Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220702957> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4220702957 abstract "Abstract The runoff sequence has the characteristics of non-linear and non-steady state, which leads to the low accuracy of direct prediction. In order to extract the implicit information in the original data more effectively, the complex runoff sequence is decomposed into multiple components by using singular spectrum analysis (SSA) and wavelet packet decomposition (WPD) decomposition methods. The auto-correlation function (ACF) and partial auto-correlation function (PACF) methods are used to select the previous runoff order that has a significant impact on the current runoff. Then six kinds of neural network models are selected as simulation methods. The daily runoff and monthly runoff of the Baihe (BH) and Huangjiagang (HJG) stations in the Hanjiang River Basin (HRB) were taken as the research object. The research shows that the kurtosis value of each component obtained by the SSA decomposition method has a certain randomness, while the kurtosis value of each component of WPD gradually decreases, but the amount of information carried by the first component is too large. Although the monthly runoff changes are more regular, due to the large amount of daily runoff data used for training, the model runoff simulation effect is better than that of monthly runoff. Most models have the problem that the simulated runoff is too large when the runoff is small, and the simulation results are too small when the runoff is large. The main decision of the model results is the structure of the model itself, and the two decomposition methods have little effect on the prediction effect of the models. This study can provide a way to select a forecasting method for nonlinear and non-steady-state runoff time series forecasting." @default.
- W4220702957 created "2022-04-03" @default.
- W4220702957 creator A5014920443 @default.
- W4220702957 creator A5021536658 @default.
- W4220702957 creator A5023051545 @default.
- W4220702957 creator A5023214008 @default.
- W4220702957 creator A5050610415 @default.
- W4220702957 creator A5053838491 @default.
- W4220702957 creator A5057661079 @default.
- W4220702957 creator A5065220600 @default.
- W4220702957 date "2022-03-28" @default.
- W4220702957 modified "2023-10-04" @default.
- W4220702957 title "Runoff Forecasting Based on Combining Multiple Neural Networks and Modal Decomposition" @default.
- W4220702957 doi "https://doi.org/10.21203/rs.3.rs-1470398/v1" @default.
- W4220702957 hasPublicationYear "2022" @default.
- W4220702957 type Work @default.
- W4220702957 citedByCount "0" @default.
- W4220702957 crossrefType "posted-content" @default.
- W4220702957 hasAuthorship W4220702957A5014920443 @default.
- W4220702957 hasAuthorship W4220702957A5021536658 @default.
- W4220702957 hasAuthorship W4220702957A5023051545 @default.
- W4220702957 hasAuthorship W4220702957A5023214008 @default.
- W4220702957 hasAuthorship W4220702957A5050610415 @default.
- W4220702957 hasAuthorship W4220702957A5053838491 @default.
- W4220702957 hasAuthorship W4220702957A5057661079 @default.
- W4220702957 hasAuthorship W4220702957A5065220600 @default.
- W4220702957 hasBestOaLocation W42207029571 @default.
- W4220702957 hasConcept C105795698 @default.
- W4220702957 hasConcept C125112378 @default.
- W4220702957 hasConcept C127413603 @default.
- W4220702957 hasConcept C166963901 @default.
- W4220702957 hasConcept C187320778 @default.
- W4220702957 hasConcept C18903297 @default.
- W4220702957 hasConcept C24749216 @default.
- W4220702957 hasConcept C33923547 @default.
- W4220702957 hasConcept C39432304 @default.
- W4220702957 hasConcept C41008148 @default.
- W4220702957 hasConcept C50477045 @default.
- W4220702957 hasConcept C76886044 @default.
- W4220702957 hasConcept C86803240 @default.
- W4220702957 hasConceptScore W4220702957C105795698 @default.
- W4220702957 hasConceptScore W4220702957C125112378 @default.
- W4220702957 hasConceptScore W4220702957C127413603 @default.
- W4220702957 hasConceptScore W4220702957C166963901 @default.
- W4220702957 hasConceptScore W4220702957C187320778 @default.
- W4220702957 hasConceptScore W4220702957C18903297 @default.
- W4220702957 hasConceptScore W4220702957C24749216 @default.
- W4220702957 hasConceptScore W4220702957C33923547 @default.
- W4220702957 hasConceptScore W4220702957C39432304 @default.
- W4220702957 hasConceptScore W4220702957C41008148 @default.
- W4220702957 hasConceptScore W4220702957C50477045 @default.
- W4220702957 hasConceptScore W4220702957C76886044 @default.
- W4220702957 hasConceptScore W4220702957C86803240 @default.
- W4220702957 hasLocation W42207029571 @default.
- W4220702957 hasOpenAccess W4220702957 @default.
- W4220702957 hasPrimaryLocation W42207029571 @default.
- W4220702957 hasRelatedWork W146018078 @default.
- W4220702957 hasRelatedWork W2026371027 @default.
- W4220702957 hasRelatedWork W2055705976 @default.
- W4220702957 hasRelatedWork W2323070724 @default.
- W4220702957 hasRelatedWork W2327934318 @default.
- W4220702957 hasRelatedWork W2353133006 @default.
- W4220702957 hasRelatedWork W2376638751 @default.
- W4220702957 hasRelatedWork W2392512544 @default.
- W4220702957 hasRelatedWork W2481972191 @default.
- W4220702957 hasRelatedWork W2906158200 @default.
- W4220702957 isParatext "false" @default.
- W4220702957 isRetracted "false" @default.
- W4220702957 workType "article" @default.