Project Summary

The Irish dairy sector operates within an increasingly complex environment shaped by variability in milk composition and fluctuations in global markets. These factors create challenges for dairy processors in making both short-term operational decisions and longer-term investment choices. Within the VistaMilk programme, there is a growing need to better understand how milk moves from farm to finished product, and how this journey can be optimised to improve efficiency, value recovery, and overall sector resilience.

A key limitation lies in the lack of integrated tools that capture the full complexity of dairy processing systems. Existing approaches often consider individual components of the system in isolation, such as transport, processing, or storage, without fully accounting for how these interact.

This PhD will focus on developing a decision-support model to optimise how milk flows through the dairy processing system, from collection and transport through to processing, storage, and distribution.

Why This Scholarship Stands Out

This PhD is unique because it integrates dairy processing, data science, and agri-food economics into a single decision-support framework. Unlike traditional dairy research focused on individual unit operations, this project captures the full complexity from farm to finished product – including collection, transport, processing, storage, and distribution. You will develop expertise in modelling complex manufacturing processes, predictive and prescriptive optimisation (using Python), and scenario analysis. The collaboration between Teagasc Moorepark (world-leading dairy research) and UCC’s College of Business and Law provides a truly interdisciplinary environment. For a student interested in how data science can optimise food processing systems, this is an opportunity to build tools that directly support industry decision-making.

Key Responsibilities

• Develop a decision-support model to optimise milk flow through the dairy processing system
• Develop and integrate validated sub-models representing each stage of the process
• Link these models to a wider sectoral framework describing the journey of milk from farm to consumer
• Address key questions relating to how processing pathways interact with milk variability and market dynamics
• Use modelling approaches including optimisation and scenario analysis to support decision-making

Candidate Profile and Eligibility

Desirable:

• Knowledge of dairy processing operations
• Knowledge of data science, business analytics
• Experience with machine learning techniques and applications
• Excellent written and verbal communication skills
• Ability to work independently and as part of a team
• Ability to take initiative

Supervision Team

What They Offer

My Application Strategy

1. Highlight your Python proficiency – Predictive and prescriptive optimisation modelling is a core requirement
2. Emphasise process engineering or food processing background – Understanding manufacturing processes is essential
3. Show experience with modelling complex systems – Optimisation and scenario analysis skills are valuable
4. Demonstrate data science or machine learning interest – Desirable qualifications include ML techniques
5. Connect your application to dairy processing – Knowledge of dairy operations is desirable

Who Should Apply

This PhD is perfect for a student with a background in process engineering, food science, or data science who wants to apply modelling to real-world food processing challenges. If you are interested in how milk composition variability and market dynamics affect processing decisions, and want to build decision-support tools that integrate collection, transport, processing, storage, and distribution, this project offers training across engineering, data science, and agri-food economics. Candidates with Python proficiency and an interest in optimisation are especially encouraged.

Useful Links

• Lab Assistant | Engro Fertilizers Hyderabad
• Postdoc Root Developmental Biology Germany | IPK Gatersleben
• More PhD Positions