Hyperspectral estimation of soil organic carbon content in the west lakeside oasis of Bosten Lake based on successive projection algorithm

doi:10.3785/j.issn.1008-9209.2021.01.181

Journal of Zhejiang University (Agriculture and Life Sciences)

2021, Vol. 47

Issue (5): 673-682 DOI: 10.3785/j.issn.1008-9209.2021.01.181

Agricultural engineering

Hyperspectral estimation of soil organic carbon content in the west lakeside oasis of Bosten Lake based on successive projection algorithm

Fangpeng NIU^1,²(

),Xinguo LI^1,²(

), MAMATTURSUN?Eziz^1,²,Hui ZHAO^1,²

^1.College of Geographic Sciences and Tourism, Xinjiang Normal University, Urumqi 830054, China
^2.Xinjiang Laboratory of Lake Environment and Resources in Arid Zone, Urumqi 830054, China

Download:

HTML

HTML ( )

PDF(1483KB)
Export: BibTeX | EndNote (RIS)

Abstract

Taking the west lakeside oasis of Bosten Lake as the study area, using the measured soil organic carbon content and hyperspectral data, the successive projection algorithm (SPA) was used to filter the characteristic variables from the full-band spectral data, and then the full-band and characteristic bands were used to construct partial least square regression (PLSR) and support vector machine (SVM) models to estimate soil organic carbon content. The results showed that: 1) The soil organic carbon content varied from 0.75 to 48.13 g/kg, with an average value of 13.31 g/kg, showed moderate variability, with a coefficient of variation of 63.19%. 2) The soil organic carbon content and the original spectral reflectance showed a negative correlation, with －0.62＜correlation coefficient (r)＜－0.07. After the bands were preprocessed by Savitzky-Golay-standard normal variate-first derivative (SG-SNV-1st Der), the number of bands that passed the extremely significant test (P＜0.01) were 414, mainly concentrated in 487-575, 725-998 and 1 464-1 514 nm. The correlation between 788, 800 and 1 768 nm was the highest, with the correlation coefficients of more than 0.80. 3) After the spectra were preprocessed by SG-SNV-1st Der, the coefficient of determination (R²) of validation set of PLSR model constructed by SPA was 0.79; root mean square error (RMSE) was 3.58 g/kg; residual prediction deviation (RPD) was 1.99; and ratio of performance to interquartile distance (RPIQ) was 2.23. However, the validation set constructed by SPA combined with SVM was R²=0.81, RMSE=3.16 g/kg, RPD=2.25, RPIQ=2.53. It shows that the model constructed by SPA combined with SVM can better estimate soil organic carbon content in the study area.

Key words： soil organic carbon hyperspectral data successive projection algorithm support vector machine lakeside oasis

Received: 18 January 2021 Published: 27 October 2021

CLC:

S 153.6

Corresponding Authors: Xinguo LI E-mail: niufp0225@163.com;onlinelxg@sina.com

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Fangpeng NIU
	Xinguo LI
	MAMATTURSUN?Eziz
	Hui ZHAO

Cite this article:

Fangpeng NIU,Xinguo LI, MAMATTURSUN?Eziz,Hui ZHAO. Hyperspectral estimation of soil organic carbon content in the west lakeside oasis of Bosten Lake based on successive projection algorithm. Journal of Zhejiang University (Agriculture and Life Sciences), 2021, 47(5): 673-682.

URL:

http://www.zjujournals.com/agr/10.3785/j.issn.1008-9209.2021.01.181 OR http://www.zjujournals.com/agr/Y2021/V47/I5/673

基于连续投影算法的博斯腾湖西岸湖滨绿洲土壤有机碳含量的高光谱估算

以博斯腾湖西岸湖滨绿洲为研究区，利用实测的土壤有机碳含量与高光谱数据，应用连续投影算法（successive projection algorithm, SPA）从全波段光谱数据中筛选特征变量，并分别采用全波段和特征波段构建偏最小二乘回归（partial least square regression, PLSR）与支持向量机（support vector machine, SVM）模型来估算土壤有机碳含量。结果表明：1）土壤有机碳质量分数变化范围为0.75～48.13 g/kg，平均值为13.31 g/kg，呈中等变异性，变异系数为63.19%。2）土壤有机碳含量与原始光谱反射率表现为负相关性［－0.62＜相关系数（r）＜－0.07］；经SG平滑结合标准化正态变换后进行一阶微分（Savitzky-Golay-standard normal variate-first derivative, SG-SNV-1st Der）预处理后，通过极显著性检验（P＜0.01）的波段数达到414个，主要集中在487～575、725～998和1 464～ 1 514 nm处，其中在788、800与1 768 nm波长处的相关性最高，r均大于0.80。3）光谱经SG-SNV-1st Der预处理后，用SPA构建的PLSR模型验证集的决定系数（R²）=0.79，均方根误差（root mean square error, RMSE）=3.58 g/kg，残余预测误差（residual prediction deviation, RPD）=1.99，四分位数间距性能比（ratio of performance to interquartile distance, RPIQ）=2.23；而运用SPA结合SVM构建的模型验证集R²=0.81，RMSE=3.16 g/kg，RPD=2.25，RPIQ=2.53。说明运用SPA结合SVM构建的模型能较好地估算研究区土壤有机碳含量。

关键词： 土壤有机碳, 高光谱数据, 连续投影算法, 支持向量机, 湖滨绿洲

Fig. 1 Soil spectral reflectance curve after SG smoothing and SG-SNV-1st Der pretreatments

Table 1 Descriptive statistics of soil organic carbon (SOC) content

Fig. 2 Characteristics of spectral reflectance curve of soil organic carbon content

Fig. 3 Correlation coefficient curve between soil organic carbon content and spectral reflectance

Fig. 4 Screening of preprocessing spectral characteristic wavelength by SPA

Table 2 PLSR modeling results of the two spectral modes

Fig. 5 Scatter plot of PLSR model of full-band and characteristic bands under the two spectral modesA. Original spectrum; B. Pretreatment spectrum.

Table 3 SVM modeling results of the two spectral modes

Fig. 6 Scatter plot of SVM model of full-band and characteristic bands under the two spectral modesA. Original spectrum; B. Pretreatment spectrum.


[1]	WANG J P, WANG X J, ZHANG J, et al. Soil organic and inorganic carbon and stable carbon isotopes in the Yanqi Basin of northwestern China. European Journal of Soil Science, 2015,66:95-103. DOI:10.1111/ejss.12188 doi: 10.1111/ejss.12188

[2]	贡璐,朱美玲,刘曾媛,等.塔里木盆地南缘典型绿洲土壤有机碳、无机碳与环境因子的相关性.环境科学,2016,37(4):1516-1522. DOI:10.13227/j.hjkx.2016.04.042 GONG L, ZHU M L, LIU Z Y, et al. Correlation among soil organic carbon, soil inorganic carbon and the environmental factors in a typical oasis in the southern edge of the Tarim Basin. Environmental Science, 2016,37(4):1516-1522. (in Chinese with English abstract) doi: 10.13227/j.hjkx.2016.04.042

[3]	童庆禧,张兵,张立福.中国高光谱遥感的前沿进展.遥感学报,2016,20(5):689-707. DOI:10.11834/jrs.20166264 TONG Q X, ZHANG B, ZHANG L F. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 2016,20(5):689-707. (in Chinese with English abstract) doi: 10.11834/jrs.20166264

[4]	NAWAR S, MOUAZEN A M. Predictive performance of mobile vis-near infrared spectroscopy for key soil properties at different geographical scales by using spiking and data mining techniques. Catena, 2017,151:118-129. DOI:10.1016/j.catena.2016.12.014 doi: 10.1016/j.catena.2016.12.014

[5]	CHEN Y, WANG J L, LIU G J, et al. Hyperspectral estimation model of forest soil organic matter in northwest Yunnan Province, China. Forests, 2019,10(3):217. DOI:10.3390/f10030217 doi: 10.3390/f10030217

[6]	WANG S J, CHEN Y H, WANG M G, et al. SPA-based methods for the quantitative estimation of the soil salt content in saline-alkali land from field spectroscopy data: a case study from the Yellow River irrigation regions. Remote Sensing, 2019,11(8):967. DOI:10.3390/rs11080967 doi: 10.3390/rs11080967

[7]	王涛,喻彩丽,张楠楠,等.基于去包络线和连续投影算法的枣园土壤电导率光谱检测研究.干旱地区农业研究,2019,37(5):193-199, 217. DOI:10.7606/j.issn.1000-7601.2019.05.29 WANG T, YU C L, ZHANG N N, et al. Spectral detection of electrical conductivity in jujube orchard soil based on continuum-removal and SPA. Agricultural Research in the Arid Areas, 2019,37(5):193-199, 217. (in Chinese with English abstract) doi: 10.7606/j.issn.1000-7601.2019.05.29

[8]	章海亮,罗微,刘雪梅,等.应用遗传算法结合连续投影算法近红外光谱检测土壤有机质研究.光谱学与光谱分析,2017,37(2):584-587. DOI:10.3964/j.issn.1000-0593(2017)02-0584-04 ZHANG H L, LUO W, LIU X M, et al. Measurement of soil organic matter with near infrared spectroscopy combined with genetic algorithm and successive projection algorithm. Spectroscopy and Spectral Analysis, 2017,37(2):584-587. (in Chinese with English abstract) doi: 10.3964/j.issn.1000-0593(2017)02-0584-04

[9]	孙亚楠,李仙岳,史海滨,等.河套灌区土壤水溶性盐基离子高光谱综合反演模型.农业机械学报,2019,50(5):344-355. DOI:10.6041/j.issn.1000-1298.2019.05.039 SUN Y N, LI X Y, SHI H B, et al. Hyperspectral integrated inverse model for water-soluble salt ions content in Hetao Irrigation District. Transactions of the Chinese Society for Agricultural Machinery, 2019,50(5):344-355. (in Chinese with English abstract) doi: 10.6041/j.issn.1000-1298.2019.05.039

[10]	张子鹏,丁建丽,王敬哲,等.利用三维光谱指数定量估算土壤有机质含量:以新疆艾比湖流域为例.光谱学与光谱分析,2020,40(5):1514-1522. DOI:10.3964/j.issn.1000-0593(2020)05-1514-09 ZHANG Z P, DING J L, WANG J Z, et al. Quantitative estimation of soil organic matter content using three-dimensional spectral index: a case study of the Ebinur Lake Basin in Xinjiang. Spectroscopy and Spectral Analysis, 2020,40(5):1514-1522. (in Chinese with English abstract) doi: 10.3964/j.issn.1000-0593(2020)05-1514-09

[11]	SUN W J, LI X J, NIU B B. Prediction of soil organic carbon in a coal mining area by Vis-NIR spectroscopy. PLoS ONE, 2018,13(4):e0196198. DOI:10.1371/journal.pone.0196198 doi: 10.1371/journal.pone.0196198

[12]	HONG Y S, CHEN Y J, YU L, et al. Combining fractional order derivative and spectral variable selection for organic matter estimation of homogeneous soil samples by VIS-NIR spectroscopy. Remote Sensing, 2018,10(3):479. DOI:10.3390/rs10030479 doi: 10.3390/rs10030479

[13]	牛芳鹏,李新国,靳万贵,等.博斯腾湖西岸湖滨绿洲土壤盐分特征.中国土壤与肥料,2020(3):8-15. DOI:10.11838/sfsc.1673-6257.19219 NIU F P, LI X G, JIN W G, et al. Characteristics of soil salinity in the western lakeside oasis of Bosten Lake. Soil and Fertilizer Sciences in China, 2020(3):8-15. (in Chinese with English abstract) doi: 10.11838/sfsc.1673-6257.19219

[14]	吴才武,夏建新,段峥嵘.土壤有机质测定方法述评与展望.土壤,2015,47(3):453-460. DOI:10.13758/j.cnki.tr.2015.03.004 WU C W, XIA J X, DUAN Z R, et al. Review on detection methods of soil organic matter (SOM). Soils, 2015,47(3):453-460. (in Chinese with English abstract) doi: 10.13758/j.cnki.tr.2015.03.004

[15]	何挺,程烨,王静.野外地物光谱测量技术及方法.中国土地科学,2002(5):30-36. DOI:10.3969/j.issn.1001-8158.2002.05.006 HE T, CHENG Y, WANG J. The technology and method of field spectrometry. China Land Science, 2002(5):30-36. (in Chinese with English abstract) doi: 10.3969/j.issn.1001-8158.2002.05.006

[16]	张子鹏,丁建丽,王敬哲.基于谐波分析算法的干旱区绿洲土壤光谱特性研究.光学学报,2019,39(2):391-401. DOI:10.3788/AOS201939.0228003 ZHANG Z P, DING J L, WANG J Z. Spectral characteristics of oasis soil in arid area based on harmonic analysis slgo-rithm. Acta Optica Sinica, 2019,39(2):391-401. (in Chinese with English abstract) doi: 10.3788/AOS201939.0228003

[17]	董春旺,梁高震,安霆,等.红茶感官品质及成分近红外光谱快速检测模型建立.农业工程学报,2018,34(24):306-313. DOI:10.11975/j.issn.1002-6819.2018.24.037 DONG C W, LIANG G Z, AN T, et al. Near-infrared spectroscopy detection model for sensory quality and chemical constituents of black tea. Transactions of the CSAE, 2018,34(24):306-313. (in Chinese with English abstract) doi: 10.11975/j.issn.1002-6819.2018.24.037

[18]	GALVAO R K H, ARAUJO M C U, JOSé G E, et al. A method for calibration and validation subset partitioning. Talanta, 2005,67(4):736-740. DOI:10.1016/j.talanta.2005.03.025 doi: 10.1016/j.talanta.2005.03.025

[19]	CHANG C W, LAIRD D A, MAUSBACH M J, et al. Near‐infrared reflectance spectroscopy-principal components regression analyses of soil properties. Soil Science Society of America Journal, 2001,65(2):480-490. DOI:10.2136/sssaj2001.652480x doi: 10.2136/sssaj2001.652480x

[20]	MCBRATNEY A, FERNANDEZ-AHUMADA E, PALAGOS B, et al. Critical review of chemometric indicators commonly used for assessing the quality of the prediction of soil attributes by NIR spectroscopy. Trends in Analytical Chemistry, 2010,29(9):1073-1081. DOI:10.1016/j.trac.2010.05.006 doi: 10.1016/j.trac.2010.05.006

[21]	郑立华,李民赞,安晓飞,等.基于近红外光谱和支持向量机的土壤参数预测.农业工程学报,2010,26():81-87. DOI:10.3969/j.issn.1002-6819.2010.z2.016 ZHEN L H, LI M Z, AN X F, et al. Forecasting soil parameters based on NIR and SVM. Transactions of the CSAE, 2010,26():81-87. (in Chinese with English abstract) doi: 10.3969/j.issn.1002-6819.2010.z2.016

[22]	汪周伟,钱淑苹.东北主要土壤的光谱反射特性.土壤通报,1984(5):209-211. WANG Z W, QIAN S P. Spectral reflection characteristics of main soils in Northeast China. Chinese Journal of Soil Science, 1984(5):209-211. (in Chinese)

[23]	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.光谱学与光谱分析,2010,30(12):3355-3358. DOI:10.3964/j.issn.1000-0593(2010)12-3355-04 LIU H J, ZHANG X L, ZHENG S F, et al. Black soil organic matter predicting model based on field hyperspectral reflectance. Spectroscopy and Spectral Analysis, 2010,30(12):3355-3358. (in Chinese with English abstract) doi: 10.3964/j.issn.1000-0593(2010)12-3355-04

[24]	徐彬彬,季耿善.土壤光谱反射特性研究及其应用.土壤学进展,1987(1):1-9. XU B B, JI G S. Study on spectral reflectance characteristics of soil and its application. Progress in Soil Science, 1987(1):1-9. (in Chinese)

[25]	马利芳,熊黑钢,张芳.基于野外VIS-NIR光谱的土壤盐分主要离子预测.土壤,2020,52(1):188-194. DOI:10.13758/j.cnki.tr.2020.01.027 MA L F, XIONG H G, ZHANG F. Prediction of major ions in soil salinity based on field VIS-NIR spectroscopy. Soils, 2020,52(1):188-194. (in Chinese with English abstract) doi: 10.13758/j.cnki.tr.2020.01.027

[26]	李冠稳,高小红,肖能文,等.特征变量选择和回归方法相结合的土壤有机质含量估算.光学学报,2019,39(9):361-371. DOI:10.3788/AOS201939.0930002 LI G W, GAO X H, XIAO N W, et al. Estimation of soil organic matter content based on characteristic variable selection and regression methods. Acta Optica Sinica, 2019,39(9):361-371. (in Chinese with English abstract) doi: 10.3788/AOS201939.0930002

[27]	韩建,李雨昭,曹志民,等.SPA-PLS的高含水原油近红外光谱含水率分析.光谱学与光谱分析,2019,39(11):3452-3458. DOI:10.3964/j.issn.1000-0593(2019)11-3452-07 HAN J, LI Y Z, CAO Z M, et al. Water content prediction for high water-cut crude oil based on SPA-PLS using near infrared spectroscopy. Spectroscopy and Spectral Analysis, 2019,39(11):3452-3458. (in Chinese with English abstract) doi: 10.3964/j.issn.1000-0593(2019)11-3452-07

[28]	VISCARRA ROSSEL R A, WALVOORT D J J, MCBRATNEY A B, et al. Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties. Geoderma, 2006,131(1/2):59-75. DOI:10.1016/j.geoderma.2005.03.007 doi: 10.1016/j.geoderma.2005.03.007

[29]	杨爱霞,丁建丽.新疆艾比湖湿地土壤有机碳含量的光谱测定方法对比.农业工程学报,2015,31(18):162-168. DOI:10.11975/j.issn.1002-6819.2015.18.023 YANG A X, DING J L. Comparative assessment of two methods for estimation of soil organic carbon content by Vis-NIR spectra in Xinjiang Ebinur Lake Wetland. Transactions of the CSAE, 2015,31(18):162-168. (in Chinese with English abstract) doi: 10.11975/j.issn.1002-6819.2015.18.023

[30]	曾胤,陆宇振,杜昌文,等.应用红外光声光谱技术及支持向量机模型测定土壤有机质含量.土壤学报,2014,51(6):1262-1269. DOI:10.11766/trxb201311110526 ZENG Y, LU Y Z, DU C W, et al. Applying infrared photoacoustic spectroscopy and support vector machine model to quantify soil organic matter content. Acta Pedologica Sinica, 2014,51(6):1262-1269. (in Chinese with English abstract) doi: 10.11766/trxb201311110526

[1]	Chaoyang MO,Xinlin ZHANG,Jingping YANG. Influence of rhizosphere priming effects on accumulation and decomposition of soil organic carbon[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2021, 47(4): 527-533.

[2]	HU Gensheng, WU Wentian, LUO Juhua, HUANG Wenjiang, LIANG Dong, HUANG Linsheng. Remote sensing monitoring of wheat aphids by combining HJ satellite images with least square twin support vector machine model.[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2017, 43(2): 211-219.

[3]	BO Xiaoyan, MI Wenbao, XU Hao, ZHANG Xueyi, MI Nan, SONG Yongyong. Contents and ecological stoichiometry characteristics of soil carbon, nitrogen and phosphorus in wetlands of Ningxia plain[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2016, 42(1): 107-118.

[4]	Deng Xunfei, Chen Xiaojia, Ma Wanzhu, Wang Fei, Ren Zhouqiao, Qin Fangjin, Lü Xiaonan. Variability of soil organic carbon in plough layers and its impact factors in a coastal reclamation area on south coast of Hangzhou Bay[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2015, 41(03): 349-357.

[5]	WU Jiasen1,2, ZHANG Jinchi1, HUANG Jianqin2, TONG Zhipeng3,YE Jing2， GU Guangtong4. Distribution characteristics of soil organic carbon in Carya cathayensis producing regions of Lin’an City, Zhejiang Province*[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2013, 39(4): 413-420.

[6]	FENG Lei，ZHANG Derong， CHEN Shuangshuang，FENG Bin, XIE Chuanqi，CHEN Youyuan，HE Yong. Early detection of gray mold on eggplant leaves using hyperspectral imaging technique.[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2012, 38(3): 311-317.

[7]	CEN Yi-lang,SONG Tao,HE Yong,BAO Yi-dan. Rapid detection method of soil organic matter contents using visible/near infrared diffuse reflectance spectral data[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2011, 37(3): 300-306.

Viewed

Full text

Abstract

Cited

Shared

Discussed