Crop-Agnostic Radar-to-Optical Image Synthesis and Closed-Loop AI Decision Automation for UK Arable, Viticulture and Soft Fruit Production Systems

About the project

About the Project Agriculture is undergoing a digital transformation, driven by advances in Artificial Intelligence (AI), Earth Observation and autonomous decision support technologies. However, a major challenge remains: most crop-monitoring systems rely on optical imagery that becomes unusable at night or during cloudy conditions, severely limiting operational effectiveness in countries such as the UK. This PhD project will develop innovative AI technologies that enable continuous crop monitoring by combining optical, hyperspectral imagery and radar observations. Using different data from diverse sensors, this PhD will investigate how AI, multimodal learning and explainable machine learning can fuse information from radar, optical and hyperspectral sensors to provide reliable insights into crop condition, stress, disease risk and productivity. The student will develop state-of-the-art machine learning and AI methods, such as transformer architectures, diffusion models and uncertainty-aware systems. These techniques will be used to get value from data, translating multimodal data into decision support and decision making for crop management in UK Agri-Tech applications. A distinctive aspect of the project is the development of fusion frameworks that enable operation capabilities regardless of cloud cover, enabling more resilient agricultural monitoring across arable farming, vineyards and soft-fruit production systems. This aligns closely with emerging trends in autonomous and intelligent agriculture. The student will receive interdisciplinary training spanning AI, explainable AI, Earth Observation sensor modalities, remote sensing, precision agriculture and environmental monitoring. They will gain experience working with multimodal satellite, hyperspectral and radar datasets, advanced machine learning and AI methods and real-world agricultural applications, developing a highly demanded skillset at the interface between AI and sustainable food production. Supervisors: Dr Jaime Zabalza, j.zabalza@strath.ac.uk Dr Gareth J. Norton, g.norton@abdn.ac.uk Prof Paul Murray, paul.murray@strath.ac.uk Chris Felder chris@linear-labs.com Applications: Our fully-funded studentship package includes: All PhD tuition fees paid. A tax-free stipend at UKRI rates to cover living costs. A Research Training Support Grant (RTSG) of £3,000 each year to support travel, training and consumables costs (up to £12,000 in total). Additional funding to support outreach and dissemination, attendance at summer schools, research events, and development projects. Interested applicants should visit ' https://www.sustain-cdt.ai/how-to-apply ' for full instructions on how to submit their application. Requirements: Honours degree (minimum 2:1) in Electronic & Electrical Engineering, Computer Science, Earth Observation Data Science with strong expertise in signal & image processing, computer vision, hyperspectral imaging, SAR data. It is essential that the PhD student is self-driven, curious, interested in working across disciplines and exploring new areas, as well as eager to work as part of an interdisciplinary team. The student will be expected to engage with their peers and other academic staff, get involved in departmental events and seminars, and show enthusiasm for public/policy engagement activities. Desirable: a master’s degree in AI, Machine Learning, Environmental Sciences (Agri-Tech). Enquiries: Dr Jaime Zabalza, j.zabalza@strath.ac.uk Application Deadline: 12:00 noon (UK time) Friday, 16 October 2026

Research areas