Please use this identifier to cite or link to this item:
|Title:||Suspended sediment flux modeling with artificial neural network: An example of the Longchuanjiang River in the Upper Yangtze Catchment, China|
|Keywords:||Artificial neural network|
Suspended sediment flux
|Source:||Zhu, Y.-M., Lu, X.X., Zhou, Y. (2007). Suspended sediment flux modeling with artificial neural network: An example of the Longchuanjiang River in the Upper Yangtze Catchment, China. Geomorphology 84 (1-2) : 111-125. ScholarBank@NUS Repository. https://doi.org/10.1016/j.geomorph.2006.07.010|
|Abstract:||Artificial neural network (ANN) was used to model the monthly suspended sediment flux in the Longchuanjiang River, the Upper Yangtze Catchment, China. The suspended sediment flux was related to the average rainfall, temperature, rainfall intensity and water discharge. It is demonstrated that ANN is capable of modeling the monthly suspended sediment flux with fairly good accuracy when proper variables and their lag effect on the suspended sediment flux are used as inputs. Compared with multiple linear regression and power relation models, ANN can generate a better fit under the same data requirement. In addition, ANN can provide more reasonable predictions for extremely high or low values, because of the distributed information processing system and the nonlinear transformation involved. Compared with the ANNs that use the values of the dependent variable at previous time steps as inputs, the ANNs established in this research with only climate variables have an advantage because it can be used to assess hydrological responses to climate change. © 2006 Elsevier B.V. All rights reserved.|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 5, 2017
WEB OF SCIENCETM
checked on Nov 12, 2017
checked on Dec 9, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.