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

Direct imaging is an active research topic in astronomy for the detection andthe characterization of young sub-stellar objects. The very high contrastbetween the host star and its companions makes the observations particularlychallenging. In this context, post-processing methods combining several imagesrecorded with the pupil tracking mode of telescope are needed. In previousworks, we have presented a data-driven algorithm, PACO, capturing locally thespatial correlations of the data with a multi-variate Gaussian model. PACOdelivers better detection sensitivity and confidence than the standardpost-processing methods of the field. However, there is room for improvementdue to the approximate fidelity of the PACO statistical model to the timeevolving observations. In this paper, we propose to combine the statisticalmodel of PACO with supervised deep learning. The data are first pre-processedwith the PACO framework to improve the stationarity and the contrast. Aconvolutional neural network (CNN) is then trained in a supervised fashion todetect the residual signature of synthetic sources. Finally, the trainednetwork delivers a detection map. The photometry of detected sources isestimated by a second CNN. We apply the proposed approach to several datasetsfrom the VLT/SPHERE instrument. Our results show that its detection stageperforms significantly better than baseline methods (cADI, PCA), and leads to acontrast improvement up to half a magnitude compared to PACO. Thecharacterization stage of the proposed method performs on average on par withor better than the comparative algorithms (PCA, PACO) for angular separationabove 0.5".

deep PACO: Combining statistical models with deep learning for exoplanet detection and characterization in direct imaging at high contrast