Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Daily suspended sediment forecast by an integrated dynamic neural network
Department of Civil and Architectural Engineering, KTH Royal Institute of Technology, Stockholm, Sweden.
Luleå tekniska universitet, Institutionen för teknikvetenskap och matematik, Strömningslära och experimentell mekanik.ORCID-id: 0000-0003-0820-617X
Department of Civil and Architectural Engineering, KTH Royal Institute of Technology, Stockholm, Sweden; Vattenfall AB, R&D Hydraulic Laboratory, Älvkarleby, Sweden .
2022 (engelsk)Inngår i: Journal of Hydrology, ISSN 0022-1694, E-ISSN 1879-2707, Vol. 604, artikkel-id 127258Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Suspended sediment is of importance in river and dam engineering. While, due to its high nonlinearity and stochasticity, sediment prediction by conventional methods is a challenging task. Consequently, this paper establishes a new hybrid model for an improved forecast of suspended sediment concentration (SSC). It is a nonlinear autoregressive network with exogenous inputs (NARX) integrated with a data pre-processing framework (denoted as INARX). In this model, wavelet transformation (WT) is used for time series decomposition and multigene genetic programing (MGGP) for details scaling. The two incorporated modules improve time and frequency domain analysis, allowing the network to unveil the embedded characteristics and capture its non-stationarity. At a hydrological station on the upper reaches of the Yangtze River, the records of daily water stage, flow discharge and suspended sediment are collected and refer to a nine-year period during 2004-2012. The data are used to evaluate the models. Several wavelets are explored, showing that the Coif3 leads to the most accurate prediction. Compared to the sediment rating curve (SRC), the conventional MGGP, multilayer perceptron neural network (MLPNN) and NARX, the INARX demonstrates the best forecast performance. Its mean coefficient of determination (CD) increases by 7.7%-38.6% and the root mean squared error (RMSE) reduces by 15.1%-54.5%. The INARX with the Coif3 wavelet is further evaluated for flood events and multistep forecast. Under flood conditions, the model generates satisfactory results, with CD > 0.83 and 84.7% of the simulated data falling within the ±0.1 kg/m3 error. For the multistep forecast, at a one-week lead time, the network also yields predictions with acceptable accuracy (mean CD = 0.78). The model performance deteriorates if the lead time becomes larger. The established framework is robust and reliable for real-time and multistep SSC forecast and provides reference for time series modeling, e.g. streamflow, river temperature and salinity.

sted, utgiver, år, opplag, sider
Elsevier, 2022. Vol. 604, artikkel-id 127258
Emneord [en]
River suspended sediment, wavelet transformation, multigene genetic programing, multilayer perceptron neural network, INARX
HSV kategori
Forskningsprogram
Strömningslära
Identifikatorer
URN: urn:nbn:se:ltu:diva-87155DOI: 10.1016/j.jhydrol.2021.127258ISI: 000731346800003Scopus ID: 2-s2.0-85120692547OAI: oai:DiVA.org:ltu-87155DiVA, id: diva2:1595914
Merknad

Validerad;2022;Nivå 2;2022-01-01 (johcin)

Tilgjengelig fra: 2021-09-20 Laget: 2021-09-20 Sist oppdatert: 2022-06-01bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Xie, Qiancheng

Søk i DiVA

Av forfatter/redaktør
Xie, Qiancheng
Av organisasjonen
I samme tidsskrift
Journal of Hydrology

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 74 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf