Hyperspectral sensors offer real-time understanding of crop nitrogen status

Farmers across the country utilize nitrogen fertilizers to increase crop yield. As input costs and pollution concerns rise, farmers are looking for ways to pinpoint the perfect application amount.

In a recently published study, a research team at the University of Illinois used hyperspectral sensors on planes to understand the real-time nitrogen status of a corn crop.

"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, lead author on the study, in a news release. "It also provides much higher spectral and spatial resolution than similar studies using satellite imagery."

The plane and sensor flew over an experimental field three times during the 2019 growing season. The sensor, capable of detecting wavelengths in the visible and near-infrared spectrum, detected leaf and canopy nitrogen characteristics with up to 85% accuracy.

"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," Wang said.

Nitrogen and chlorophyll content subtly change the amount of energy reflected off the ground. With hyperspectral sensors, researchers were able to detect differences of just 3 to 5 nanometers across their entire range.

"Other airborne remote sensing technologies pick up the visible spectrum and possibly near-infrared, just four spectral bands. That's not even close to what we can do with this hyperspectral sensor. It's really powerful," said Kaiyu Guan, co-author on the study, in a news release.

The researchers believe data from hyperspectral sensors can be used with the Maximum Return To Nitrogen (MRTN) corn nitrogen rate calculator.

"Under our approach, we can detect the nitrogen status of the crop and make some real-time adjustments for the agricultural stakeholders," Wang said. "MRTN provides recommended nitrogen fertilization rates based on the economic trade-off between soil nitrogen fertilizer rates and end-of-season yield. Our remote-sensing approach can feed plant nutrient status into the MRTN system, enabling real-time crop nitrogen management. It can potentially shift the current recommendations based on pre-growing season, soil-centric fertilization to a diagnosis based on real-time plant nutrition, improving agroecosystem nitrogen use efficiency."

An algorithm developed by the team to detect nitrogen reflectance data from the hyperspectral sensor may be used on future technology.

"NASA is planning a new satellite hyperspectral mission, as are other commercial satellite companies," Wang said. "Our study can potentially provide the algorithm for those missions because we already demonstrated its accuracy in the aircraft hyperspectral data."

The end goal is to outfit satellites with the sensors, allowing farmers to see their food nutrient status early in the growing season. The result would be more informed decisions about nitrogen side dressing and ultimately improved environmental sustainability in agronomic systems.

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