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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The next generation of wide-field deep astronomical surveys will deliverunprecedented amounts of images through the 2020s and beyond. As both thesensitivity and depth of observations increase, more blended sources will bedetected. This reality can lead to measurement biases that contaminate keyastronomical inferences. We implement new deep learning models availablethrough Facebook AI Research's Detectron2 repository to perform thesimultaneous tasks of object identification, deblending, and classification onlarge multi-band coadds from the Hyper Suprime-Cam (HSC). We use existingdetection/deblending codes and classification methods to train a suite of deepneural networks, including state-of-the-art transformers. Once trained, we findthat transformers outperform traditional convolutional neural networks and aremore robust to different contrast scalings. Transformers are able to detect anddeblend objects closely matching the ground truth, achieving a median boundingbox Intersection over Union of 0.99. Using high quality class labels from theHubble Space Telescope, we find that the best-performing networks can classifygalaxies with near 100\% completeness and purity across the whole test sampleand classify stars above 60\% completeness and 80\% purity out to HSC i-bandmagnitudes of 25 mag. This framework can be extended to other upcoming deepsurveys such as the Legacy Survey of Space and Time and those with the RomanSpace Telescope to enable fast source detection and measurement. Our code,\textsc{DeepDISC} is publicly available at\url{https://github.com/grantmerz/deepdisc}.

Detection, Instance Segmentation, and Classification for Astronomical  Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and  Demonstration with Hyper Suprime-Cam Data