CAREER: Smart Sensing of Nitrogen for Precision Agriculture

About This Grant

Efficient nitrogen management is critical for sustaining U.S. agricultural productivity while reducing environmental pollution and economic losses associated with fertilizer overuse. Despite widespread adoption of precision agriculture tools such as drones and satellite imagery, farmers still lack the ability to detect nitrogen deficiency before visible symptoms appear, when yield losses are often already unavoidable. Because nitrogen stress first manifests as molecular-level changes within plants, early diagnosis requires direct measurements rather than external observations. This CAREER project addresses this need by developing a low-cost, environmentally sustainable sensor system that can monitor molecular signals in plants, soils, and water in real time, enabling timely and precise nitrogen management decisions. By improving the synchronization between nitrogen supply and crop demand, the project aims to enhance nitrogen use efficiency, reduce nitrogen losses, and support smart agriculture processes. The project integrates research with education by engaging K-12 students, undergraduate students, and farmers in hands-on sensor deployment, data analysis, and entrepreneurship training, thereby strengthening workforce development for a future with smart and sustainable agriculture that advances the nation’s health and prosperity. The goal of this project is to develop and validate an integrated, miniaturized, circular sensor suite capable of real-time, multiparametric monitoring of molecular-level nitrogen dynamics driven by Genetics/Environment/Management interactions. The research will advance microneedle-structured, multiplexed electrochemical sensors for in-plant, soil, and water measurements, fabricated using biodegradable and bioresorbable materials to enable sensor recycling and eliminate electronic waste. Field-scale experiments will be conducted to capture spatiotemporal nitrogen responses across crops, environments, and management practices. Machine Learning/Artificial Intelligence models will be developed to analyze sensor data, quantify nitrogen dynamics, and generate data-driven nitrogen recommendations. Together, these innovations will overcome the limitations of conventional laboratory-based and discrete sensing technologies, provide new insights into nitrogen cycling under real field conditions, and establish a scalable platform for sensor-driven precision and sustainable agriculture. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.