Identity statement area | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | mtc-m16b.sid.inpe.br |
Holder Code | isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S |
Identifier | x6e6X3pFwXQZ3DUS8rS5/Cys5B |
Repository | cptec.inpe.br/walmeida/2004/06.24.14.34 |
Last Update | 2015:11.18.17.41.27 marciana |
Metadata | cptec.inpe.br/walmeida/2004/06.24.14.34.11 |
Metadata Last Update | 2018:06.05.03.51.12 administrator |
Secondary Key | INPE--PRE/ |
Citation Key | VijaykumarStePreCamNow:2002:OpNeNe |
Title | Optimized Neural Network Code for Data Assimilation  |
Format | CD-ROM |
Year | 2002 |
Date | 4-9 ago. |
Access Date | 2021, Jan. 18 |
Number of Files | 1 |
Size | 170 KiB |
Context area | |
Author | 1 Vijaykumar, Nandamudi Lankalapali 2 Stephanyl, Stephan 3 Preto, Airam Jonatas 4 Campos Velho, Haroldo Fraga de 5 Nowosad, Alexandre G. |
Group | 1 LAC-INPE-MCT-BR 2 DMD-INPE-MCT-BR |
Affiliation | 1 INPE-Sao Jose dos Campos-12227-010-SP-Brasil |
e-Mail Address | fabia@cptec.inpe.br |
Conference Name | Congresso Brasileiro de Meteorologia, 12. |
Conference Location | Foz do Iguacu |
Pages | 3841-3849 |
Book Title | Anais |
Secondary Type | PRE CN |
Tertiary Type | Artigos |
Organization | SBMET |
History | 2008-06-10 21:14:27 :: administrator -> estagiario :: 2010-05-11 16:53:48 :: estagiario -> administrator :: 2013-09-22 23:27:12 :: administrator -> marciana :: 2002 2014-10-24 16:31:28 :: marciana -> administrator :: 2002 2015-03-04 14:04:57 :: administrator -> marciana :: 2002 2015-11-18 17:41:27 :: marciana -> administrator :: 2002 2018-06-05 03:51:12 :: administrator -> marciana :: 2002 |
Content and structure area | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Content Type | External Contribution |
Abstract | The data assimilation process can be described as a procedure that uses observational data to improve the prediction made by an inaccurate mathematical modelo Recent1y, neural networks have been proposed as a new method for data assimilation. The Multilayer Perceptron network with backpropagation learning was chosen for this procedure. Neural networks are inherent1y a parallel procedure. This paper presents some strategies being used to achieve an optimized parallel code for the network training. Code optimizations include the use of either High Perfonnance Fortran directives or Message Passing Interface library calls. A neural network for Data Assimilation was trained based on both the physical models of the Lorenz and shallow water equations. |
Area | MET |
source Directory Content | there are no files |
agreement Directory Content | there are no files |
Conditions of access and use area | |
data URL | http://mtc-m16b.sid.inpe.br/rep/x6e6X3pFwXQZ3DUS8rS5/Cys5B |
zipped data URL | http://mtc-m16b.sid.inpe.br/zip/x6e6X3pFwXQZ3DUS8rS5/Cys5B |
Language | en |
User Group | administrator marciana |
Reader Group | administrator marciana |
Visibility | shown |
Read Permission | allow from all |
Update Permission | not transferred |
Allied materials area | |
Next Higher Units | 8JMKD3MGPCW/3ESGTTP |
Host Collection | cptec.inpe.br/walmeida/2003/04.25.17.12 |
Notes area | |
Empty Fields | accessionnumber archivingpolicy archivist callnumber copyholder copyright creatorhistory descriptionlevel dissemination doi edition editor electronicmailaddress isbn issn keywords label lineage mark mirrorrepository nextedition notes numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project publisher publisheraddress resumeid rightsholder secondarydate secondarymark serieseditor session shorttitle sponsor subject targetfile tertiarymark type url versiontype volume |
Description control area | |
e-Mail (login) | marciana |
update | |
| |