MODELING AND ANALYSIS OF ALGAL BLOOMS IN ARAS DAM BY ARTIFICIAL NEURAL NETWORK


JAHANGIRI-RAD MAHSA

DOI: 10.17378/AWC2015_37


ABSTRACT. Modeling and analysis of algal blooms in Aras Dam by artificial neural network. Man made practices have contributed to large-scale algal blooms that have caused serious ecological, aesthetic, water purification and water distribution problems. Aras Dam, which provides Arasful city with drinking water, has chronic algal blooms since 1990. This study addresses the use of artificial neural network (ANN) model to anticipate the chlorophyll-a concentration in water of dam reservoir. Operation tests carried out by collecting water samples from 5 stations and examined for physical quality parameters namely: water temperature, total suspended solids (TSS), biochemical oxygen demands (BOD), ortophosphate, total phosphorous and nitrate concentrations using standard methods. Chlorophyll-a was also checked separately in order to investigate the accuracy of the predicted results by ANN. The results showed that a network was highly accurate in predicting the Chl-a concentration. A good agreement between actual data and the ANN outputs for training was observed, indicating the validation of testing data sets. The initial results of the research indicate that the dam is enriched with nutrients (phosphorus and nitrogen). The Chl-a concentration that were predicted by the model were beyond the standard levels; indicating the possibility of eutrophication especially during fall season.


Keywords: Aras dam, Chlorophyll-a concentration, artificial neural network.

 

FULL TEXT