Optimal pest detection networks for robust management decisions

Sugar beet is a strategically important crop whose productivity is increasingly threatened by insect pests, including aphids that transmit virus yellows and beet flea beetles. Climate change is altering pest distributions and seasonal dynamics, increasing the need for surveillance systems that provide early warning of outbreaks and support timely management decisions.

Monitoring networks are central to Integrated Pest Management (IPM), informing interventions such as spray thresholds. However, current systems are often spatially sparse, costly to maintain, and focused primarily on pest detection. Beneficial insects, despite their key role in natural pest suppression, are rarely incorporated into monitoring network design or decision-support tools. As agriculture seeks to reduce pesticide reliance while maintaining productivity, there is a need to develop monitoring approaches that jointly consider pests and beneficial insects while improving detection accuracy, reducing costs, and supporting on-farm decision making.

This PhD will use extensive historical datasets and field sites provided by the British Beet Research Organisation (BBRO) to develop and test next-generation monitoring frameworks for agricultural pests. The student will create a pipeline for optimising trap placement, accounting for spatial and temporal variation in pest and beneficial insect populations and improving the translation of monitoring data into management actions.

Using GIS, geospatial optimisation, artificial intelligence, and reinforcement learning, the project will design monitoring networks that balance early detection, operational costs, and beneficial insect protection. Research will evaluate methods including location-allocation models (such as p-median and maximal coverage approaches), Bayesian optimisation, and reinforcement learning. Decision-support systems will be developed to compare traditional spray-threshold methods with advanced forecasting tools that integrate trap captures, beneficial insect abundance, weather forecasts, and projected pest dynamics.

The final year will focus on testing and validating these tools within BBRO monitoring networks. The student will work closely with researchers at the University of Lincoln, the University of Aberdeen, and BBRO, gaining expertise in invasion ecology, population modelling, AI, pest monitoring, and pest management, with opportunities to obtain BASIS qualification in arable pest management.