In the heart of Israel’s Hefer Valley, a revolution is brewing in the citrus orchards. Dagan Avioz, a researcher from the Technion – Israel Institute of Technology and the French Associates Institute for Agriculture and Biotechnology of Dryland, is leading a groundbreaking study that promises to transform how farmers manage nitrogen fertilization. By harnessing the power of unmanned aerial vehicles (UAVs) and satellite data, Avioz and his team are paving the way for more sustainable and efficient citrus farming practices.
Traditional methods of monitoring nitrogen levels in citrus orchards are labor-intensive and prone to error. Farmers often rely on frequent leaf and soil sampling, followed by time-consuming laboratory analysis. This not only drives up costs but also fails to capture the dynamic spatiotemporal variability of nitrogen content across different citrus cultivars. Avioz’s innovative approach aims to change this by integrating multispectral and temporal data from UAVs and Sentinel-2 satellites to estimate canopy nitrogen content (CNC) with unprecedented accuracy.
The study, conducted over three years, involved two phases. The first phase focused on four plots of the ‘Newhall’ cultivar, while the second phase expanded to include twelve additional plots featuring five different citrus cultivars. The methodology was meticulous, involving leaf sampling for laboratory nitrogen analysis, acquiring and preprocessing UAV and satellite images, and using Structure-from-Motion (SfM) photogrammetry to extract structural features of the trees.
One of the key innovations of this research is the use of Random Forest (RF) models to estimate CNC. By combining UAV-derived vegetation indices (VIs) and SfM data with Sentinel-2 VIs, the team was able to generate canopy-scale CNC heatmaps. “The integrated model showed superior performance compared to models relying solely on UAV-VIs or Sentinel-2 VIs,” Avioz explains. “This demonstrates the clear advantage of multi-platform data fusion over single-source approaches.”
The results are compelling. The integrated RF model achieved an R² value of 0.80 and a root mean square error (RMSE) of 0.17 kg/m², significantly outperforming models that used only UAV-VIs or Sentinel-2 VIs. Moreover, the study found a strong positive correlation between CNC and yield, highlighting the critical role of nitrogen dynamics in orchard productivity. “This research provides a scalable, data-driven framework to enhance nutrient management and support sustainable orchard practices,” Avioz notes.
The implications for the citrus industry are profound. By improving nitrogen use efficiency (NUE), farmers can reduce environmental impact while optimizing fertilization. This not only leads to healthier orchards but also to higher yields and better-quality fruit. The study, published in the journal ‘Intelligent Agricultural Technology’ (Smart Agricultural Technology translated to English), offers a blueprint for the future of precision agriculture.
As the world grapples with the challenges of climate change and resource scarcity, innovations like Avioz’s are more important than ever. By leveraging advanced remote sensing technologies, farmers can make data-driven decisions that promote sustainability and profitability. This research is a testament to the power of interdisciplinary collaboration and the potential of technology to revolutionize traditional industries.
The future of citrus farming is here, and it’s flying high above the orchards, capturing data that will shape the next generation of sustainable agriculture. As Avioz and his team continue to refine their methods, the citrus industry stands on the brink of a new era, one where precision and sustainability go hand in hand.