If you would like more information or have any questions about this scholarship, please contact the project supervisors.
Human-centric agentic AI for emergency response training and simulation
Applications will remain open until a candidate has been appointed
Supporting a PhD candidate as part of the REACH Trailblazer Program to research human-centric agentic AI for emergency response training and simulation
Key details
Project supervisor
Deakin school and faculty
Additional supervisors
Location
Geelong Waurn Ponds campus
Value and duration
This scholarship is available over three years and offers:
- a stipend of $37,450 per annum tax exempt (2026 rate)
- a top-up of $10,000 per annum tax exempt
- a relocation allowance of $500–1,500 (for single to family) for students moving from interstate
For international students, the awardee will also receive:
- tuition fees offset for the duration of four years
- single Overseas Student Health Cover policy for the duration of the student visa.
Research aim
The project will explore hybrid Artificial Intelligence (AI) architectures combining knowledge representation, machine learning, and human-in-the loop reasoning to deliver adaptive, trustworthy decision-support systems for high-risk operational contexts. In collaboration with Fire Rescue Victoria (FRV), the research will be validated in realistic emergency training and simulation environments, with a focus on scenarios involving energy systems, industrial assets, and circular economy infrastructure. The outcomes will support improved situational awareness, faster and more effective emergency response, and reduced disruption to critical clean energy and resource recovery systems.
Background information
Human-Centric Agentic AI for Climate-Resilient Emergency Decision Support and Sustainable Infrastructure Protection Climate-driven disasters are placing increasing pressure on emergency response systems and the resilience of critical infrastructure underpinning Australia’s transition to a low-carbon and circular economy. This includes renewable energy systems, hydrogen production and distribution assets, and recycling and resource recovery facilities, which are highly vulnerable to cascading risks during extreme events.
Current emergency decision-support and training systems are limited in their ability to model dynamic risk escalation, integrate heterogeneous operational data, and provide adaptive, real-time guidance under uncertainty - particularly in complex, multi-sector infrastructure environments.
This PhD project will develop novel human-centric, agentic AI approaches to enhance climate resilience, emergency decision making, and protection of sustainable infrastructure systems. The research will design explainable AI/ML models that integrate simulation data, geospatial intelligence, infrastructure telemetry, and human decision traces to model incident evolution, predict escalation risks, and optimise response strategies.
Am I eligible?
To be eligible you must:
- meet Deakin's PhD entry requirements
- enrol full time
- hold an honours degree (first class) or an equivalent standard masters degree with a substantial research component
- be an international candidate (optional)
- be a domestic student candidate (domestic includes candidates with Australian Citizenship, Australian Permanent Residency, or New Zealand Citizenship) (optional)
Please refer to the research degree entry pathways page for further information.
Additional requirements:
- Strong software development skills, with experience in designing, implementing and maintaining robust software systems.
- Proficiency in Unity development, including experience with interactive or simulation-based environments, scenario development, and integration of software components within Unity.
- Strong knowledge of deep learning and artificial intelligence, with practical experience in developing, training and evaluating AI models.
- Experience integrating AI models with interactive or simulation environments would be highly desirable.
- Strong programming skills, particularly in Python and C#, and familiarity with relevant machine learning and deep learning frameworks.
- Ability to work with multidisciplinary research and industry teams to translate operational requirements into functional technical solutions.
Ready to apply?
Please email your CV and cover letter (including your interest in the project) to Dr Bahareh Nakisa. Your CV should highlight your skills, education, publications and relevant work experience. If successful, you will be invited to submit a formal application.
Research degree entry requirements
Set yourself up for success. Each type of Deakin research degree has specific entry requirements designed to ensure that graduate researchers are well prepared for the challenges of advanced study.
Contact us
Email Dr Bahareh Nakisa
