Hyperspectral reflectance characteristics paramter extraction for soil classification model

Huanjun LIU; Xiaokang ZHANG; Xinle ZHANG; Hongfeng WU; Huining JIN; Shengnan YU; Zhengchao QIU

doi:10.11834/jrs.20176038

Views : 0 下载量: 258 CSCD: 7 更多指标

PDF
Export
Share
Collection
Album

Hyperspectral reflectance characteristics paramter extraction for soil classification model
Vol. 21, Issue 1, Pages: 105-114(2017)
Published： 2017-1 ，
DOI： 10.11834/jrs.20176038

扫描看全文

Huanjun LIU, Xiaokang ZHANG, Xinle ZHANG, et al. Hyperspectral reflectance characteristics paramter extraction for soil classification model. [J]. Journal of Remote Sensing 21(1):105-114(2017)
DOI：

Huanjun LIU, Xiaokang ZHANG, Xinle ZHANG, et al. Hyperspectral reflectance characteristics paramter extraction for soil classification model. [J]. Journal of Remote Sensing 21(1):105-114(2017) DOI： 10.11834/jrs.20176038.

摘要

提出了一种无损、快速、成本低的土壤分类方法，选取松嫩平原4种典型土壤(黑土、黑钙土、风砂土和草甸土)耕层(0—20 cm)土样的实验室反射光谱数据作为研究对象，采用重采样、包络线消除法处理光谱数据，提取反映反射光谱特征的光谱特征参数，利用K均值聚类(K-means clustering)和决策树(decision tree)分别进行聚类分析和分类模型构建，实现土壤的快速分类。结果表明，利用表层土壤反射光谱特征参数构建的决策树分类模型可以对研究区土壤进行分类。研究成果有望加快土壤制图，为土壤理化性质的时空变化研究提供技术支持。

Abstract

Soil taxonomy plays a significant role in soil remote sensing. Soil spectral reflectance is the comprehensive representation of soil’s physical and chemical parameters. The study of soil spectral reflectance features is the physical basis for soil remote sensing

and it provides new ideas and methods for soil classification.To quickly classify soil based on topsoil reflectance spectral characteristics and provide an effective method

the room spectral reflectance in the visible and near-infrared region (400—2500 nm) of 148 soil samples

including black

chernozem

blown

and meadow soils

were collected from Songnen plain

which is located in Heilongjiang province. Given that the high-frequency noise of reflectance spectrum is relatively strong in the range of 400 nm to 430 nm and 2450 nm to 2500 nm

we chose the visible and near-infrared region of 430 nm to 2450 nm.The spectral reflectance of soil samples were measured using ASDFieldSpec 3 in the laboratory. Resampling and continuum removal techniques were used to process spectral data and extract the spectral characteristic parameters (i.e.

the absorption positions of the spectral curve

the vale’s area

the slope of the spectral curve

the distance between adjacent absorption positions

the depth of the vale

and the width of the vale)

respectively. When the K-means clustering results based on spectral reflectance were compared with the K-means clustering results based on the spectral characteristic parameters

the spectral characteristic parameters were found to be more suitable for soil classification. Finally

the spectral characteristic parameters were used to constructsoil classification model that is based on the decision tree. The classification accuracy of black

chernozem

blown

and meadow soilsare 97.22%

94.2%

85.29% and 55.56%

respectively.These results were obtained by using the decision tree model. The most effective spectral characteristic parameters include the second absorption positions of the spectral curve

the first vale’s area

the first two vales’ area

and the slope of the spectral curve at 500 nm to 600 nm and 1340 nm to 1360 nm. Meadow soilis often distributed in the lower area

and the spectral curve of the topsoil of meadow soil is similar to its adjacent soil

which is regarded asa trend toward its adjacent soil. The spectral characteristic parameters that were extracted could be used to study the soil classification

and the decision tree model that is based on the spectral characteristic parameters of topsoil reflectance has achieved excellent results. This paper provides a convenient

rapid

and nondestructive approach for soil classification

which helps in soil mapping.

关键词

土壤分类光谱特征参数K均值聚类决策树松嫩平原

Keywords

soil taxonomyspectral characteristic parametersK-means clusteringdecision treeSongnen plain

references

Bu Y D, Chen F Q and Pan J C. 2014. Stellar spectral subclasses classification based on Isomap and SVM. New Astronomy, 28: 35–43

戴昌达. 1981. 中国主要土壤光谱反射特性分类与数据处理的初步研究//国家遥感中心. 遥感文选. 北京: 科学出版社: 315–323

Dai C D. 1981. Preliminary study on classification and data processing of spectral reflectance characteristics of main soils in China // Remote Sensing Anthology. Beijing: Science Press: 315–323

Dalal R C and Henry R J. 1986. Simultaneous determination of moisture, organic carbon, and total nitrogen by near infrared reflectance spectrophotometry. Soil Science Society of America Journal, 50(1): 120–123

何挺, 王静, 程烨, 林宗坚. 2006. 土壤氧化铁光谱特征研究. 地理与地理信息科学, 22(2): 30–34

He T, Wang J, Cheng Y and Lin Z J. 2006. Study on spectral features of soil Fe2O3. Geography and Geo-Information Science, 22(2): 30–34

黄应丰, 刘腾辉. 1995. 华南主要土壤类型的光谱特性与土壤分类. 土壤学报, 32(1): 58–68

Huang Y F and Liu T H. 1995. Spectral characteristics of main types of soils in southern China and soil classification. Acta Pedologica Sinica, 32(1): 58–68

Hummel J W, Sudduth K A and Hollinger S E. 2001. Soil moisture and organic matter prediction of surface and subsurface soils using an NIR soil sensor. Computers and Electronics in Agriculture, 32(2): 149–165

Kemper T and Sommer S. 2002. Estimate of heavy metal contamination in soils after a mining accident using reflectance spectroscopy. Environmental Science and Technology, 36(12): 2742–2747

Kovačević M, Bajat B and Gajić B. 2010. Soil type classification and estimation of soil properties using support vector machines. Geoderma, 154(3/4): 340–347

李丹, 彭智平, 韩留生, 王重洋, 刘尉, 黄思宇, 陈水森. 2015. 基于土壤反射光谱特性的广东省稻田土壤快速分类. 热带地理, 35(1): 29–34

Li D, Peng Z P, Han L S, Wang C Y, Liu W, Huang S Y and Chen S S. 2015. Rapid soil classification of paddy field in Guangdong province based on visible and near infrared reflectance spectra. Tropical Geography, 35(1): 29–34

刘焕军, 张柏, 张渊智, 宋开山, 王宗明, 李方, 胡茂桂. 2008. 基于反射光谱特性的土壤分类研究. 光谱学与光谱分析, 28(3): 624–628

Liu H J, Zhang B, Zhang Y Z, Song K S, Wang Z M, Li F and Hu M G. 2008. Soil taxonomy on the basis of reflectance spectral characteristics. Spectroscopy and Spectral Analysis, 28(3): 624–628

Lu Y L, Bai Y L, Yang L P, Wang L, Wang Y L, Ni L and Zhou L P. 2015. Hyper-spectral characteristics and classification of farmland soil in northeast of China. Journal of Integrative Agriculture, 14(12): 2521–2528

马海姣, 崔晨风. 2014. 基于可见-近红外光谱和神经网络的土壤类型鉴别. 江苏农业科学, 42(4): 284–286

Ma H J and Cui C F. 2014. Identification of soil types based on visible-near infrared spectroscopy and neural networks. Jiangsu Agriculture Sciences, 42(4): 284–286

Oliveira J F, Brossard M, Vendrame P R S, Mayi III S, Corazza E J, Marchão R L and de Fátima Guimarães M. 2013. Soil discrimination using diffuse reflectance Vis–NIR spectroscopy in a local toposequence. Comptes Rendus Geoscience, 345(11/12): 446–453

史舟, 王乾龙, 彭杰, 纪文君, 刘焕军, 李曦, Viscarra Rossel R A. 2014. 中国主要土壤高光谱反射特性分类与有机质光谱预测模型. 中国科学: 地球科学, 44(5): 978–988

Shi Z, Wang Q L, Peng J, Ji W J, Liu H J, Li X and Viscarra Rossel R A. 2014. Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations. Science China: Earth Sciences, 57(7): 1671–1680

宋召青, 陈垚. 2015. 基于支持向量机的多类分类算法综述. 海军航空工程学院学报, 30(5): 442–446

Song Z Q, Chen Y. 2015. An overview of multi-class algorithm based on support vector machine. Journal of Naval Aeronautical and Astronautical University, 30(5): 442–446

Stoner E R and Baumgardner M F. 1982. Characteristic variations in reflectance of surface soils. Soil Science Society of America Journal, 45(6): 1161–4465

Vasques G M, Demattê J A M, Viscarra Rossel R A, Ramírez-López L and Terra F S. 2014. Soil classification using visible/near-infrared diffuse reflectance spectra from multiple depths. Geoderma, 223–225: 73–78

汪海燕, 黎建辉, 杨风雷. 2014. 支持向量机理论及算法研究综述. 计算机应用研究, 31(5): 1281–1286

Wang H Y, Li J H and Yang F L. 2014. Overview of support vector machine analysis and algorithm. Application Research of Computers, 31(5): 1281–1286

王人潮, 苏海萍, 王深法. 1986. 浙江省主要土壤光谱反射特性及其模糊分类在土壤分类中的应用研究. 浙江农业大学学报, 12(4): 108–115

Wang R C, Su H P and Wang S F. 1986. Studies on spectral reflectance of typical soils and its fuzzy category in soil classification in Zhejiang province. Acta Agriculture Universitatis Zhejiang, 12(4): 108–115

王遵义, 金春华, 刘飞, 王艳艳, 鲍一丹. 2010. 基于光谱技术的土壤快速分类方法研究. 浙江大学学报(农业与生命科学版), 36(3): 282–286

Wang Z Y, Jin C H, Liu F, Wang Y Y and Bao Y D. 2010. Rapid discrimination of soil variety based on spectroscopic techniques. Journal of Zhejiang University (Agriculture and Life Sciences), 36(3): 282–286

徐彬彬, 季耿善. 1987. 土壤光谱反射特性研究及其应用. 土壤学进展, 15(1): 1–9

Xu B B and Ji G S. 1987. Research and application of spectral reflectance characteristics of soil. Advances in Soil Science, 15(1): 1–9

徐咏文, 段萍, 罗志华. 2005. 浅析中国土壤分类的发生与现状. 安徽农业科学, 33(10): 2003–2004

Xu Y W, Duan P and Luo Z H. 2005. Analysis of the occurrence and Current situation of soil classification in China. Journal of Anhui Agricultural Sciences, 33(10): 2003–2004

曾庆猛, 孙宇瑞, 严红兵. 2009. 土壤质地分类的近红外光谱分析方法研究. 光谱学与光谱分析, 29(7): 1759–1763

Zeng Q M, Sun Y R and Yan H B. 2009. Nir spectral analysis for soil textural classification. Spectroscopy and Spectral Analysis, 29(7): 1759–1763

张金会, 何政军, 田希. 2012. 基于支持向量机和神经网络对分类问题的比较研究. 机械工程师, (8): 31–32

Zhang J H, He Z J and Tian X. 2012. The comparative study of classification based on support vector machines and neural networks. Mechanical Engineer, (8): 31–32

Alert me when the article has been cited

提交

Terrestrial change detection integrating the Dynamic Ratio and the Max-difference Algorithm

Construction and application of knowledge decision tree after a disaster for water body information extraction from remote sensing images

Intelligence fusion method research of multisource high-resolution remote sensing images

Mapping winter wheat growing areas in the North China Plain with FY-3 250 m resolution data

Extracting rubber plantation with decision tree model based on object-oriented method