Please use this identifier to cite or link to this item:
|Title:||Artificial neural networks: A flexible approach to modelling|
|Citation:||Water, 2004; 31(8):55-60|
|Publisher:||Australian Water Association Inc|
|Maier, H.R., Dandy, G.C.|
|Abstract:||Artificial neural networks (ANNs) are a computational tool based on an analogy to the structure and operation of the human brain. They provide a flexible way of approximating highly non-linear relationships between variables without the need to make a priori assumptions about the form of the relationships. ANN models have been used for prediction and forecasting in a large number of areas of hydrology and water resources. In this paper, a number of case studies are presented to demonstrate the successful application of ANNs in the water industry. These case studies include forecasting salinity in the River Murray 14 days in advance, forecasting Anabaena spp in the River Murray 4 weeks in advance, predicting the alum dose required to achieve pre-determined water quality levels at a water treatment plant and forecasting chlorine levels near the downstream end of the Myponga trunk main 24 hours in advance. The case studies demonstrate that ANNs perform extremely well in a variety of modelling and forecasting roles.|
|Appears in Collections:||Civil and Environmental Engineering publications|
Environment Institute publications
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.