干旱区研究

干旱区研究 >

2014 , Vol. 31 >Issue 6: 1005 - 1009

DOI: https://doi.org/10.13866/j.azr.2014.06.04

水土资源

基于PLSR-BP复合模型的绿洲土壤pH高光谱反演

  • 王凯龙 ,
  • 熊黑钢 ,
  • 张芳
展开
  • 1.新疆大学资源与环境科学学院,新疆 乌鲁木齐 830046;
    2.北京联合大学应用文理学院,北京 100191;
    3.教育部新疆绿洲生态重点实验室,新疆 乌鲁木齐 830046
王凯龙(1988-),男,硕士,研究方向为遥感应用及干旱区环境研究. E-mail:wkl1005@126.com
熊黑钢. E-mail:xhg1956@sohu.com

收稿日期: 2013-04-11

  修回日期: 2013-06-13

  网络出版日期: 2014-11-25

基金资助

国家自然科学基金(41171165,41261049);北京联合大学人才强校计划人才资助项目(BpHR2012E01);新疆大学博士启动基金(BS110124)

收起

PLSR-BP Complex Model-Based Hyper-Spectrum Retrieval of Oasis Soil pH

  • WANG Kai-long ,
  • XIONG Hei-gang ,
  • ZHANG Fang
Expand
  • 1. College of Resources & Environmental Science, Xinjiang University, Urumqi 830046, Xinjiang, China;
    2. College of Art & Science, Beijing Union University, Beijing 100083, China;
    3. Key Laboratory of Oasis Ecology (Xinjiang University), Ministry of Education, Urumqi 830046, Xinjiang, China

Received date: 2013-04-11

  Revised date: 2013-06-13

  Online published: 2014-11-25

Fold

摘要

以土壤pH、野外实测光谱以及多元散射校正(MSC)预处理后的光谱数据为基础,利用数学方法(主成分回归PCA、偏最小二成回归PLSR、BP神经网络模型)分别建立了土壤pH的预测模型。结果表明:土壤实测光谱和经过MSC方法预处理的光谱数据均与pH存在良好的相关性,并呈极显著水平,后者的相关性更高。PCA和PLSR两种土壤pH估测模型均具有良好的预测能力。BP神经网络模型则因输入变量多,预测精度较低。但利用PCA和PLSR模型所获得主成分,作为BP神经网络的输入变量所建立的复合模型,可明显提高模型稳定性和预测能力。

关键词： 高光谱; 土壤盐碱化; 多元散射校正; 预测模型; 奇台; 新疆

本文引用格式

王凯龙 , 熊黑钢 , 张芳 . 基于PLSR-BP复合模型的绿洲土壤pH高光谱反演[J]. 干旱区研究, 2014 , 31(6) : 1005 -1009 . DOI: 10.13866/j.azr.2014.06.04

Abstract

Based on soil pH data, measured VIS-NIR reflectance and the data pretreated by multiplicative scatter correction(MSC) at the given spots, soil pH prediction models were established by using principle components analysis-PCA, partial least squares regression -PLSR and back propagation -BP. The results showed that soil pH had a good correlation with both the original reflectance and the spectral data pretreated by MSC. The correction between the soil pH and the spectral data pretreated by MSC was more obvious. PCA and PLSR soil pH prediction models both have good predictability on soil alkalinization. BP neural network model had a lower forecasting precision because of the amount of input variables. However, using the principal components obtained from PCA and PLSR models as input variables, the predictability and the stability of the BP neural network model can be significantly improved. Compared with PLSR, BP and PCA, the prediction results of PLSR-BP model is the best.

Key words： hyper-spectrum; soil alkalinization; multiplicative scatter correction; prediction model; Qitai; Xinjiang

参考文献

〔1〕 江红南,塔西甫拉提·特依拜,徐佑成,等.于田绿洲土壤盐渍化遥感监测研究〔J〕.干旱区研究,2007,24(2):168-173.〔Jiang Hongnan,Tahiplot Tiyip,Xu Youcheng,et al.Study on remote sensing monitoring of soil salinization in arid areas〔J〕.Arid Zone Research,2007,24(2):168-173.〕
〔2〕 王芳芳,吴世新,乔木,等.基于3S技术的新疆耕地盐渍化状况调查与分析〔J〕.干旱区研究,2009,26(3):195-201.〔Wang Fangfang,Wu Shixin,Qiao Mu,et al.Investigation and analysis on the salinization degree of cultivated land in Xinjiang based on 3S technology〔J〕.Arid Zone Research,2009,26(3):195-201.〕
〔3〕 刘焕军,张柏,王宗明,等.基于反射光谱特征的土壤盐碱化评价〔J〕.红外与毫米波学报,2008,27(2):138-142.〔Liu Huanjun,Zhang Bai,Wang Zongming,et al.soil saline-alkalization evaluation basing on spectral reflectance characteristics〔J〕.Journal of Infrared and Millimeter Waves,2008,27(2):138-142.〕
〔4〕 张飞,塔西甫拉提·特依拜,丁建丽,等.渭干河—库车河三角洲绿洲土壤盐渍化现状特征及其与光谱的关系〔J〕.环境科学研究,2009,22(2):227-235.〔Zhang Fei,Tahiplot Tiyip,Ding Jianli,et al.Relationships between soil salinization and spectra in the delta oasis of Weigan and Kuqa rivers〔J〕.Research of Enviromental Science,2009,22(2):227-235.〕
〔5〕 贺军亮,蒋建军,周生路,等.土壤有机质含量的高光谱特性及其反演〔J〕.中国农业科学,2007,40(3):638-643.〔He Junliang,Jiang Jianjun,Zhou Shenglu,et al.The hyperspectral characteristics and retrieval of soil organic matter content〔J〕.Scientia Agricultura Sinica,2007,40(3):638-643.〕
〔6〕 王静,刘湘南,黄方,等.基于ANN技术和高光谱遥感的盐渍土盐分预测〔J〕.农业工程学报,2009,25(12):161-166.〔Wang Jing,Liu Xiangnan,Huang Fang,et al.Salinity forecasting of saline soil based on ANN and hyperspectral remote sensing〔J〕.Transactiongs of the Chinese Society of Agricultural Engineering,2009,25(12):161-166.〕
〔7〕 吐尔逊·艾山,塔西甫拉提·特依拜,买买提沙吾提,等.基于BP神经网络的盐碱土盐分反演模型研究〔J〕.环境污染与防治,2011,33(2):23-28.〔Tursun Hasan,Tashpolat Tiyip,Mamatsawut.Study on the saline-alkali soil salinity inversion model in the arid regions based on BP neural network〔J〕.Environmental Pollution and Control,2011,33(2):23-28.〕
〔8〕 Ferenc C.Spectral band selection for the characterization of salinity status of soils〔J〕.Remote Sensing of Environment,1993,43:231-242.
〔9〕 翁永玲,戚浩平,方洪宾,等.基于PLSR方法的青海茶卡-共和盆地土壤盐分高光谱遥感反演〔J〕.土壤学报,2010,47(6):1 255-1 263.〔Weng Yongling,Qi Haoping,Fang Hongbin,et al.PLSR-Based hyperspectral remote sensing retrieval of soil salinity of Chaka-Gonghe basin Qinghai Province〔J〕.Acta Pedologica Sinica,2010,47(6):1 255-1 263.〕
〔10〕 张晓光,黄标,季峻峰,等.基于可见近红外高光谱的东北盐渍土盐分定量模型研究〔J〕.光谱学与光谱分析,2012,32(8):2 075-2 079.〔Zhang Xiaoguang,Huang Biao,Ji Junfeng,et al.Quantitative prediction of soil salinity content with visible-near infrared hyper-spectra in northeast China〔J〕.Spectroscopy and Spectral Analysis,2012,32(8):2 075-2 079.〕
〔11〕 何挺,王静,林宗坚,等.土壤有机质光谱特征研究〔J〕.武汉大学学报,2006,31(11):975-979.〔He Ting,Wang Jing,Lin Zongjian,et al.Spectral features of soil organic matter〔J〕.Journal of Wuhan University,2006,31(11):975-979.〕
〔12〕 樊重俊.贝叶斯向量自回归分析方法及其应用〔J〕.数理统计与管理,2010,29(6):576-582.〔Fan Chongjun.Approach for vector autoregressive processes and its application〔J〕.Application of Statistics and Management,2010,29(6):576-582.〕
〔13〕 殷春霞,胡铁松,郭元裕.基于偏最小二乘回归的径向基函数网络的学习算法及其应用〔J〕.武汉水利电力大学学报,2000,33(2):80-85.〔Yin Chunxia,Hu Tiesong,Guo Yuanyu,et al.A new training method of radial basis function network based on partial least square regression and its application〔J〕.Journal of Wuhan University of Hydraulic and Electric Engineering,2000,33(2):80-85.〕
〔14〕 何方国,齐欢.基于改进遗传算法的BP神经网络及应用〔J〕.华中师范大学学报:自然科学版,2007,41(1):51-54.〔He Fangguo,Qi Huan.Back propagation neural network based on modified genetic algorithm and its application〔J〕.Journal of Huazhong Normal University:Natural Science,2007,41(1):51-54.〕
〔15〕 刘润幸.利用SPSS进行主成分回归分析〔J〕.中国公共卫生,2001,17(8):746-753.〔Liu Runxing.Principal component regression analysis with SPSS〔J〕.China Public Health,2001,17(8):746-753.〕
〔16〕 高洪智,卢启鹏.土壤主要养分近红外光谱分析及其测量系统〔J〕.光谱学与光谱分析,2011,31(5):1 245-1 249.〔Gao Hongzhi,Lu Qipeng.Near infrared spectral analysis and measuring system for primary nutrient of soil〔J〕.Spectroscopy and Spectral Analysis,2011,31(5):1 245-1 249.〕
〔17〕 梁雪,吉海彦,王鹏新,等.用MSC-ANN方法建立冬小麦叶片叶绿素与反射光谱的定量分析模型研究〔J〕.光谱学与光谱分析,2010,30(1):188-191.〔Liang Xue,Ji Haiyan,Wang Pengxin,et al.Study of building quantitative analysis model for chlorophyll in winter wheat with reflective spectrum using MSC-ANN algorithm〔J〕.Spectroscopy and Spectral Analysis,2010,30(1):188-191.〕
Options
文章导航

/

〈 〉