What you'll receive
- a scholarship of $32,000 per year for 3 years (a base stipend of $27,000 and a top-up of $5,000)
- up to a maximum of $5,000 per year for project costs (to be agreed between CSIRO and QUT on a case by case basis).
International students will also receive a fee sponsorship.
You'll also get the opportunity to work on a cutting-edge project in digital agriculture: Hyperspectral Deep learning.
- meet QUT’s PhD admission criteria(PDF file, 92.7 KB)
- have the skills and experience required for the topic you are applying for.
How to apply
Submit your application to the supervisor of the project you are interested in.
Your application must include:
- a cover letter
- an up-to-date curriculum vitae (CV)
- full academic transcript
- a summary (up to 2 pages) of your scientific career, including:
- a summary of your final project from your most recent degree
- a paragraph on your research interests
- contact details of 3 referees (email, address and phone numbers).
- If your application is successful at this stage, you will be asked to complete an application form.
What happens next?
This scholarship will stay open until a suitable candidate is found.
If your application is not successful, we'll notify you by email.
For more information about the application process please contact Prof Sridha Sridharan via email email@example.com
QUT Supervisors: Prof Sridha Sridharan and Prof Clinton Fookes
CSIRO Supervisor: Dr Peyman Moghadam and Dr Everard Edwards
About the scholarship
Plant diseases are responsible for major economic losses in yield and quality affecting agricultural industry worldwide. Disease control strategies are widely focused on spraying pesticides uniformly over cropping areas at different times during the growth cycle.
These control strategies, though effective, have adverse economic and ecological effects, introducing new pests and elevating chemical resistance. Hyperspectral imaging combined with machine learning provides an opportunity to develop fast and non-invasive methods of detecting plant diseases and potentially discriminating between different disease types (e.g. virus, fungus, bacteria) before the human eye can see them.
Hyperspectral cameras are currently undergoing a change from bulky and expensive equipment towards mobile and portable devices. A hyperspectral camera comprises of hundreds of bands with shortwave dependencies. It is possible to use these shortwave dependencies of hyperspectral information to design and develop deep networks for object classification, semantic segmentation and scene understanding. Both spectral and spatial relationship need to be modelled by the deep networks simultaneously.
The research in this PhD programme will develop algorithms for hyperspectral deep learning suitable for detecting plant diseases and potentially discriminating between different disease types. The research will involve the development of learning with self-supervision algorithms to address the significant weakness of most current deep networks.