Close

1. Identity statement
Reference TypeJournal Article
Siteplutao.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier8JMKD3MGP3W/474P3R2
Repositorysid.inpe.br/plutao/2022/06.15.13.04.48   (restricted access)
Last Update2022:06.20.13.49.37 (UTC) lattes
Metadata Repositorysid.inpe.br/plutao/2022/06.15.13.04.49
Metadata Last Update2023:01.03.16.52.55 (UTC) administrator
DOI10.14529/jsfi220105
ISSN2409-6008
Labellattes: 5142426481528206 1 CamposVelhoFSBWSCC:2022:PaIm
Citation KeyCamposVelhoFSBWSCC:2022:PaIm
TitleData Assimilation by Neural Network for Ocean Circulation: Parallel Implementation
Year2022
Access Date2024, May 16
Type of Workjournal article
Secondary TypePRE PI
Number of Files1
Size881 KiB
2. Context
Author1 Campos Velho, Haroldo Fraga de
2 Furtado, Helaine Cristina Morais
3 Sambatti, Sabrina Bérgoch Monteiro
4 Barros, Carla Osthoff Ferreira de
5 Welter, Maria Eugenia Sausen
6 Souto, Roberto Pinto
7 Carvalho, Diego
8 Cardoso, Douglas O.
Resume Identifier1 8JMKD3MGP5W/3C9JHC3
Group1 COPDT-CGIP-INPE-MCTI-GOV-BR
Affiliation1 Instituto Nacional de Pesquisas Espaciais (INPE)
2 Universidade Federal do Oeste do Pará (UFOPA)
3
4 Laboratório Nacional de Computação Científica (LNCC)
5 Laboratório Nacional de Computação Científica (LNCC)
6 Laboratório Nacional de Computação Científica (LNCC)
7 Centro Federal de Educação Tecnológica Celso Suckow da Fonseca
8 Centro Federal de Educação Tecnológica Celso Suckow da Fonseca
Author e-Mail Address1 haroldo.camposvelho@inpe.br
JournalSupercomputing Frontiers and Innovations
Volume9
Number1
Pages74-86
History (UTC)2022-06-20 13:49:38 :: lattes -> administrator :: 2022
2023-01-03 16:52:55 :: administrator -> simone :: 2022
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Version Typepublisher
KeywordsData assimilation
Articial Neural Network
Shallow water equations
Parallel processing
AbstractData assimilation (DA) is an essential issue for operational prediction centers, where a com-puter code is applied to simulate physical phenomena by solving differential equations. The pro-cedure to determine the best initial condition combining data from observation and previousforecasting (background) is carried out by a data assimilation method. The Kalman filter (KF) isa technique for data assimilation, but it is computationally expensive. An approach to reduce thecomputational effort for DA is to emulate the KF by a neural network. The multi-layer perceptronneural network (MLP-NN) is employed to emulate the Kalman in a 2D ocean circulation model,and algorithmic complexity to KF and NN is presented. A shallow-water system models the oceandynamics. Synthetic measurements are used for evaluating the MLP-NN for the data assimilationprocess. Here, a parallel version for the DA procedure by the neural network is described andtested, showing the performance improvement for a parallel version of the NN-DA.
AreaCOMP
Arrangementurlib.net > BDMCI > Fonds > Produção a partir de 2021 > CGIP > Data Assimilation by...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Contentthere are no files
4. Conditions of access and use
Languageen
Target Filesuperfri-2022-1-74-86.pdf
User Grouplattes
Reader Groupadministrator
lattes
Visibilityshown
Read Permissiondeny from all and allow from 150.163
Update Permissionnot transferred
5. Allied materials
Next Higher Units8JMKD3MGPCW/46KUES5
Citing Item Listsid.inpe.br/mtc-m21/2012/07.13.14.49.40 3
sid.inpe.br/bibdigital/2022/04.03.23.11 2
URL (untrusted data)https://superfri.org/index.php/superfri/issue/view/33
DisseminationPORTALCAPES; SCOPUS.
Host Collectiondpi.inpe.br/plutao@80/2008/08.19.15.01
6. Notes
Empty Fieldsalternatejournal archivingpolicy archivist callnumber copyholder copyright creatorhistory descriptionlevel e-mailaddress format isbn lineage mark mirrorrepository month nextedition notes orcid parameterlist parentrepositories previousedition previouslowerunit progress project rightsholder schedulinginformation secondarydate secondarykey secondarymark session shorttitle sponsor subject tertiarymark tertiarytype
7. Description control
e-Mail (login)simone
update 


Close