New Drone Tech Could Revolutionize Sesame Farming Amid Climate Challenges

Scientists have developed a drone-based system that can detect nitrogen and water deficiencies in sesame crops with unprecedented accuracy, ...

Qodobada Muhiimka ah

  • By Pesach Benson • June 30, 2025   Jerusalem, 30 June, 2025 (TPS-IL) — Scientists have developed a drone-based system that can detect nitrogen and water deficiencies in sesame crops with unprecedented accuracy, offering a smarter and more sustainable approach to farming, the Hebrew University of Jerusalem announced on Monday.
  • While traditional remote sensing techniques could only detect combined nitrogen and water deficiencies with 40–55% accuracy, the team’s new approach boosted that figure to between 65% and 90%, thanks to a custom-built deep learning model trained on multimodal imagery.

Jerusalem, 30 June, 2025 (TPS-IL) — Scientists have developed a drone-based system that can detect nitrogen and water deficiencies in sesame crops with unprecedented accuracy, offering a smarter and more sustainable approach to farming, the Hebrew University of Jerusalem announced on Monday. The innovation combines hyperspectral, thermal, and RGB imaging with artificial intelligence to monitor crop stress more effectively than traditional methods.

Led by Dr. Ittai Herrmann the study was conducted in collaboration with Virginia State University, the University of Tokyo, and Israel’s Volcani Institute. The Volcani Institute is the Ministry of Agriculture’s research arm. The findings were published in the peer-reviewed ISPRS Journal of Photogrammetry and Remote Sensing.

“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.”

Field tests were carried out at the Experimental Farm of the Robert H. Smith Faculty of Agriculture in Rehovot. Researchers cultivated sesame plants under varying levels of irrigation and nitrogen. Rom Tarshish, an MSc student involved in the project, collected plant traits and leaf-level spectral data. Dr. Maitreya Mohan Sahoo later processed the drone imagery using machine learning techniques to generate detailed maps of plant health indicators, such as leaf nitrogen and water content.

The results marked a major advance. While traditional remote sensing techniques could only detect combined nitrogen and water deficiencies with 40–55% accuracy, the team’s new approach boosted that figure to between 65% and 90%, thanks to a custom-built deep learning model trained on multimodal imagery.

This research is particularly significant for sesame, a crop valued for its resilience to harsh conditions and its growing role in global food systems. The oilseed is not only rich in nutrients but is also gaining traction in areas where climate change is altering agricultural patterns.

“Our method offers real-time insights that could allow farmers to optimize fertilizer and water usage,” said Dr. Herrmann. “That means higher yields with fewer inputs—both economically and environmentally.”

The scientists said the system could be adapted for other crops.