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.
Research on Estimation Model of Winter Wheat Leaf Area Index based on Spectral and Texture Features of Sentinel-2A Image
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(R2=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.
Simple regression modelMultiple linear regression modelRandom forest regression modelWin-ter wheatLeaf Area Index(LAI)Sentinel-2A
NETL
NSTL
万方数据
