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

Large sky spectroscopic surveys have reached the scale of photometric surveysin terms of sample sizes and data complexity. These huge datasets requireefficient, accurate, and flexible automated tools for data analysis and scienceexploitation. We present the Galaxy Spectra Network/GaSNet-II, a supervisedmulti-network deep learning tool for spectra classification and redshiftprediction. GaSNet-II can be trained to identify a customized number of classesand optimize the redshift predictions for classified objects in each of them.It also provides redshift errors, using a network-of-networks that reproduces aMonte Carlo test on each spectrum, by randomizing their weight initialization.As a demonstration of the capability of the deep learning pipeline, we use 260kSloan Digital Sky Survey spectra from Data Release 16, separated into 13classes including 140k galactic, and 120k extragalactic objects. GaSNet-IIachieves 92.4% average classification accuracy over the 13 classes (larger than90% for the majority of them), and an average redshift error of approximately0.23% for galaxies and 2.1% for quasars. We further train/test the samepipeline to classify spectra and predict redshifts for a sample of 200k 4MOSTmock spectra and 21k publicly released DESI spectra. On 4MOST mock data, wereach 93.4% accuracy in 10-class classification and an average redshift errorof 0.55% for galaxies and 0.3% for active galactic nuclei. On DESI data, wereach 96% accuracy in (star/galaxy/quasar only) classification and an averageredshift error of 2.8% for galaxies and 4.8% for quasars, despite the smallsample size available. GaSNet-II can process ~40k spectra in less than oneminute, on a normal Desktop GPU. This makes the pipeline particularly suitablefor real-time analyses of Stage-IV survey observations and an ideal tool forfeedback loops aimed at night-by-night survey strategy optimization.

Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions