QAAFI Other Projects and FABA Projects - Summer Research Programs
General information on the program, including how to apply, is available from the UQ Student Employability Centre’s program website.
A food system approach to understanding the Brisbane food system
Primary Supervisors:
Dr Selina Fyfe | selina.fyfe@uq.edu.au
Prof Damian Hine | d.hine@uq.edu.au
Please contact Prof Damian Hine (d.hine@uq.edu.au) and Dr Selina Fyfe (selina.fyfe@uq.edu.au) before submitting an application.
Duration: 6 weeks (25 - 30 hours per week); flexible working arrangements, hybrid, on site (Long Pocket and St Lucia)
The Brisbane food system project consists of a number of smaller projects that analyse Brisbane's food system using a modified food system approach. A food system approach seeks to understand the activities, drivers and outcomes within a food system and the interlinkages within them. This gives a broad understanding of subjects within the food system and the interlinkages and flow throughs that occur. Summer students will do research into a part of one of these smaller projects.
Expected outcomes: This project will give students an understanding of what food systems are, how food systems work and of how food system analysis can be done.
Suitability: This project is open to applications from masters students or 3rd – 4th year undergraduate students with a background in any of the following: food science, social science, political science, food systems or system science.
Data-Driven Market Intelligence and Machine Learning for identifying Emerging Trends in the Food and Beverage Industry
Primary Supervisors:
Dr Rimjhim Agarwal | rimjhim.agarwal@uq.edu.au
Dr Sera Jacob | sera.jacob@uq.edu.au
Prof Damian Hine | d.hine@uq.edu.au
Please contact Rimjhim Agarwal (rimjhim.agarwal@uq.edu.au), Sera Jacob (sera.jacob@uq.edu.au) and Prof Damian Hine (d.hine@uq.edu.au) before submitting an application.
Duration: 6 weeks (30 hours per week); On site preffered (St Lucia Campus)
This project will focus on applying advanced data science techniques to model food and beverage trends using Gartner's Hype cycle. Using open-source datasets, retail reports, investment data, patents and consumer insights, the student will explore patterns in areas such as plant-based alternatives, functional foods, sustainable packaging, and supply chain innovation. By leveraging machine learning models and statistical methods, the student will generate actionable market intelligence. Outcomes will be translated into interactive visualizations and structured outputs, designed for industry stakeholders and SMEs.
Expected outcomes: This project provides hands-on experience in text mining, natural language processing, and bibliometric analysis.Students will learn to design and implement pipelines that convert unstructured scientific texts into structured datasets suitable for communication with relevant stakeholders. This project helps students in building skills of integrating scientific and technical knowledge into decision-support tools. It will also provide students to strengthen their ability to communicate complex findings in accessible and actionable formats for industry stakeholders.
Suitability: This project is open to applications from 3rd-4th year undergraduate, or masters students with background in data science, AI or computer science.
Natural Language Processing and Knowledge Extraction from Scientific Literature to Enhance the FaBA Food and Beverage Innovation Dashboard
Primary Supervisors:
Dr Rimjhim Agarwal | rimjhim.agarwal@uq.edu.au
Dr Sera Jacob | sera.jacob@uq.edu.au
Prof Damian Hine | d.hine@uq.edu.au
Please contact Rimjhim Agarwal (rimjhim.agarwal@uq.edu.au), Sera Jacob (sera.jacob@uq.edu.au) and Prof Damian Hine (d.hine@uq.edu.au) before submitting an application.
Duration: 6 weeks (30 hours per week); On site preffered (St Lucia Campus)
This project will investigate how advanced text-mining and natural language processing (NLP) methods can be used to extract, classify, and synthesize insights from scientific literature, patents, and government publications in the food and beverage sector. The student will develop a pipeline to process unstructured text into structured outputs, which will be integrated into the FaBA Innovation Dashboard. This will enable the dashboard to provide food and beverage industry with rapid access to evidence-based insights on emerging technologies, nutritional developments, and regulatory changes.
Expected outcomes: This project provides hands-on experience in text mining, natural language processing, and bibliometric analysis.Students will learn to design and implement pipelines that convert unstructured scientific texts into structured datasets suitable for communication with relevant stakeholders. This project helps students in building skills of integrating scientific and technical knowledge into decision-support tools. It will also provide students to strengthen their ability to communicate complex findings in accessible and actionable formats for industry stakeholders.
Suitability: This project is open to applications from 3rd-4th year undergraduate, or masters students with background in data science, AI or computer science