Exploring the Best Hyperspectral Features for LAI Estimation Using Partial Least Squares Regression
Exploring the Best Hyperspectral Features for LAI Estimation Using Partial Least Squares Regression
复制标题
DOI：
10.3390/rs6076221
复制
发表时间：
2014-07-01
期刊：
影响因子：
5
通讯作者：
Yang, Guijun
中科院分区：
文献类型：
--
作者：
Li, Xinchuan;Zhang, Youjing;Yang, Guijun
利用光谱特征估计叶面积指数（LAI）是高光谱数据的一项具有挑战性的任务。在这项研究中，选择冬小麦的高光谱反射率来优化光谱特征的选择，并评估它们在2008年和2009年不同生长阶段模拟叶面积指数的性能。我们使用不同的技术提取高光谱特征，包括反射光谱和一阶导数光谱，吸收和反射的位置和植被指数。为了找到具有最佳预测精度的最佳特征子集，采用偏最小二乘回归（PLSR）和投影变量重要性（VIP）来估计LAI值。结果表明，红边近红外光谱区（680 nm ~ 1300 nm）对叶面积指数最为敏感。该区域的大部分特征与叶面积指数（LAI）有很高的相关性，VIP值较高，尤其是750 nm处的一阶导数波段（r = 0.900，VIP = 1.144）。添加大量的特征不会显著提高PLSR模型的准确性。基于具有最高VIP值的14个特征的PLSR模型在验证数据集上预测LAI，平均自举R-2值为0.880，平均RMSE为0.943，并且产生的估计LAI结果优于此结果，包括整个54个特征数据集，平均R-2为0.875，平均RMSE为0.965。因此，本研究的结果表明，使用VIP值的最佳功能只有少数是足够的叶面积指数估计。
The use of spectral features to estimate leaf area index (LAI) is generally considered a challenging task for hyperspectral data. In this study, the hyperspectral reflectance of winter wheat was selected to optimize the selection of spectral features and to evaluate their performance in modeling LAI at various growth stages during 2008 and 2009. We extracted hyperspectral features using different techniques, including reflectance spectra and first derivative spectra, absorption and reflectance position and vegetation indices. In order to find the best subset of features with the best predictive accuracy, partial least squares regression (PLSR) and variable importance in projection (VIP) were applied to estimated LAI values. The results indicated that the red edge-NIR spectral region (680 nm-1300 nm) was the most sensitive to LAI. Most features in this region exhibited a high correlation with LAI and had higher VIP values, especially the first derivative waveband at 750 nm (r = 0.900, VIP = 1.144). Adding a large number of features would not wsignificantly improve the accuracy of the PLSR model. The PLSR model based on the fourteen features with the highest VIP values predicted LAI with a mean bootstrapped R-2 value of 0.880 and a mean RMSE of 0.943 on the validation dataset and produced an estimated LAI result better than that, including the entire 54-feature dataset with a mean R-2 of 0.875 and a mean RMSE of 0.965. The results of this study thus suggest that the use of only a few of the best features by VIP values is sufficient for LAI estimation.