Red crown rot (RCR) is a growing threat to Illinois soybean fields, capable of causing up to 50% yield loss. Early detection is key to managing this destructive disease, but traditional scouting methods, whether by hand or drone, can be time-consuming and expensive. A new research project aims to change that by using advanced drone and satellite imagery to develop a model that will help farmers predict RCR outbreaks more efficiently.

Identification of red crown rot hotspots (red) in a commercial soybean field using remote sensing.

Dr. Boris Camiletti, leading the project, provided a recent update: the team has developed a satellite imagery model that classifies field areas as healthy or diseased with 76% accuracy. By analyzing 10 x 10 ft pixels in satellite images, the model can identify disease hotspots, providing farmers with early warning signs of RCR in their fields.

The team tested the model at several locations and found a troubling trend. Comparing satellite images from 2022 and 2024, they discovered that diseased areas in one location had skyrocketed from 6% to 26%. This rapid spread highlights the urgency of monitoring and managing red crown rot. 

How You Can Help 

In the next phase of the study, researchers are seeking additional fields affected by red crown rot to improve the model’s accuracy and calibrate it for on-farm use. If you have a field with confirmed red crown rot, your participation in this study could help strengthen the model and provide valuable information for managing this disease more effectively. 

By working together, farmers and researchers can fine-tune detection methods and develop better management practices for this widespread issue. 

If you’re interested in participating or learning more about the study, contact Dr. Boris Camiletti at bxc@illinois.edu. Your involvement could make a difference in shaping the future of RCR management. 

To learn more about this Illinois Soybean Checkoff-funded research, visit the Field Advisor Research Hub. 

Rapid spread of red crown rot within a field, as detected by remote sensing.