Data-Driven Approach for Monitoring Corn Biomass

This research article presents an integrative data-driven approach for monitoring corn biomass using UAV-based imagery. The study evaluates the effectiveness of 13 spectral indices across five groups under varying irrigation water and nitrogen fertilizer levels. Conducted at Urmia University, Iran, the research utilized a randomized complete block design with three irrigation levels during four replications. A fixed-wing UAV equipped with a Sequoia sensor captured aerial imagery at three growth stages: stem elongation, flowering, and silking. Variance decomposition analysis was employed to examine the impact of irrigation and nitrogen levels on vegetation indices and biomass. The study found that indices based on near-infrared and red-edge spectral bands performed best, with the MERIS terrestrial chlorophyll index achieving the highest accuracy in biomass estimation. Bayesian model averaging models were proposed to enhance biomass estimation accuracy by leveraging various vegetation indices. This research contributes to precision agriculture by improving biomass monitoring methodologies.