Prediction of Annual Runoff Using Neural Network

摘要

The purpose of this paper is concerned with the use of artificial neural networks (ANN) aimed at prediction of annual runoff. Universal Learning Network (ULN) proposed here is a new type of neural network. All nodes of this network are inter-connected and each pair of nodes can be connected with multiple branches that may have arbitrary time delays. Simulation shows that ULN can memory the sample information successfully and can build the nonlinear model of annual runoff effectively. Compared with the traditional prediction using Kalman filter algorithm, neural network is convenient and gets good generalization ability.