A new study unveils an advanced drone-based system that offers, for the first time, a smarter way to monitor sesame health. By combining hyperspectral, thermal, and RGB imagery with deep learning, researchers have developed a powerful method for detecting simultaneous nitrogen and water deficiencies in field-grown sesame. This innovative approach leverages cutting-edge UAV-imaging technology and artificial intelligence to improve the accuracy of stress detection in crops. The integration of multiple data sources enables identification of combined nutrient and water-related deficiencies. This significant step forward in the field of precision farming not only enhances crop management but also supports more sustainable and efficient use of water and fertilizers, key components in building climate-resilient food systems.
[Hebrew University of Jerusalem]– A team of researchers led by Dr. Ittai Herrmann at The Hebrew University of Jerusalem in collaboration with Virginia State University, University of Tokyo and the Volcani Institute, has applied an advanced drone-based system that accurately detects combined nitrogen and water deficiencies in field-grown sesame paving the way for more efficient and sustainable farming.
Published in the ISPRS Journal of Photogrammetry and Remote Sensing, the study showcases how unmanned aerial vehicles (UAVs) equipped with hyperspectral, thermal, and RGB sensors can work in tandem with artificial intelligence models to diagnose complex crop stress scenarios. Traditional remote sensing methods often fall short in detecting combined environmental stresses like water and nutrient shortages. This study is among the first to successfully address this challenge in an indeterminate crop such as sesame.
“By integrating data from multiple UAV-imaging sources and training deep learning models to analyze it, we can now distinguish between stress factors that were previously challenging to tell apart,” said Dr. Herrmann. “This capability is vital for precision agriculture and for adapting to the challenges of climate change.”
The team’s multimodal ensemble approach improved classification accuracy of combined nutrient and water stress from just 40–55% using conventional methods to an impressive 65–90% with their custom-developed deep learning system.
The field experiment was conducted at the Experimental Farm of Robert H. Smith Faculty of Agriculture in Rehovot. Seeds were supplied by Prof, Zvi Peleg. Rom Tarshish, an MSc student at the time, grew sesame plants under varied irrigation and nitrogen treatments and acquired plant traits and leaf level spectral data. Dr. Maitreya Mohan Sahoo analyzed the UAV-imagery through machine learning pipelines to generate maps of leaf nitrogen content, water content, and other physiological traits, which helped identify early stress markers.
Sesame, a climate-resilient oilseed crop with growing global demand, was chosen due to its nutritional importance and potential for expansion into new agro-ecosystems. This new remote-sensing method may enable growers to reduce fertilizer and water use while maintaining yield, improving both economic and environmental outcomes.