摘要
运用Hyperion数据,以黑龙江省大庆市某一实验区为例,开展对土壤含盐量定量提取的研究,通过对图像预处理、特征提取、建立BP神经网络模型(Back Propagation Network)等研究工作,探讨反演土壤含盐量的方法。研究结果表明:神经网络模型具有极强的线性和非线性拟合能力,模拟遥感影像特征与土壤盐分之间比较复杂的关系上有很大优势。研究结果不但为利用Hyperion数据反演土壤含盐量提供理论依据,而且还为其它地表参数的反演提供参考。
One experimental area in Daqing city in Heilongjiang province is taken as an example to perform the quantitative inversion of soil salinity using Hyperion data in this paper.The inversion method of soil salinity using Hyperion data is discussed by the image preprocessing,the feature extraction and the establishment of BP neural network model.It gives a lot of help in soil suveying system and promoting the development in quantitative retrieval of soil salinity.Meanwhile,this model provides reference for solving other non-linear problems.
出处
《测绘工程》
CSCD
2010年第6期65-67,72,共4页
Engineering of Surveying and Mapping
作者简介
唐彦（1957-），女，副教授．
