用户名: 密码: 验证码:
基于支持向量机的土壤主要盐分离子高光谱反演模型
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Hyperspectral Inverse Model for Soil Salt Ions Based on Support Vector Machine
  • 作者:王海江 ; 蒋天池 ; YUNGER ; John ; A ; 李亚莉 ; 田甜 ; 王金刚
  • 英文作者:WANG Haijiang;JIANG Tianchi;YUNGER John A;LI Yali;TIAN Tian;WANG Jin'gang;The Key Laboratory of Oasis Eco-agriculture,Xinjiang Production and Construction Group;College of Agronomy,Shihezi University;Department of Biology,Governors State University;Research Institute of Soil,Fertilizer and Agricultural Water Conservation,Xinjiang Academy of Agricultural Sciences;
  • 关键词:土壤 ; 盐分离子 ; 新疆 ; 高光谱 ; 反演模型
  • 英文关键词:soil;;salt ions;;Xinjiang;;hyperspectral;;inverse model
  • 中文刊名:NYJX
  • 英文刊名:Transactions of the Chinese Society for Agricultural Machinery
  • 机构:新疆生产建设兵团绿洲生态农业重点实验室;石河子大学农学院;州长州立大学生物系;新疆农业科学院土壤肥料与农业节水研究所;
  • 出版日期:2018-03-12 16:03
  • 出版单位:农业机械学报
  • 年:2018
  • 期:v.49
  • 基金:国际科技合作项目(2015DFA11660);; 石河子大学校级项目(RCZX201522);石河子大学大学生研究训练计划项目(SRP2017024)
  • 语种:中文;
  • 页:NYJX201805031
  • 页数:8
  • CN:05
  • ISSN:11-1964/S
  • 分类号:270-277
摘要
快速、无损、定量地获取土壤盐分离子组成及含量是盐渍化土壤治理、改良和利用的重要依据。以新疆盐渍化土壤为研究对象,应用高光谱分析技术获取不同区域土壤盐分离子的特征光谱,在对光谱数据去噪、数据变换基础上分析了鲜样(T1)、风干(T2)和干燥(T3)3类土壤,过2、1、0.15 mm筛处理对离子含量光谱拟合模型精度的影响,建立了基于支持向量机的土壤主要盐分离子光谱反演模型,并对模型的精度和普适性进行了检验。结果表明:土壤原始特征光谱与盐分离子含量均不存在显著相关性,最大相关系数为Na+的0.41;通过光谱数据变换能够明显增强特征波段与离子含量的相关性,K+、Na+、Mg2+、Ca2+、SO_4~(2-)、Cl-和HCO-3的最优变换形式分别为(lgR)'、(lgR)'、R'、(lgR)'、CR、R'和CR,T1处理构建的拟合模型均不能很好地反演离子含量,T3处理的模型估测精度优于T2,土壤粒径越细对土壤离子含量的光谱反演效果越好。分析各处理模型的决定系数和标准误差表明,经T3处理、过0.15 mm筛所构建的离子拟合模型预测精度最高,其中K~+、Na~+、Ca2+和SO_4~(2-)的RPD分别为2.153、2.674 5、2.051和2.786 4,以未参与建模和检验的石河子垦区土样对4种离子模型的普适性检验,其R2分别为0.621 4、0.689 7、0.614 4和0.650 7,说明构建的模型适于估算该区域土壤K+、Na+、Ca2+和SO_4~(2-)的含量。
        The rapid,nondestructive and quantitative analysis of the composition and content of soil salt ions is an important basis for the treatment,improvement and utilization of salinized soil. Taking the saline soil of Xinjiang as the research object,the hyperspectral analysis technique was used to obtain the spectral characteristic of soil salt ions in different regions; compared the effect on the accuracy of the soil salt ions fitting model in different treatments which included fresh soil,air drying and oven-dry sample and different particle sizes( 2 mm,1 mm and 0. 15 mm,respectively). After the transformation of spectral data,the spectral inversion models of main salt ions were established based on support vector machine( SVM),and the accuracy and universality of the model were tested. The results showed that there was no significant correlation between the original spectral characteristics and soil salt ions content,and the maximum correlation coefficient was Na+( R = 0. 41). It was clear that the spectral data transformation can significantly enhance the correlation between the characteristic bands and the ions content,the optimal transformation forms of K+,Na+,Mg2 +,Ca2 +,SO_4~(2-),Cl-and HCO-3 were( lgR) ',( lgR) ',R',( lgR) ',CR,R' and CR,respectively. The fitting models of T1 treatment cannotinverse the ions content very well,the accuracy of T3 model was better than that of T2,and the smaller the soil particle size was,the better the spectral inversion effect of soil ions content was. The prediction accuracy of the ions fitting model was the highest by T3 and over 0. 15 mm sieves,the relative prediction deviation of K+,Na+,Ca2 +and SO_4~(2-) were 2. 153,2. 674 5,2. 051 and 2. 786 4,respectively,the universality test of four ion models was carried out by using samples from Shihezi area other than modeling and validation,the R2 of test models were 0. 621 4,0. 689 7,0. 614 4 and 0. 650 7,respectively. The models were suitable for estimating the content of soil K+,Na+,Ca2 +and SO_4~(2-) in Xinjiang area.
引文
1郗金标,张福锁,毛达如,等.新疆盐渍土分布与盐生植物资源[J].土壤通报,2005,36(3):299-303.XI Jinbiao,ZHANG Fusuo,MAO Daru,et al.Saline-soil distribution and halophyte resources in Xinjiang[J].Chinese Journal of Soil Science,2005,36(3):299-303.(in Chinese)
    2郭全恩.土壤盐分离子迁移及其分异规律对环境因素的响应机制[D].杨凌:西北农林科技大学,2010.GUO Quanen.The response mechanism of soil salt ion transfer and diversity rule to environment factors and risk analysis[D].Yangling:Northwest A&F University,2010.(in Chinese)
    3张永峰,殷薄.混合盐碱胁迫对苗期紫花苜蓿抗氧化酶活性及丙二醛含量的影响[J].草业学报,2009,18(1):46-50.ZHANG Yongfeng,YIN Bo.Influences of salt and alkali mixed stresses on antioxidative activity and MDA content of Medicago sativa at seedling stage[J].Acta Prataculturae Sinica,2009,18(1):46-50.(in Chinese)
    4 BEN-DOR E,BANIN A.Near-infrared analysis as a rapid method to simultaneously evaluate several soil properties[J].SSSAJ,1995,59(2):364-372.
    5 ENDOVITSKY A P,MINKINA T M,KALINICHENKO V P,et al.The association of ions in the soil solution of saline soils[J].American Journal of Agricultural&Biological Science,2014,9(2):238-244.
    6魏昌龙,赵玉国,李德成,等.基于相似光谱匹配预测土壤有机质和阳离子交换量[J].农业工程学报,2014,30(1):81-88.WEI Changlong,ZHAO Yuguo,LI Decheng,et al.Prediction of soil organic matter and cation exchange capacity based on spectral similarity measuring[J].Transactions of the CSAE,2014,30(1):81-88.(in Chinese)
    7彭杰,刘焕军,史舟,等.盐渍化土壤光谱特征的区域异质性及盐分反演[J].农业工程学报,2014,30(17):167-174.PENG Jie,LIU Huanjun,SHI Zhou,et al.Regional heterogeneity of hyperspectral characteristics of salt-affected soil and salinity inversion[J].Transactions of the CSAE,2014,30(17):167-174.(in Chinese)
    8 SRIVASTAVA R,SETHI M,YADAV R K,et al.Visible-near infrared reflectance spectroscopy for rapid characterization of saltaffected soil in the indo-gangetic plains of haryana,India[J].Journal of the Indian Society of Remote Sensing,2017,45(2):307-315.
    9屈永华,段小亮,高鸿永,等.内蒙古河套灌区土壤盐分光谱定量分析研究[J].光谱学与光谱分析,2009,29(5):1362-1366.QU Yonghua,DUAN Xiaoliang,GAO Hongyong,et al.Quantitative retrieval of soil salinity using hyperspetral data in the region of Inner Mongolia Hetal irrigation district[J].Spectroscopy and Spectral Analysis,2009,29(5):1362-1366.(in Chinese)
    10 WENG Y L,GONG P,ZHU Z L.Reflectance spectroscopy for the assessment of soil salt content in soils of the Yellow River delta of China[J].International Journal of Remote Sensing,2008,29(19):5511-5531.
    11 ZHANG T T,ZENG S L,GAO Y,et al.Using hyperspectral vegetation indices as a proxy to monitor soil salinity[J].Ecological Indicators,2011,11(6):1552-1562.
    12卢霞.滨海盐土盐分含量与其光谱特征的关系研究[J].水土保持通报,2012,32(5):186-190.LU Xia.Relationship between saline concentration and its reflectance spectra for seashore saline soil[J].Bulletin of Soil and Water Conservation,2012,32(5):186-190.(in Chinese)
    13李民赞,郑立华,安晓飞,等.土壤成分与特性参数光谱快速检测方法及传感技术[J/OL].农业机械学报,2013,44(3):73-87.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20130315&flag=1.DOI:10.6041/j.issn.1000-1298.2013.03.015.LI Minzan,ZHENG Lihua,AN Xiaofei,et al.Fast measurement and advanced sensors of soil parameters with NIR spectroscopy[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2013,44(3):73-87.(in Chinese)
    14鲍士旦.土壤农化分析[M].北京:中国农业出版社,2000.
    15吕真真,刘广明,杨劲松.新疆玛纳斯河流域土壤盐分特征研究[J].土壤学报,2013,50(2):289-295.LZhenzhen,LIU Guangming,YANG Jingsong.Soil salinity characteristics of manas river valley in Xinjiang[J].Acta Pedologica Sinica,2013,50(2):289-295.(in Chinese)
    16向红英,柳维扬,彭杰,等.基于连续统去除法的南疆水稻土有机质含量预测[J].土壤,2016,48(2):389-394.XIANG Hongying,LIU Weiyang,PENG Jie,et al.Predicting organic matter content in paddy soil using method of continuum removal in southern Xinjiang,China[J].Soils,2016,48(2):389-394.(in Chinese)
    17刘亚秋,陈红艳,王瑞燕,等.基于可见/近红外光谱的黄河口区土壤盐分及其主要离子的定量分析[J].中国农业科学,2016,49(10):1925-1935.LIU Yaqiu,CHEN Hongyan,WANG Ruiyan,et al.Quantitative analysis of soil salt and its main ions based on visible/near infrared spectroscopy in estuary area of Yellow River[J].Scientia Agricultura Sinica,2016,49(10):1925-1935.(in Chinese)
    18王海江,张花玲,任少亭,等.基于高光谱反射特性的土壤水盐状况预测模型研究[J/OL].农业机械学报,2014,45(7):133-138.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20140721&flag=1.DOI:10.6041/j.issn.1000-1298.2014.07.021.WANG Haijiang,ZHANG Hualing,REN Shaoting,et al.Prediction model of soil water-salt based on hyperspectral reflectance characteristics[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2014,45(7):133-138.(in Chinese)
    19侯艳军,塔西甫拉提·特依拜,买买提·沙吾提,等.荒漠土壤有机质含量高光谱估算模型[J].农业工程学报,2014,30(16):113-120.HOU Yanjun,TASHPOLAT·Tiyip,MAMAT·Sawut,et al.Estimation model of desert soil organic matter content using hyperspectral data[J].Transactions of the CSAE,2014,30(16):113-120.(in Chinese)
    20孙建英,李民赞,唐宁,等.东北黑土的光谱特性及其与土壤参数的相关性分析[J].光谱学与光谱分析,2007,27(8):1502-1505.SUN Jianying,LI Minzan,TANG Ning,et al.Spectral characteristics and their correlation with soil parameters of black soil in northeast China[J].Spectroscopy and Spectral Analysis,2007,27(8):1502-1505.(in Chinese)
    21卢艳丽,白由路,王磊,等.黑土土壤中全氮含量的高光谱预测分析[J].农业工程学报,2010,26(1):256-261.LU Yanli,BAI Youlu,WANG Lei,et al.Determination for total nitrogen content in black soil using hyperspectral data[J].Transactions of the CSAE,2010,26(1):256-261.(in Chinese)
    22张娟娟,田永超,姚霞,等.基于高光谱的土壤全氮含量估测[J].自然资源学报,2011,26(5):881-890.ZHANG Juanjuan,TIAN Yongchao,YAO Xia,et al.Estimating soil total nitrogen content based on hyperspectral analysis technology[J].Journal of Natural Resources,2011,26(5):881-890.(in Chinese)
    23徐丽华,谢德体,魏朝富,等.紫色土土壤全氮和全磷含量的高光谱遥感预测[J].光谱学与光谱分析,2013,33(3):723-727.XU Lihua,XIE Deti,WEI Chaofu,et al.Prediction of total nitrogen and total phosphorus concentrations in purple soil using hyperspectral data[J].Spectroscopy and Spectral Analysis,2013,33(3):723-727.(in Chinese)
    24张瑶,李民赞,郑立华,等.基于近红外光谱分析的土壤分层氮素含量预测[J].农业工程学报,2015,31(9):121-126.ZHANG Yao,LI Minzan,ZHENG Lihua,et al.Prediction of soil total nitrogen content in different layers based on near infrared spectral analysis[J].Transactions of the CSAE,2015,31(9):121-126.(in Chinese)
    25 KIRSHNAN P,ALEXANDER J D,BUTLER B J,et al.Reflectance technique for predicting soil organic matter[J].SSSAJ,1980,44(6):1282-1285.
    26 DALAL R C,HENRY R J.Simultanous determination of moisture,organic carbon,and total nitrogen by near infrared reflectance spectrophotometry[J].SSSAJ,1986,50(1):120-123.
    27鲍一丹,何勇,方慧,等.土壤的光谱特征及氮含量的预测研究[J].光谱学与光谱分析,2007,27(1):62-65.BAO Yidan,HE Yong,FANG Hui,et al.Spectral characterization and N content prediction of soil with different particle size and moisture content[J].Spectroscopy and Spectral Analysis,2007,27(1):62-65.(in Chinese)
    28马创,申广荣,王紫君,等.不同粒径土壤的光谱特征差异分析[J].土壤通报,2015,46(2):292-298.MA Chuang,SHEN Guangrong,WANG Zijun,et al.Analysis of spectral characteristics for different soil particle sizes[J].Chinese Journal of Soil Science,2015,46(2):292-298.(in Chinese)
    29武红旗,范燕敏,何晶,等.不同粒径土壤的反射光谱对荒漠土壤有机质含量的响应[J].草地学报,2014,22(2):266-270.WU Hongqi,FAN Yanmin,HE Jing,et al.Response of soil hyperspectral characteristics of different particle sizes to soil organic matter[J].Acta Agrectir Sinica,2014,22(2):266-270.(in Chinese)
    30朱琦,董桂梅,杨仁杰,等.土壤粒度差异对光谱法检测土壤全氮含量的影响研究[J].天津农学院学报,2015,22(4):29-32.ZHU Qi,DONG Guimei,YANG Renjie,et al.Influences of soil particle size difference on detecting total nitrogen contents in soil by spectrometry[J].Journal of Tianjin Agricultural College,2015,22(4):29-32.(in Chinese)
    31何挺,王静,程烨,等.土壤水分光谱特征研究[J].土壤学报,2006,43(6):1027-1032.HE Ting,WANG Jing,CHENG Ye,et al.Spectral features of soil moisture[J].Acta Pedologica Sinica,2006,43(6):1027-1032.(in Chinese)
    32刘秀英,王力,宋荣杰,等.黄绵土风干过程中土壤含水率的光谱预测[J/OL].农业机械学报,2015,46(4):266-272.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20150439&flag=1.DOI:10.6041/j.issn.1000-1298.2015.04.039.LIU Xiuying,WANG Li,SONG Rongjie,et al.Prediction of soil moisture content in air-drying loess using spectral data[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2015,46(4):266-272.(in Chinese)
    33代希君,张艳丽,彭杰,等.土壤水溶性盐基离子的高光谱反演模型及验证[J].农业工程学报,2015,31(22):139-145.DAI Xijun,ZHANG Yanli,PENG Jie,et al.Prediction and validation of water-soluble salt ions content using hyperspectral data[J].Transactions of the CSAE,2015,31(22):139-145.(in Chinese)
    34张俊华,秦君琴,李明.基于土壤光谱特征的宁夏银北地区盐碱地盐分预测研究[J].水土保持通报,2013,33(5):123-129,164.ZHANG Junhua,QIN Junqin,LI Ming.Prediction of soil salt content based on spectral characteristics of soil in Northern Yinchuan City,Ningxia Hui Autonomous Region[J].Bulletin of Soil and Water Conservation,2013,33(5):123-129,164.(in Chinese)

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700