Researchers program drone to hunt PVY in potatoes

Researchers say they’ve accurately detected potato virus Y using cameras mounted on drones.
John O’Connell

Capital Press

Published on January 20, 2017 4:34PM

John O’Connell/Capital Press
Donna Delparte, an assistant professor of geosciences at Idaho State University, shows the large drone built by ISU’s robotics and communications program to support heavy cameras she’s acquired for evaluating causes of yield declines in potatoes and sugar beets. She and J.R. Simplot Co. will partner on the research.

John O’Connell/Capital Press Donna Delparte, an assistant professor of geosciences at Idaho State University, shows the large drone built by ISU’s robotics and communications program to support heavy cameras she’s acquired for evaluating causes of yield declines in potatoes and sugar beets. She and J.R. Simplot Co. will partner on the research.

Buy this photo

POCATELLO, Idaho — Researchers say they’ve pinpointed individual spud plants infected with potato virus Y with 90 percent accuracy, using hyperspectral cameras mounted on drones.

Donna Delparte, an assistant professor of geosciences at Idaho State University, and graduate student Mike Griffel have successfully tested a “computer-learning” algorithm they developed to tease out PVY from spectral imaging “background noise,” such as field variability and unrelated crop stress.

“Our premise was to look at all of these wavelengths of light the human eye can’t see and look for differences between healthy plants and plants infected with PVY,” Griffel said, adding their images had leaf-scale resolution.

Griffel said the project detected disease well before potato crops reached the row-closure stage, far earlier than people can spot symptoms of PVY by scouting fields.

To develop their algorithm, they compiled crop data in fields over three seasons, ending in 2016. The researchers first analyzed fields from the ground with a high-tech camera capable of recording 100 bands of the light spectrum.

After studying the images, they selected the 15 most useful bands for identifying PVY based on its unique light reflection. Delparte programmed more basic hyperspectral cameras mounted on drones to detect those bands while surveying the same potato fields from the air.

They developed the algorithm based on common spectral signatures among sick plants. Their software “learned” to ignore field variability based on comparisons of sick plant signatures with signatures reflected from adjacent healthy plants.

PVY, vectored by aphids, is a major disease affecting potato seed growers and is the primary target of Idaho’s annual winter grow-out in Hawaii, which evaluates the health of certified seed lots. The researchers shared their findings with seed growers during the Idaho Seed Potato Growers seminar Jan. 17 in Pocatello.

“We feel like we’re right on the cusp of taking this to a really fast, efficient way of detecting the virus,” Delparte said.

The first three years of research were funded with grants from USDA and the Idaho Global Entrepreneurial Mission. Delparte said she’s seeking additional funding from seed growers and industry sources to leverage more grants and continue the work, delving into other diseases and crops.

“Our hope is in another round of research and testing, we can tighten that work flow so we get faster and faster and get results back quickly to the grower,” Delparte said.

Griffel envisions the technology will eventually enable drones to text GPS coordinates of sick plants to field agronomists, or direct drones to spray and kill sick plants upon detection.

“I think this type of data would give Idaho a marketing bump,” Griffel said.

Griffel said cameras commonly mounted on drones by companies providing data for agricultural producers and other industries aren’t sensitive enough to pick up PVY. However, he said his research findings could aid in development of simpler cameras, recording only bands of importance to PVY.



Marketplace

Share and Discuss

Guidelines

User Comments