摘要
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1464~1514 nm处,其中在788、800与1768 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。
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 1464-1514 nm.The correlation between 788,800 and 1768 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.
作者
牛芳鹏
李新国
麦麦提吐尔逊·艾则孜
赵慧
NIU Fangpeng;LI Xinguo;MAMATTURSUN·Eziz;ZHAO Hui(College of Geographic Sciences and Tourism,Xinjiang Normal University,Urumqi 830054,China;Xinjiang Laboratory of Lake Environment and Resources in Arid Zone,Urumqi 830054,China)
出处
《浙江大学学报（农业与生命科学版）》
CAS
CSCD
北大核心
2021年第5期673-682,共10页
Journal of Zhejiang University:Agriculture and Life Sciences
基金
国家自然科学基金(41661047,U2003301)
新疆维吾尔自治区重点实验室开放课题(2018D04026)。
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
soil organic carbon
hyperspectral data
successive projection algorithm
support vector machine
lakeside oasis
