Analyzing Drone Images to Understand How Root Crops Respond to Drought

Root crops such as potatoes, carrots, and cassava are notably good at hiding deficiencies or diseases that might impact their growth. Their leaves appear green and healthy, but farmers tend to experience unpleasant surprises while harvesting their crops.

This raises an issue for plant breeders, who must wait for months or years before identifying how crops react to changes in temperature or drought. Crop productivity is affected due to the impaired knowledge of the growing conditions or what nutrients the crop requires earlier.

A new study published in the Plant Methods journal on June 14^th, 2020, reports the use of machine learning to help predict root growth and health using above-ground imagery.

One of the great mysteries for plant breeders is whether what is happening above the ground is the same as what's happening below.

Michael Gomez Selvaraj, Study Co-Author and Crop Physiologist, Alliance of Bioversity International and International Center for Tropical Agriculture

Selvaraj added, “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.”

Since the cost of drones has been declining and hardware for capturing physical images via crop trials has turned simpler, a major hurdle has been to examine huge amounts of visual data, and extracting useful data for breeders to use.

With the help of drone images, the Pheno-i platform can now combine data from thousands of high-resolution images, examining them using machine learning to generate a spreadsheet. This indicates how plants react to stimuli in the field in real-time.

At present, by employing the technology, breeders can react instantly, by applying fertilizer if water or a specific nutrient is lacking. Moreover, the data enables researchers to rapidly identify which crops are more resistant to climate shocks, so they can recommend farmers to grow more drought- or heat-resilient types.

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. 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.

Michael Gomez Selvaraj, Study Co-Author and Crop Physiologist, Alliance of Bioversity International and International Center for Tropical Agriculture

The technology could be used even for other crops.

According to Joe Tohme, the research director of Crops for Nutrition and Health at Alliance of Bioversity International, “Automated image analytical software and machine learning models developed from this study is promising and could be applied to other crops than cassava to accelerate digital phenotyping work in the alliance research framework.”

Journal Reference:

Selvaraj, M. G., et al. (2020) Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz). Plant Methods. doi.org/10.1186/s13007-020-00625-1.

Source: https://ciat.cgiar.org/