A new indirect multi - step - ahead prediction model for a 3 long - term hydrologic prediction

A dependable long-term hydrologic prediction is essential to planning, designing and 12 management activities of water resources. A three-stage indirect multi-step-ahead prediction model, 13 which combines dynamic spline interpolation into multilayer adaptive time-delay neural network 14 (ATNN), is proposed in this study for the long term hydrologic prediction. In the first two stages, a 15 group of spline interpolation and dynamic extraction units are utilized to amplify the effect of 16 observations in order to decrease the errors accumulation and propagation caused by the previous 17 prediction. In the last step, variable time delays and weights are dynamically regulated by ATNN and 18 the output of ATNN can be obtained as a multi-step-ahead prediction .We use two examples to 19 illustrate the effectiveness of the proposed model. One example is the sunspots time series that is a 20 well-known nonlinear and non-Gaussian benchmark time series and is often used to evaluate the 21 effectiveness of nonlinear models. Another example is a case study of a long-term hydrologic 22 prediction which uses the monthly discharges data from the Manwan Hydropower Plant in Yunnan 23 Province of China. Application results show that the proposed method is feasible and effective. 24