By Scout Nelson
A field of crops may appear healthy and green, but hidden stress caused by heat or insufficient water can affect plant health long before visible symptoms appear. Detecting these early signs is the focus of research led by Kelechi Igwe, a doctoral student in biological and agricultural engineering at Kansas State University.
Igwe's research explores new ways to identify crop stress before farmers can see it in the field. The goal is to provide growers with an early warning system that helps them take action and reduce potential yield losses.
Plants often respond to environmental stress by closing tiny pores on their leaves called stomata. These structures regulate the exchange of water and gases between the plant and its environment and can provide valuable insights into crop health.
The movement of water through these pores is measured through stomatal conductance, an important indicator of stress. Lower stomatal conductance levels can signal that plants are being affected by drought, heat or other challenging environmental conditions.
Traditional methods of measuring stomatal conductance require researchers to collect readings from individual leaves using specialized instruments known as porometers. While accurate, this process is time-consuming and impractical for monitoring large agricultural fields.
To address this challenge, Igwe combined drone imagery with environmental data, including air temperature and soil moisture measurements. This approach allowed him to evaluate crop conditions across an entire field without manually inspecting every plant.
Using these datasets, he developed a machine-learning model capable of estimating stomatal conductance. The model was trained with field measurements collected at the same time as drone observations and helped create detailed maps showing stress levels throughout the field.
The resulting stress maps highlighted areas where crops were experiencing water-related stress. These visualizations revealed differences in plant health that may not be noticeable through conventional field inspections.
Igwe's findings demonstrate the potential of drones and artificial intelligence to make invisible crop stress easier to identify. Early detection can enable farmers to make timely decisions about irrigation and other management practices.
The research represents an important advance in precision agriculture, helping producers improve water management, reduce crop losses and enhance productivity. It also highlights Kansas State University's commitment to developing innovative solutions for modern agricultural challenges.
Photo Credit: kansas-state-university
Categories: Kansas, Crops, Equipment & Machinery