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

Next generation telescopes, like Euclid, Rubin/LSST, and Roman, will open newwindows on the Universe, allowing us to infer physical properties for tens ofmillions of galaxies. Machine learning methods are increasingly becoming themost efficient tools to handle this enormous amount of data, because they areoften faster and more accurate than traditional methods. We investigate howwell redshifts, stellar masses, and star-formation rates (SFR) can be measuredwith deep learning algorithms for observed galaxies within data mimicking theEuclid and Rubin/LSST surveys. We find that Deep Learning Neural Networks andConvolutional Neutral Networks (CNN), which are dependent on the parameterspace of the training sample, perform well in measuring the properties of thesegalaxies and have a better accuracy than methods based on spectral energydistribution fitting. CNNs allow the processing of multi-band magnitudestogether with $H_{\scriptscriptstyle\rm E}$-band images. We find that theestimates of stellar masses improve with the use of an image, but those ofredshift and SFR do not. Our best results are deriving i) the redshift within anormalised error of less than 0.15 for 99.9$\%$ of the galaxies with S/N>3 inthe $H_{\scriptscriptstyle\rm E}$-band; ii) the stellar mass within a factor oftwo ($\sim0.3 \rm dex$) for 99.5$\%$ of the considered galaxies; iii) the SFRwithin a factor of two ($\sim0.3 \rm dex$) for $\sim$70$\%$ of the sample. Wediscuss the implications of our work for application to surveys as well as howmeasurements of these galaxy parameters can be improved with deep learning.

Euclid preparation: XXIII. Derivation of galaxy physical properties with deep machine learning using mock fluxes and H-band images