Large AI-Based Multimodal Analysis for Automated Geological Interpretation

About the research project

Accurate identification of material composition and structural characteristics is fundamental to geoscience and natural-resource exploration. Traditionally, these tasks depend on manual expert analysis of physical samples and supporting laboratory data. While effective, such approaches are labor-intensive, subjective, and difficult to scale, creating an opportunity for computational methods that enable automation, reproducibility, and large-scale inference.

Recent developments in large AI models, such as vision transformers, multimodal foundation models, and domain-adaptive large language models, offer new potential to transform how complex physical specimens are analysed. These models can learn from diverse datasets that combine imagery, text, and structured measurements, and are capable of capturing subtle patterns that are often overlooked by conventional machine-learning techniques. Their ability to integrate heterogeneous data sources makes them promising tools for advanced scientific interpretation.

This PhD project investigates how large, multimodal AI systems can be developed and adapted to support automated interpretation of geological materials, with a focus on mineral identification and rock classification using hand-sample and thin-section imagery. The project aims to produce new computational methods, workflows, and theoretical insights that advance both AI research and its scientific applications.

The PhD project will address the following overarching goals:

• Design and curate multimodal datasets that combine images, textual descriptions, and limited spectral or compositional data, enabling investigation of cross-modal learning for scientific interpretation.
• Develop and fine-tune large AI models (e.g., vision-language models, generative models, transformer-based architectures) for classification, clustering, and feature extraction tasks involving complex natural materials.
• Create novel techniques for explainability and scientific interpretability, ensuring that AI-generated insights align with domain-specific knowledge such as established petrographic, structural, or compositional features.
• Build and evaluate prototype systems that demonstrate automated analysis workflows suitable for research or industry contexts.

The project will be co-supervised by researchers from the School of ICT and the Centre for Ore Deposit and Earth Sciences (CODES). The expected outcomes will form the foundation for next-generation intelligent systems that support automated geological interpretation and can be extended to a wide range of domains beyond geoscience. This PhD project provides an opportunity to contribute both to cutting-edge AI research and to transformative scientific applications.

Primary supervisor

Meet Doctor Quan Bai

Funding

Applicants will be considered for a Research Training Program (RTP) scholarship or Tasmania Graduate Research Scholarship (TGRS) which, if successful, provides:

• a living allowance stipend funded by University of Tasmania of $34,315 per annum for 3.5 years
• a relocation allowance of up to $2,000
• a tuition fees offset covering the cost of tuition fees for up to four years (domestic applicants only)

A tuition fee offset may be offered to eligible international applicants following competitive assessment 

As part of the application process you may indicate if you do not wish to be considered for scholarship funding.

Other funding opportunities and fees

For further information regarding other scholarships on offer, and the various fees for undertaking a research degree, please visit our Scholarships and fees on research degrees page.

Eligibility

Applicants should review the Higher Degree by Research minimum entry requirements.

Ensure your eligibility for the scholarship round by referring to our Key Dates.

Additional eligibility criteria specific to this project/scholarship:

• Master’s degree (or equivalent Honours degree) in Computer Science with sufficient research components.
• Demonstrated academic excellence in relevant coursework and research.
• Excellent written and verbal communication skills, including experience preparing academic papers, reports, or technical documentation.
• Ability to work effectively in a collaborative and multidisciplinary research environment.
• Demonstrated motivation to contribute to next-generation intelligent systems and agentic AI applications.
• Applicants must be able to undertake the project on-campus

Selection criteria

The project is competitively assessed and awarded. Selection is based on academic merit and suitability to the project as determined by the College.

Additional essential selection criteria specific to this project:

• Solid understanding of AI techniques, including natural language processing (NLP), machine learning, or large language models (LLMs).
• Strong analytical and problem-solving skills, with demonstrated ability to synthesise complex ideas

Additional desirable selection criteria specific to this project:

• Proven ability to conduct independent research, perform literature reviews, and design experiments.
• Strong programming skills in Python (preferred) and familiarity with data processing libraries.

Application process

1. Select your project, and check that you meet the eligibility and selection criteria, including citizenship;
2. Contact Doctor Quan Bai to discuss your suitability and the project's requirements; and
3. In your application:
   • Copy and paste the title of the project from this advertisement into your application. If you don’t correctly do this your application may be rejected.
   • Submit a signed supervisory support form, a CV including contact details of 2 referees and your project research proposal.
4. Apply prior to 1 October 2026.

Full details of the application process can be found under the ' How to apply ' section of the Research Degrees website.

Following the closing date applications will be assessed within the College. Applicants should expect to receive notification of the outcome by email by the advertised outcome date.

Apply nowExplore other projects