Cargando…

Deep learning exoplanets detection by combining real and synthetic data

Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the us...

Descripción completa

Detalles Bibliográficos
Autores principales: Cuéllar, Sara, Granados, Paulo, Fabregas, Ernesto, Curé, Michel, Vargas, Héctor, Dormido-Canto, Sebastián, Farias, Gonzalo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9132280/
https://www.ncbi.nlm.nih.gov/pubmed/35613093
http://dx.doi.org/10.1371/journal.pone.0268199
_version_ 1784713343734382592
author Cuéllar, Sara
Granados, Paulo
Fabregas, Ernesto
Curé, Michel
Vargas, Héctor
Dormido-Canto, Sebastián
Farias, Gonzalo
author_facet Cuéllar, Sara
Granados, Paulo
Fabregas, Ernesto
Curé, Michel
Vargas, Héctor
Dormido-Canto, Sebastián
Farias, Gonzalo
author_sort Cuéllar, Sara
collection PubMed
description Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the use of various databases provided by space and ground-based telescopes. This article proposes the development of a deep learning system for detecting planetary transits in Kepler Telescope light curves. The approach is based on related work from the literature and enhanced to validation with real light curves. A CNN classification model is trained from a mixture of real and synthetic data. The model is then validated only with unknown real data. The best ratio of synthetic data is determined by the performance of an optimisation technique and a sensitivity analysis. The precision, accuracy and true positive rate of the best model obtained are determined and compared with other similar works. The results demonstrate that the use of synthetic data on the training stage can improve the transit detection performance on real light curves.
format Online
Article
Text
id pubmed-9132280
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-91322802022-05-26 Deep learning exoplanets detection by combining real and synthetic data Cuéllar, Sara Granados, Paulo Fabregas, Ernesto Curé, Michel Vargas, Héctor Dormido-Canto, Sebastián Farias, Gonzalo PLoS One Research Article Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the use of various databases provided by space and ground-based telescopes. This article proposes the development of a deep learning system for detecting planetary transits in Kepler Telescope light curves. The approach is based on related work from the literature and enhanced to validation with real light curves. A CNN classification model is trained from a mixture of real and synthetic data. The model is then validated only with unknown real data. The best ratio of synthetic data is determined by the performance of an optimisation technique and a sensitivity analysis. The precision, accuracy and true positive rate of the best model obtained are determined and compared with other similar works. The results demonstrate that the use of synthetic data on the training stage can improve the transit detection performance on real light curves. Public Library of Science 2022-05-25 /pmc/articles/PMC9132280/ /pubmed/35613093 http://dx.doi.org/10.1371/journal.pone.0268199 Text en © 2022 Cuéllar et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Cuéllar, Sara
Granados, Paulo
Fabregas, Ernesto
Curé, Michel
Vargas, Héctor
Dormido-Canto, Sebastián
Farias, Gonzalo
Deep learning exoplanets detection by combining real and synthetic data
title Deep learning exoplanets detection by combining real and synthetic data
title_full Deep learning exoplanets detection by combining real and synthetic data
title_fullStr Deep learning exoplanets detection by combining real and synthetic data
title_full_unstemmed Deep learning exoplanets detection by combining real and synthetic data
title_short Deep learning exoplanets detection by combining real and synthetic data
title_sort deep learning exoplanets detection by combining real and synthetic data
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9132280/
https://www.ncbi.nlm.nih.gov/pubmed/35613093
http://dx.doi.org/10.1371/journal.pone.0268199
work_keys_str_mv AT cuellarsara deeplearningexoplanetsdetectionbycombiningrealandsyntheticdata
AT granadospaulo deeplearningexoplanetsdetectionbycombiningrealandsyntheticdata
AT fabregasernesto deeplearningexoplanetsdetectionbycombiningrealandsyntheticdata
AT curemichel deeplearningexoplanetsdetectionbycombiningrealandsyntheticdata
AT vargashector deeplearningexoplanetsdetectionbycombiningrealandsyntheticdata
AT dormidocantosebastian deeplearningexoplanetsdetectionbycombiningrealandsyntheticdata
AT fariasgonzalo deeplearningexoplanetsdetectionbycombiningrealandsyntheticdata