Hybrid Neural Network Models for Hydrologic Time Series Forecasting Based on Genetic Algorithm

Abstract

Hydrologic time series forecasting is very an important area in water resource. Based on the multi-time scale and the nonlinear characteristics of the rainfall-runoff time series, a new hybrid neural network (NN) has been suggested by Genetic Algorithm (GA) selection the lag period of time series for NN input variables, optimization neural network architecture and connection weights. The evolved neural network architecture and connection weights are then input into a new neural network. The new neural network is trained using back -- propagation (BP) algorithm for hydrologic time series forecasting. The ensemble strategy is implemented using the quadratic programming. The present model absorbs some merits of GA and artificial neural network. Case studies, the short and long term prediction of hydrological time series, have been researched. The comparison results revealed that the suggested model could increase the forecasted accuracy and prolong the length time of prediction.