Development of an Artificial Intelligence-based mosquito identification system using Morphological Images

Theme: Ecology genetics and evolution, Zoology and wildlife biology

Description: 

Mosquito surveillance programs rely on accurate species identification to monitor vectors of human and animal diseases. Traditional identification methods are labour-intensive, require specialist expertise, and can be challenging when specimens are damaged or when dealing with immature stages. Recent advances in computer vision and artificial intelligence (AI) offer opportunities to automate mosquito identification using digital images.
This project aims to develop a machine-learning algorithm capable of identifying the major mosquito species found in Brisbane from both aquatic (larval and pupal) and adult life stages. Students will establish laboratory colonies of 5 species, generate a comprehensive image dataset, and develop a computer vision model to classify 5 mosquito species.

Additional Information:  

This project is suitable for students with a background in entomology, ecology, zoology, data science or artificial intelligence who are interested in combining biological research with emerging AI technologies. The project provides a balance of laboratory, imaging, and computational research.Students will gain skills and experience in mosquito rearing, species identification, digital imaging, AI and machine learning.

Contact: Dr Maggy Lord