狗牙根叶片相对含水量高光谱反演估算  

Estimation of relative water content in bermudagrass leaves based on hyperspectroscopy

作　　者：喻启坤 李雯 汤丽斯 韩宇 李培英[1,2,3] 孙宗玖 YU Qi-kun;LI Wen;TANG Li-si;HAN Yu;LI Pei-ying;SUN Zong-jiu(Grassland College,Xinjiang Agricultural University,Urumqi 830052,China;Xinjiang Key Laboratory of Grassland Resources and Ecology,Urumqi 830052,China;Key Laboratory of Grassland Resources and Ecology of the Ministry of Education of the Western Arid Zone,Urumqi 830052,China)

机构地区：[1]新疆农业大学草业学院,新疆乌鲁木齐830052 [2]新疆草地资源与生态自治区重点实验室,新疆乌鲁木齐830052 [3]西部干旱区草地资源与生态教育部重点实验室,新疆乌鲁木齐830052

出　　处：《草业学报》2024年第12期59-72,共14页Acta Prataculturae Sinica

基　　金：新疆维吾尔自治区重点研发项目(2023B02031-1);国家自然科学基金(31960362)资助。

摘　　要：为了探讨高光谱技术在监测植物受干旱胁迫程度及筛选抗旱材料中的应用,以18个狗牙根基因型为材料,进行为期12 d的自然干旱,测定各材料土壤含水量和叶片相对含水量,同时利用美国SVC HR-768便携式光谱仪,获取不同干旱时间各材料的高光谱相片,以经过高光谱SG平滑和SG平滑+一阶导数结合处理的光谱反射率作为自变量,经Pearson相关性分析和连续投影筛选与叶片相对含水量相关性较好且各材料共有的特征波段,并利用方差膨胀因子检验其共线性,之后通过BP神经网络、支持向量机和随机森林3种机器学习算法建立狗牙根叶片相对含水量的反演模型。结果表明:1)通过连续投影算法共筛选出5个SG平滑+一阶导数特征波段,分别为406、569、706、736、786 nm,与叶片相对含水量的相关性较高(P>0.5),且波段间共线性较弱,可作为抗旱监测的敏感波段。2)以敏感波段为基础建立的随机森林反演模型,决定系数(R^(2))和均方根误差(RMSE)分别为0.939和8.552,相较于支持向量机和BP神经网络,R^(2)分别提高了5%和8%,表现出最好的预测效果和普适性,其测试集的R^(2)为0.925,RMSE为9.008。研究结果可为未来利用高光谱进行广谱性狗牙根叶片相对含水量无损高精监测提供技术支撑。Hyperspectral techniques have been widely used to monitor the degree of drought stress and screen for drought-resistant plant materials.In this study,18 bermudagrass genotypes were subjected to natural drought for 12 days.The soil water content and leaf relative water content of each material were determined,and hyperspectral photos were obtained at different timepoints during the drought treatment using an SVC HR-768 portable spectrometer.The spectral reflectance,which was processed using a combination of hyperspectral Savitzkye Golay smoothing and Savitzkye Golay smoothing+first derivative,was used as the independent variable,and characteristic bands that were well correlated with the relative water content of leaves and,on the basis of Pearson’s correlation and continuous projection analyses,were common among all the materials screened.Then,an inversion model of the relative water content of bermudagrass leaves was established using three machine-learning algorithms:the BP neural network,support vector machine,and random forest algorithms.The main results were as follows:1)Five Savitzkye Golay smoothing+first derivative characteristic bands were screened out using the continuous projection algorithm;the bands were located at 406,569,706,736,and 786 nm,respectively,and showed high correlations(P>0.5)with the relative water content of bermudagrass leaves.The covariance among the bands was weak,so these bands could be used as sensitive bands for drought monitoring.2)The coefficient of determination(R^(2))and root-mean-square error(RMSE)of the random forest inversion model based on the sensitive wavebands were 0.939 and 8.552,respectively,which were 5%and 8%higher,respectively,than those of the support vector machine and BP neural network models.Thus,the random forest inversion model showed the best prediction effect and universality.The R^(2) of the test set was 0.925,and the RMSE was 9.008.The results of our study provide technical support for the development of a non-destructive and high-precision method to m

关 键 词：狗牙根 不同基因型 叶片相对含水量 高光谱技术 

分 类 号：S688.4[农业科学—观赏园艺]