Machine learning initialization to accelerate Stokes profile inversions

Detalhes bibliográficos
Autor(a) principal: Gafeira, R.
Data de Publicação: 2021
Outros Autores: Orozco Suárez, D., Milic, I., Quintero Noda, C., Ruiz Cobo, B., Uitenbroek, H.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Texto Completo: https://hdl.handle.net/10316/95678
https://doi.org/10.1051/0004-6361/201936910
Resumo: 14 pages, 10 figures, Accepted for publication on Astronomy and Astrophysics [preprint]
id RCAP_ead6470bb3c4e8fcf5f985f0ebe7e9d7
oai_identifier_str oai:estudogeral.uc.pt:10316/95678
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Machine learning initialization to accelerate Stokes profile inversionsSunAtmosphere14 pages, 10 figures, Accepted for publication on Astronomy and Astrophysics [preprint]In this work, we discuss the application of convolutional neural networks (CNNs) as a tool to advantageously initialize Stokes profile inversions. To demonstrate the usefulness of CNNs, we concentrate in this paper on the inversion of LTE Stokes profiles. We use observations taken with the spectropolarimeter onboard the Hinode spacecraft as a test benchmark. First, we carefully analyze the data with the SIR inversion code using a given initial atmospheric model. The code provides a set of atmospheric models that reproduce the observations. These models are then used to train a CNN. Afterwards, the same data are again inverted with SIR but using the trained CNN to provide the initial guess atmospheric models for SIR. The CNNs allow us to significantly reduce the number of inversion cycles when used to compute initial guess model atmospheres, decreasing the computational time for LTE inversions by a factor of two to four. CNN's alone are much faster than assisted inversions, but the latter are more robust and accurate. The advantages and limitations of machine learning techniques for estimating optimum initial atmospheric models for spectral line inversions are discussed. Finally, we describe a python wrapper for the SIR and DeSIRe codes that allows for the easy setup of parallel inversions. The assisted inversions can speed up the inversion process, but the efficiency and accuracy of the inversion results depend strongly on the solar scene and the data used for the CNN training. This method (assisted inversions) will not obviate the need for analyzing individual events with the utmost care but will provide solar scientists with a much better opportunity to sample large amounts of inverted data, which will undoubtedly broaden the physical discovery space.EDP Sciences2021-03-16info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttps://hdl.handle.net/10316/95678https://hdl.handle.net/10316/95678https://doi.org/10.1051/0004-6361/201936910eng0004-63611432-0746http://arxiv.org/abs/2103.09651v1http://arxiv.org/abs/2103.09651v1http://arxiv.org/abs/2103.09651v1http://arxiv.org/abs/2103.09651v1Gafeira, R.Orozco Suárez, D.Milic, I.Quintero Noda, C.Ruiz Cobo, B.Uitenbroek, H.info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2025-03-11T15:32:22Zoai:estudogeral.uc.pt:10316/95678Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-29T05:43:40.820927Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Machine learning initialization to accelerate Stokes profile inversions
title Machine learning initialization to accelerate Stokes profile inversions
spellingShingle Machine learning initialization to accelerate Stokes profile inversions
Gafeira, R.
Sun
Atmosphere
title_short Machine learning initialization to accelerate Stokes profile inversions
title_full Machine learning initialization to accelerate Stokes profile inversions
title_fullStr Machine learning initialization to accelerate Stokes profile inversions
title_full_unstemmed Machine learning initialization to accelerate Stokes profile inversions
title_sort Machine learning initialization to accelerate Stokes profile inversions
author Gafeira, R.
author_facet Gafeira, R.
Orozco Suárez, D.
Milic, I.
Quintero Noda, C.
Ruiz Cobo, B.
Uitenbroek, H.
author_role author
author2 Orozco Suárez, D.
Milic, I.
Quintero Noda, C.
Ruiz Cobo, B.
Uitenbroek, H.
author2_role author
author
author
author
author
dc.contributor.author.fl_str_mv Gafeira, R.
Orozco Suárez, D.
Milic, I.
Quintero Noda, C.
Ruiz Cobo, B.
Uitenbroek, H.
dc.subject.por.fl_str_mv Sun
Atmosphere
topic Sun
Atmosphere
description 14 pages, 10 figures, Accepted for publication on Astronomy and Astrophysics [preprint]
publishDate 2021
dc.date.none.fl_str_mv 2021-03-16
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10316/95678
https://hdl.handle.net/10316/95678
https://doi.org/10.1051/0004-6361/201936910
url https://hdl.handle.net/10316/95678
https://doi.org/10.1051/0004-6361/201936910
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 0004-6361
1432-0746
http://arxiv.org/abs/2103.09651v1
http://arxiv.org/abs/2103.09651v1
http://arxiv.org/abs/2103.09651v1
http://arxiv.org/abs/2103.09651v1
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv EDP Sciences
publisher.none.fl_str_mv EDP Sciences
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833602453426143232

Registros relacionados