Evaluation of phytoplankton composition of the pelagic region of do? Anci dam reservoir (Bursa, Turkey) by artificial neural network (ANN) and clustering technique

Abstract

This study was carried out in four stations in the Doganci Dam Reservoir in the northwestern part of the Anatolian Region of Turkey. Within this study, phytoplankton composition were evaluated by using artificial neural network and clustering technique. For this purpose, phytoplankton algal flora and some physico-chemical parameters were investigated in water samples taken from four different stations in Doganci Dam Reservoir. A total of 75 taxa belonging to the divisions of Bacillariophyceae (45), Chlorophyceae (12), Cyanophyceae (12), Dinophyceae (2), Chrysophyceae (2) and Euglenophyceae (2) were detected in the algal flora of the pelagic region. In terms of species diversity in the phytoplankton, Bacillariophyceae members were dominant, followed by Chlorophyceae and Cyanophyceae members. As a result of the research, the type list determined is the first report on the phytoplankton composition of the dam reservoir and it is thought to be beneficial in terms of future water quality and water pollution research. Cluster analysis is a classification method that is used to arrange a set of form into clusters. The aim of this method is to classify a set of clusters such that cases within a cluster are more similar to each other and to submit summary information of the data to researchers. For predicting phytoplankton biomass, in this study, ANN was combined with a clustering technique. This case study demonstrated the good performance of ANN models in describing phytoplankton dynamics, and the potential of coupling ANN with a clustering technique to describe the spatial heterogeneity of natural ecosystems.