湖滨绿洲土壤有机碳含量的支持向量机估算模型

doi:10.6048/j.issn.1001-4330.2024.06.022

摘要/Abstract

摘要：

【目的】利用高光谱数据快速估算土壤有机碳含量,为干旱区湖滨绿洲合理开发土地资源提供科学依据。【方法】以新疆博斯腾湖北岸湖滨绿洲为研究区,将实测的土壤有机碳含量数据与高光谱数据相结合,对原始光谱进行SG平滑(SavitzkyGolay smoothing,SG)、连续统去除(Continuum Removal,CR)、连续小波变换(Continuous Wavelet Transform,CWT)预处理,采用连续投影算法(Successive Projections Algorithm,SPA)筛选特征波段;应用支持向量机(Support Vector Machines,SVM)模型估算土壤有机碳含量。【结果】(1)研究区土壤有机碳含量为0.69~50.32 g/kg,平均值为14.15 g/kg,标准差为9.51 g/kg,呈中等变异性,变异系数为67.20%。(2)土壤原始光谱反射率在350~750 nm,光谱反射率呈上升趋势,在750~2 150 nm,光谱反射率呈相对平稳趋势,在2 150~2 500 nm,光谱反射率逐渐下降;连续小波变换对土壤原始光谱预处理后随着分解尺度的增加,光谱局部特征明显,吸收峰和反射峰越来越平滑;采用连续投影算法筛选的光谱特征波段集中于350~952 nm、1 007~1 742 nm、2 082~2 381 nm,且特征波段仅占可见光-近红外光谱波段的0.30%。(3)连续小波变换结合连续投影算法构建的SVM模型,其训练集和验证集分别R²=0.76,RMSE=4.78和R²=0.94,RMSE=3.30,RPD=2.50。【结论】CWT-SPA-SVM可有效估算研究区土壤有机碳含量。

关键词: 土壤有机碳含量; 连续小波变换; 连续投影算法; 支持向量机模型; 高光谱数据

Abstract:

【Objective】 To study rapid estimation of soil organic carbon content using hyperspectral data in the hope of providing scientific basis for rational development of land resources in lakeside oases in arid regions. 【Methods】 The north lakeside oasis of Bosten Lake was taken as the study area and the measured soil organic carbon content data were combined with the hyperspectral data. Successive Projections Algorithm (SPA) was used to screen the successive bands after SG smoothing (SG), Continuum Removal (CR) and Continuous Wavelet Transform (CWT) pre-processing for the original spectra. Support Vector Machines (SVM) models were used to estimate soil organic carbon content. 【Results】 Soil organic carbon content in the study area ranged from 0.69 g/kg to 50.32 g/kg, with an average value of 14.15 g/kg and a standard deviation of 9.51 g/kg, showing moderate variability and coefficient of variation of 67.20%. The original spectral reflectance of soil changed with the increase of wavelength, at 350-750 nm, the spectral reflectance increased, at 750-2,150 nm, the spectral reflectance showed a relatively stable trend; from 2,150 nm to 2,500 nm, the spectral reflectance gradually decreased. With the increase of decomposition scale, the local characteristics of the original spectrum of soil after pretreatment by continuous wavelet transform became more and more obvious, and the absorption and reflection peaks were becoming smoother and smoother. The feature bands selected by the continuous projection algorithm were concentrated in 350-952, 1,007-1,742 and 2,082-2,381 nm, and the feature bands only accounted for 0.30% of the Vis-NIR spectrum. The training set and verification set of the SVM model constructed by continuous wavelet transform and continuous projection algorithm were R²=0.76, RMSE=4.78 and R²=0.94, RMSE=3.30, RPD=2.50, respectively. 【Conclusion】 The CWT-SPA-SVM could be effectively estimate soil organic carbon content in the study area.

Key words: soil organic carbon content; continuous wavelet transform; successive projections algorithm; support vector machines model; hyperspectral data

中图分类号:

S151.9

杨吉祥, 李新国. 湖滨绿洲土壤有机碳含量的支持向量机估算模型[J]. 新疆农业科学, 2024, 61(6): 1477-1486.

YANG Jixiang, LI Xinguo. Support vector machines estimation model of soil organic carbon content in lakeside oasis[J]. Xinjiang Agricultural Sciences, 2024, 61(6): 1477-1486.

图/表 7

图1 研究区土壤有机碳含量支持向量机模型构建流程

Fig.1 Flowchart of SVM model of soil organic carbon content development in the study area

表1 研究区土壤有机碳含量的统计性描述

Tab.1 The statistics descriptive of soil organic contents in the study area

样本类型 Sample type	样本数 Samples number	统计指标Statistical index
样本类型 Sample type	样本数 Samples number	最大值Max (g/kg)	最小值Min (g/kg)	平均值Mean (g/kg)	标准差SD (g/kg)	变异系数 CV(%)
样本总集Total sample	64	50.32	0.69	14.15	9.51	67.20
训练集Training set	43	50.32	0.69	14.09	9.88	70.12
验证集Validation set	21	36.65	3.47	14.27	8.94	62.64

图2 土壤原始光谱

Fig.2 Soil Spectra of the original

图3 基于SG平滑、连续统去除、连续小波变换(1~10尺度)的光谱反射

Fig.3 Spectral reflection of based on SG、CR 、CWT(1-10 scales)

图4 基于SPA算法筛选光谱特征波段分布

Fig.4 The position of spectra feature bands selected by the SPA

表2 基于SVM的建模结果

Tab.2 The models results of based SVM

模型 Models	尺度 Scales	训练集Training set		验证集Validation set
模型 Models	尺度 Scales	R²	RMSE	R²	RMSE	RPD
CWT-SPA-SVM	1 2 3 4 5 9 10	0.46 0.76 0.50 0.85 0.70 0.41 0.32	6.80 4.78 6.55 3.28 5.17 7.20 7.56	0.88 0.94 0.96 0.87 0.88 0.88 0.71	3.88 3.30 3.10 4.30 4.68 4.21 7.71	2.22 2.50 2.61 1.84 1.49 1.86 0.58

图5 SVM(2尺度)模型散点图

Fig.5 Scatterplots of oil rganic ontent based on SVM(2 scale)

参考文献 29

[1]	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.
[2]	Shi Z, Ji W, Viscarra Rossel R A, et al. Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis-NIR spectral library[J]. European Journal of Soil Science, 2015, 66(4): 679-687.
[3]	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[J]. European Journal of Soil Science, 2015, 66(1): 95-103.
[4]	Ribeiro S G, dos Santos Teixeira A, de Oliveira M R R, et al. Soil organic carbon content prediction using soil-reflected spectra: a comparison of two regression methods[J]. Remote Sensing, 2021, 13(23): 4752.
[5]	Amin I, Fikrat F, Mammadov E, et al. Soil organic carbon prediction by vis-NIR spectroscopy: case study the kur-aras plain, Azerbaijan[J]. Communications in Soil Science and Plant Analysis, 2020, 51(6): 726-734.
[6]	朱建伟, 刘玉学, 吴超凡, 等. 施用生物炭后土壤有机碳的近红外光谱模型研究与应用[J]. 生态学报, 2020, 40(20): 7430-7440.
	ZHU Jianwei, LIU Yuxue, WU Chaofan, et al. Study on near-infrared spectroscopy model of soil organic carbon after biochar addition and its application[J]. Acta Ecologica Sinica, 2020, 40(20): 7430-7440.
[7]	勾宇轩, 赵云泽, 李勇, 等. 基于CWT-sCARS的东北旱作农田土壤有机质高光谱反演[J]. 农业机械学报, 2022, 53(3): 331-337.
	GOU Yuxuan, ZHAO Yunze, LI Yong, et al. Soil organic matter content in dryland farmland in Northeast China with hyperspectral reflectance based on CWT-sCARS[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(3): 331-337.
[8]	张锐, 李兆富, 潘剑君. 小波包-局部最相关算法提高土壤有机碳含量高光谱预测精度[J]. 农业工程学报, 2017, 33(1): 175-181.
	ZHANG Rui, LI Zhaofu, PAN Jianjun. Coupling discrete wavelet packet transformation and local correlation maximization improving prediction accuracy of soil organic carbon based on hyperspectral reflectance[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(1): 175-181.
[9]	玉米提·买明, 王雪梅. 连续小波变换的土壤有机质含量高光谱估测[J]. 光谱学与光谱分析, 2022, 42(4): 1278-1284.
	Yumiti Maiming, WANG Xuemei. Hyperspectral estimation of soil organic matter content based on continuous wavelet transformation[J]. Spectroscopy and Spectral Analysis, 2022, 42(4): 1278-1284.
[10]	廖钦洪, 顾晓鹤, 李存军, 等. 基于连续小波变换的潮土有机质含量高光谱估算[J]. 农业工程学报, 2012, 28(23): 132-139.
	LIAO Qinhong, GU Xiaohe, LI Cunjun, et al. Estimation of fluvo-aquic soil organic matter content from hyperspectral reflectance based on continuous wavelet transformation[J]. Transactions of the Chinese Society of Agricultural Engineering, 2012, 28(23): 132-139.
[11]	孟珊, 李新国, 焦黎. 基于CARS算法的湖滨绿洲土壤表层有机碳估算[J]. 环境科学与技术, 2022, 45(8): 218-225.
	MENG Shan, LI Xinguo, JIAO Li. Estimation of surface soil organic carbon in lakeside oasis based on CARS algorithm[J]. Environmental Science & Technology, 2022, 45(8): 218-225.
[12]	牛芳鹏, 李新国, 麦麦提吐尔逊·艾则孜, 等. 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[J]. 浙江大学学报(农业与生命科学版), 2021, 47(5): 673-682.
	NIU Fangpeng, LI Xinguo, Mamattursun Eziz, et al. Hyperspectral estimation of soil organic carbon content in the west lakeside oasis of Bosten Lake based on successive projection algorithm[J]. Journal of Zhejiang University (Agriculture and Life Sciences), 2021, 47(5): 673-682.
[13]	章海亮, 刘雪梅, 何勇. SPA-LS-SVM检测土壤有机质和速效钾研究[J]. 光谱学与光谱分析, 2014, 34(5): 1348-1351.
	ZHANG Hailiang, LIU Xuemei, HE Yong. Measurement of soil organic matter and available K based on SPA-LS-SVM[J]. Spectroscopy and Spectral Analysis, 2014, 34(5): 1348-1351. PMID
[14]	Peng X T, Shi T Z, Song A H, et al. Estimating soil organic carbon using VIS/NIR spectroscopy with SVMR and SPA methods[J]. Remote Sensing, 2014, 6(4): 2699-2717.
[15]	叶红云, 熊黑钢, 张芳, 等. 基于CWT的人类不同程度干扰下干旱区土壤有机质含量估算研究[J]. 激光与光电子学进展, 2019, 56(5): 051101.
	YE Hongyun, XIONG Heigang, ZHANG Fang, et al. CWT-based estimation of soil organic matter content in arid area under different human disturbance degrees[J]. Laser & Optoelectronics Progress, 2019, 56(5): 051101.
[16]	牛芳鹏, 李新国, 麦麦提吐尔逊·艾则孜, 等. 基于光谱指数的博斯腾湖西岸湖滨绿洲土壤有机碳含量估算模型[J]. 江苏农业学报, 2022, 38(2): 414-421.
	NIU Fangpeng, LI Xinguo, Mamattursun Eziz, et al. Estimation model of soil organic carbon content in lakeside oasis on the west coast of Bosten Lake based on spectral index[J]. Jiangsu Journal of Agricultural Sciences, 2022, 38(2): 414-421.
[17]	艾孜提艾力·克依木, 李新国, 赵慧, 等. 基于地理加权回归模型的绿洲土壤表层有机质含量高光谱估算[J]. 新疆农业科学, 2022, 59(1): 223-230. DOI
	Hazirtiali Keyim, LI Xinguo, ZHAO Hui, et al. Hyperspectral estimation of surface soil organic matter content in the oasis based on geographically weighted regression model[J]. Xinjiang Agricultural Sciences, 2022, 59(1): 223-230. DOI
[18]	孙问娟, 李新举. 煤矿区土壤有机碳含量的高光谱预测模型[J]. 水土保持学报, 2018, 32(5): 346-351.
	SUN Wenjuan, LI Xinju. Hyperspectral prediction model of soil organic carbon content in coal mining area[J]. Journal of Soil and Water Conservation, 2018, 32(5): 346-351.
[19]	郭斌, 白昊睿, 张波, 等. 基于RF和连续小波变换的露天煤矿土壤锌含量高光谱遥感反演[J]. 农业工程学报, 2022, 38(10): 138-147.
	GUO Bin, BAI Haorui, ZHANG Bo, et al. Inversion of soil zinc contents using hyperspectral remote sensing based on random forest and continuous wavelet transform in an opencast coal mine[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(10): 138-147.
[20]	吴倩, 姜琦刚, 史鹏飞, 等. 基于高光谱的土壤碳酸钙含量估算模型研究[J]. 国土资源遥感, 2021, 33(1): 138-144.
	WU Qian, JIANG Qigang, SHI Pengfei, et al. The estimation of soil calcium carbonate content based on Hyperspectral data[J]. Remote Sensing for Land & Resources, 2021, 33(1): 138-144.
[21]	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[J]. 农业工程学报, 2015, 31(18): 162-168.
	YANG Aixia, DING Jianli. Comparative assessment of two methods for estimation of soil organic carbon content by Vis-NIR spectra in Xinjiang Ebinur Lake Wetland[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(18): 162-168.
[22]	于雷, 洪永胜, 周勇, 等. 连续小波变换高光谱数据的土壤有机质含量反演模型构建[J]. 光谱学与光谱分析, 2016, 36(5): 1428.
	YU Lei, HONG Yongsheng, ZHOU Yong, et al. Inversion of soil organic matter content using hyperspectral data based on continuous wavelet transformation[J]. Spectroscopy and Spectral Analysis, 2016, 36(5): 1428. PMID
[23]	赵明松, 谢毅, 陆龙妹, 等. 基于高光谱特征指数的土壤有机质含量建模[J]. 土壤学报, 2021, 58(1): 42-54.
	ZHAO Mingsong, XIE Yi, LU Longmei, et al. Modeling for soil organic matter content based on hyperspectral feature indices[J]. Acta Pedologica Sinica, 2021, 58(1): 42-54.
[24]	章涛, 于雷, 易军, 等. 高光谱小波能量特征估测土壤有机质含量[J]. 光谱学与光谱分析, 2019, 39(10): 3217-3222.
	ZHANG Tao, YU Lei, YI Jun, et al. Determination of soil organic matter content based on hyperspectral wavelet energy features[J]. Spectroscopy and Spectral Analysis, 2019, 39(10): 3217-3222.
[25]	Chen L H, Lai J, Tan K, et al. Development of a soil heavy metal estimation method based on a spectral index: combining fractional-order derivative pretreatment and the absorption mechanism[J]. The Science of the Total Environment, 2022, 813: 151882.
[26]	林鹏达, 佟志军, 张继权, 等. 基于CWT的黑土有机质含量野外高光谱反演模型[J]. 水土保持研究, 2018, 25(2): 46-52, 57.
	LIN Pengda, TONG Zhijun, ZHANG Jiquan, et al. Inversion of black soil organic matter content with field hyperspectral reflectance based on continuous wavelet transformation[J]. Research of Soil and Water Conservation, 2018, 25(2): 46-52, 57.
[27]	Li R Y, Gao M X, Xu Z X, et al. Hyper-spectral estimation of soil organic matter in apple orchard based on CWT[J]. IOP Conference Series: Earth and Environmental Science, 2021, 734(1): 012030.
[28]	刘翠英, 张津瑞, 曾涛, 等. 傅里叶变换红外光谱的土壤团聚体有机碳和全氮含量估测[J]. 光谱学与光谱分析, 2020, 40(12): 3818-3824.
	LIU Cuiying, ZHANG Jinrui, ZENG Tao, et al. Determination of soil organic carbon and total nitrogen contents in aggregate fractions from Fourier transform infrared spectroscopy[J]. Spectroscopy and Spectral Analysis, 2020, 40(12): 3818-3824.
[29]	肖艳, 辛洪波, 王斌, 等. 基于小波变换和连续投影算法的黑土有机质含量高光谱估测[J]. 国土资源遥感, 2021, 33(2): 33-39.
	XIAO Yan, XIN Hongbo, WANG Bin, et al. Hyperspectral estimation of black soil organic matter content based on wavelet transform and successive projections algorithm[J]. Remote Sensing for Land & Resources, 2021, 33(2): 33-39.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	14	0	0	19

来源	本网站	其他网站

次数	21	12
比例	64%	36%

摘要

114

最新录用	在线预览	正式出版

0	0	114

来源	本网站	其他网站

次数	41	73
比例	36%	64%