Using artificial neural network for reservoir water quality analysis in Taiwan

Eutrophication has been considered as one of the most serious water quality problems of reservoirs in Taiwan. The back-propagation artificial neural network (ANN) was used to predict the water quality variation of the LungLuanTan Reservoir in southern Taiwan in current research. Three mathematical models were established and to predict the variation of parameters including total phosphorus (TP), secchi disk depth (SD), and dissolved oxygen (DO). The field data were divided into training and testing sets randomly. In all, the results indicated the model performing well to address the water quality and eutrophication problems found in reservoir. The artificial neural network is a valuable tool for reservoir water quality management.