Sun Chuanliang, Zhang Weixin, Zhao Genping, Wu Qian, Liang Wanjie, Ren Ni, Cao Hongxin, Zou Lidong
Department of Digital Technology, Institute of Agriculture Information, Jiangsu Academy of Agricultural Sciences, Nanjing, China.
School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand.
Front Plant Sci. 2024 Dec 6;15:1504119. doi: 10.3389/fpls.2024.1504119. eCollection 2024.
Aboveground biomass (AGB) is a key indicator of crop nutrition and growth status. Accurately and timely obtaining biomass information is essential for crop yield prediction in precision management systems. Remote sensing methods play a key role in monitoring crop biomass. However, the saturation effect makes it challenging for spectral indices to accurately reflect crop changes at higher biomass levels. It is well established that rapeseed biomass during different growth stages is closely related to phenotypic traits. This study aims to explore the potential of using optical and phenotypic metrics to estimate rapeseed AGB. Vegetation indices (VI), texture features (TF), and structural features (SF) were extracted from UAV hyperspectral and ultra-high-resolution RGB images to assess their correlation with rapeseed biomass at different growth stages. Deep neural network (DNN), random forest (RF), and support vector regression (SVR) were employed to estimate rapeseed AGB. We compared the accuracy of various feature combinations and evaluated model performance at different growth stages. The results indicated strong correlations between rapeseed AGB at the three growth stages and the corresponding indices. The estimation model incorporating VI, TF, and SF showed higher accuracy in estimating rapeseed AGB compared to models using individual feature sets. Furthermore, the DNN model (R = 0.878, RMSE = 447.02 kg/ha) with the combined features outperformed both the RF (R = 0.812, RMSE = 530.15 kg/ha) and SVR (R = 0.781, RMSE = 563.24 kg/ha) models. Among the growth stages, the bolting stage yielded slightly higher estimation accuracy than the seedling and early blossoming stages. The optimal model combined DNN with VI, TF, and SF features. These findings demonstrate that integrating hyperspectral and RGB data with advanced artificial intelligence models, particularly DNN, provides an effective approach for estimating rapeseed AGB.
地上生物量（AGB）是作物营养和生长状况的关键指标。在精准管理系统中，准确及时地获取生物量信息对于作物产量预测至关重要。遥感方法在监测作物生物量方面发挥着关键作用。然而，饱和效应使得光谱指数在较高生物量水平下准确反映作物变化具有挑战性。众所周知，不同生长阶段的油菜生物量与表型性状密切相关。本研究旨在探索利用光学和表型指标估算油菜AGB的潜力。从无人机高光谱和超高分辨率RGB图像中提取植被指数（VI）、纹理特征（TF）和结构特征（SF），以评估它们与不同生长阶段油菜生物量的相关性。采用深度神经网络（DNN）、随机森林（RF）和支持向量回归（SVR）估算油菜AGB。我们比较了各种特征组合的准确性，并评估了不同生长阶段的模型性能。结果表明，三个生长阶段的油菜AGB与相应指数之间存在强相关性。与使用单个特征集的模型相比，结合VI、TF和SF的估算模型在估算油菜AGB方面表现出更高的准确性。此外，具有组合特征的DNN模型（R = 0.878，RMSE = 447.02 kg/ha）优于RF模型（R = 0.812，RMSE = 530.15 kg/ha）和SVR模型（R = 0.781，RMSE = 563.24 kg/ha）。在生长阶段中，抽薹期的估算准确率略高于苗期和初花期。最优模型将DNN与VI、TF和SF特征相结合。这些发现表明，将高光谱和RGB数据与先进的人工智能模型（特别是DNN）相结合，为估算油菜AGB提供了一种有效的方法。
