Avocado drones track nitrogen fruit quality and yield tree by tree

An international research team has developed a precision monitoring system for avocado production capable of linking nitrogen use with yield and fruit quality at the individual tree level.

The framework combines UAV multispectral imagery LiDAR based canopy measurements and environmental variables such as temperature vapor pressure deficit and evapotranspiration through an explainable machine learning approach.

The study addresses one of the major challenges in perennial orchard management the absence of integrated systems able to connect nitrogen dynamics canopy structure environmental conditions productivity and postharvest quality within a single analytical framework.

Research was conducted between 2022 and 2024 across three contrasting environments including a controlled lysimetric experiment in Gilat a semi arid commercial orchard in Kfar Menachem and a humid commercial orchard in Kabri.

Random Forest models achieved high accuracy when predicting leaf nitrogen concentration and canopy nitrogen content demonstrating reliable scaling from leaf level measurements to full canopy analysis.

The framework also delivered strong and consistent performance in avocado yield prediction across all study sites.

Regarding postharvest quality researchers found that late season nitrogen status canopy structure and weather conditions had a greater influence on fruit decay risk than fertilizer application alone.

The results additionally showed that nitrogen use efficiency reached its optimal level at intermediate fertilization inputs around N20 within the controlled experiment.

According to the authors this technological framework could support more precise nitrogen management strategies in avocado orchards while further validation across cultivars seasons and production regions will still be required.

Source

Grozdov, I., Erel, R., Baram, S., Alkan, N., Porat, T., Cohen, H., Bar Noy, Y., & Paz-Kagan, T. (2026). Precision management in avocado: UAV-based monitoring of nitrogen use efficiency, yield, and postharvest quality. 

https://www.sciencedirect.com/science/article/pii/S2772375526004016