支持向量机在土壤镁含量高光谱估算中的应用
作者:
作者单位:

南京信息工程大学,南京信息工程大学,安徽省气象局

中图分类号:

S151.9

基金项目:

国家(973计划)项目(2010CB950701,G20000779)


Application of Support Vector Machine on Soil Magnesium Content Estimation Based on Hyper-Spectra
Author:
Affiliation:

Nanjing University of Information Science & Technology,Nanjing University of Information Science & Technology,Anhui Meteorological Bureau

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [31]
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    研究利用土壤样本实验反射光谱,分析了土壤镁(Mg)含量与土壤反射光谱的关系,比较了主成分回归分析 (PCR)、偏最小二乘回归分析 (PLSR) 和支持向量机回归分析 (SVMR) 等方法,以及土壤反射光谱及其变换光谱与土壤Mg含量之间的估算模型,为土壤Mg含量高光谱估算提供依据。结果表明:PCR、PLSR、SVMR 3种建模方法在Mg含量的估算中,SVMR的估算精度相对较高,估算精度平均达到80.96%,分别比PCR和PLSR提高了6.16%、4.20%;对于不同的数学变换处理方法,一阶微分变换相对较好,估算精度平均为80.76%,分别比反射率、倒数对数变换提高了4.95%、4.61%。因此,运用土壤反射光谱一阶微分变换的SVMR进行建模,可以相对较好地估算全Mg含量,精度达84.04%。

    Abstract:

    Based on the measured reflectance spectra of soil samples in the laboratory, the relationship between soil magnesium content and reflectance spectra was analyzed, and the methods of principal component regression (PCR) and partial least squares regression (PLSR) were compared with support vector machine regression (SVMR) analysis for soil magnesium content estimation, then the estimation models of magnesium content between the reflectance spectra and its transforms were established to provide the basis for soil magnesium content estimation by hyper-spectra. The results showed that the average prediction accuracy of SVMR model reached 80.96%, higher than PCR and PLSR models by 6.16% and 4.20%, respectively. The first derivative of the reflectance spectra obtained the best outcome in the different mathematical transforms with an average estimation accuracy of 80.76%, higher by 4.95% and 4.61% than reflectivity and reciprocal logarithmic transforms, respectively. Therefore, SVMR model of first derivative transform was optimal to estimate the total magnesium content with an accuracy of 84.04%.

    参考文献
    [1]姚艳敏, 魏娜, 唐鹏钦, 李志斌, 余强毅, 许新国, 陈佑启, 何英彬. 黑土土壤水分高光谱特征及反演模型. 农业工程学报, 2011, 27 (8): 95-100.
    [2]彭杰, 向红英, 王家强, 柳维扬, 迟春明, 牛建龙. 基于野外实测高光谱数据的干旱区耕作土壤含水量反演研究. 干旱地区农业研究, 2013, 31 (2): 241-246.
    [3]陈红艳, 赵庚星, 李希灿, 朱西存, 隋龙, 王银娟. 基于小波变换的土壤有机质含量高光谱估测. 应用生态学报, 2011, 22 (11): 2935-2942.
    [4]栾福明, 张小雷, 熊黑钢, 张芳, 王芳. 基于不同模型的土壤有机质含量高光谱反演比较分析. 光谱学与光谱分析, 2013, 33 (1): 196-200.
    [5]王淼, 潘贤章, 解宪丽, 王昌昆, 刘 娅, 李燕丽, 潘剑君. 土壤含水量对反射光谱法预测红壤土壤有机质的影响研究. 土壤, 2012, 44 (4): 645-651.
    [6]汪善勤, 舒 宁, 蔡崇法. 基于PCA和SRRI的潮土土壤属性与田间光谱关系研究. 土壤, 2008, 40 (6): 966~970.
    [7]彭杰, 周清, 张杨珠, 向红英. 有机质对土壤光谱特性的影响研究. 土壤学报, 2013, 50 (3): 517-524.
    [8]徐永明. 基于实验室光谱的土壤营养元素反演研究. 北京: 中国科学院遥感应用研究所, 2005.
    [9]陈红艳. 土壤主要养分含量的高光谱估测研究. 山东: 山东农业大学, 2012.
    [10]Cheng WC, Laird DA. Near-infrared reflectance spectroscopic analysis of soil C and N. Soil Science, 2002, 167 (2): 110-116.
    [11]Malley DF, Yesmin L, Eilers RG. Rapid analysis of hog manure and manure-amended soils using near-infrared spectroscopy. Soil Science Society of America Journal, 2002, 66 (5): 1677-1686.
    [12]Chodak M, Ludwig B, Khanna P, Beese F. Use of near infrared spectroscopy to determine biological and chemical characteristics of organic layers under spruce and beech stands. Journal of Plant Nutrition and Soil Science, 2002, 165 (1): 27-33.
    [13]Thomasson JA, Sui R, Cox MS,Al-Rajehy A. Soil reflectance sensing for determining soil properties in precision agriculture. Transactions of the ASAE, 2001, 44 (6): 1445-1453.
    [14]黄鸿翔, 陈福兴, 徐明岗, 秦道株, 高菊生, 朱永兴. 红壤地区土壤镁素状况及镁肥施用技术的研究. 土壤肥料, 2000 (5): 19-23.
    [15]刘光崧. 土壤理化分析与剖面描述. 北京: 中国标准出版社, 1996: 52.
    [16]沈润平, 丁国香, 魏国栓, 孙波. 基于人工神经网络的土壤有机质含量高光谱反演. 土壤学报, 2009, 46 (3): 391-397.
    [17]Kemper T, Sommer S. Estimate of Heavy Metal Contamination in Soil after a Mining Accident Using Reflectance Spectroscopy. Environmental Science Technology, 2002, 36 (12):2742-2747.
    [18]Tsai F, Philpot W. Derivative analysis of hyper-spectral data. Remote Sensing of Environment, 1998, 66: 41-51.
    [19]Yoder BJ, Pettigrew-Crosby RE. Predicting nitrogen and chlorophyll content and concentrations from reflectance spectra (400-2500nm) at leaf and canopy scales. Remote Sensing of Environment, 1995, 53 (2): 199-211.
    [20]Serrano L, Penuelas J, Ustin SL. Remote sensing of nitrogen and lignin in Mediterranean vegetation from AVIRIS data: Decomposing biochemical from structural signals. Remote Sensing of Environment, 2002, 81 (2-3): 337-354.
    [21]Jolliffe IT. Principal Component Analysis. New York: Springer, 1986.
    [22]王慧文. 偏最小二乘回归方法及其应用. 北京:国防工业出版社, 1999.
    [23]黄长平, 刘波, 张霞, 童庆禧. 土壤重金属Cu含量遥感反演的波段选择与最佳光谱分辨率研究. 遥感技术与应用, 2010, 25 (3): 353-357.
    [24]叶磊, 骆兴国. 支持向量机应用概述. 电脑知识与技术. 2010, 6 (34): 9815-9816.
    [25]Vapnik V. The Nature of Statistical Leaning Theory. New York: Springer-Verlag, 1995.
    [26]郑光辉, 周生路, 吴绍华. 土壤砷含量高光谱估算模型研究. 光谱学与光谱分析, 2011, 31 (1): 173-176.
    [27]廖丽霞, 胡红青, 贺纪正. 中南地区几种地带性土壤表面电荷特性与pH的关系. 华中农业大学学报, 2005, 24 (1): 29-32.
    [28]于天仁, 季国亮, 丁昌璞. 可变电荷土壤的电化学. 北京: 科学出版社, 1996.
    [29]王璐, 蔺启忠, 贾东, 石火生, 黄秀华. 多光谱数据定量反演土壤营养元素含量可行性分析. 环境科学, 2007, 28 (8): 1822-1828.
    [30]Viscarra Rossel RA, Walvoort DJJ, McBratney AB. Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties. Geoderma, 2006, 131 (1-2): 59-75.
    [31]Viscarra Rossel RA, Chen C. Digitally mapping the information content of visible–near infrared spectra of surficial Australian soils. Remote Sensing of Environment, 2011, 115 (6): 1443-1455.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

田 烨,沈润平,丁国香.支持向量机在土壤镁含量高光谱估算中的应用[J].土壤,2015,47(3):602-607. TIAN Ye, SHEN Run-ping, DING Guo-xiang. Application of Support Vector Machine on Soil Magnesium Content Estimation Based on Hyper-Spectra[J]. Soils,2015,47(3):602-607

复制
分享
文章指标
  • 点击次数:1196
  • 下载次数: 3212
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2014-02-21
  • 最后修改日期:2014-05-25
  • 录用日期:2014-06-25
  • 在线发布日期: 2015-07-13
文章二维码