Semi-Autonomous "Hyperspectral" Drones Show Promise for Monitoring Lodging Maize Crops

Researchers from the Agricultural College of Yangzhou University, the Beijing Academy of Agriculture and Forestry Sciences, and Henan Agricultural University have come up with a better way of monitoring the regrowth of maize crops: drones capable of hyperspectral imaging.

"UAV [Uncrewed Aerial Vehicle]-based hyperspectral imaging technology revolutionizes the way we monitor and assess the recovery of lodging crops," says first author Qian Sun of the team's work. "This advanced method allows for rapid, non-destructive evaluation of plant health and growth. This not only aids in better understanding the state of plants but also enhances overall crop management practices, potentially leading to more effective interventions and improved agricultural production."

Maize grows as tall thin stalks that mature into top-heavy ears of the grain, which are great for corn mazes — but vulnerable to being blown down by increasingly-common adverse weather events like storms. Known as "lodging," the fall causes shorter plants and overlapping leaves that fail to grow to their full potential — and the typical approach to monitoring for lodging is old-fashioned footwork, with investigators spending significant time driving around the fields to check for the issue.

That's time the researchers say can be saved by farming the job out to semi-autonomous aerial drones fitted with hyperspectral imaging sensors capable of assessing canopy height, coverage, and even the plants' physiological activity like chlorophyll production. "This technique allows for more precise monitoring and assessment of lodging crop conditions compared to traditional methods,” claims co-corresponding author Xiaohe Gu. "In particular, this study proposed a comprehensive evaluation framework that combines the canopy structure and the physiological activity, delivering a precise and efficient means of assessing the recovery grades of lodging maize."

"The ultimate goal is to revolutionize agricultural practices through the widespread adoption of UAV-based hyperspectral technology," co-author author Liping Chen concludes. "By making this advanced tool a standard component in crop monitoring, we aim to significantly enhance the accuracy and efficiency of assessing plant health and recovery. This will enable farmers and agronomists to manage crops more effectively, optimize interventions, and ultimately increase yield and productivity."

The team's work has been published under open-access terms in the Journal of Remote Sensing.