ASABE Technical Library - Abstract

Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, view access and subscription options

AI-Driven Nitrogen Management Using Crop as Biosensor

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2026 ASABE Annual International Meeting  2601005.(doi:10.13031/aim.202601005)
Authors:   Ahmed Abdalla, Salman Mirzaee, Ali Mirzakhani Nafchi
Keywords:   Artificial Intelligence, Biosensors, N-Rich Spots, Variability

Abstract. Spatial and temporal variability in crop nitrogen (N) response often limits the effectiveness of traditional uniform and rule-based N recommendation methods. This study evaluated AI-driven N-Rich Spots (NRS) using crops as Biosensor, an in-season decision-support and framework for adaptive N management in corn production. Static field information, including grid-based soil sampling at multiple spatial resolutions and soil-based sensor data (apparent electrical conductivity, ECa), was first used to characterize soil variability and delineate management zones. Within each zone, NRS biosensors were strategically established acting as in-field references representing response to N. Crop growth and N response inside and outside the biosensor spots were quantified using vegetation indices derived from satellite and UAV-based remote sensing. These multi-source datasets were integrated using AI-based analytical workflows to compare relative crop performance, estimate zone-specific N demand, and generate variable-rate N prescription maps. The NRBS approach successfully captured both spatial and temporal differences in the response of the N and provided actionable in-season N recommendations. Results demonstrate that integrating static soil information, real-time crop sensing, and AI-driven analytics enables a robust and scalable N management strategy. By directly using the crop as a biosensor, the NRS framework improves N use efficiency while supporting environmentally and economically sustainable fertilization decisions.

(Download PDF)    (Export to EndNotes)