English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Upcoming large astronomical surveys are expected to capture an unprecedentednumber of strong gravitational lensing systems. Deep learning is emerging as apromising practical tool for the detection and quantification of thesegalaxy-scale image distortions. The absence of large quantities ofrepresentative data from current astronomical surveys motivates the developmentof a robust forward-modeling approach using synthetic lensing images. Using amock sample of strong lenses created upon a state-of-the-art extragalacticcatalogs, we train a modular deep learning pipeline for uncertainty-quantifieddetection and modeling with intermediate image processing components fordenoising and deblending the lensing systems. We demonstrate a high degree ofinterpretability and controlled systematics due to domain-specific task modulestrained with different stages of synthetic image generation. For lens detectionand modeling, we obtain semantically meaningful latent spaces that separateclasses of strong lens images and yield uncertainty estimates that explain theorigin of misclassified images and provide probabilistic predictions for thelens parameters. Validation of the inference pipeline has been carried outusing images from the Subaru telescope's Hyper Suprime-Cam camera, and LSSTDESC simulated DC2 sky survey catalogues.

A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling