Drones Help Detect Disease

Published online: Jan 26, 2016
Viewed 2223 time(s)

Idaho researchers have found a way to use drones to detect diseased potato plants.

Led by Idaho State University assistant geosciences professor Donna Delparte, researchers mounted high-tech cameras on drones and flew them 60 meters above potato fields. They were able to detect individual diseased and stressed plants early and accurately. Delparte discussed the research last week at the Idaho Potato Conference in Pocatello, Idaho.

Delparte’s project started in 2014 and used drones to gather images of about a half-dozen potato and sugarbeet fields in 2015.

The project was funded by the USDA and the Idaho Department of Commerce’s Global Entrepreneurial Mission. The J.R. Simplot Company also helped Delparte with soil analysis, crop expertise and grower recruitment.

“There’s so much new technology coming into the marketplace,” said Simplot technology director Allan Fetters. “This is a good opportunity to work with ISU and understand how we might use this technology to bring value to farmers of Idaho.”

The researchers are now trying to create algorithms that will let them identify the exact diseases using a method developed by Louise-Marie Dandurand, a University of Idaho plant physiologist. Durand was able to use the way a plant reflects radiation to differentiate between ailments like nematode feeding or potato virus Y infection.

“Happy plants have a consistent pattern, or signature,” explained Mike Griffel, a Simplot agronomy manager working with Delparte. He said most of the research has focused on potato virus Y infection in Russet Norkotah, which tends to mask symptoms of the disease.

“We want to figure out how we can help seed growers identify and remove (seed-borne) virus infection before it has a chance to become in-season infection,” Griffel said.

Delparte said the team is working on new algorithms to automate that kind of detection so growers can quickly eliminate infected plants.

“Initial results are showing great promise to build out the algorithms and potentially could lead to commercialization opportunities and getting it to growers,” she said.


Source: Washington Times