Pan Yuanyuan, Li Jingyu, Zhang Jiayi, He Jiaoyang, Zhang Zhihao, Yao Xia, Cheng Tao, Zhu Yan, Cao Weixing, Tian Yongchao
National Engineering and Technology Center for Information Agriculture, Engineering and Research Center of Smart Agriculture (Ministry of Education), Key Laboratory for Crop System Analysis and Decision Making (Ministry of Agriculture and Rural Affairs), Jiangsu Key Laboratory for Information Agriculture, Jiangsu Collaborative Innovation Center for Modern Crop Production, Nanjing Agricultural University, Nanjing 210095, China.
Jiangsu Academy of Agricultural Sciences Wuxi Branch, Wuxi 214174, China.
Plant Phenomics. 2024 Dec 5;6:0276. doi: 10.34133/plantphenomics.0276. eCollection 2024.
The accuracy of leaf nitrogen accumulation (LNA) estimation is often compromised by the vertical heterogeneity of crop nitrogen. In this study, an estimation model of LNA considering vertical heterogeneity of wheat was developed based on unmanned aerial vehicle (UAV) multispectral data and near-ground hyperspectral data, both collected at different view zenith angles (e.g., 0°, -30°, and -45°). Winter wheat plants were evenly divided into 3 layers from top to bottom, and LNA was obtained for the upper, middle, and lower leaf layers, as well as for various combinations of these layers (upper and middle, middle and lower, and the entire canopy, referred to as LNA). The linear regression (LR) and random forest regression (RF) models were constructed to estimate the LNA for each individual leaf layer. Subsequently, models for estimating LNA that considered the impact of vertical heterogeneity (namely, LR-LNA and RF-LNA) were established based on the relationships between LNA and LNA in different leaf layers. Meanwhile, LNA models that did not consider the effect of vertical heterogeneity (LR-LNA and RF-LNA) were used for comparative validation. The validation datasets consisted of UAV-simulated data from hyperspectral reflectance and UAV-measured data. Results showed that LNA models had markedly higher accuracy compared to LNA. The optimal scheme for estimating LNA was the combination of the upper, middle, and lower layers based on the normalized difference red edge index. Among these models, RF-LNA demonstrated higher accuracy than LR-LNA, with a validation relative root mean square error of 19.3% and 17.8% for the UAV-measured and simulated dataset, respectively.
叶片氮素积累量（LNA）估算的准确性常常受到作物氮素垂直异质性的影响。本研究基于无人机（UAV）多光谱数据和近地高光谱数据，开发了一种考虑小麦垂直异质性的LNA估算模型，这些数据均在不同的观测天顶角（如0°、-30°和-45°）下采集。冬小麦植株从顶部到底部被均匀分为3层，并获取了上部、中部和下部叶层以及这些叶层的各种组合（上部和中部、中部和下部以及整个冠层，称为LNA）的LNA。构建了线性回归（LR）和随机森林回归（RF）模型来估算每个单独叶层的LNA。随后，基于不同叶层的LNA与LNA之间的关系，建立了考虑垂直异质性影响的LNA估算模型（即LR-LNA和RF-LNA）。同时，使用未考虑垂直异质性影响的LNA模型（LR-LNA和RF-LNA）进行对比验证。验证数据集由高光谱反射率的无人机模拟数据和无人机测量数据组成。结果表明，与LNA相比，LNA模型的准确性显著更高。基于归一化差值红边指数估算LNA的最佳方案是上部、中部和下部叶层的组合。在这些模型中，RF-LNA的准确性高于LR-LNA，对于无人机测量数据集和模拟数据集，其验证相对均方根误差分别为19.3%和17.8%。
