结合灰色扩充的GA-BP神经网络模型在渭河水质遥感反演中的应用

以渭河陕西段水域为研究对象，用遗传算法改进的BP神经网络，结合灰色理论，建立了一种结合灰色扩充的GA-BP神经网络模型，对渭河水质中的主要污染指标CODmn(高锰酸盐指数)、COD(化学需氧量)、NH₃-N(氨氮)、DO(溶解氧)进行了遥感反演建模。实验证明：改进后的人工神经网络模型在预测精度上高于普通的BP神经网络模型和传统的多元线性回归模型，可用于渭河水质遥感反演建模。


Gray Expansion Combined GA—BP Neural Network Model for Water Quality Retrieving of Weihe River by Remote Sensing

Aiming at the Weihe river in Shaanxi,a gray expanded GA—BP(Genetic Algorithm—Back Propagation) neural network model is established in this paper,which combines the BP neural network improved by GA with the gray theory.It is used to retrieve the four main pollution index  (permanganate index),(chemical oxygen demand),(ammonia nitrogen), (dissolved oxygen) for Weihe river.Experimental results show that compared with the ordinary BP neural network model and the traditional multiple linear regression model,the improved artificial neural network has better prediction accuracy,and can be used to retrieve Weihe river quality parameters by remote sensing.