干旱区生态环境知识资源中心(Arid): 博斯腾湖西岸湖滨绿洲土壤含盐量高光谱估算

Arid

	博斯腾湖西岸湖滨绿洲土壤含盐量高光谱估算
其他题名	Hyperspectral estimation of soil salt content in lake oasis on the west bank of Bosten lake
	赵慧; 李新国; 靳万贵; 麦麦提吐尔逊·艾则孜; 牛芳鹏
来源期刊	中山大学学报. 自然科学版
ISSN	0529-6579
出版年	2020
卷号	59 期号:4 页码:56-63
中文摘要	以博斯腾湖西岸湖滨绿洲土壤盐分及其对应的高光谱数据为研究对象,对原始光谱反射率($R$)进行均方根($\sqrt R $)、对数($\lg R;$)、倒数($1/R$)、对数倒数($1/{\rm{lg}}R$)变换,引入分数阶微分对变换的光谱反射率进行0 ~2内的微分预处理,通过显著性检验优选特征波段,并利用特征波段进行偏最小二乘回归的建模和验证。结果表明:1)通过显著性检验较多的特征波段是:$1/R$为691个波段,比通过原始波段多226个波段;且随着阶数的增加,在各阶数中通过显著性检验的波段数量呈先增加后减少的趋势;通过数量较多的特征波段是$1/R$的0.4阶和0.6阶,分别为145、150;2)原始光谱反射率的相关性极大值绝对值是:2阶为0.53,其他4种数学变换的相关性极大值绝对值比R高0.11~0.16,特征波段主要集中在600~1 000 nm和2 020~2 330 nm;3)在原始光谱反射率及其变换值的各分数阶微分利用偏最小二乘回归建模中,$1/{\rm{lg}}R$的0.2阶建立的模型为最佳模型,${R^2}_{\rm{C}} = 0.78$,${\rm{RMS}}{{\rm{E}}_{\rm{C}}} = 1.56$,${R^2}_V = 0.63$,${\rm{RMS}}{{\rm{E}}_{\rm{V}}} = 1.44$。
英文摘要	Taking the soil salinity and corresponding hyperspectral data of the lakeside oasis on the west bank of the Bosten Lake as the research object,the root mean square $R$,logarithmic $\lg\;R$,reciprocal $1/R$,reciprocal $1/{\rm{lg}}R$ were used to transform the original spectral reflectance.The fractional differentiation was introduced to perform differential preprocessing within 0-2 on the transformed spectral reflectance.The characteristic band through significance test was used to model and verify partial least squares regression.The results show that:1)The characteristic bands that passed the significance test were mostly $1/R$ of 691 bands,which was 226 more bands than the original band R.With increasing orders,the number of bands that passed the significance test in each order showed a trend of increasing first and then decreasing.The characteristic bands that passed more were 0.4 and 0.6 orders of $1/R$,which were 145 and 150,respectively.2)The absolute value of the correlation maximum value of the original spectrum $R$ was 2nd order 0.53.The absolute value of the correlation maximum value of the other four mathematical transformations was 0.11-0.16,higher than $R$.The characteristic bands were mainly concentrated at 600-1 000 nm and 2 020-2 330 nm.3)The fractional differential of the original spectral $R$,the root mean square $R$,the logarithm $\lg R;$,the reciprocal $1/R$,and the logarithm reciprocal $1/{\rm{lg}}R$ was modeled by partial least squares regression.The model established at 0.2th order of $1/{\rm{lg}}R$ was the best one,with ${R^2}_{\rm{C}} = 0.78$,${\rm{RMS}}{{\rm{E}}_{\rm{C}}} = 1.56$,${R^2}_V = 0.63$,${\rm{RMS}}{{\rm{E}}_{\rm{V}}} = 1.44$.
中文关键词	分数阶微分 ; 土壤含盐量 ; 光谱变换 ; 偏最小二乘回归 ; 高光谱估算
英文关键词	fractional differential soil salinity spectral transformation partial least squares regression methods hyperspectral estimation
类型	Article
语种	中文
收录类别	CSCD
WOS研究方向	Remote Sensing
CSCD记录号	CSCD:6777549
来源机构	新疆师范大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/336756
作者单位	赵慧, 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, 新疆 830054, 中国.; 李新国, 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, 新疆 830054, 中国.; 靳万贵, 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, 新疆 830054, 中国.; 麦麦提吐尔逊·艾则孜, 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, 新疆 830054, 中国.; 牛芳鹏, 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, 新疆 830054, 中国.
推荐引用方式 GB/T 7714	赵慧,李新国,靳万贵,等. 博斯腾湖西岸湖滨绿洲土壤含盐量高光谱估算[J]. 新疆师范大学,2020,59(4):56-63.
APA	赵慧,李新国,靳万贵,麦麦提吐尔逊·艾则孜,&牛芳鹏.(2020).博斯腾湖西岸湖滨绿洲土壤含盐量高光谱估算.中山大学学报. 自然科学版,59(4),56-63.
MLA	赵慧,et al."博斯腾湖西岸湖滨绿洲土壤含盐量高光谱估算".中山大学学报. 自然科学版 59.4(2020):56-63.