Detecting beetles from the air with remote sensing and artificial intelligence

With the challenge of reducing pesticide use, early detection and monitoring of crop pests is essential in controlling pest dynamics. Colorado potato beetle is one of the most devastating insect pests in potato crops and its impact on crop damage and subsequent yield loss is expected to increase even further due to climate change.

Research aim

This MSc thesis project aims to explore the feasibility of detecting the beetle and its abundance from the air by using data from high resolution cameras that were mounted on drones. A big data set is available with actual counts on the potatoes over the last growing season (2020).

Types of work

In this thesis project you will explore the feasibility of detecting and counting beetles from remote sensing images. This may involve the application of advanced machine learning techniques such as deep learning.

We are looking for a motivated student that is interested in this relevant topic. Depending on your interest you can take a more ecologically oriented focus, or a more prediction-oriented focus. In the former, you will analyse the field data in more detail to understand dispersal patterns of the beetle (collection of additional field data is an option). In the latter, you would apply state of the art image analysis techniques on an important agricultural problem, and skills on, or, affinity with remote sensing imaging and machine learning is needed (e.g. the courses data science for ecology, deep learning, machine learning would prepare you for this thesis).