Skip to main content
ARS Home » Midwest Area » Columbia, Missouri » Cropping Systems and Water Quality Research » Research » Publications at this Location » Publication #419910

Research Project: Innovative Cropping System Solutions for Sustainable Production on Spatially Variable Landscapes

Location: Cropping Systems and Water Quality Research

Title: Estimating corn leaf chlorophyll content using airborne multispectral imagery and machine learning

Author
item TIAN, FENGKAI - University Of Missouri
item ZHOU, JIANFENG - University Of Missouri
item Ransom, Curtis
item ALOYSIUS, NOEL - University Of Missouri
item Sudduth, Kenneth

Submitted to: Smart Agricultural Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/14/2024
Publication Date: 3/1/2025
Citation: Tian, F., Zhou, J., Ransom, C.J., Aloysius, N., Sudduth, K.A. 2025. Estimating corn leaf chlorophyll content using airborne multispectral imagery and machine learning. Smart Agricultural Technology. 10. Article 100719. https://doi.org/10.1016/j.atech.2024.100719
DOI: https://doi.org/10.1016/j.atech.2024.100719

Interpretive Summary: Chlorophyll content can be measured to indicate the health of a plant and fertilizer needs—especially nitrogen. The current method of measuring chlorophyll in corn plants is time-consuming, labor-intensive, and lacks detailed coverage, making it difficult for farmers to use chlorophyll content as a tool for managing nitrogen fertilizer decisions. Our study tested the use of drones equipped with high end cameras to estimate chlorophyll levels in corn leaves at different growth stages. By applying machine learning to the images captured by the drones, we developed a model that accurately predicts chlorophyll content without the need for manual measurements. This drone-based approach allows for quick, efficient, and detailed monitoring of crop health over large areas. By accurately mapping chlorophyll levels, farmers can make timely decisions about nitrogen fertilizer application, saving time and resources while potentially increasing crop yields.

Technical Abstract: Chlorophyll is crucial for photosynthesis and impacts plant growth and yield in crops. Accurate estimation of plant health and fertilizer status is essential for effective nitrogen (N) management in corn. However, crop chlorophyll is primarily quantified using handheld sensors, which is time-consuming, labor intensive and of low spatial resolution. This study aimed to evaluate an airborne multispectral imaging system in estimating the chlorophyll content of corn leaves at four vegetative growth stages. Three replicates of 12 nitrogen rates (between 0 and 285 kg ha-1) were applied to corn at V4 growth stage. Soil apparent electrical conductivity (ECa) of all test plots was measured before planting and corn leaf chlorophyll content was measured using a commercial handheld chlorophyll meter at four growth stages (V8, V9, V11 and V12). An unmanned aerial vehicle (UAV) - based multispectral camera collected imagery at the same time as chlorophyll readings. Machine learning models developed based on image features derived from UAV images were used to predict leaf chlorophyll content. Results showed that an epsilon support vector regression model with a sequential forward feature selection achieved the best performance (R^2 = 0.87, MAE = 1.80, and RMSE = 2.26 chlorophyll units). There was no significant difference in model performance across the four growth stages. By utilizing the developed model, researchers and growers can effectively map the chlorophyll content of corn leaves at different growth stages, enabling them to make timely and informed management decisions.