Enhancing In-Season Nitrogen Management in Corn Using UAS-based Remote Sensing and Soil Data Integration

Issue

Managing nitrogen fertilizer in corn is a challenge for farmers. Too much or poorly timed nitrogen leads to water pollution, greenhouse gas emissions and wasted input costs. Traditional approaches, like applying a fixed amount of fertilizer early in the season, do not account for how crop needs change over time or how soils vary across a field. Remote sensing tools exist but are often limited, since they only use one type of data and cannot fully capture the relationship between the crop, soil, and environment.

Objective

This project aims to improve how nitrogen is managed in corn by developing and testing a new tool, the Crop Nitrogen Vigor Index (CNVI). The CNVI will combine aerial imagery from drones (including canopy structure and crop “greenness”) with soil data to more accurately measure a crop’s nitrogen needs. The specific goals are to:

1. Build the CNVI tool using drone-based canopy and soil measurements.
2. Test two ways to calibrate the tool—using high-nitrogen strips in fields and using “virtual” calibration based on crop reflectance data.
3. Compare CNVI to existing nitrogen models to see if it better predicts crop nitrogen status.
4. Apply nitrogen at variable rates based on CNVI and compare outcomes with conventional uniform applications.
5. Measure effects on yield, nitrogen use efficiency and environmental impacts.
6. Explore how drone data could be scaled up to satellite imagery for broader use.

Approach

The project will take place on Iowa State University research farms across different soil and management conditions. Researchers will:

• Use drones equipped with LiDAR and multispectral cameras to collect crop data at key growth stages.
• Collect soil and plant samples to measure nitrogen levels and validate the tool.
• Apply nitrogen fertilizer using both traditional and CNVI-based recommendations, comparing yields, efficiency and environmental indicators like soil nitrate.
• Test machine learning models to link remote sensing data with crop nitrogen needs.
• Compare drone data with satellite imagery to evaluate the potential for larger-scale adoption.

The results will be shared with farmers, agronomists and industry partners through field days, extension programs, digital platforms and scientific publications. The long-term goal is to create a practical, science-based tool that helps farmers improve profitability while reducing nitrogen losses to the environment.