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

Component separation is the process with which emission sources inastrophysical maps are generally extracted by taking multi-frequencyinformation into account. It is crucial to develop more reliable methods forcomponent separation for future CMB experiments. We aim to develop a new methodbased on fully convolutional neural networks called the Cosmic microwavebackground Extraction Neural Network (CENN) in order to extract the CMB signalin total intensity. The frequencies used are the Planck channels 143, 217 and353 GHz. We validate the network at all sky, and at three latitude intervals:lat1=0^{\circ}<b<5^{\circ}, lat2=5^{\circ}<b<30^{\circ} andlat3=30^{\circ}<b<90^{\circ}, without using any Galactic or point source masks.For training, we make realistic simulations in the form of patches of area 256pixels, which contain the CMB, Dust, CIB and PS emissions, Sunyaev-Zel'dovicheffect and the instrumental noise. After validate the network, we compare thepower spectrum from input and output maps. We analyse the power spectrum fromthe residuals at each latitude interval and at all sky and we study theperformance of our model dealing with high contamination at small scales. Weobtain a power spectrum with an error of 13{\pm}113 {\mu}K^2 for multipoles upto above 4000. For residuals, we obtain 700{\pm}60 {\mu}K^2 for lat1, 80{\pm}30{\mu}K^2 for lat2 and 30{\pm}20 {\mu}K^2 for lat3. For all sky, we obtain20{\pm}10 {\mu}K^2. We validate the network in a patch with strongcontamination at small scales, obtaining an error of 50{\pm}120 {\mu}K^2 andresiduals of 40{\pm}10 {\mu}K^2. Therefore, fully convolutional neural networksare promising methods to perform component separation in future CMBexperiments. Particularly, CENN is reliable against different levels ofcontamination from Galactic and point source foregrounds at both large andsmall scales.

CENN: A fully convolutional neural network for CMB recovery in realistic microwave sky simulations