Variational Inference for Deblending Crowded Starfields

Abstract

In images collected by astronomical surveys, stars and galaxies often overlap visually. Deblending is the task of distinguishing and characterizing individual light sources in survey images. We propose StarNet, a Bayesian method to deblend sources in astronomical images of crowded star fields. StarNet leverages recent advances in variational inference, including amortized variational distributions and an optimization objective targeting an expectation of the forward KL divergence. In our experiments with SDSS images of the M2 globular cluster, StarNet is substantially more accurate than two competing methods: Probabilistic Cataloging (PCAT), a method that uses MCMC for inference, and DAOPHOT, a software pipeline employed by SDSS for deblending. In addition, the amortized approach to inference gives StarNet the scaling characteristics necessary to perform Bayesian inference on modern astronomical surveys.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Dark Energy Survey Year 1 Results: Cosmological Constraints from Galaxy Clustering and Weak Lensing
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Galactic Globular and Open Clusters in the Sloan Digital Sky Survey. I. Crowded Field Photometry and Cluster Fiducial Sequences in ugriz
• Finding Strong Gravitational Lenses in the DESI DECam Legacy Survey
• Deblending galaxy superpositions with branched generative adversarial networks
• Deep Generative Models for Galaxy Image Simulations
• Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
• Multiband Probabilistic Cataloging: A Joint Fitting Approach to Point Source Detection and Deblending

Cited by in corpus (4)

• A neural simulation-based inference approach for characterizing the Galactic Center $\gamma$-ray excess
• Data Compression and Inference in Cosmology with Self-Supervised Machine Learning
• Machine Learning and Cosmology
• Neural Posterior Estimation for Cataloging Astronomical Images with Spatially Varying Backgrounds and Point Spread Functions