Study As
Full Time

Principal Supervisor
Associate Professor Jixue Liu

Main Campus
Mawson Lakes

Applications Close
12 Dec 2022

Study Level

Applications Open To
Domestic Candidate

Tuition Fees:
All domestic students are eligible for a fee waiver. International students who receive a stipend are eligible for a fee waiver. Find out more about fees and conditions.

Project Stipend:
$28,854 p.a. available to domestic applicants only

Develop early detection systems for wildfires

The University of South Australia – Australia’s University of Enterprise – is offering a state-of-the-art project-based PhD with real-world application in our Industrial AI Research Centre, in partnership with Geoscience Australia, using data analytics to advance early fire detection systems. 

Wildfires threaten our communities, the environment, and the economy. Detecting wildfires early plays an important role in mitigating the resulting damages. Traditionally, fires are mostly detected via staffed fire towers in forests, but this method is not effective when the fires are small, in remote areas, or when the fire starts at night. 

In recent years, satellite imaging has progressed greatly, generating a large amount of data. This satellite imagery, after being pre-­processed, can be used in fire detection. 

This project aims to detect fires by fire smoke, using satellite imagery. The project is motivated by the fact that smoke takes up a large volume of area and can be more easily observed visually. Through advancements in hyperspectral sensors, non­visual spectrums can now be used in the detection, as it reduces the interference of lighting and clouds, with this means of detection. 

In this research degrees project, you will focus on early fire smoke detection using this hyperspectral raw imagery onboard satellites, as it saves power consumption (which is very important to onboard models on a satellite) and also reduces detection time. The project aims to produce effective algorithms for satellite onboard early fire detection.

Join the dynamic and collegial Data Analytics Group based in UniSA's Industrial AI Research Centre, where we have a strong track record of research using data mining, machine learning and artificial intelligence. In our team, you will have access to robust peer support, and benefit from the world-class expertise of our senior researchers.  

What you’ll do

In this project-based research degree, you will first conduct an extensive literature review on smoke detection, which should include both pixel-based and machine learning-based smoke detection. You will also implement existing deep learning convolutional neural network (CNN) models, collect raw satellite imagery data and conduct model-based data labelling. 

These tasks will lead to your first piece of work of data labelling and bring you to the core research problems. The core problems are designing and implementing an effect model for early fire smoke and detection, and designing and implementing a compact model for onboard processing without compromising accuracy. 

You will receive expert training in machine learning and remote sensing. 

There are opportunities for you to travel to domestic and international conferences, helping you build your professional network. 

Upon completing the project, you will be an expert in smoke detection from images. This opens up job opportunities in any remote sensing data-based modelling, prediction, and analysis, in both academia and industry.

Where you’ll be based

You will be based in UniSA’s Industrial AI Research Centre. The Centre brings together experts from across computer sciences to develop solutions for autonomous and augmented intelligence systems. We are a part of the global revolution in artificial intelligence, machine learning, Industry 4.0 and Internet-of-Things (IoT) technologies. 

Our researchers work with organisations around the world to develop solutions that cater to their specific needs. We have worked with Siemens, BP Australia, Yokogawa Electric and more, growing these partnerships over time to continually design sophisticated AI-driven solutions. 

Supervisory Team 
Financial Support 

This project is funded for reasonable research expenses.  Additionally, a living allowance scholarship of $28,854 per annum is available to Australian and New Zealand citizens, and permanent residents of Australia, including permanent humanitarian visa holders.  Australian Aboriginal and/or Torres Strait Islander applicants will be eligible to receive an increased stipend rate of $45,076 per annum. A fee-offset or waiver for the standard term of the program is also included.  For full terms and benefits of the scholarship please refer to our scholarship information. International applicants are not invited to apply at this time.

Eligibility and Selection 

This project is open to applications from Australian or New Zealand citizens, and Australian permanent residents or permanent humanitarian visa holders. International applicants are not invited to apply at this time.

Applicants must meet the eligibility criteria for entrance into a PhD. Additionally applicants must meet the projects selection criteria: 
  • A GPA of Distinction or above (average mark larger than or equal to 75%) from both undergraduate and post graduate studies.
  • An undergraduate degree from Computer Science/Information Technology, Mathematics, or Engineering
  • Good programming skills supported by evidence like completed projects. Please describe the functions/components of the projects and indicate what functions/components were programmed by you if the projects involved others.
Applicant who can also demonstrate the following will be highly regarded:
  • Experiences in data mining and especially in deep learning are appreciated
All applications that meet the eligibility and selection criteria will be considered for this project. A merit selection process will be used to determine the successful candidate.

The successful applicant is expected to study full-time and to be based at our Mawson Lakes Campus in the north of Adelaide. 

Essential Dates 

Applicants are expected to start in a timely fashion upon receipt of an offer.  Extended deferral periods are not available. Applications close on Monday, 12th December

How to apply:

Applications must be lodged online, please note UniSA does not accept applications via email.

For further support see our step-by-step guide on how to apply , or contact the Graduate Research team on +61 8 8302 5880, option 1 or email us at You will receive a response within one working day.

IMPORTANT: This site is optimised for the latest versions of Internet Explorer, Safari, Firefox and Chrome. Note that earlier versions of any browsers mentioned are supported, but likely to demonstrate slower response times.

By choosing to continue, you agree to the privacy policy. Show Privacy Policy