Airborne hyperspectral imaging reveals nitrogen deficiency in crops

18 Jan 2022

University of Illinois study shows potential for such images to contribute to food production.

Despite advances in modern agriculture, overuse of fertilizers spurred by fears of low crop yield is a continuing source of damage to the environment.

Excess nitrogen from fertilizers ends up in groundwater and ultimately in the atmosphere as a component of greenhouse gases, so there is an urgent need for nondestructive and high spatial resolution monitoring of the nitrogen present in crops at any particular time.

A project at the University of Illinois at Urbana-Champaign (UIUC) has now demonstrated a way to accomplish this that could prove valuable for the agriculture industry, through airborne hyperspectral imaging.

As described in International Journal of Applied Earth Observation and Geoinformation, the UIUC team put hyperspectral sensors on planes as a route to quickly and accurately detecting nitrogen status and photosynthetic capacity in corn, said to be the first study of its kind.

The airborne platform employed two sensors with spectral ranges of 400 to 1000 and 950 to 2500 nanometers, effectively covering visible to shortwave infrared bands, and was designed to allow spatial resolution down to 0.5 meters.

"Field nitrogen measurements are very time- and labor-consuming, but the airplane hyperspectral sensing technique allows us to scan the fields very fast, at a few seconds per acre," said Sheng Wang from UIUC.

"It also provides much higher spectral and spatial resolution than similar studies using satellite imagery. Our approach fills a gap between field measurements and satellites and provides a cost-effective and highly accurate approach to crop nitrogen management in sustainable precision agriculture."

You can't manage what you can't measure

Deriving the data of interest from a crop's spectral response is not necessarily straightforward, and for this project the calculation involved the team taking in-field leaf and canopy measurements to provide the ground-truth data for comparison with airborne sensor data.

Computational methods taking account of leaf models, radiative transfer, viewing angles and time of day, plus data about the reflectance of both leaf canopy and soil, can then quantify critical crop traits including leaf chlorophyll content and nitrogen content at leaf and canopy scales. Nitrogen deficiency or surplus then be assessed.

The project flew three observational runs over an Illinois crop field, and successfully detected the important leaf and canopy nitrogen characteristics, including several related to photosynthetic capacity and grain yield, with up to 85 percent accuracy according to the team.

"That’s close to ground-truth quality,” said Kaiyu Guan of UIUC's Department of Natural Resources and Environmental Science. "We can even rely on the airborne hyperspectral sensors to replace ground-truth collection without sacrificing much accuracy. Meanwhile, airborne sensors allow us to cover much larger areas at low cost."

The precision of the airborne hyperspectral measurements will be crucial to the successful use of the technique in real-world agriculture, with UIUC looking to future satellite missions from both NASA and independent contractors as the ultimate location for such hyperspectral imaging platforms.

"You can't manage what you can't measure," said Guan. "That is why we put so much effort into this technology."