Skip to main content

Machine Learning and Computer Vision for Ecological Inference

Primary supervisor

Alan Dorin

"A picture is worth a thousands words"... or so the saying goes. How much information can we extract from an image of an insect on a flower? What species is the insect? What species is the flower? Where was the photograph taken? And at what time of the year? What time of the day? What was the weather like on the day the photograph was taken? This project aims to extract useful ecological and/or horticultural data from digital images by analysing their content. The aim is to infer information that might not be immediately apparent, even to the photographer, in order to improve our understanding of animal/plant interactions for boosting food production and natural ecosystem sustainability.


Required knowledge

The applicant needs to be familiar with the principles of computer vision and machine learning. They will require computer programming skills and aptitude. A formal ecology or biology background is not required although it would be an advantage. Similarly, an interest in image processing and/or photography would be helpful but is not required. Most of all, applicants need to be curious about the natural world!

Project funding

Project based scholarship

Learn more about minimum entry requirements.