Our 2024 Studentships
We are delighted to announce our fully-funded, four-year PhD studentships in the application of Artificial Intelligence to sustainable agri-food, to start in October 2024.
Explore the projects in more detail below and apply via our Application Page.
Integrated Analyses to Promote Sustainable Soil Health (SUSTAINable Soils)
Prof Mat Goddard, University of Lincoln; Dr Nicolas Rubido, University of Aberdeen; Prof Simon Parsons, University of Lincoln; Dr Dan Magnone, University of Lincoln
Soils produce 97% of the world’s food calories; provide key water regulation processes for flood management; harbour the highest levels of biodiversity on Earth; and contain the largest dynamic reservoir of carbon on Earth. However, there is virtually no integrated holistic knowledge of soil properties, and more importantly how these are affected by land use and management change. This project will contribute to an evidence base that will support land-use change decisions to help mitigate climate change, with opportunity to work across a broad range of computer science, applied mathematics, and environmental and soil science areas. Read more.
Available
Flavour-centric Innovation for Cultivated Meat: Bridging the Sensory Gap in Cellular Agriculture
Dr Tassos Koidis, Queen's University Belfast; Prof Georgios Leontidis, University of Aberdeen; Multus Biotechnology
As the global population rapidly increases, the quest for sustainable and nutritious alternatives to traditional animal products becomes crucial. Cellular agriculture, which involves growing animal cells in a controlled environment to produce food, offers a promising solution. However, the success of cultivated meat in the market hinges on replicating the sensory experiences of traditional meat. This project aims to transform cellular agriculture by prioritizing flavour-centric production while maintaining viable manufacturing volumes. Read more.
Available
Home applicants only
Food Authentication Using Portable Sensors: Addressing Food Fraud and Food Mislabelling
Prof Hui Wang, Queen's University Belfast; Prof Louise Manning, University of Lincoln
Worried about food fraud and mislabelling? These issues erode consumer confidence in the agri-food system, leaving us questioning the authenticity of what we eat. This project proposes an innovative solution: a portable food authenticator that leverages everyday technology to rebuild trust. Using portable sensors and machine learning, sophisticated algorithms trained on real data will identify food types, detect adulteration, and even uncover discrepancies between labelled information and the actual food composition. Read more.
Available
Home applicants only
Artificial Intelligence for Satellite Assessment in Grassland Ecosystems
(AI-SAGE)
Dr Robert Atkinson, Dr Lan Qie, University of Lincoln; Dr Christos Tachtatzis, University of Strathclyde; Fresh Milk Company
Satellite Earth Observation (EO) Data has emerged as a game-changer in accurately assessing plant biodiversity and ecosystem functions within agricultural landscapes, spanning both grassland and arable terrains. The current challenges in harnessing EO data through Deep Neural Networks (DNNs) is not a scarcity of data, but the limited availability of detailed, pixel-level annotations. The studentship aims to: extract biodiversity indicators in grassland landscapes;
bridge this gap between large volumes of data and limited pixel level annotations; explore domain shift (EO trained models typically do not transfer between geographies); and develop guidance on grassland management strategies. Read more.
Available
Home applicants only
Understanding Multi-Objective Optimisation Algorithms for Land Use
Dr Daniel Magnone, University of Lincoln; Professor Nir Oren, University of Aberdeen; Professor Simon Parsons, University of Lincoln
The UK’s land use can be considered a complex, multi-objective optimisation problem, balancing economic yield, biodiversity enhancement, and carbon storage. With the recent introduction of the Environmental Land Management Scheme (ELMS), the need for a decision- support system to help stakeholders understand the impacts and trade-offs of land parcel allocation is clear and timely. This PhD project will utilise advances in formal argumentation theory and dialogue to encode, reason, and explain the behaviour of multi-objective optimisation algorithms. The research will focus on optimising carbon storage, biodiversity enhancement, and economic yield from agriculture. Read more.
Available
Machine Learning and Bayesian Modelling Approaches for Big Data in Beef Agriculture & Food Production
Dr Arran Hodgkinson, Queen's University Belfast; Prof Ilias Kyriazakis, Queen’s University Belfast; Dr Mingjun Zhong, University of Aberdeen; Agri-Food and Biosciences Institute
Machine learning (ML) is an invaluable modern technique whose insights could radically change farming practices, both to the benefit of livestock and farmers. As such, we are looking for a motivated candidate with a strong background in data analytics, statistics, and machine learning to take on this exciting project. Fundamentally, this project intends to utilise cutting-edge ML and probability-based statistical strategies to directly address inefficiencies in feeding practices within the bovine livestock supply chain, employing modelling techniques alongside real-world databases. These models will seek to increase sustainability and animal welfare, by facilitating an individual- or subpopulation-based approach to feeding and nutritional consideration. Read more.
Available
Novel Applications of Artificial Intelligence Technologies in Veterinary Ultrasound Scanners
Christos Tachtatzis, University of Strathclyde; Prof Sam Martin, University of Aberdeen; Fraser Hamilton, IMV Imaging (UK) Ltd (Industry Supervisor)
Fish production for human consumption is increasing globally to meet food demands from a growing population. Interventions must be introduced to de-risk the impact of climate change on the growing aquaculture industry. This exciting PhD aims to improve sustainability in the aquaculture industry through the combination of ultrasound and AI. The goal is to monitor fish health, reduce the risk of disease and improve efficiency in the industry. Read more.
Available
Towards Sustainable Net-Zero Farming Using Machine Learning
Dr Vladimir Stankovic, University of Strathclyde; Dr Marta Dondini, University of Aberdeen; Dr Lina Stankovic, University of Strathclyde; RHD (Scotland) Ltd
The agri-sector, especially dairy farming, is a major contributor to greenhouse gas (GHG) emissions. Understanding the variation in GHG emissions among different farming practices helps to identify sustainable approaches that reduce pollution. The aim of the PhD research is to develop an AI-driven methodology for holistic quantification of GHG emissions in dairy farming, taking into account all sources of GHG emissions and provide recommendations for GHG reduction. Besides hands-on mentored research, the student will develop broader research skills related to AI and mathematical modelling, and transferrable skills related to professional development. Read more.
Available
Development of a milk (mid-infrared) MIR Spectral deep learning neural network as a classifier model for GHG emission profiles in dairy cattle
Prof Craig Michie, University of Strathclyde; Prof Chris Creevey, Queen’s University Belfast; Dr Mazdak Salavati, SRUC
A recent technology which has been taken up globally is milk mid-infrared spectroscopy or MIR. The project aims to develop an MIR spectral deep learning neural network as a classifier model for Green House Gas (GHG) emission profiles in dairy cattle – harnessing the power of digital transformation and field applications of AI to tackle the urgent issue of reducing the carbon footprint of the dairy supply chain. Read more.
Available
Robotics and AI to Support Scalable Agronomy (RAISSA)
Prof Marc Hanheide, University of Lincoln; Prof Georgios Leontidis, University of Aberdeen; plus an Industry Supervisor
The use of Robotics and AI to help agronomists scale their services will be crucial in meeting the growing demand for food while reducing environmental impact. This project aims to develop methods for autonomous data gathering and interpretation supporting agronomic decision-making in agriculture by creating models of data fidelity and anomalies. Read more.
Home applicants only
Transparent Carbon Footprint Quantification and Reporting in Agriculture
Dr Milan Markovic, University of Aberdeen; Dr Paul Williams, Queen’s University Belfast; plus an Industry Supervisor)
Agriculture, responsible for 10% of global greenhouse gas emissions, holds significant potential for negative emissions, particularly in soil carbon sequestration. However, existing Monitoring, Reporting, and Verification (MRV) systems lack standardization, transparency, and face challenges in data availability. This PhD will explore the practical applications of AI technologies to capture additional information which could enhance transparency and thus support novel MRV systems. Read more.
Home applicants only
Machine Learning Crop Breeding in Precision-Controlled Vertical Farming for a Sustainable Future
Dr Aiden Durrant, University of Aberdeen; Dr Mamatha Thota, University of Lincoln; Professor Derek Stewart, Advanced Plant Growth Centre, The James Hutton Institute; Dr Tanveer Khan, Intelligent Growth Solutions (Industry Advisor)
This PhD opportunity addresses the imperative for innovative crops and production systems in vertical farming environments. The goal is to develop advanced Artificial Intelligence (AI) methods for Computer Vision (CV) to address plant production and breeding, assessing the impact of AI-driven approaches in controlled vertical farming settings. Read more.
Home applicants only
Data and knowledge dual-driven artificial intelligence in remote sensing
Anna Jurek-Loughrey, Queen’s University Belfast; Yeran Sun, University of Lincoln; plus an Industry Supervisor
Remote sensing data analysis plays a crucial role in advancing sustainable agriculture. However, the complexity of remote sensing, with intricate environmental interactions and the variability of natural landscapes, poses challenges for data-driven approaches. The key aim of this project will be to explore innovative AI technology that integrates both data-driven and knowledge-driven methods, aiming for more accurate and trustworthy remote sensing results. Read more.
Home applicants only
Intelligent, Energy-efficient De-leafing for the Soft Fruit Industry
Prof Elizabeth Sklar, University of Lincoln; Prof Greg Keeffe, Queen’s University Belfast; Sarah Palmer, Driscolls Genetics Limited (Industry Supervisor)
Plants that produce fruit also produce leaves; but when such plants are cultivated for fruit production, it is desirable to prune excess leaves and concentrate the plant's energy on growing fruit. This project will explore the application of intelligent robots to undertake de-leafing, including investigation of in-field practices conducted by human workers and study of plant science strategies to optimise fruit yield. Read more.
Home applicants only
Nature-based Solutions for Restoration of Degraded Soils in
Sub-Saharan Africa
Prof Jo Smith, University of Aberdeen; Prof Anil Fernando, University of Strathclyde; Getahun Yakob, Southern Agricultural Research Institute (SARI), Ethiopia (Industry Supervisor), Moses Kimani, Lentera Ltd, Kenya (Adviser)
Many soils in Sub-Saharan Africa are degrading due to high levels of erosion, decreasing organic matter, salinisation, acidification and contamination, resulting in declining productivity, farm income and household well-being. This project will use machine-learning to investigate the use of nature-based solutions to improve soil health, so allowing increased resilience to climate change. Read more.
Home applicants only
Advanced Video Processing to Optimise Feeding of Livestock in Farms
Dr Paul Murray, University of Strathclyde; Prof Ilias Kyriazakis, Queen’s University Belfast; Anthony McMahon Peacock Technology (Industry Supervisor)
A key contributor to the GHG footprint of milk production is associated with animal feedstock, which, if not optimised for each animal, can lead to increases in CH4. This PhD project will introduce new video processing tools to interpret animal eating and feeding- behaviours with the aim of personalising and optimising the feedstock for individual farm animals. To achieve this, the successful candidate will design state-of-the-art image and video processing analytics using AI (artificial intelligence) and machine learning (ML), potentially in combination with traditional signal processing techniques. Read more.
Home applicants only
Multi-Object Visual Tracking (MOT) of Animals in Agriculture
Niall McLaughlin, Queen’s University Belfast; Christos Tachtatzis, University of Strathclyde; plus an Industry Supervisor
Computer vision, video analytics, and AI can help monitor and improve animal welfare while improving farm productivity. However, monitoring animals poses unique challenges for AI, including tracking with erratic and non-linear motion and coping with changes in appearance as animals grow. This studentship will seek to develop improved Multi-Object Visual Tracking (MOT) algorithms, laying the foundation for future methods for applying AI in agriculture and opening avenues for new commercial applications. Read more.