基于神经网络的洪水水位预测算法

Flood level prediction algorithm based on neural network

鉴于洪水变化难以预料,及其给社会和人民群众带来的危害,提出一种新的洪水水位变化的预测算法。利用神经网络能以任意精度逼近非线性函数的特点,采用神经网络的有监督式学习,并将预测误差作为反馈来调整水位预测网络中的权值分布,以达到学习的目的。通过程序编程对此算法进行调试,得到了较理想的预测效果。

Aiming at the unexpected flood change and the hazard to society and the people, this paper puts forward a new prediction algorithm for flood level change. It utilized the characteristic that neural network can approach nonlinear function with arbitrary precision, supervision, and regarded the prediction error as feedback adopted neural network＇ s learning method with to adjust the weighted values in flood level prediction network in order to achieve the objective of study. Debugging this algorithm by programming, the better prediction result is obtained.