摘要
以黄河三角洲地区为实验区域,利用实测的土壤全盐含量数据,结合中国产的中巴地球资源卫星02B(CBERS-02B)多光谱遥感影像,分别应用传统的多元线性回归模型和BP人工神经网络模型,对其进行含盐量反演建模,并对2种模型的精度进行比较.实验表明,应用BP人工神经网络建模,明显改善了反演精度;且该反演模型更适宜于高盐度区域(全盐含量>1%)土壤含盐量反演制图,具有较好的应用前景.
The Yellow River delta is rich in land resource, but serious soil salinization affects local agricultural production and poses a threat to stability of ecological environment. The traditional multiple linear regression model and the BP artificial neural network model were both used to derive the soil salinity in the Yellow River delta based on the home-made CBERS-02B muhispectral images. It is found that the BP artificial neural network model performs much better than the multiple linear regression model in inversing soil salinity, especially for heavy saline soil area.
出处
《中国科学院研究生院学报》
CAS
CSCD
北大核心
2013年第2期220-227,共8页
Journal of the Graduate School of the Chinese Academy of Sciences
基金
国家自然科学基金(40801124)
山东省中青年科学家科研奖励基金(2010BSA06013)
中国科学院创新团队国际合作伙伴计划
中国科学院数字地球重点实验室开放基金(2011LDE015)
中国科学院研究生院院长基金资助
