Potato growers must monitor the nitrogen status of their crop to fertilize in the most efficient and sustainable way possible. This is often done by collecting petioles – the parts of the plant that connect leaflets to stems – from numerous plants in each field. Growers mail petioles to a laboratory for nitrate analysis and wait for results. The system works but could be better, according to Yi Wang, an assistant professor and University of Wisconsin-Extension sustainable vegetable-production specialist.
“Collecting petioles is time-consuming and labor-intensive, and sometimes results can be misleading because a lot of factors can affect petiole nitrate numbers such as weather conditions or the time of day of sample collection,” she said. “And the results don’t catch spatial variation (of nitrogen needs) within the field.”
So she’s leading an effort to develop a set of tools that will give potato growers a potentially easier, faster and more comprehensive way to assess a crop’s nitrogen needs. The project involves collecting and processing data from a hyperspectral camera. The camera is mounted to an unmanned-aerial vehicle or low-flying airplane flown over potato-research plots grown with different nitrogen levels. Computer-assisted models have been developed to link the imagery with in-season plant-nitrogen status and end-of-season yield, quality and economic return.
“The goal is to help potato growers with their nitrogen management using a platform that blankets the entire field unlike the traditional petiole nitrate testing,” Wang said.
Hyperspectral cameras capture images that detect hundreds or thousands of spectral bands of sunlight reflected from the crop canopy.
“Factors that cause variation in canopy health such as nutrient status, water status or disease pressures are related to spectral reflectance and therefore can be visualized in hyperspectral images,” said Trevor Crosby, a graduate student who works on the project.
One flight over a 70-meter by 150-meter research field can collect dozens of images with hundreds of spectral bands. It takes time to crunch the data so the research team is looking to expedite image processing.
Wang is working with two collaborators. Phil Townsend, a professor in the forest and wildlife ecology department at UW-Madison, uses remote-sensing technologies. Paul Mitchell, a professor and UW-Extension agricultural economist, will help with economic analysis that informs the computer model’s nitrogen-application recommendations.
“Dr. Townsend’s group has created a program that makes image processing really efficient,” Wang said.
Crosby is collecting ground measurements, gathering data from research plots at different potato-growth stages. He’s studying leaf-area index, leaf and vine total nitrogen content, and environmental factors such as soil moisture and temperature, solar radiation, and wind speed. At harvest, he’ll measure total tuber yield and size profile.
He’ll then develop models to link the hyperspectral imagery with ground measurements. He’ll use in-season imagery to predict real-time crop-nitrogen status. With guidance from Mitchell, he’ll also use the modeled in-season crop nitrogen status, together with environmental factors data, to predict end-of-season tuber productivity and economic return.
“With issues concerning nitrates in groundwater, we need to find ways to make better use of our fertility inputs; we’re hopeful that Yi’s new project can help direct those efforts,” said Andy Diercks, a potato grower at Coloma Farms LLC.
“Hyperspectral imaging has the potential to show the plant’s response to deficiencies in inputs before the human eye can see it,” Diercks said. “If we can gain a few days in responding to nutrient stress, the impact to the health of the plants would be significant. And the possibility of using fewer inputs to remedy the situation would be a serious win-win.”