강우자료 형태에 따른 인공신경망의 일유입량 예측 정확도 평가

Influence of Rainfall observation Network on Daily Dam Inflow using Artificial Neural Networks

Abstract

The objective of this study was to evaluate the influence of rainfall observation network on daily dam inflow using artificial neural networks(ANNs). Chungju Dam and Soyangriver Dam were selected for the study watershed. Rainfall and dam inflow data were collected as input data for construction of ANNs models. Five ANNs models, represented by Model 1 (In watershed, point rainfall), Model 2 (All in the Thiessen network, point rainfall), Model 3 (Out of watershed in the Thiessen network, point rainfall), Model 1-T (In watershed, area mean rainfall), Model 2-T (All in the Thiessen network, area mean rainfall), were adopted to evaluate the influence of rainfall observation network. As a result of the study, the models that used all station in the Thiessen network performed better than the models that used station only in the watershed or out of the watershed. The models that used point rainfall data performed better than the models that used area mean rainfall. Model 2 achieved the highest level of performance. The model performance for the ANNs model 2 in Chungju dam resulted in the $R^2$ value of 0.94, NSE of 0.94 $NSE_{ln}$ of 0.88 and PBIAS of -0.04 respectively. The model-2 predictions of Soyangriver Dam with the $R^2$ and NSE values greater than 0.94 were reasonably well agreed with the observations. The results of this study are expected to be used as a reference for rainfall data utilization in forecasting dam inflow using artificial neural networks.

Fig. 1 Study area – Soyangriver dam watershed

Fig. 2 Study area – Chungju dam watershed

Fig. 3 Architecture of artificial neuron

Fig. 4 Structure of artificial neural network

Fig. 5 MSE according to time lags (Chungju dam)

Fig. 6 MSE according to time lags (Soyangriver dam)

Fig. 7 Scatter plots comparing observed and simulated Chungju dam inflow by artificial neural network for testing period

Fig. 8 Scatter plots comparing observed and simulated Soyangriver dam inflow by artificial neural network for testing period

Fig. 9 Time series of observed and simulated of Chungju dam inflow according to the meteorological range

Fig. 10 Time series of observed and simulated of Soyangriver dam inflow according to the meteorological range

Fig. 11 Time series of observed and simulated of Chungju dam inflow according to the use of area mean rainfall

Fig. 12 Time series of observed and simulated of Soyangriver dam inflow according to the use of area mean rainfall

Table 1 Thiessen area of Soyangriver dam watershed

Table 2 Thiessen area of Chungju dam watershed

Table 3 Type of Input rainfall in model

Table 4 Time lags and hidden node of each model

Table 5 Training and testing statics for each models