Postdoctoral Research Fellow Crop Trait Prediction with ML

• School of Mathematics and Physics

• Analytics for the Australian Grains Industry (AAGI)

• Play a lead role in developing crop trait prediction solutions

• Utilizes physics-informed machine learning (PIML).

• Uses crop models to generate training data and test predictions against observed datasets.

• Based at our vibrant and picturesque St Lucia Campus

About UQ

As part of the UQ community, you’ll have the opportunity to work alongside the brightest minds, who have joined us from all over the world, and within an environment where interdisciplinary collaborations are encouraged.

As part of our commitment to research excellence, we are proud to provide our staff with access to world-class facilities and equipment, grant writing support, greater research funding opportunities, and post-fellowship contracts via our UQ Amplify initiative .

At the core of our teaching remains our students, and their experience with us sets a foundation for success far beyond graduation. Not only do we have one of the largest PhD enrolments in Australia, but we have also made a commitment to making education opportunities available for all Queenslanders, regardless of personal, financial, or geographical barriers.

About This Opportunity 

The grains industry has a gross value of > $30 billion per year produced from sowing 25 M ha of crops and is a major export industry for Australia. The Grains Research and Development Corporation (GRDC) uses grower levies to fund more than 800 research, development and extension (RD&E) investments worth $177 million (2022-23). UQ co-invests in grains research including via a new initiative, Analytics for the Australian Grains Industry (AAGI) which involves researchers and students from the Schools of Agriculture and Food Sustainability, Maths and Physics, and Electronic Engineering and Computer Science as well as from QAAFI (Queensland Alliance for Agriculture and Food Innovation – co-funded by the Queensland Government).

AAGI is a five-year strategic partnership across UQ, Curtin University, and the University of Adelaide that is aimed at harnessing analytics to drive the sector’s profitability and global impact. AAGI gives Australian growers an opportunity to be world leaders in analytics-driven decision making to drive efficiency and precision and support farm enterprise risk management. AAGI at UQ provides an exciting environment for researchers to focus their efforts on developing their expertise and emerging research profile in their discipline.

This is a fixed-term position for up to 3 years. This postdoctoral fellowship position based in the School of Mathematics and Physics will play a lead role in developing crop trait prediction solutions based on physics informed machine learning to allow accurate predictions by combining physical knowledge and data. Methods will include use of deterministic crop models to generate training data for PIML, and testing against observed datasets. In addition to AAGI, this position will service research needs of other UQ and GRDC supported projects.

Key responsibilities will include: 

• Produce quality research outputs consistent with discipline norms by publishing or exhibiting in high quality fora.

• Work collaboratively with AAGI, UQ and grains industry colleagues to deliver research, analytical support and teaching activities

• Provide analytical support for research projects supported by AAGI and which are aligned with the expertise of the applicant

• Contribute to transfer of knowledge, technology and practices to colleagues and to researchers within the Australian grains industry

• Review and draw upon best practice research methodologies

• Contribute to the effective supervision of Honours and Higher Degree by Research students

• On an as-needs basis:

  • Provide feedback, coaching, and professional development to others in the research teams, including to Service and Support of AAGI investments

  • Manage research support staff effectively throughout the employee lifecycle in accordance with University policy and procedures

  • Work to promptly resolve conflict and grievances when they arise, in accordance with University policy and procedures.

• Demonstrate citizenship and leadership behaviours that align to the UQ values.

• Provide support to other academic positions and unit operations as needed during other team members absences.

• Contribute to internal service roles and administrative processes as required, including participation in decision-making and service on relevant committees.

• Collaborate in service activities external to the immediate organisation unit.

• Develop external links and partnerships by cultivating relationships with the grains industry, government departments, professional bodies and the wider community.

This is a research-focused position. Further information can be found by viewing UQ’s Criteria for Academic Performance .

This is a full-time (100%), fixed-term position for up to 3 years at Academic level A. The full-time equivalent base salary will be in the range $77,324.85 - $102,945.12 plus a generous super allowance of up to 17%. The total FTE package will be up to $90,470.08 - $120,445.79 annually. 

The greater benefits of joining the UQ community are broad:  from being part of a Group of Eight university, to recognition of prior service with other Australian universities, up to 26 weeks of paid parental leave, 17.5% annual leave loading, flexible working arrangements including hybrid on site/WFH options and flexible start/finish times, and genuine career progression opportunities via the academic promotions process.

About You  

• Completion or near completion of a PhD in the discipline area

• In-depth understanding of fundamentals of machine learning and deep learning, and proficiency in using machine learning or deep learning libraries such as scikit-learn, PyTorch, Tensorflow

• Advanced skills in computer programming for data manipulation and analysis methods including multi-dimensional analytics of large temporal and/or spatial datasets

• Experience in use of multi-modal techniques in forecasting and prediction in time series

• Experience in the principles of crop growth models and use of crop simulation software is desirable.

• Demonstrated success in collaboration in interdisciplinary team-work environments

• Evidence of publications in reputed refereed journals and presenting at conferences.

• Evidence of capacity to develop and deliver educational or training materials

• Demonstrated experience in successful supervision of undergraduate and/or higher degree research projects.

You must have unrestricted work rights in Australia for the duration of this appointment. Visa sponsorship may be available for this appointment. You can find out more about life in Australia’s Sunshine State here

For more information about this opportunity, please contact Dr Nan Ye via [email protected] .

For application queries, please contact [email protected]  stating the job reference number (below) in the subject line. 

Want to Apply? 

All applicants must upload the following documents in order for your application to be considered:

• Resume

• Cover letter addressing the ‘About You’ section

Other Information 

At UQ we know that our greatest strengths come from our diverse mix of colleagues, this is reflected in our ongoing commitment to creating an environment focused on equity, diversity and inclusion .  We ensure that we are always attracting, retaining and promoting colleagues who are representative of the diversity in our broader community, whether that be gender identity , LGBTQIA+ , cultural and/or linguistic , Aboriginal and/or Torres Strait Islander peoples , or people with a disability . Accessibility requirements and/or adjustments can be directed to [email protected]  

If you are a current employee (including casual staff and HDR scholars) or hold an unpaid/affiliate appointment, please login to your staff Workday account and visit the internal careers board to apply for this opportunity. Please do NOT apply via the external job board.

Applications close Tuesday, 9 April 2024 at 11.00pm AEST (R-35591). Please note that interviews have been tentatively scheduled the week commencing April 22 2024.