【摘要】：葉綠素質(zhì)量分?jǐn)?shù)是評估冬小麥生長狀況和預(yù)測產(chǎn)量的重要參數(shù),估算葉綠素質(zhì)量分?jǐn)?shù)對于冬小麥的生長監(jiān)測具有重要意義。利用SPAD-502葉綠素儀和SVCHR 1024i型便攜式高光譜儀對冬小麥冠層葉綠素質(zhì)量分?jǐn)?shù)和光譜特征進(jìn)行田間測量,分別利用回歸分析方法和BP神經(jīng)網(wǎng)絡(luò)方法搭建冬小麥葉綠素質(zhì)量分?jǐn)?shù)的估算模型,并將模型估算的葉綠素質(zhì)量分?jǐn)?shù)與田間實(shí)測的葉綠素質(zhì)量分?jǐn)?shù)進(jìn)行對比,分析反演精度,從中篩選出精度最高的模型。結(jié)果表明:基于BP神經(jīng)網(wǎng)絡(luò)的冬小麥冠層葉綠素質(zhì)量分?jǐn)?shù)估算模型擬合精度要優(yōu)于其他7種基于植被指數(shù)的估算模型,其相關(guān)系數(shù)(R)為0.961 4,均方根誤差(RMSE)為1.875 4,相對誤差(RE)為2.815 2%,以及檢驗(yàn)方程的決定系數(shù)(R~2)為0.704 8,RMSE為1.744 6,RE為2.845 1%。研究結(jié)果為估測冬小麥冠層葉綠素質(zhì)量分?jǐn)?shù)提供參考,從而為冬小麥葉綠素質(zhì)量分?jǐn)?shù)的實(shí)時(shí)、快速、無損監(jiān)測奠定基礎(chǔ)。
[Abstract]:Chlorophyll content is an important parameter to evaluate the growth status of winter wheat and predict the yield. It is of great significance to estimate the chlorophyll mass fraction for the growth monitoring of winter wheat. The chlorophyll content and spectral characteristics of winter wheat canopy were measured by SPAD-502 chlorophyll meter and SVCHR 1024i portable high spectrometer. The estimation model of chlorophyll mass fraction of winter wheat was established by regression analysis and BP neural network method, and the chlorophyll mass fraction estimated by the model was compared with the measured chlorophyll mass fraction in the field, and the inversion accuracy was analyzed. The model with the highest accuracy is selected from it. The results showed that the fitting accuracy of the estimation model of chlorophyll content in winter wheat canopy based on BP neural network was better than that of the other seven estimation models based on vegetation index. The correlation coefficient (R) was 0.961, the root mean square error (RMSE) was 1.875 4, the relative error (RE) was 2.815 2%, and the determination coefficient (R 鈮，

本文編號：2505456