Close

1. Identity statement
Reference TypeJournal Article
Sitemtc-m12.sid.inpe.br
Holder Codeisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identifier6qtX3pFwXQZGivnJRY/KU9yN
Repositorysid.inpe.br/mtc-m12@80/2006/04.28.18.38   (restricted access)
Last Update2006:12.19.16.21.23 (UTC) administrator
Metadata Repositorysid.inpe.br/mtc-m12@80/2006/04.28.18.38.18
Metadata Last Update2018:06.05.00.40.45 (UTC) administrator
Secondary KeyINPE-14457-PRE/9527
ISSN0022-1694
Citation KeyPereiraFoSant:2006:MoDeUr
TitleModeling a densely urbanized watershed with an artificial neural network, weather radar and telemetric data
Year2006
MonthFev.
Access Date2024, Apr. 28
Secondary TypePRE PI
Number of Files1
Size513 KiB
2. Context
Author1 Pereira Filho, Augusto José
2 Santos, Cláudia Cristina dos
Group1
2 DSR-INPE-MCT-BR
Affiliation1 Universidade de São Paulo
2 Instituto Nacional de Pesquisas Espaciais
JournalJournal of Hydrology
Volume317
Number1-2
Pages31-48
History (UTC)2006-04-28 18:38:18 :: claudia -> marciana ::
2006-05-16 12:09:09 :: marciana -> administrator ::
2006-08-02 21:31:31 :: administrator -> marciana ::
2006-08-02 22:08:49 :: marciana -> administrator ::
2006-09-03 21:43:56 :: administrator -> marciana ::
2007-04-20 14:45:15 :: marciana -> administrator ::
2009-08-12 01:08:39 :: administrator -> marciana ::
2011-05-23 01:04:43 :: marciana -> administrator ::
2018-06-05 00:40:45 :: administrator -> marciana :: 2006
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
KeywordsGEOCIENCIAS
Geosciences
models
rainfall-runoff
urban hydrology
artificial neural network
weather radar
nowcasting
AbstractArtificial neural networks (ANN) are widely used in a myriad of fields of research and development, including the predictability of time series. This work is concerned with one of such applications to simulate and to forecast stage level and streamflow at the Tamanduatei river watershed, one of the main tributaries of the Alto Tiete river watershed in Sao Paulo State, Brazil. This heavily urbanized watershed is within the Metropolitan Area of Sao Paulo (MASP) where recurrent flash floods affect a population of more than 17 million inhabitants. Flash floods events between 1991 and 1995 were selected and divided up into three groups for training, verification and forecasting purposes. Weather radar rainfall estimation and telemetric stage level and streamflow data were input to a three-layer feed forward ANN trained with the Linear Least Square Simplex training algorithm (LLSSIM) by Hsu et al. [Hsu, K.L., Gupta, H.V., Sorooshian, S., 1996. A superior training strategy for three-layer feed forward artificial neural networks. Tucson, University of Arizona. (Technique report, HWR no. 96-030, Department of Hydrology and Water Resources)]. The performance of the ANN is improved by 40% when either streamflow or stage level were input together with the rainfall. The ANN simulated flood waves tend to be dominated by phase errors. The ANN showed slightly better results then a multi-parameter auto-regression model and indicates its usefulness in flash flood forecasting. (C) 2005 Elsevier B.V. All rights reserved.
AreaSRE
Arrangementurlib.net > BDMCI > Fonds > Produção anterior à 2021 > DIDSR > Modeling a densely...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Contentthere are no files
4. Conditions of access and use
Languageen
Target Filepereira filho - modeling.pdf
User Groupadministrator
claudia
marciana
Visibilityshown
Copy HolderSID/SCD
Archiving Policydenypublisher denyfinaldraft24
Read Permissiondeny from all and allow from 150.163
5. Allied materials
Next Higher Units8JMKD3MGPCW/3ER446E
DisseminationWEBSCI; PORTALCAPES; MGA; COMPENDEX.
Host Collectionsid.inpe.br/banon/2001/04.06.10.52
6. Notes
Empty Fieldsalternatejournal archivist callnumber copyright creatorhistory descriptionlevel documentstage doi e-mailaddress electronicmailaddress format isbn label lineage mark mirrorrepository nextedition notes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup resumeid rightsholder schedulinginformation secondarydate secondarymark session shorttitle sponsor subject tertiarymark tertiarytype typeofwork url versiontype
7. Description control
e-Mail (login)marciana
update 


Close