Forecasting Water Quality Parameters by ANN Model using Pre-processing Technique at The Downstream of Cheongpyeong Dam

In this study, the water quality parameters (Temperature, DO, pH, Electric Conductivity, TN, TP, Turbidity and Chlorophyll-a) at the downstream of Cheongpyeong dam are predicted using artificial neural network. The artificial neural network(ANN) is a powerful computational technique for modeling complex relationship between input and output data. Typically, Time series generally consists of a linear combination of trend, periodicity and stochastic component. In this study, to reduce the influence of trend, periodicity and stochastic component and to enhance the performance of ANN model, developed the Ensemble ANN model with stratified sampling method. 7 parameters (Temperature, DO, pH, Electric Conductivity, TN, TP, and Chlorophyll-a) have the higher than 0.85 R squared. And 5 parameters (Temperature, DO, pH, TN, and TP shows than 1.0 RMSE