Back to Search
Start Over
Data-driven modelling in the context of sediment transport
- Source :
-
Physics & Chemistry of the Earth - Parts A/B/C . 2005, Vol. 30 Issue 4/5, p297-302. 6p. - Publication Year :
- 2005
-
Abstract
- Abstract: Numerous models for predicting sediment transport rates have been developed over time. Nevertheless, the predictive accuracy of these models is often questionable. The transport mechanism is complex, and the deterministic transport models are based on simplifying assumptions that often lead to large prediction errors. Data-driven modelling can be useful for modelling processes about which adequate knowledge of the physics is limited. In the present paper a sediment transport model based on an artificial neural network (ANN) is presented. The predictive accuracy of the ANN model on the data sets compiled by Brownlie was found to be better than that of Engelund-Hansen and Van Rijn. A conclusion is reached that the data-driven modelling approach is suitable for modelling sediment transport. [Copyright &y& Elsevier]
Details
- Language :
- English
- ISSN :
- 14747065
- Volume :
- 30
- Issue :
- 4/5
- Database :
- Academic Search Index
- Journal :
- Physics & Chemistry of the Earth - Parts A/B/C
- Publication Type :
- Academic Journal
- Accession number :
- 17992047
- Full Text :
- https://doi.org/10.1016/j.pce.2004.12.001