地球科学进展 ›› 2010, Vol. 25 ›› Issue (6): 625 -629. doi: 10.11867/j.issn.1001-8166.2010.06.0625

研究论文 上一篇    下一篇

土壤铅含量高光谱遥感反演中波段选择方法研究
温健婷 1,张霞 1,张兵 2,赵冬 1   
  1. 1.中国科学院遥感应用研究所,北京 100101; 
    2.中国科学院对地观测与数字地球科学中心,北京 100190
  • 收稿日期:2009-09-01 修回日期:2010-03-23 出版日期:2010-06-10
  • 通讯作者: 温健婷 E-mail:jianting.wen@gmail.com
  • 基金资助:

    国防科工委民用航天空间应用项目“新一代环境监测高光谱卫星指标论证”;国家科技支撑计划项目“环北京区域多源空间数据处理技术研究”(编号:2007BAH15B01)资助

A Study of Band Selection Method for Retrieving Soil Lead Content with Hyperspectral Remote Sensing Data

Wen Jianting 1, Zhang Xia 1, Zhang Bing 2, Zhao Dong 1   

  1. 1.Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing 100101, China; 
    2.Center for Earth Observation & Digital Earth, Chinese Academy of Sciences, Beijing 100190, China  
  • Received:2009-09-01 Revised:2010-03-23 Online:2010-06-10 Published:2010-06-10
  • Contact: Wen Jianting E-mail:jianting.wen@gmail.com

利用高光谱遥感数据进行了南京郊外土壤重金属元素铅的含量反演,由于高光谱数据波段众多,波段选择或变换至关重要。比较了基于次贪婪的前向选择模型的最小角度拟合和基于遗传算法进行波段选择的最小二乘和偏最小二乘拟合,结果发现基于遗传算法的偏最小二乘反演结果优于全波段的偏最小二乘,表明波段选择在高光谱反演重金属中是有益的。尽管采取了波段选择后的各方法在反演时均能达到70%以上的训练精度,但因遗传算法搜索的解空间范围更宽广,使得基于遗传算法的偏最小二乘优于前向选择模型的最小角度拟合。最后还比较了基于遗传算法的普通最小二乘和偏最小二乘拟合,结果表明偏最小二乘更优,因此在高光谱反演重金属含量当中,偏最小二乘精度较高,而在波段选择方法中,遗传算法更优。

To retrieve the lead content in the soil from hyperspectral remote sensing data, we should select bands or do some transformation first. In this paper, we compared Least Angle Regression, which is a modest forward choose method, and least squares regression and partial least squares regression based on genetic algorithm. As a validation result of  the test area in Jianning, Nanjing, regression results with band selection are better than those without. Although Least Angle Regression, partial least squares regression with genetic algorithm can reach 70% training correctness, the latter based on genetic algorithm is better, because it can reach a larger solution space. At last, we conclude that partial least squares regression is a good choice for the lead content retrieval in soil by hyperspectral remote sensing data, and genetic algorithm can improve the retrieval by band selection promisingly.

中图分类号: 

[1] Kooistra L, Wehrens R, Leuven R S E W, et al. Possibilities of visible near infrared spectroscopy for the assessment of soil contamination in river floodplains[J].Analytica Chimica Acta,2001,446(1/2): 97-105.
[2] Chi Guangyu, Liu Xinhui, Liu Suhong, et al. Spectral characteristics of vegetation in environment pollution monitoring[J].Environmental Science and Technology,2005, 28(suppl.): 16-19.[迟光宇, 刘新会, 刘素红,等. 环境污染监测中的植被光谱效应研究[J]. 环境科学与技术, 2005, 28(增刊): 16-19.]
[3] Wu Y, Chen J, Wu X, et al. Possibilities of reflectance spectroscopy for the assessment of contaminant elements in suburban soils[J].Applied Geochemistry,2005,(20): 1 051-1 059.
[4] Efron B, Hastie T, Johnstone I, et al. Least angle regression[J]. The Annals of Statistics,2004, 32(2): 407-451.
[5] Kooistra L, Wanders J, Epema G F, et al. The potential of field spectroscopy for the assessment of sediment properties in river floodplains[J].Analytica Chimica Acta,2003,484(2): 189-200. 
[6] Reeves J B, Mccarty G W, Mimmo T. The potential of diffuse reflectance spectroscopy for the determination of carbon inventories in soils[J].Environmental Pollutution,2002,(116): 277-284. 
[7] Goldberg D E. Genetic Algorithms in Search, Optimization and Machine Learning[M].New York: Addison-Wesley, 1989.
[8] Holland J H. Adaption in Natural and Artificial systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence[M].Cambridge, MA: MIT Press, 1992.
[9] Broadhurst D, Goodacre R, Jones A, et al. Genetic algorithms as a method for variable selection in multiple linear regression and partial least squares regression, with applications to pyrolysis mass spectrometry[J].Analytica Chimica Acta,1997, 8(34): 71-86.

[1] 李江峰, 蔡晓军, 王文, 李倩文, 雷彦森. 偏最小二乘回归在水汽和地面气温多模式集成预报中的应用研究[J]. 地球科学进展, 2018, 33(4): 404-415.
[2] 张韧, 洪梅, 刘科峰, 朱伟军. 基于副热带高压异常活动个例的动力模型重构与变异特性剖析[J]. 地球科学进展, 2014, 29(11): 1250-1261.
[3] 朱子先, 臧淑英. 基于遗传神经网络的克钦湖叶绿素反演研究[J]. 地球科学进展, 2012, 27(2): 202-208.
阅读次数
全文


摘要