Prediction of Flow Flooding in Changhua River Based on Time Series Models

Short-term forecasting of water level in the Changhua River is important for flood prevention strategies. The main objective is to reach to the appropriate model to predict the flow, so, in this paper we used Autoregressive Integrated Moving Average (ARIMA) model, Artificial Neural Network (ANN) model and the combination of the neural network and time series analysis using previous residual and an estimated value of the ARIMA model called Hybrid (ARIMA_ANN) model. The result showed that the most appropriate model to predict the flow is the hybrid (ARIMA_ANN) model, where it gives more accurate results rather than ARIMA and ANN each separately. Furthermore, artificial neural networks give the best prediction rather than ARIMA models in accordance with the standards of prediction accuracy RMSE, MAP, MAPE.