driven point spread function modeling with a differentiable optical model
• Cosmological Parameter Estimation and Inference using Deep Summaries
• Simulation-based inference of deep fields: galaxy population model and redshift distributions
• The PAU Survey: Background light estimation with deep learning techniques
• Instrument-To-Instrument translation: Instrumental advances drive restoration of solar observation series via deep learning
• Star-Image Centering with Deep Learning: HST/WFPC2 Images
• Phasing segmented telescopes via deep learning methods: application to a deployable CubeSat
• Joint estimation of atmospheric and instrumental defects using a parsimonious point spread function model.On-sky validation using state of the art worldwide adaptive-optics assisted instruments
• UFig v1: The ultra-fast image generator
• GalSBI: Phenomenological galaxy population model for cosmology using simulation-based inference
• GalSBI-SPS: a stellar population synthesis-based galaxy population model for cosmology and galaxy evolution applications
• A Convolutional Neural Network for the Recovery of Transfer Functions From Velocity-Resolved Reverberation Mapping Data