AI-Based Image Profiling and Detection for the Beetle Byte Quintet using Vision Transformer (ViT) in Advanced Stored Product Infestation Monitoring

Authors: SERFA, RONNIE - Orise Fellow; Pordesimo, Lester; Campbell, James; Armstrong, Paul; Gerken, Alison

Submitted to: Entomologia Experimentalis et Applicata
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 9/17/2025
Publication Date: 10/22/2025
Citation: Serfa, R.O., Pordesimo, L.O., Campbell, J.F., Armstrong, P.R., Gerken, A.R. 2025. AI-Based Image Profiling and Detection for the Beetle Byte Quintet using Vision Transformer (ViT) in Advanced Stored Product Infestation Monitoring. Entomologia Experimentalis et Applicata. https://doi.org/10.1111/eea.70018.
DOI: https://doi.org/10.1111/eea.70018

Interpretive Summary: When it comes to pest control, using advanced technology can save both time and money. For businesses dealing with stored grains, the stakes are even higher—timely pest identification can reduce damage and protect valuable food supplies. The choice of pest management tactic largely depends on the type of species present; however, stored product beetles are difficult to identify. Numerous species exhibit visually similar traits: reddish-brown pigmentation, relatively small body size (1.5-4 mm in length), and flattened bodies. Computer vision models can be trained to recognize species based on subtle morphological differences such as body form, wing coatings, and head patterns. For this study, we trained Vision Transformer (ViT), a robust computer vision program, to accurately recognize five prevalent stored product beetle pest species (sawtoothed grain beetle, lesser grain borer, red flour beetle, maize weevil, and rusty grain beetle). Despite using an inexpensive camera, our model achieved 97.4% in accurately identifying these five species. Ultimately, the incorporation of these technologies into field-scale pest monitoring systems may revolutionize the management of stored-product insects, resulting in enhanced food safety, decreased losses, and more effective pest control tactics.

Technical Abstract: Managing beetles that infest stored products is crucial for reducing losses in harvest supply chains and improving food security and safety. Successful pest management programs require effective and timely monitoring programs, but traditional methods for detecting pests are time- and labor-intensive and require taxonomic expertise. New, automated methods using computer vision have the potential to improve accuracy and speed of detection, but often struggle to differentiate between beetle species, which tend to be small and morphologically similar. Our research centers on five economically significant beetle species, referred to as the 'Beetle Byte Quintet,' and proposes a novel methodology leveraging Vision Transformers (ViT) to enhance the precision and robustness of their classification. The method involves using an image profiling technique to capture morphological characteristics like body shape, color and exoskeleton structures that are key for distinguishing between species. By utilizing this species profiling, the ViT model achieved an accuracy rate of over 99.34% during training and 96.57% during testing. These findings highlight the models’ ability to generalize and maintain precision with new unseen data surpassing traditional computer vision algorithms significantly. The integration of ViT can help enable real time monitoring and is adaptable to a range of pest monitoring solutions for large scale storage settings which addresses the complexities of environments. This AI driven approach not only simplifies species identification but also promotes accurate and targeted pest control practices leading to reduced economic losses and improved food security.