基于Sentinel⁃2A影像光谱和纹理特征的冬小麦叶面积指数估算模型研究  

Research on Estimation Model of Winter Wheat Leaf Area Index based on Spectral and Texture Features of Sentinel-2A Image

作　　者：陈家华 张立福 黄长平 郎萍 康孝岩 CHEN Jiahua;ZHANG Lifu;HUANG Changping;LANG Ping;KANG Xiaoyan(Arerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院空天信息创新研究院,北京100094 [2]中国科学院大学,北京100049

出　　处：《遥感技术与应用》2024年第2期290-305,共16页Remote Sensing Technology and Application

基　　金：国家自然科学基金重点基金项目(41830108);国家自然科学基金重点基金项目(41971321);中国科学院前沿科学重点研究计划(ZDBS-LY-DQC012);中国科学院青年创新促进会优秀会员(Y2021047)资助。

摘　　要：叶面积指数(Leaf Area Index,LAI)是反映作物生长状态的重要指标,常用植被指数来反演。传统的反演模型大都是基于多变量的多元回归模型,而基于双变量的多元回归模型在LAI反演中的潜力还未被充分发掘。通过提取卫星影像的光谱特征和纹理特征,基于皮尔逊相关系数分析各个遥感特征与冬小麦LAI之间的相关性,利用简单回归模型(Simple Regression,SR)、多元线性回归模型(Multiple Linear Regression,MLR)和随机森林回归模型(Random Forest Regression,RFR)开展遥感特征与冬小麦LAI之间的关系模型构建反演研究,并结合精度指标(决定系数R2,均方根误差RMSE,相对均方根误差rRMSE)判定各反演模型的反演精度,以提出最优的反演模型。研究表明:①所有植被指数和部分纹理指数在反演LAI中取得了较好的反演效果(R2>0.6)。其中,通用归一化植被指数(Universal Normalized Vegetation Index,UNVI)在各植被指数中表现最好(R2=0.754,RMSE=0.606,rRMSE=12.99%)。除了部分波段的均值特征反演精度与植被指数相当外,大多数纹理特征反演冬小麦LAI的精度欠佳;②通过两两变量组合,得到了冬小麦LAI反演精度最高的双变量多元线性回归模型(R2=0.780,RMSE=0.573,rRMSE=12.29%);③在有多个输入变量(至少3种特征变量)的情况下,RFR的反演效果优于MLR。相较于纹理特征,纹理指数的反演性能更佳。研究结果可为后续基于卫星影像的大规模农作物LAI的监测工作提供一种新的思路与方法。Leaf Area Index(LAI)is an important indicator to reflect the growth state of crops,which is usually estimated by vegetation index.Traditional inversion models are mostly based on multivariate regression mod⁃els,while the potential of multivariate regression models based on bivariates in LAI inversion has not been fully explored.By extracting the spectral features and texture features of satellite images,the correlation between each remote sensing feature and winter wheat LAI was analyzed based on Pearson correlation coefficient.Using Simple Regression model(SR),Multiple Linear Regression model(MLR)and Random Forest Regression model(RFR),the relationship between remote sensing characteristics and LAI of winter wheat was studied.The inversion accuracy of each inversion model was determined by the accuracy index(determination coefficient R2,root mean square error RMSE,relative root mean square error rRMSE).Based on the above evaluation in⁃dicators,the optimal inversion model was proposed.The results showed:(1)All vegetation indexes and some texture indexes have achieved good inversion results in LAI inversion(R2>0.6).Among them,the Universal Normalized Vegetation Index performed the best among all vegetation indices(R^(2)=0.754,RMSE=0.606,rRMSE=12.99%).Except for the mean feature inversion accuracy of some bands that is comparable to vegeta⁃tion index,the accuracy of most texture feature inversion for the winter wheat LAI is poor;(2)The bivariate multivariate linear regression model with the highest LAI inversion accuracy for winter wheat was obtained through bivariate combination(R2=0.780,RMSE=0.573,rRMSE=12.29%);(3)In the case of multiple in⁃put variables(at least 3 feature variables),RFR performed better than MLR.Compared to texture features,the inversion performance of texture indices was better.The research results can provide a new approach and method for monitoring large-scale crop LAI based on satellite imagery in the future.

关 键 词：简单回归模型 多元线性回归模型 随机森林回归模型 冬小麦 LAI Sentinel⁃2A 

分 类 号：S512[农业科学—作物学] TP79[自动化与计算机技术—检测技术与自动化装置]