SIU researchers develop AI robot for early soybean disease detection
Researchers at Southern Illinois University Carbondale (SIU) are working on an innovative technology that could help soybean farmers identify plant diseases before visible symptoms appear.
The project combines robotics and artificial intelligence (AI) to provide farmers with a faster and more accurate way to protect their crops.
While soybean prices have increased over the years, production costs have also risen significantly. Soybean farmers face several challenges that affect crop yield, including unfavorable weather, pests, weeds, and plant diseases.
According to the SIU researchers, diseases caused by soil-borne fungi are among the biggest threats to soybean production. These diseases often spread through rainfall and attack plants long before any visible signs appear. By the time symptoms become noticeable on leaves or stems, the crop may already have suffered serious damage.
“If a disease overpowers your field, late-stage fungicide application is not very efficient," says Billy Ram, assistant professor of precision agriculture at Southern Illinois University Carbondale. "Once the disease attacks the farmer’s crops, the yield can be reduced to 60 to 70%. It has a real economic impact.”
To address this issue, Ram and Samuel Singh, doctoral students in agricultural sciences, began researching methods to detect diseases much earlier. Their current focus is frogeye leaf spot, a damaging soybean disease that creates lesions on leaves and can spread to stems and pods.
Initially, the research team used drones equipped with hyperspectral and multispectral imaging technology to study crop health. While the drones provided valuable information, they struggled to capture detailed images of the lower parts of soybean plants and the underside of leaves where symptoms often begin.
Discussing this challenge, Ram said, “At the end of the day, we’re only working with cameras. We’re solving an engineering problem more than an agronomic problem. The challenge is how efficiently can you collect a large source of data while the equipment is traveling the field.”
To improve disease monitoring, the researchers designed a battery-powered robot equipped with GPS, multiple cameras, and autonomous navigation features. The robot can move through soybean rows, collect close-range images from different angles, and monitor individual plants throughout the field.
Ram described the system’s goal, saying, “The robot should be able to drive down the field, keep track of each plant, identify if the plant has a disease and which type, and then share what percentage of the crop is diseased.”
The next step is developing advanced AI models capable of identifying frogeye leaf spot with high accuracy. The researchers also aim to create disease maps that highlight affected areas in a field. These maps would help farmers apply fungicides only where needed, reducing costs and improving efficiency.
Sharing his vision, Singh said, “I want to design maps that help farmers detect hot spots, so farmers can see the hot spots and know what site-specific areas to apply fungicides instead of spraying all over the field.”
He added, “As an engineer, we love working on solutions that actually help people, not just something that sounds good on paper. The future means humans using robots to make life easier and more efficient.”
The new robot and AI system could play an important role in the future of soybean farming by helping growers detect diseases earlier, reduce crop losses, and make more informed management decisions.
Photo Caption: Samuel Singh, a doctoral student in the agricultural sciences program, showcases a robot equipped with multiple cameras that can capture plant diseases on soybean crops.
Photo Credit: Todd Duermyer, Southern Illinois University