A Stochastic Model for Mid-to-Long-Term Runoff Forecast

In order to mine important information in hydrologic series data adequately and improve results of mid-to-long term runoff forecast, factors influencing forecast results have been analyzed firstly, and a stochastic model for mid-to-long term runoff forecast has been established based on WA, ANN, and hydrologic frequency analysis. The main idea is: analyze runoff series in multi time scales by WA firstly, and separate the deterministic components and random signals in original series; Followed by using ANN to simulate and forecast the deterministic components, and using hydrologic frequency analysis to get forecast results of random series under different guaranteed efficiency; Stack the two as final results. The model has been verified by applying to the estuary area of the Yellow River watershed. Results show that this model is of high precision, high eligible rate, can understand the variation characters of series meanwhile, and is able to quantitatively describe the influence of uncertain factors. Thus it is better than traditional forecast models because of having more reasonable forecast results.