Early detection of soybean sudden death syndrome using remote sensing

Soybean sudden death syndrome is a disease of major economic importance in the North and South Americas regarding yield losses. Monitoring soybean health and detecting SDS at initial crop stages is essential to facilitate sustainable, environment-friendly, and cost-effective management practices in grower’s fields. However, SDS is challenging to detect at the onset and demands regular intensive crop scouting which is labor-intensive, time-consuming, and often requires destructive sampling. At Iowa State University, we are using different remote sensing platforms and machine learning algorithms for early and accurate detection of SDS at different spatial scales. Our initial findings revealed accurate detection of SDS even before the onset of foliar symptoms. This research will provide valuable information to help farmers identify important diseases, even before they are visible in the field. This information eventually may also support the farmer’s decision for site-specific management applications in precision agriculture settings, which may reduce additional chemical applications. Also, this technology can be expanded to the regional scale for the monitoring and mapping of other economically significant plant diseases which can reduce the economic expense and ecological impact in crop production systems.