Winter wheat nitrogen estimation based on ground-level and UAV-mounted sensors

Authors: SONG, XIAOYU - Beijing Academy Of Agricultural Sciences; YANG, GUIJUN - Beijing Academy Of Agricultural Sciences; XU, XINGGANG - Beijing Academy Of Agricultural Sciences; ZHANG, DONGYAN - Beijing Academy Of Agricultural Sciences; Yang, Chenghai; FENG, HAIKUAN - National Engineering Research Center For Information Technology In Agriculture

Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/7/2022
Publication Date: 1/11/2022
Citation: Song, X., Yang, G., Xu, X., Zhang, D., Yang, C., Feng, H. 2022. Winter wheat nitrogen estimation based on ground-level and UAV-mounted sensors. Sensors. https://doi.org/10.3390/s22020549.
DOI: https://doi.org/10.3390/s22020549

Interpretive Summary: A better understanding of wheat nitrogen status is important for improving fertilizer management in precision farming. In this study, four sensors mounted on an unmanned aerial vehicle were evaluated for their ability to estimate winter wheat nitrogen. Advanced statistical methods were compared to identify the best combinations of vegetation indices from the sensors to estimate wheat leaf nitrogen concentration, plant nitrogen concentration, and the nutrition index. Analysis results revealed that different sensors provide varying estimation accuracies at different wheat growth stages. Optimal sensors and analysis methods were then identified for estimating these winter wheat nitrogen indicators across different growth stages. The results from this study provide practical guidance for the selection of ground-based and airborne sensors and for the extraction of nitrogen data from these sensors for estimating nitrogen status for precision management.

Technical Abstract: A better understanding of wheat nitrogen status is important for improving N fertilizer management in precision farming. In this study, four different sensors were evaluated for their ability on winter wheat nitrogen estimation. A Gaussian process regression (GPR) method with a sequential backward feature removal (SBBR) routine was used to identify the best combinations of vegetations indices (VIs) sensitive to wheat N indicators for different sensors. Wheat leaf N concentration (LNC), plant N concentration (PNC), and the nutrition index (NNI) were estimated by the VIs through parametric regression (PR), multivariable linear regression (MLR) and Gaussian process regression (GPR). The study results reveal that the optical fluorescence sensor provides more accurate estimates of winter wheat N status at a low canopy coverage condition. The Dualex Nitrogen Balanced Index (NBI) is the best leaf level indicators for wheat LNC, PNC and NNI at the early wheat growth stage. At the early growth stage, Multiplex indices are the best canopy level indicators for LNC, PNC, and NNI. At the late growth stage, ASD VIs provide ac-curate estimates for wheat N indicators. The study also reveals that the GPR with SBBR analysis method provides more accurate estimates of winter wheat LNC, PNC and NNI with best VI combinations for these sensors across the different winter wheat growth stages, compared with the MLR and PR methods.