Summary
Vine weevil is an economically important pest of soft fruit and ornamental crops globally.Historically, management of this pest relied on broad-spectrum synthetic insecticides
More recently, control has shifted toward integrated pest management (IPM) compatible methods, such as the use of entomopathogenic nematodes and fungi to target soil-dwelling larvae.
Such methods require reliable pest monitoring tools to be truly effective. However, existing tools have been demonstrated to be largely unreliable and time-consuming to implement.
This project aimed to develop a prototype monitoring tool that could automatically identify adult vine weevil.
Results presented here indicate that pre-trained machine learning models can reliably identify adult vine weevil in laboratory and semi-field environments.
The research also demonstrates that retrofitting monitoring tools with low-cost electronic components can enhance functionality without negatively impacting insect-monitoring tool interactions.
This is the first report of such technologies being specifically developed for vine weevil management.
This work demonstrates the feasibility of an automated monitoring approach, which could benefit growers by delivering data about crop pest populations to better inform management decisions.
However, further development of the prototype is required before commercial deployment.
