文献类型： 外文期刊

作者： Zhai, Qiang ¹ ; Ye, Chun ¹ ; Li, Shuang ³ ; Liu, Jizhong ¹ ; Guo, Zhiming ³ ; Chang, Ruzhi ³ ; Hua, Jing ⁴ ;

作者机构： 1.Nanchang Univ, Sch Mechatron Engn, Nanchang, Jiangxi, Peoples R China

2.Jiangxi Acad Agr Sci, Inst Agr Engn, Jiangxi Prov Engn Res Ctr Informat Technol Agr, Jiangxi Prov Engn Res Ctr Intelligent Agr Machine, Nanchang, Jiangxi, Peoples R China

3.Weichai Power Co Ltd, Weifang City, Shandong, Peoples R China

4.Jiangxi Agr Univ, Sch Software, Nanchang, Jiangxi, Peoples R China

期刊名称：PLOS ONE （ 影响因子：3.752； 五年影响因子：4.069 ）

ISSN： 1932-6203

年卷期： 2022 年 17 卷 11 期

页码：

收录情况： SCI

摘要： The nitrogen nutrition status affects the main factors of rice yield. In traditional rice nitrogen nutrition monitoring methods, most experts enter the farmland to observe leaf color and growth and apply an appropriate amount of nitrogen fertilizer according to the results. However, this method is labor- and time-consuming. To realize automatic rice nitrogen nutrition monitoring, we constructed the Jiangxi rice nitrogen nutrition monitoring model based on a convolution neural network (CNN) using the same region rice canopy image in different generation periods. Our CNN model was evaluated using multiple evaluation criteria (Accuracy, Recall, Precision, and F1 score). The results show that the same CNN model could distinguish the rice nitrogen nutrition status in different periods, which can completely realize the automatic discrimination of nitrogen nutrition status so as to guide the scientific nitrogen application of rice in this area. This will greatly improve the discrimination efficiency of the nitrogen nutrition status and reduce the time and labor cost. The application of the proposed method also proved that the CNN model can be applied in the discrimination of the nitrogen nutrition status. Among CNN models, GoogleNet model proposed a CNN architecture named Inception which can improve the depth of the network and extract higher-level features without changing the amount of calculation of the model. The GoogleNet model achieved the highest accuracy, 95.7%.