Artificial Neural Network Approaches to the Prediction of Eutrophication and Algal Blooms in Aras Dam, Iran

Background and purpose: eutrophication is one of the major environmental problems inwaterways causing substantial adverse impact on domestic, livestock and recreational use ofwater resources. aras dam, iran which provides arasful city with drinking water, has chronicalgal blooms since 1990. levels of up to 900,000 cells/ml of toxic cyanobacteria (mainlyanabaena and microcystis) have been recorded in the dam.materials and methods: in this study, artificial neural network (ann) model was investigatedto predict the chlorophyll-a (chl-a) concentration in water of dam reservoir. water sampleswere collected from 5 stations and analyzed for physical quality parameters including; watertemperature, total suspended solids, biochemical oxygen demands, orthophosphate, totalphosphorous and nitrate concentrations using standard methods. chl-a was also measuredseparately in order to investigate the accuracy of the predicted results by ann.results: the results showed that a network was highly accurate in predicting the chl-aconcentration. the mean squared error and coefficient of correlation (r2) between experimentaldata and model outputs were calculated. a good agreement between actual data and the annoutputs for training was observed, indicating the validation of testing data sets. the initialresults of the research indicate that the dam is enriched with nutrients (phosphorus and nitrogen)and is on the verge of being eutrophic.conclusion: the chl-a concentration that was predicted by the model was beyond the standardlevels; indication the possibility of eutrophication especially during fall season.