Neural networks for predicting seawater bacterial levels
- 1 September 2005
- journal article
- research article
- Published by Thomas Telford Ltd. in Proceedings of the ICE - Water Management
- Vol. 158 (3), 111-118
- https://doi.org/10.1680/wama.2005.158.3.111
Abstract
In this study artificial neural networks (ANNs) have been applied to predict faecal coliform concentration levels at compliance points along bathing water zones situated in the south west of Scotland, UK. Hydrological parameters, such as river discharges, sunshine, rainfall and tidal conditions, were used as the input data for these networks. Data collected at seven locations during the period 1990–2000 were used to train and verify the neural networks. A novel technique called the gamma test was used for data analysis to aid in the construction of ANN models. In general, the river discharges and tidal range were found to be the most important variables affecting the level of bacteria concentration at the compliance points. For compliance points close to the meteorological station, the amount of rainfall was found to be relatively significant in the model results. Relatively good correlation coefficients were obtained for the learning and verifying process for all of the ANNs and these networks confirmed that the samples failed to comply with the standard values specified in the European Union Bathing Water Directive in 57·4% of the cases.Keywords
This publication has 17 references indexed in Scilit:
- Application of artificial neural networks in tide-forecastingOcean Engineering, 2002
- Hydro-environmental modelling for bathing water compliance of an estuarine basinWater Research, 2002
- Neural Network LearningPublished by Cambridge University Press (CUP) ,1999
- Back-Propagation Neural Network in Tidal-Level ForecastingJournal of Waterway, Port, Coastal, and Ocean Engineering, 1999
- Application of artificial neural networks to the simulation of a two dimensional flowJournal of Hydraulic Research, 1999
- Forecasting with artificial neural networks:: The state of the artInternational Journal of Forecasting, 1998
- Concepts for Neural NetworksPublished by Springer Science and Business Media LLC ,1998
- Forecasting raw-water quality parameters for the North Saskatchewan River by neural network modelingWater Research, 1997
- Principles of Artificial Neural NetworksInterval Methods for Circuit Analysis, 1997
- Neural networksCommunications of the ACM, 1994