Comparison between Linear and Non-linear ANN Models for Predicting Water Quality Parameters at Tigris River | ||
| Journal of Engineering | ||
| Article 1, Volume 20, Issue 10, October 2014, Pages 1-15 | ||
| Authors | ||
| Rafa Hashim Al Suhili; Zainab Jaber Mohammed | ||
| Abstract | ||
| In this research, Artificial Neural Networks (ANNs) technique was applied in an attempt to predict the water levels and some of the water quality parameters at Tigris River in Wasit Government for five different sites. These predictions are useful in the planning, management, evaluation of the water resources in the area. Spatial data along a river system or area at different locations in a catchment area usually have missing measurements, hence an accurate prediction. model to fill these missing values is essential. The selected sites for water quality data prediction were Sewera, Numania , Kut u/s, Kut d/s, Garaf observation sites. In these five sites models were built for prediction of the water level and water quality parameters. the following (Biological Oxygen Demand(BOD_5), Phosphate,(PO_4) Sulfate(SO_4), Nitrate(NO_3), Calcium(Ca), Magnesium(Mg), Total Hardness(TH), Potassium(K), Sodium (Na), Chloride (CL), Total Dissolved Solids (TDS), Electric conductivity (EC), Alkalinity(ALK)). The ANN models tried herein were the Multisite- Multivariate ANN models (5-sites, 14 variables), five models were built, one for each of the five stations as the missing data station. The linear ANN (traditional) models fail to make the prediction of all variables with high correlation coefficient simultaneously. Hence a non- linear input ANN model was developed herein and believed to be a new modification in ANN modeling. It was found that the ANNs have the ability to predict water level and water quality parameters at all the sites with a good degree of accuracy, the range of correlation coefficients obtained are (12.9%-97.2%) for linear models, while for this model with Non-linear terms, The range of correlation coefficients obtained is (71.8%-99.6%). | ||
| Keywords | ||
| artificial neural network; Water level; The water quality parameters; Tigris River; non; Linear Model | ||
|
Statistics Article View: 61 PDF Download: 36 |
||