Article (Scientific journals)
Supervised detection of exoplanets in high-contrast imaging sequences
Gómez González, Carlos; Absil, Olivier; Van Droogenbroeck, Marc
2018In Astronomy and Astrophysics, 613, p. 71
Peer Reviewed verified by ORBi
 

Files


Full Text
GomezGonzalez18_supervised_detection_exoplanets-HCI.pdf
Publisher postprint (3.83 MB)
Download

https://www.aanda.org/articles/aa/abs/2018/05/aa31961-17/aa31961-17.html - Copyright ESO 2018, published by EDP Sciences


All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
methods: data analysis; techniques: high angular resolution; techniques: imaging spectroscopy; planetary systems; planets and satellites: detection
Abstract :
[en] Context. Post-processing algorithms play a key role in pushing the detection limits of high-contrast imaging (HCI) instruments. State-of-the-art image processing approaches for HCI enable the production of science-ready images relying on unsupervised learning techniques, such as low-rank approximations, for generating a model point spread function (PSF) and subtracting the residual starlight and speckle noise. Aims. In order to maximize the detection rate of HCI instruments and survey campaigns, advanced algorithms with higher sensitivities to faint companions are needed, especially for the speckle-dominated innermost region of the images. Methods. We propose a reformulation of the exoplanet detection task (for ADI sequences) that builds on well-established machine learning techniques to take HCI post-processing from an unsupervised to a supervised learning context. In this new framework, we present algorithmic solutions using two different discriminative models: SODIRF (random forests) and SODINN (neural networks). We test these algorithms on real ADI datasets from VLT/NACO and VLT/SPHERE HCI instruments. We then assess their performances by injecting fake companions and using receiver operating characteristic analysis. This is done in comparison with state-of-the-art ADI algorithms, such as ADI principal component analysis (ADI-PCA). Results. This study shows the improved sensitivity versus specificity trade-off of the proposed supervised detection approach. At the diffraction limit, SODINN improves the true positive rate by a factor ranging from ∼2 to ∼10 (depending on the dataset and angular separation) with respect to ADI-PCA when working at the same false-positive level. Conclusions. The proposed supervised detection framework outperforms state-of-the-art techniques in the task of discriminating planet signal from speckles. In addition, it offers the possibility of re-processing existing HCI databases to maximize their scientific return and potentially improve the demographics of directly imaged exoplanets.
Research center :
Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège
STAR - Space sciences, Technologies and Astrophysics Research - ULiège
Telim
Disciplines :
Space science, astronomy & astrophysics
Author, co-author :
Gómez González, Carlos ;  Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > Astroph. extragalactique et observations spatiales (AEOS)
Absil, Olivier  ;  Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > PSILab
Van Droogenbroeck, Marc  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Language :
English
Title :
Supervised detection of exoplanets in high-contrast imaging sequences
Publication date :
01 June 2018
Journal title :
Astronomy and Astrophysics
ISSN :
0004-6361
eISSN :
1432-0746
Publisher :
EDP Sciences, Les Ulis, France
Volume :
613
Pages :
A71
Peer reviewed :
Peer Reviewed verified by ORBi
European Projects :
FP7 - 337569 - VORTEX - Taking extrasolar planet imaging to a new level with vector vortex coronagraphy
Name of the research project :
VORTEX
Funders :
UE - Union Européenne [BE]
Funding text :
The authors would like to thank the python open-source scientific community and the developers of the Keras deep learning library. The authors acknowledge fruitful discussions and ideas from the participants in the Exoplanet Imaging and Characterization workshop organized by the W.M. Keck Institute for Space Studies. The research leading to these results has received funding from the European Research Council Under the European Union’s Seventh Framework Program (ERC Grant Agreement n. 337569) and from the French Community of Belgium through an ARC grant for Concerted Research Action.
Available on ORBi :
since 09 January 2018

Statistics


Number of views
244 (47 by ULiège)
Number of downloads
100 (15 by ULiège)

Scopus citations®
 
30
Scopus citations®
without self-citations
20
OpenCitations
 
40

Bibliography


Similar publications



Contact ORBi