Drones and AI offer faster corn health checks, study finds

Researchers at the University of Missouri have demonstrated that drones combined with artificial intelligence can assess the health of corn crops more efficiently than traditional field scouting methods, offering potential gains in fertilizer use and environmental management.

The study, conducted in mid-Missouri corn fields, used drones fitted with multispectral cameras to capture wavelengths such as near-infrared and red-edge light, which are linked to plant health but invisible to the human eye. By pairing these images with soil data and processing them through machine-learning models, the team estimated leaf chlorophyll levels — a key indicator of nitrogen status — across entire fields with high accuracy.

“Knowing the chlorophyll content of each plant helps farmers determine the right time, location and amount of nitrogen application,” said Jianfeng Zhou, associate professor in the College of Agriculture, Food and Natural Resources and co-director of research at Mizzou’s Digital Agriculture Research and Extension Center. “That can increase yields while reducing excess chemical use that impacts the environment.”

Corn is among the most nitrogen-demanding crops, making precise nutrient management a significant cost and sustainability issue. Over-application raises expenses and can lead to water pollution, while under-application can reduce yields.

The research team, led by doctoral student Fengkai Tian, noted that such monitoring could be delivered commercially by ag-tech service providers, allowing farmers to benefit without investing in drone operations or data processing capabilities. While the study focused on corn, the method could be adapted for other crops, including soybeans and wheat, with adjustments to account for different nutrient profiles.

The findings, published in Smart Agricultural Technology, were produced in collaboration with the U.S. Department of Agriculture’s Agricultural Research Service. The work reflects a wider push within precision agriculture to integrate remote sensing, AI and targeted input management to improve efficiency and reduce environmental impacts.