干旱区生态环境知识资源中心(Arid): 基于实测高光谱和Sentinel-2B影像的银川平原土壤盐分反演

Arid

	基于实测高光谱和Sentinel-2B影像的银川平原土壤盐分反演
其他题名	Inversion of soil salinity in Yinchuan Plain based on measured hyperspectral data and Sentinel-2B images
	毛鸿欣; 贾科利; 张旭
来源期刊	云南大学学报. 自然科学版
ISSN	0258-7971
出版年	2021
卷号	43 期号:5 页码:929-941
中文摘要	土壤盐渍化是干旱半干旱区土壤资源损害、生境破坏和农业生产损失的重要影响因素,定量反演和监测盐渍化土壤,对防护土地生态安全具有重要意义.文章基于光谱变换筛选盐分特征波段和特征光谱指数,构建实测高光谱和Sentinel-2B影像的岭回归模型和偏最小二乘回归盐分反演模型,并以特征光谱指数为敏感参量进行星-地光谱匹配,构建匹配后盐分反演模型,实现银川平原土壤盐分定量反演.结果表明,盐分指数3(Salinity index 3, ${S_3}$)、强度指数l(Intensity index 1,${\rm{In}}{{\rm{t}}_1}$)和强度指数2(Intensity index 2, ${\rm{In}}{{\rm{t}}_2}$)能够实现实测高光谱端元到多光谱像元尺度的匹配,有效地提升模型精度;经光谱匹配后构建的偏最小二乘模型精度最高(${R^2} = 0.721$, ${\rm{RMSE}} = 4.856\;{\rm{g}} \cdot {\rm{k}}{{\rm{g}}^{ - 1}}$).相比单独利用影像建模,其${R^2}$提升了0.309,均方根误差(Root Mean Square Error, RMSE)减小了$2.085\;{\rm{g}} \cdot {\rm{k}}{{\rm{g}}^{ - 1}}$.盐分反演结果与实地采样具有较好一致性,表明特征光谱指数可为不同尺度遥感数据间光谱匹配与联合,实现地表点到空间面尺度盐渍化定量监测,为土壤盐分监测提供理论借鉴和实践参考.
英文摘要	Soil salinization in arid and semi-arid areas has a substantial negative influence on soil resources, eco-environment, and agricultural production. Quantitative inversion and monitoring of salinized soil can effectively protect land ecological security. Based on a spectral transformation method, indices of salinity characteristic bands and characteristic spectrum are derived, and salinity inversion models, including ridge regression (RR) and partial least square regression (PLSR) are constructed from measured hyperspectral and Sentinel-2B images. Characteristic spectrum indices are used as sensitive indices to match the Sentinel-2B images, the post-match salinity inversion models are constructed, and finally, soil salinity in Yinchuan Plain, Ningxia, China is quantitatively inverted and analyzed. The results show that the characteristic spectral indices of ${{\rm{S}}_3}$ (Salinity index, ${{\rm{S}}_3}$), ${\rm{In}}{{\rm{t}}_1}$ (Intensity index 1,${\rm{In}}{{\rm{t}}_1}$), and ${\rm{In}}{{\rm{t}}_2}$ (Intensity index 2,${\rm{In}}{{\rm{t}}_2}$) can realize the scale transition from measured hyperspectral cell to multispectral image pixel, which efficiently improves the accuracy of the salinity inversion model of multispectral image. The PLSR model after spectral matching can perform the best accuracy (${R^2} = 0.721$, ${\rm{RMSE}} = 4.856\;{\rm{g}} \cdot {\rm{k}}{{\rm{g}}^{ - 1}}$) of soil salinity inversion, with a 0.309 increment of ${R^2}$ and a $2.085\;{\rm{g}} \cdot {\rm{k}}{{\rm{g}}^{ - 1}}$ decrement of RMSE compared with the single Sentinel-2B image modeling. The result of salinity inversion is consistent with that from the field samplings, which demonstrates that characteristic spectrum indices contribute to spectral matching and fusion at different remote sensing image scales, and realize the quantitative monitoring of salinization from surface points to spatial dimensions, so the study could provide a theoretical and practical reference for soil salinity monitoring.
中文关键词	高光谱遥感 ; Sentinel-2B影像 ; 土壤盐分反演 ; 光谱变换 ; 光谱匹配 ; 银川平原
英文关键词	hyperspectral remote sensing Sentinel-2B soil salinity inversion spectral transformation spectral matching Yinchuan Plain
类型	Article
语种	中文
收录类别	CSCD
WOS类目	Agriculture
CSCD记录号	CSCD:7077324
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/378034
作者单位	毛鸿欣, 宁夏大学地理科学与规划学院, 银川, 宁夏 750021, 中国.; 贾科利, 宁夏大学地理科学与规划学院, 银川, 宁夏 750021, 中国.; 张旭, 宁夏大学地理科学与规划学院, 银川, 宁夏 750021, 中国.
推荐引用方式 GB/T 7714	毛鸿欣,贾科利,张旭. 基于实测高光谱和Sentinel-2B影像的银川平原土壤盐分反演[J],2021,43(5):929-941.
APA	毛鸿欣,贾科利,&张旭.(2021).基于实测高光谱和Sentinel-2B影像的银川平原土壤盐分反演.云南大学学报. 自然科学版,43(5),929-941.
MLA	毛鸿欣,et al."基于实测高光谱和Sentinel-2B影像的银川平原土壤盐分反演".云南大学学报. 自然科学版 43.5(2021):929-941.