The Scottish seed potato industry has an excellent reputation worldwide as a reliable supplier of high-health seed potatoes to over 40 countries. Central to this reputation is Scotland's rigorous Seed Potato Classification Scheme, which assures the continuing high-health status and purity of Scottish seed potatoes through inspection of all seed potato crops. Ware potato crops grown near seed crops can act as sources of pests and diseases. Growers must notify the Scottish Government of any ware crops which are planted in Scotland. This enables crops to be included in the 10 % of ware crops which are inspected annually. Accurate locations of ware crops underpin the measures which support high potato health in Scotland and ensures a coordinated response in the event of a disease outbreak. As potato cultivation patterns can change dynamically throughout the season, additional tools that support timely identification of potato-growing fields could help target inspections more effectively. This study will investigate whether advanced machine learning techniques can be applied to satellite imagery and historical crop records to develop predictive models capable of identifying potato-growing fields throughout the growing season. This will support timely inspections, the inspection selection process and strengthen disease control and prevention within Scotland’s seed potato sector.

Scotland is about to generate a new, high-resolution, whole-country LiDAR dataset that will provide unprecedented structural information on land cover and vegetation, collected on a four-year cycle and supported by complementary aerial photography. This national resource has clear potential to support plant health monitoring and risk assessment, but its practical applications, limitations, and implementation requirements for plant health purposes have not yet been systematically explored.

This project will evaluate how the forthcoming LiDAR dataset could be used to improve plant health outcomes in Scotland. It will identify and assess opportunities for applying LiDAR data to plant health challenges, including early detection of risks, monitoring vegetation change, and supporting surveillance and risk assessment activities. The project will examine the strengths and limitations of LiDAR for plant health investigations and explore how it can be combined with other remote sensing technologies, such as satellite- and drone-based data, to enhance insights. Technical, operational, and organisational barriers to effective use will also be identified, including data handling requirements and skills gaps.

Through expert engagement, targeted case studies, and a stakeholder workshop, the project will provide clear, evidence-based advice to support investment in tools and approaches that maximise plant health benefits from this national data resource.