Enhanced Estimation of Rice Leaf Nitrogen Content via the Integration of Hybrid Preferred Features and Deep Learning Methodologies

• Published in: Agronomy (Basel) Vol. 14; no. 6; p. 1248
• Main Authors: Peng, Yiping, Zhong, Wenliang, Peng, Zhiping, Tu, Yuting, Xu, Yanggui, Li, Zhuxian, Liang, Jianyi, Huang, Jichuan, Liu, Xu, Fu, Youqiang
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.06.2024
• Subjects: Accuracy; Agricultural practices; Agricultural sciences; Algorithms; Artificial neural networks; Correlation coefficient; Correlation coefficients; Crop management; Cultivation; Data mining; Deep learning; Drone aircraft; feature optimization; Fertilization; Fertilizers; Grain cultivation; Hyperspectral imaging; leaf nitrogen content (LNC); Least squares method; Leaves; Machine learning; Methods; Neural networks; Nitrogen; Performance prediction; Regression analysis; Rice; Spatial distribution; Statistical analysis; Statistical methods; Statistical models; Support vector machines; Sustainable agriculture; UAV hyperspectral; Unmanned aerial vehicles; Variables; Vegetation; China

Efficiently obtaining leaf nitrogen content (LNC) in rice to monitor the nutritional health status is crucial in achieving precision fertilization on demand. Unmanned aerial vehicle (UAV)-based hyperspectral technology is an important tool for determining LNC. However, the intricate coupling between...