Scientists use AI and drone images to interpret crop health

Scientists at the International Center for Tropical Agriculture (CIAT) are analyzing drone images captured above the soil to examine what is going on below. With the help of machine learning, the experts are revolutionizing the way that farmers and breeders monitor crop health. 

The Pheno-i platform provides real-time data that can be used to determine how root crops are responding to heat or drought. 

The main objective of the phenotyping platform is to contribute to sustainable agriculture and the development of more climate-resilient crops. 

Root crops like carrots and potatoes often show no signs of the diseases and deficiencies that affect their growth. The plant leaves may look green and healthy, but that is not always a good indication of what is going on beneath the soil. 

Plant breeders have to wait months or years before discovering how crops respond to temperature changes or dry spells. Without the right nutrients or growing conditions, crop health and development can be stifled early on. 

“One of the great mysteries for plant breeders is whether what is happening above the ground is the same as what’s happening below,” said study co-author Michael Selvaraj.

“That poses a big problem for all scientists. You need a lot of data: plant canopy, height, other physical features that take a lot of time and energy, and multiple trials, to capture what is really going on beneath the ground and how healthy the crop really is.”

Drone technology is becoming much cheaper, and capturing physical images during crop trials is now easier than ever before. However, analyzing vast quantities of visual information, and then converting it into useful data, has been a major challenge. 

The Pheno-i platform merges data from thousands of high-resolution drone images, analyzes them through machine learning, and then produces a spreadsheet. Scientists using the platform can assess crop health and see how plants are responding to external conditions in real-time.

The technology makes it possible for breeders to immediately identify what crops need, such as when they are lacking nutrients or water. 

The data also helps scientists determine which crops are more resilient to climate change. 

“We’re helping breeders to select the best root crop varieties more quickly, so they can breed higher-yielding, more climate-smart varieties for farmers,” said Gomez Selvaraj.

“The drone is just the hardware device, but when linked with this precise and rapid analytics platform, we can provide useful and actionable data to accelerate crop productivity.”

The study is published in the journal Plant Methods.

—

By Chrissy Sexton, Earth.com Staff Writer