新疆农业科学 ›› 2024, Vol. 61 ›› Issue (6): 1477-1486.DOI: 10.6048/j.issn.1001-4330.2024.06.022

• 植物保护•土壤肥料•节水灌溉 • 上一篇    下一篇

湖滨绿洲土壤有机碳含量的支持向量机估算模型

杨吉祥(), 李新国()   

  1. 新疆师范大学地理科学与旅游学院/新疆干旱区湖泊环境与资源实验室,乌鲁木齐 830054
  • 收稿日期:2023-11-04 出版日期:2024-06-20 发布日期:2024-08-08
  • 通信作者: 李新国(1971-),男,甘肃玉门人,教授,博士,硕士生导师,研究方向为土壤资源及遥感,(E-mail)onlinelxg@163.com
  • 作者简介:杨吉祥(1994-),男,山西吕梁人,硕士研究生,研究方向为资源与环境遥感,(E-mail)geojixiang@163.com
  • 基金资助:
    新疆维吾尔自治区自然科学基金项目(2022D01A214);国家自然科学基金项目(41661047)

Support vector machines estimation model of soil organic carbon content in lakeside oasis

YANG Jixiang(), LI Xinguo()   

  1. College of Geographic Sciences and Tourism, Xinjiang Normal University/Xinjiang Laboratory of Lake Environment and Resources in Arid Zone, Urumqi 830054, China
  • Received:2023-11-04 Published:2024-06-20 Online:2024-08-08
  • Correspondence author: LI Xinguo (1971-), male, from Yumen, Gansu, professor, Ph.D.,research direction: soil resource changes and their remote sensing applications, (E-mail)nlinelxg@163.com
  • Supported by:
    Natural Science Foundation of Xinjiang Uygur Autonomous Region(2022D01A214);National Natural Science Foundation of China(41661047)

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: 


ISSN 1001-4330 CN 65-1097/S
邮发代号:58-18
国外代号:BM3342
主管:新疆农业科学院
主办:新疆农业科学院 新疆农业大学 新疆农学会

出版单位:《新疆农业科学》编辑部
地址:乌鲁木齐市南昌路403号新疆农业科学院
邮编:830091
电话:0991-4502046
E-mail:xjnykx-h@xaas.ac.cn


版权所有 © 《新疆农业科学》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发
总访问量:551237 今日访问:1345 在线人数:4
网站
微信公众号
淘宝购买
微店购买