Qin Shizhe, Ding Yiren, Zhou Zexuan, Zhou Meng, Wang Hongyu, Xu Feng, Yao Qiushuang, Lv Xin, Zhang Ze, Zhang Lifu
Xinjiang Production and Construction Crops Oasis Eco-Agriculture Key Laboratory, Shihezi University College of Agriculture, Shihezi, China.
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China.
Front Plant Sci. 2023 Mar 1;14:1117277. doi: 10.3389/fpls.2023.1117277. eCollection 2023.
Precise monitoring of cotton leaves' nitrogen content is important for increasing yield and reducing fertilizer application. Spectra and images are used to monitor crop nitrogen information. However, the information expressed using nitrogen monitoring based on a single data source is limited and cannot consider the expression of various phenotypic and physiological parameters simultaneously, which can affect the accuracy of inversion. Introducing a multi-source data-fusion mechanism can improve the accuracy and stability of cotton nitrogen content monitoring from the perspective of information complementarity.
Five nitrogen treatments were applied to the test crop, Xinluzao No. 53 cotton, grown indoors. Cotton leaf hyperspectral, chlorophyll fluorescence, and digital image data were collected and screened. A multilevel data-fusion model combining multiple machine learning and stacking integration learning was built from three dimensions: feature-level fusion, decision-level fusion, and hybrid fusion.
The determination coefficients (R) of the feature-level fusion, decision-level fusion, and hybrid-fusion models were 0.752, 0.771, and 0.848, and the root-mean-square errors (RMSE) were 3.806, 3.558, and 2.898, respectively. Compared with the nitrogen estimation models of the three single data sources, R increased by 5.0%, 6.8%, and 14.6%, and the RMSE decreased by 3.2%, 9.5%, and 26.3%, respectively.
The multilevel fusion model can improve accuracy to varying degrees, and the accuracy and stability were highest with the hybrid-fusion model; these results provide theoretical and technical support for optimizing an accurate method of monitoring cotton leaf nitrogen content.
精确监测棉花叶片氮含量对于提高产量和减少肥料施用量至关重要。光谱和图像被用于监测作物氮信息。然而，基于单一数据源的氮监测所表达的信息有限，无法同时考虑各种表型和生理参数的表达，这可能会影响反演的准确性。引入多源数据融合机制可以从信息互补的角度提高棉花氮含量监测的准确性和稳定性。
对室内种植的试验作物新陆早53号棉花施加五种氮处理。收集并筛选棉花叶片高光谱、叶绿素荧光和数字图像数据。从特征级融合、决策级融合和混合融合三个维度构建了一个结合多种机器学习和堆叠集成学习的多级数据融合模型。
特征级融合、决策级融合和混合融合模型的决定系数（R）分别为0.752、0.771和0.848，均方根误差（RMSE）分别为3.806、3.558和2.898。与三种单一数据源的氮估计模型相比，R分别提高了5.0%、6.8%和14.6%，RMSE分别降低了3.2%、9.5%和26.3%。
多级融合模型可以不同程度地提高准确性，其中混合融合模型的准确性和稳定性最高；这些结果为优化准确监测棉花叶片氮含量的方法提供了理论和技术支持。
