Protecting America’s Forests from a Devastating Disease

Beech leaf disease (BLD) is killing forest trees across the United States. Caused by the nematode Litylenchus crenatae , the disease was first detected in the United States in Ohio in 2012 and has spread to at least 15 other states, from Maine to Virginia to Michigan. It was also recently discovered in the Canadian province of Ontario.

Beech tree saplings infected with BLD usually die within 5 years of infection. Mature trees can take several years to die of the infection. Early detection is key for managing tree devastation in forests. However, diagnosing BLD in trees can be difficult, as it currently relies on visually identifying the distinctive dark banding that forms between leaf veins, which is not possible at certain tree heights or at early stages. Although artificial intelligence (AI) has been increasingly used to support plant disease identification, no AI-based system had previously been developed for detecting BLD from images. 

ARS researchers Benjamin Waldo and Paulo Vieira at the Mycology and Nematology Genetic Diversity and Biology Laboratory trained a machine learning model capable of identifying BLD in real-world images with over 95% accuracy. This work provides an important step toward a more comprehensive BLD detection system and establishes a foundation for future image-based diagnostics of foliar nematode diseases. This innovative technology will assist tree and forest health professionals in rapidly identifying the presence of BLD and enhancing their ability to control the spread of this devastating tree disease.