Estimation of Chlorophyll Content in Winter Wheat Based on UAV Hyperspectral

文献类型： 外文期刊

第一作者： Feng Hai-kuan

作者： Feng Hai-kuan;Tao Hui-lin;Zhao Yu;Fan Yi-guang;Yang Gui-jun;Feng Hai-kuan;Yang Fu-qin

作者机构：

关键词： Winter wheat; Chlorophyll content; Vegetation index; Red edge parameter; Partial least squares regression

期刊名称：SPECTROSCOPY AND SPECTRAL ANALYSIS （ 影响因子：0.609； 五年影响因子：0.516 ）

ISSN： 1000-0593

年卷期： 2022 年 42 卷 11 期

页码：

收录情况： SCI

摘要： Chlorophyll content (SPAD) is a vital index for crop growth evaluation, which can monitor the growth of crops and is crucial for agricultural management, so it is important to estimate SPAD quickly and accurately. In this study, the remote sensing images of the jointing, flagging, and flowering stages were acquired using UAV hyperspectral for winter wheat. The vegetation indices and red edge parameters were extracted to explore the ability of vegetation indices and red edge parameters to estimate SPAD. Firstly, the vegetation indices and red edge parameters were correlated with the SPAD of different fertility stages. Then, the SPAD was estimated based on the vegetation indices, vegetation indices combined with red edge parameters , and using partial least square regression (PLSR) method. Finally, the SPAD distribution map was produced to verify the validity of the model. The results showed that (1) most of the vegetation indices and red edge parameters were correlated with SPAD at highly significant levels (0. 01 significant) in all three major reproductive stages; (2) the SPAD estimation model constructed from individual vegetation index had the best performance for LCI among vegetation indexes (best R-2 = 0. 56 , RMSE= 2. 96, NRMSE=8. 14%) and Dr/Dr min performed best (best R-2 = 0. 49 , RMSE= 3. 18, NRMSE= 8. 76%) ; (3) SPAD estimation model based on vegetation indices combined with red edge parameters was the best and better than SPAD estimation model based on vegetation indices only. Meanwhile, both models reached the highest accuracy at the flowering stage as the fertility stage progressed, with R-2 of 0. 73 and 0. 78, RMSE of 2. 49 and 2. 22, and NRMSE of 5. 57% and 4. 95% , respectively. Therefore, based on the vegetation indices combined with the red edge parameters, using the PLSR method can improve the estimation effect of SPAD, which can provide a new method for SPAD monitoring based on UAV remote sensing, and also provide a reference for agricultural management.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序