Please wait a minute...
img

官方微信

遥感技术与应用  2015, Vol. 30 Issue (1): 186-198    DOI: 10.11873/j.issn.1004-0323.2015.1.0186
模型与反演     
三江源区不同土壤类型有机质含量高光谱反演
杨扬,高小红,贾伟,张威,李金山,张艳娇,田成明
(青海师范大学生命与地理科学学院,青藏高原环境与资源教育部重点实验室,青海 西宁810008)
Hyperspectral Retrieval of Soil Organic Matter for Different Soil Types in the Three-River Headwaters Region
Yang Yang,Gao Xiaohong,Jia Wei,Zhang Wei,Li Jinshan,Zhang Yanjiao,Tian Chengming
(School of Life and Geographical Sciences,Key Laboratory of Ministry of Education on Environment 
and Resource in Qinghai\|Tibet Plateau,Qinghai Normal University,Xining 810008,China)
 全文: PDF(5158 KB)  
摘要:

近年来高光谱遥感技术被广泛运用于土壤有机质含量反演的研究中。基于三江源区玉树县和玛多县采集的146个土壤样品的室内ASD FieldSpec 4实测光谱数据及4种变换形式,利用偏最小二乘回归(PLSR)和人工神经网络(ANN)建立土壤有机质含量高光谱预测模型。结果表明:ANN模型反演土壤有机质含量的整体精度高于PLSR模型,总均方根误差均在17.51以下;但是,不同土壤类型的最佳反演模型及指标却有所差异:高山草甸土和沼泽土的最佳反演模型和指标均为ANN模型和BD指标,模型总均方根误差分别为10.29和3.29;高山草原土的最佳反演模型是PLSR模型,最佳指标是REF指标,模型总均方根误差为5.59;山地草甸土的最佳反演模型为〖JP2〗PLSR模型,最佳指标为BD指标,模型总均方根误差为4.68。研究发现,利用ANN模型和PLSR模型都能较好地预测三江源区4种土壤类型的有机质含量,而波段深度则是该区域的最佳反演指标。〖JP〗

关键词: 土壤有机质土壤类型高光谱反演模型三江源    
Abstract:

In recent years,hyperspectral remote sensing technology has been widely used in the inversion of soil organic matter contents.In this paper,in order to inverse soil organic matter contents,indoor spectral of 146 soil sampling data,which is collected from Yushu and Maduo County in Three\|River Headwaters Regions,was measured by ASD FieldSpec4;Thereafter,soil organic hyperspectral forecast models for soil matter contents in four kinds of transformation forms were respectively established using Partial Least Squares Regression (PLSR) and Artificial Neural Network (ANN) method.
The results showed that the overall accuracy of using ANN model to estimate soil organic matter content is higher than that of using PLSR model,and its total root mean square errors were all less than 17.51,however,The different soil types have showed different optimal estimation models and the optimal indicators.The optimal retrieval models and indicators of Alpine meadow and marsh soil are both the ANN model and BD (Band Depth),and their total root mean square errors are 10.29 and 3.29 respectively;PLSR model is the optimal estimation model of Alpine steppe soil,the optimal indicator is REF,with the model’s total root mean square error of 5.59;PLSR model is the best inversion model for Mountain meadow soil and the optimal index is BD index,with the model’s total root mean square error of 4.68.The results further indicated that the ANN model and the PLSR model can better predict SOM contents of four soil types inThree\|River\|Headwater Region,and

Key words: Soil organic matter    Soil type    Hyper-spectral retrieval    Three-river headwaters region
收稿日期: 2013-09-27 出版日期: 2015-03-11
:  TP 79  
基金资助:

青海省科技厅自然科学基金项目“全球气候变化扰动对江河源头环境界面污染物交换的影响”(青科发计字[2011]136号,2011-Z-903)。

通讯作者: 高小红(1963-),女,陕西白水人,博士,教授,主要从事遥感应用与地理空间数据分析研究。Email:xiaohonggao226@gmail.com。   
作者简介: 杨扬(1989-),女,江苏盐城人,硕士研究生,主要从事遥感应用与地理空间数据分析研究。Email:yysunday0207@sina.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
杨扬
高小红
贾伟
张威
李金山
张艳娇
田成明

引用本文:

杨扬,高小红,贾伟,张威,李金山,张艳娇,田成明. 三江源区不同土壤类型有机质含量高光谱反演[J]. 遥感技术与应用, 2015, 30(1): 186-198.

Yang Yang,Gao Xiaohong,Jia Wei,Zhang Wei,Li Jinshan,Zhang Yanjiao,Tian Chengming. Hyperspectral Retrieval of Soil Organic Matter for Different Soil Types in the Three-River Headwaters Region. Remote Sensing Technology and Application, 2015, 30(1): 186-198.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2015.1.0186        http://www.rsta.ac.cn/CN/Y2015/V30/I1/186

[1]Huang Changyong.Soil Science[M].Beijing:China Agriculture Press,2000:32-65.[黄昌勇.土壤学[M].北京:中国农业出版社,2000:32-65.]

[2]Du Peijun,Gao Songjie.Some Key Issues of Hyperspectral Remote Sensing Data Mining[J].Remote Sensing Information,2005,(3):53-57.[杜培军,高松洁.高光谱遥感数据挖掘若干基本问题的研究[J].遥感信息,2005,(3):53-57.]

[3]Liu Wei,Chang Qingrui,Guo Man,et al.Analysis on Derivative Spectrum Feature for SOM under Different Scales of Differential Window[J].Journal of Infrared and Millimeter Waves,2011,(4):316-321.[刘炜,常庆瑞,郭曼,等.不同尺度的微分窗口下土壤有机质的一阶导数光谱响应特征分析[J].红外与毫米波学报,2011,(4):316-321.]

[4]Ji Wenjun,Li Xi,Li Chengxue,et al.Using Different Data Minig Algorithms to Predict Soil Organic Matter based on Visible Near Infrared Spectroscopy[J].Spectroscopy and Spectral Analysis,2012,(9):2393-2398.[纪文君,李曦,李成学,等.基于全谱数据挖掘技术的土壤有机质高光谱预测建模研究[J].光谱学与光谱分析,2012,(9):2393-2398.]

[5]Bowers S A,Hanks R J.Reflection of Radiant Energy from Soil[J].Purechased by Agricultural Research Service U.S.Department of Agriculture for Official Usel,1965,100(2):130-138.

[6]Galvao L S,Vitorello.Variability of Laboratory Measured Soil Lines of Soils from Southeastern Brazil[J].Remote Sensing of Environment,1998,63(2):166-181.

[7]Chang C W,Laird D A.Near-infrared Reflectance Spectroscopic Analysis of Soil C and N[J].Soil Science,2002,167:110-116.

[8]Gomez C,Viscarra Rossel R A,Mcbratney A B.Soil Organic Carbon Prediction by Hyperspectral Remote Sensing and Field VIS-NIR Spectroscopy:An Australian Case Study[J].Geoderma,2008,146(3-4):403-411.

[9]Xu Mingxing,Zhou Shenglu,Ding Wei,et al.Hyperspectral Reflectance Models for Predicting Soil Organic Matter Content in Coastal Tidal Land Area,Northern Jiangsu[J].Transactions of the Chinese Society Agricultural Engineering,2011,27(2):219-223.[徐明星,周生路,丁卫,等.苏北沿海滩涂地区土壤有机质含量的高光谱预测[J].农业工程学报,2011,27(2):219-223.]

[10]Liu Huanjun,Zhang Xinle,Zheng Shufeng,et al.Black Soil Organic Matter Prediction Model based on Field Hyperspectral Reflectance[J].Spectroscopy and Spectral Analysis,2010,(12):3355-3358.[刘焕军,张新乐,郑树峰,等.黑土有机质含量野外高光谱预测模型[J].光谱学与光谱分析,2010,(12):3355-3358.]

[11]Lu Yanli,Bai Youlu,Yang Liping,et al.Homogeneity of Retrieval Models for Soil Organic Matter of Different Soil Types in Northeast Plain Using Hyperspectral Data[J].Plant Nutrition and Fertilizer Science,2011,(2):456-463.[卢艳丽,白由路,杨俐苹,等.东北平原不同类型土壤有机质含量高光谱反演模型同质性研究[J].植物营养与肥料学报,2011,(2):456-463.]

[12]Ren Hongyan,Shi Xuezheng,Zhuan Dafang.Effects on Estimating Soil Nitrogen Content and Ratio of Carbon to Nitrogen Using Hyperspectral Reflectance[J].Remote Sensing Technology and Application,2012,27(3):372-379.[任红艳,史学正,庄大方,等.土壤全氮含量与碳氮比的高光谱反射估测影响因素研究[J].遥感技术与应用,2012,27(3):372-379.]

[13]Xu Binbin.Research of China’s Soil Spectral Line[J].Journal of Remote Sensing,1991,6(1):61-71.[徐彬彬.我国土壤光谱线之研究[J].环境遥感,1991,6(1):61-71.]

[14]Huang Yingfeng,Liu Tenghui.Spectral Characteristics of Ma-in Types of Soils in Southern China and Soil Classification[J].Acta Pedologica Sinica,1995,32(1):58-68.[黄应丰,刘腾辉.华南主要土壤类型的光谱特性与土壤分类[J].土壤学报,1995,32(1):58-68.]

[15]Liu Lei,Shen Runping,Ding Guoxiang.Studies on the Estimation of Soil Organic Matter Content based on Hyper-spectrum[J].Spectroscopy and Spectral Analysis,2011,(3):762-766.[刘磊,沈润平,丁国香.基于高光谱的土壤有机质含量估算研究[J].光谱学与光谱分析,2011,(3):762-766.]

[16]Shen Runping,Ding Guoxiang,Wei Guoshuan,et al.Retrieval of Soil Organic Matter Content from Hyper-spectrum based on ANN[J].Acta Pedologica Sinica,2009,(3):391-397.[沈润平,丁国香,魏国栓,等.基于人工神经网络的土壤有机质含量高光谱反演[J].土壤学报,2009,(3):391-397.]

[17]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.[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.]

[18]Liu Huanjun,Zhao Chunjiang,Wang Jihua,et al.Soil Organic Matter Predicting with Remote Sensing Image in Typical Black Soil Area of Northeast China[J].Transactions of the Chinese Society Agricultural Engineering,2011,(8):211-215.[刘焕军,赵春江,王纪华,等.黑土典型区土壤有机质遥感反演[J].农业工程学报,2011,(8):211-215.]

[19]Zhou Qing,Zhou Bin,Zhang Yangzhu,et al.Influence of Parent Materials on Paddy Soil Hyperspectral Sharacteristics and SOM Spectral Parameter Models[J].Acta Pedologica Sinica,2004,41(6):905-911.[周清,周斌,张杨珠,等.成土母质对水稻土高光谱特性及其有机质含量光谱参数模型影响的初步研究[J].土壤学报,2004,41(6):905-911.]

[20]Gao Zhihai,Bai Lina,Wang Bengyu,et al.Estimation of Soil Organic Matter in Desertified Lands Using Measured Soil Spectral Data[J].Scientia Silvae Sinicae,2011,(6):9-16.[高志海,白黎娜,王琫瑜,等.荒漠化土地土壤有机质含量的实测光谱估测[J].林业科学,2011,(6):9-16.]

[21]Peng Jie,Zhang Yangzhu,Pang Xinan,et al.Hyperspectral Feature of Soil Organic Matter Content in South Xinjiang[J].Arid Land Geography,2010,(5):740-746.[彭杰,张杨珠,庞新安,等.新疆南部土壤有机质含量的高光谱特征分析[J].干旱区地理,2010,(5):740-746.]

[22]He T,Wang J,Lin Z J,et al.Spectral Features of Soil Organic Matter[J].Geo-spatial Information Science,2009,12(1):33-40.

[23]Wang Wei,Shen Runping,Ji Caoxiang.Study on Heavy Cu based on Hyperspectral Remote Sensing[J].Remote Sensing Technology and Application,2011,26(3):348-354.[王维,沈润平,吉曹翔.基于高光谱的土壤重金属铜的反演研究[J].遥感技术与应用,2011,26(3):348-354.]

[24]Bendor E,Inbar Y,Chen Y.The Reflectance Spectra of Organic Matter in the Visible Near-infrared and Short Wave Infrared Region (400-2500 nm) during a Controlled Decomposition Process[J].Remote Sensing of Environment,1997,61(1):1-15.

[25]He Ting,Wang Jing,Lin Zongjian,et al.Spectral Features of Soil Organic Matter[J].Geomatics and Information Science of Wuhan University,2006,31(11):975-979.[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(信息科学版),2006,31(11):975-979.]

[26]Wei Haikun.Theory and Method of Structure Design on Neural Network[M].Beijing:National Defense Industry Press,2005:94-96.[魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社,2005:94-96.]

[27]Xu Binbin.Study on Reflectance Spectra of Soil Section[J].Soils,2000,32(6):281-287.[徐彬彬.土壤剖面的反射光谱研究[J].土壤,2000,32(6):281-287.]

[28]Ji Wenjun,Shi Zhou,Zhou Qing,et al.VIS-NIR Reflectance Spectroscopy of the Organic Matter in Several Types of Soil[J].Journal of Infrared and Millimeter Waves,2012,(3):277-282.[纪文君,史舟,周清,等.几种不同类型土壤的VIS-NIR光谱特性及有机质响应波段[J].红外与毫米波学报,2012,(3):277-282.]

[29]Agriculture Programming Office of Qinghai Province.Qinghai soil[M].Beijing:China Agriculture Press ,1997:55-259.[青海省农业资源区划办公室.青海土壤[M].北京:中国农业出版社,1997:55-259.]

[1] 杨军,裴剑杰. 一种改进的隐马尔可夫随机场遥感影像分割算法[J]. 遥感技术与应用, 2018, 33(5): 857-865.
[2] 林利斌,鲍艳松,左泉,房世波. 基于Sentinel-1与FY-3C数据反演植被覆盖地表土壤水分[J]. 遥感技术与应用, 2018, 33(4): 750-758.
[3] 马真东,摆玉龙. 基于地理处理服务的地下水脆弱性评价研究[J]. 遥感技术与应用, 2018, 33(4): 759-765.
[4] 康文慧,宋晓谕,李洁,邓晓红,王宏伟,孙栋元. 基于GIS技术的流域生态补偿方案设计[J]. 遥感技术与应用, 2018, 33(4): 766-774.
[5] 丁安心,焦子锑. 基于线性核驱动模型的BRDF模型集成与案例分析[J]. 遥感技术与应用, 2018, 33(3): 545-554.
[6] 姚星辉,尤红建. 多重观测卫星影像的无控区域网平差[J]. 遥感技术与应用, 2018, 33(3): 555-562.
[7] 牛明慧,陈福春. 基于月球反射的遥感仪器在轨定标方法[J]. 遥感技术与应用, 2018, 33(2): 337-341.
[8] 万玲,尤红建,程跃兵,卢晓军. 合成孔径雷达图像分割研究进展[J]. 遥感技术与应用, 2018, 33(1): 10-24.
[9] 赵航,陈方, 张美美. 基于改进C-V模型的冰湖轮廓提取方法研究[J]. 遥感技术与应用, 2018, 33(1): 177-184.
[10] 张雅,尹小君,王伟强. 基于Landsat 8 OLI遥感影像的天山北坡草地地上生物量估算[J]. 遥感技术与应用, 2017, 32(6): 1012-1021.
[11] 魏龙,王维真,吴月茹,马春锋. 土壤水盐介电模型对比与分析[J]. 遥感技术与应用, 2017, 32(6): 1022-1030.
[12] 杨双宝,翟振和,许可,王志森,史灵卫,王磊,崔海英,徐曦煜. 合成孔径雷达高度计数据处理方法[J]. 遥感技术与应用, 2017, 32(6): 1083-1092.
[13] 李玉琴,苏程,王习之,黄智才,章孝灿. 菲律宾吕宋岛斑岩铜金矿遥感找矿模型[J]. 遥感技术与应用, 2017, 32(6): 1151-1160.
[14] 赵梦雨,薛亮. 咸阳市生境质量变化遥感监测研究[J]. 遥感技术与应用, 2017, 32(6): 1171-1180.
[15] 曹晓晨,尤红建,刘佳音,王峰. 基于误差建模的SRTM高程精度提升方法研究[J]. 遥感技术与应用, 2017, 32(5): 801-808.