The issues of food security and sustainable agriculture are vital concerns to society and key topics in assessments of climate variability and change on productivity and food supplies. In addition, food producers are increasingly exposed to variability and frequent changes in world markets, commodity prices, accessibility to seeds and /or fertilizer and local weather. This increases their vulnerability and threatening ensuing resilience to cope economically as well as socially. However, accurate and advance knowledge of the associated risk in crop production systems can mitigate some of the impacts of such causative threats. The recent advances in digital technologies including high-resolution earth observation sensors, biophysical crop modelling and climate forecasting systems, combined with targeted artificial intelligence approaches and cloud computing solutions will fast track the development of more holistic systems approaches and unravelling of such complex systems. It is anticipated that such approaches will increasingly become more valuable in decision-making for producers/farmers, agricultural industry, financial institutions, government agencies and policy makers. As a result, it will lead to better preparedness in coping with the impact of extreme climate events leading to a reduction in the downside risk and more resilient agricultural food systems.


Dr Fred Roosta-Khorasani

Dr Fred Roosta-Khorasani is an ARC Fellow at the School of Mathematics and Physics. His research focuses on the design, analysis, and implementation of novel optimisation algorithms for training modern ML problems. Dr Fred Roosta-Khorasani and his research team design, analyse and implement novel optimisation algorithms for training modern machine learning problems. The underlying approaches draw from randomised techniques, statistics, non-convex non-linear analysis, geometry, and parallel/distributed computing. Dr Roosta-Khorasani is also interested in using novel ML models for scientific discovery, in particular the design of innovative physics-aware deep learning models and the development of their statistical learning theory.


Associate Professor Andries Potgieter

Associate Professor Andries Potgieter is a Principal Research Fellow at the Queensland Alliance for Agriculture and Food Innovation (QAAFI) at the University of Queensland. He currently leads and mentor a team of researchers in the areas of seasonal climate forecasting, remote and proximal sensing with applications in the development of crop production outlooks and less risk prone cropping systems across Australia, producing highly cited publications.

With over 30 years of experience, A/Prof Potgieter’s main research interest is in the complex integration of remote sensing technologies, spatial production modelling, climate forecasting systems at a regional scale. In particular, his interest targets agricultural research that enhances the profitability and sustainability of spatial production systems through a better understanding of the linkages and interactions of such systems across a range of spatial (e.g. field, farm, catchment, national), and temporal (i.e. seasons to decades) scales. He is a leader in the field of quantitative eco-physiological systems modelling and has successfully built up a national and international recognised research profile with strong linkages to industry (farmer groups, insurance, seed companies and bulk handlers of commodities) and domestic and national agencies (State governments, ABARES and ABS) as well as international linkages with Ag-Food Canada, Maryland University, USDA, Chinese Academy of Science (CAS), the Chinese Academy of Agricultural Sciences (CAAS) including the UN and FAO.

About AI Seminar Series

AI Seminar Series will explore relevant topics in artificial intelligence and invite industry speakers and researchers to share their knowledge, experience and success - promoting transdisciplinary AI research and collaboration.




Lecture Theatre
Hawken Building (50)